diff --git a/snapshots/anthropic/deprecations.md b/snapshots/anthropic/deprecations.md index 921d3da..085419d 100644 --- a/snapshots/anthropic/deprecations.md +++ b/snapshots/anthropic/deprecations.md @@ -64,36 +64,45 @@ At some point, Anthropic hopes to make past models publicly available again. In ## Model status - - [Claude Mythos Preview](https://anthropic.com/glasswing) (`claude-mythos-preview`) is deprecated. To migrate to [Claude Mythos 5](https://anthropic.com/glasswing) (`claude-mythos-5`), see the [migration guide](https://platform.claude.com/docs/en/models/fable-5/migration-guide#migrating-from-claude-mythos-preview). - - Current and recently retired models are listed in the following table with their status: -| API model name | Current state | Deprecated | Tentative retirement date | -| -------------------------- | ------------- | ----------------- | ---------------------------------- | -| claude-fable-5-1 | Active | N/A | Not sooner than September 1, 2027 | -| claude-fable-5 | Active | N/A | Not sooner than June 9, 2027 | -| claude-opus-5 | Active | N/A | Not sooner than July 24, 2027 | -| claude-opus-4-8 | Active | N/A | Not sooner than May 28, 2027 | -| claude-opus-4-7 | Active | N/A | Not sooner than April 16, 2027 | -| claude-opus-4-6 | Active | N/A | Not sooner than February 5, 2027 | -| claude-opus-4-5-20251101 | Active | N/A | Not sooner than November 24, 2026 | -| claude-opus-4-1-20250805 | Retired | June 5, 2026 | August 5, 2026 | -| claude-opus-4-20250514 | Retired | April 14, 2026 | June 15, 2026 | -| claude-sonnet-5 | Active | N/A | Not sooner than June 30, 2027 | -| claude-sonnet-4-6 | Active | N/A | Not sooner than February 17, 2027 | -| claude-sonnet-4-5-20250929 | Active | N/A | Not sooner than September 29, 2026 | -| claude-sonnet-4-20250514 | Retired | April 14, 2026 | June 15, 2026 | -| claude-3-7-sonnet-20250219 | Retired | October 28, 2025 | February 19, 2026 | -| claude-haiku-4-5-20251001 | Active | N/A | Not sooner than October 15, 2026 | -| claude-3-5-haiku-20241022 | Retired | December 19, 2025 | February 19, 2026 | -| claude-3-haiku-20240307 | Retired | February 19, 2026 | April 20, 2026 | +| API model name | Current state | Deprecated | Tentative retirement date | +| :------------------------- | :------------ | :----------------- | :--------------------------------- | +| claude-fable-5-1 | Active | N/A | Not sooner than September 1, 2027 | +| claude-mythos-5-1 | Active | N/A | Not sooner than September 1, 2027 | +| claude-fable-5 | Active | N/A | Not sooner than June 9, 2027 | +| claude-mythos-5 | Active | N/A | Not sooner than June 9, 2027 | +| claude-mythos-preview | Deprecated | June 9, 2026 | To be announced | +| claude-opus-5-5 | Active | N/A | Not sooner than September 22, 2027 | +| claude-opus-5 | Active | N/A | Not sooner than July 24, 2027 | +| claude-opus-4-8 | Active | N/A | Not sooner than May 28, 2027 | +| claude-opus-4-7 | Active | N/A | Not sooner than April 16, 2027 | +| claude-opus-4-6 | Active | N/A | Not sooner than February 5, 2027 | +| claude-opus-4-5-20251101 | Active | N/A | Not sooner than November 24, 2026 | +| claude-opus-4-1-20250805 | Retired | June 5, 2026 | August 5, 2026 | +| claude-opus-4-20250514 | Retired | April 14, 2026 | June 15, 2026 | +| claude-sonnet-5-5 | Active | N/A | Not sooner than September 28, 2027 | +| claude-sonnet-5 | Active | N/A | Not sooner than June 30, 2027 | +| claude-sonnet-4-6 | Active | N/A | Not sooner than February 17, 2027 | +| claude-sonnet-4-5-20250929 | Deprecated | September 30, 2026 | November 30, 2026 | +| claude-sonnet-4-20250514 | Retired | April 14, 2026 | June 15, 2026 | +| claude-3-7-sonnet-20250219 | Retired | October 28, 2025 | February 19, 2026 | +| claude-haiku-4-5-20251001 | Active | N/A | Not sooner than October 15, 2026 | +| claude-3-5-haiku-20241022 | Retired | December 19, 2025 | February 19, 2026 | +| claude-3-haiku-20240307 | Retired | February 19, 2026 | April 20, 2026 | ## Deprecation history All deprecations are listed in the following sections, with the most recent announcements first. +### 2026-09-30: Claude Sonnet 4.5 model + +On September 30, 2026, Anthropic notified developers using Claude Sonnet 4.5 of its upcoming retirement on the Claude API. + +| Retirement date | Deprecated model | Recommended replacement | +| ----------------- | ---------------------------- | ----------------------- | +| November 30, 2026 | `claude-sonnet-4-5-20250929` | `claude-sonnet-5-5` | + ### 2026-06-05: Claude Opus 4.1 model diff --git a/snapshots/cerebras/deprecations.md b/snapshots/cerebras/deprecations.md index a6d9708..83d066a 100644 --- a/snapshots/cerebras/deprecations.md +++ b/snapshots/cerebras/deprecations.md @@ -7,11 +7,11 @@ > A list of all deprecations, with the most recent announcements appearing first. - **Gemma 4 31B availability changes on public endpoints** + **Gemma 4 31B availability changes with Shared Inference** - Starting September 3, 2026, `gemma-4-31b` is no longer available on Cerebras public endpoints. This change doesn't affect [Dedicated Endpoints](/dedicated/overview), where Gemma 4 31B remains available. + Starting September 3, 2026, `gemma-4-31b` is no longer available with Cerebras Shared Inference. This change doesn't affect [Dedicated Inference](/dedicated/overview), where Gemma 4 31B remains available. - Use [`qwen-3.8-27b`](/models/qwen-3.8-27b) for public endpoint workloads. To continue using Gemma 4 31B, [contact us](https://www.cerebras.ai/contact) to set up a dedicated endpoint. + Use [`qwen-3.8-27b`](/models/qwen-3.8-27b) for Shared Inference workloads. To continue using Gemma 4 31B, [contact us](https://www.cerebras.ai/contact) to set up Dedicated Inference. diff --git a/snapshots/cohere/models.md b/snapshots/cohere/models.md index f7a094c..1fa431d 100644 --- a/snapshots/cohere/models.md +++ b/snapshots/cohere/models.md @@ -48,7 +48,8 @@ are. * The North family includes purpose-built models such as [North Small Translate](north-small-translate-1.0) for machine translation and [North Mini Code](north-mini-code-1.0) for agentic coding. Both are available through the - [Chat](../reference/chat) endpoint and support production deployment through Model Vault. + [Chat](../reference/chat) endpoint. North Mini Code also supports production deployment through + [Model Vault](../../v2/docs/model-vault). ## Command @@ -92,7 +93,8 @@ In this table, we provide some important context for using Cohere Command models ## North North is Cohere's family of purpose-built generative models. North models are available on the Cohere API for -evaluation and through [Model Vault](../../v2/docs/model-vault) for production deployment. +evaluation. [North Mini Code](north-mini-code-1.0) also supports production deployment through +[Model Vault](../../v2/docs/model-vault). | Model Name | Status | Description | Modality | Context Length | Maximum Output Tokens | Endpoints | | --------------------------- | ------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | -------- | -------------- | --------------------- | ------------------------- | @@ -103,28 +105,32 @@ evaluation and through [Model Vault](../../v2/docs/model-vault) for production d These models can be used to generate embeddings from text or classify it based on various parameters. Embeddings can be used for estimating semantic similarity between two sentences, choosing a sentence which is most likely to follow another sentence, or categorizing user feedback. The Representation model comes with a variety of helper functions, such as for detecting the language of an input. -| Model Name | Description | Modalities | Dimensions | Context Length | Similarity Metric | Endpoints | -| ------------------------------- | ------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------- | ------------------------------------------ | -------------- | ------------------------------------------------------------- | ------------------------------------------------------------------- | -| `embed-v4.0` | A model that allows for text and images to be classified or turned into embeddings | Text, Images, Mixed texts/images (i.e. PDFs) | One of '\[256, 512, 1024, 1536 (default)]' | 128k | Cosine Similarity, Dot Product Similarity, Euclidean Distance | [Embed](../reference/embed), [Embed Jobs](../reference/embed-jobs) | -| `embed-english-v3.0` | A model that allows for text to be classified or turned into embeddings. English only. | Text, Images | 1024 | 512 | Cosine Similarity | [Embed](../reference/embed), [Embed Jobs](../reference/embed-jobs) | -| `embed-english-light-v3.0` | A smaller, faster version of `embed-english-v3.0`. Almost as capable, but a lot faster. English only. | Text, Images | 384 | 512 | Cosine Similarity | [Embed](../reference/embed), [Embed Jobs](../reference/embed-jobs) | -| `embed-multilingual-v3.0` | Provides multilingual classification and embedding support. [See supported languages here.](/docs/supported-languages) | Text, Images | 1024 | 512 | Cosine Similarity | [Embed](../reference/embed), [Embed Jobs](../reference/embed-jobs) | -| `embed-multilingual-light-v3.0` | A smaller, faster version of `embed-multilingual-v3.0`. Almost as capable, but a lot faster. Supports multiple languages. | Text, Images | 384 | 512 | Cosine Similarity | [Embed](../reference/embed), [Embed Jobs](../reference/embed-jobs) | +| Model Name | Description | Modalities | Dimensions | Context Length | Similarity Metric | Endpoints | +| ------------------------------- | ------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------- | ----------------------------------------------------- | -------------- | ------------------------------------------------------------- | ------------------------------------------------------------------- | +| `embed-v5.0-pro` | Our most capable embedding model, for text and images. Higher quality than `embed-v5.0-fast`, at higher latency. | Text, Images, Mixed texts/images (i.e. PDFs) | One of '\[256, 512, 768, 1024, 1536, 2048 (default)]' | 128k | Cosine Similarity, Dot Product Similarity, Euclidean Distance | [Embed](../reference/embed) | +| `embed-v5.0-fast` | A faster, lighter version of `embed-v5.0-pro`. Allows for text and images to be classified or turned into embeddings | Text, Images, Mixed texts/images (i.e. PDFs) | One of '\[256, 512, 768, 1024, 1536, 2048 (default)]' | 128k | Cosine Similarity, Dot Product Similarity, Euclidean Distance | [Embed](../reference/embed) | +| `embed-v4.0` | A model that allows for text and images to be classified or turned into embeddings | Text, Images, Mixed texts/images (i.e. PDFs) | One of '\[256, 512, 1024, 1536 (default)]' | 128k | Cosine Similarity, Dot Product Similarity, Euclidean Distance | [Embed](../reference/embed), [Embed Jobs](../reference/embed-jobs) | +| `embed-english-v3.0` | A model that allows for text to be classified or turned into embeddings. English only. | Text, Images | 1024 | 512 | Cosine Similarity | [Embed](../reference/embed), [Embed Jobs](../reference/embed-jobs) | +| `embed-english-light-v3.0` | A smaller, faster version of `embed-english-v3.0`. Almost as capable, but a lot faster. English only. | Text, Images | 384 | 512 | Cosine Similarity | [Embed](../reference/embed), [Embed Jobs](../reference/embed-jobs) | +| `embed-multilingual-v3.0` | Provides multilingual classification and embedding support. [See supported languages here.](/docs/supported-languages) | Text, Images | 1024 | 512 | Cosine Similarity | [Embed](../reference/embed), [Embed Jobs](../reference/embed-jobs) | +| `embed-multilingual-light-v3.0` | A smaller, faster version of `embed-multilingual-v3.0`. Almost as capable, but a lot faster. Supports multiple languages. | Text, Images | 384 | 512 | Cosine Similarity | [Embed](../reference/embed), [Embed Jobs](../reference/embed-jobs) | ### Using Embed Models on Different Platforms In this table, we provide some important context for using Cohere Embed models on Amazon Bedrock, Amazon SageMaker, and more. -| Model Name | Amazon Bedrock Model ID | Amazon SageMaker | Azure AI Foundry | Oracle OCI Generative AI Service | -| :------------------------------ | :----------------------------- | :-------------------- | :---------------------- | :----------------------------------------------------------------------------------------------------------- | -| `embed-v4.0` | (Coming Soon) | Unique per deployment | `cohere-embed-v-4-plan` | (Coming Soon) | -| `embed-english-v3.0` | `cohere.embed-english-v3` | Unique per deployment | Unique per deployment | `cohere.embed-english-image-v3.0` (for images), `cohere.embed-english-v3.0` (for text) | -| `embed-english-light-v3.0` | N/A | Unique per deployment | N/A | `cohere.embed-english-light-image-v3.0` (for images), `cohere.embed-english-light-v3.0` (for text) | -| `embed-multilingual-v3.0` | `cohere.embed-multilingual-v3` | Unique per deployment | Unique per deployment | `cohere.embed-multilingual-image-v3.0` (for images), `cohere.embed-multilingual-v3.0` (for text) | -| `embed-multilingual-light-v3.0` | N/A | Unique per deployment | N/A | `cohere.embed-multilingual-light-image-v3.0` (for images), `cohere.embed-multilingual-light-v3.0` (for text) | -| `embed-english-v2.0` | N/A | Unique per deployment | N/A | N/A | -| `embed-english-light-v2.0` | N/A | Unique per deployment | N/A | `cohere.embed-english-light-v2.0` | -| `embed-multilingual-v2.0` | N/A | Unique per deployment | N/A | N/A | +| Model Name | Amazon Bedrock Model ID | Amazon SageMaker | Azure AI Foundry | Oracle OCI Generative AI Service | +| :------------------------------ | :----------------------------- | :-------------------- | :--------------------------------------------------------------------------------- | :----------------------------------------------------------------------------------------------------------- | +| `embed-v5.0-pro` | N/A | Unique per deployment | [`Cohere-Embed-V5-Pro`](https://ai.azure.com/catalog/models/Cohere-Embed-V5-Pro) | N/A | +| `embed-v5.0-fast` | N/A | Unique per deployment | [`Cohere-Embed-V5-Fast`](https://ai.azure.com/catalog/models/Cohere-Embed-V5-Fast) | N/A | +| `embed-v4.0` | (Coming Soon) | Unique per deployment | `cohere-embed-v-4-plan` | (Coming Soon) | +| `embed-english-v3.0` | `cohere.embed-english-v3` | Unique per deployment | Unique per deployment | `cohere.embed-english-image-v3.0` (for images), `cohere.embed-english-v3.0` (for text) | +| `embed-english-light-v3.0` | N/A | Unique per deployment | N/A | `cohere.embed-english-light-image-v3.0` (for images), `cohere.embed-english-light-v3.0` (for text) | +| `embed-multilingual-v3.0` | `cohere.embed-multilingual-v3` | Unique per deployment | Unique per deployment | `cohere.embed-multilingual-image-v3.0` (for images), `cohere.embed-multilingual-v3.0` (for text) | +| `embed-multilingual-light-v3.0` | N/A | Unique per deployment | N/A | `cohere.embed-multilingual-light-image-v3.0` (for images), `cohere.embed-multilingual-light-v3.0` (for text) | +| `embed-english-v2.0` | N/A | Unique per deployment | N/A | N/A | +| `embed-english-light-v2.0` | N/A | Unique per deployment | N/A | `cohere.embed-english-light-v2.0` | +| `embed-multilingual-v2.0` | N/A | Unique per deployment | N/A | N/A | ## Rerank @@ -153,7 +159,9 @@ In this table, we provide some important context for using Cohere Rerank models \ -Rerank accepts full strings rather than tokens, so the token limit works a little differently. Rerank will automatically chunk documents longer than 510 tokens, and there is therefore no explicit limit to how long a document can be when using rerank. See our [best practice guide](/docs/reranking-best-practices) for more info about formatting documents for the Rerank endpoint. +> **Note** +> +> Rerank accepts full strings rather than tokens, so the token limit works a little differently. Rerank will automatically chunk documents longer than 510 tokens, and there is therefore no explicit limit to how long a document can be when using rerank. See our [best practice guide](/docs/reranking-best-practices) for more info about formatting documents for the Rerank endpoint. ## Parse diff --git a/snapshots/deepseek/updates.md b/snapshots/deepseek/updates.md index 4debafa..9e2b2c1 100644 --- a/snapshots/deepseek/updates.md +++ b/snapshots/deepseek/updates.md @@ -34,7 +34,7 @@ Today, we officially release the DeepSeek-V4.1-Flash model. It is the smallest m DeepSeek V4.1 Flash is now available on the DeepSeek API with native multimodal support. Change the model name to `deepseek-flash` to call the latest V4.1 Flash model. The previous-generation models V4 Flash and V4 Flash Vision Exp have been retired; for compatibility, the model names `deepseek-v4-flash` and `deepseek-v4-flash-vision-exp` are temporarily routed to V4.1 Flash. -Meanwhile, extensive testing shows that V4.1 Flash now outperforms DeepSeek V4 Pro across performance, cost, speed, and total time, so we plan to retire V4 Pro in an orderly manner. After 12:00 Beijing Time on September 14, 2026, and until the future release of V4.1 Pro, all requests to `deepseek-v4-pro` will be routed to V4.1 Flash and billed at the V4.1 Flash price. +In response to user demand, we have decided to continue providing API services for DeepSeek V4 Pro after September 14, 2026, with the billing method remaining unchanged. We will provide further notice should there be any changes. Thank you for your understanding and support! **API pricing adjustment** diff --git a/snapshots/fireworks/changelog.md b/snapshots/fireworks/changelog.md index 915e6a4..881e680 100644 --- a/snapshots/fireworks/changelog.md +++ b/snapshots/fireworks/changelog.md @@ -2,8 +2,91 @@ > Fetch the complete documentation index at: https://docs.fireworks.ai/llms.txt > Use this file to discover all available pages before exploring further. +> ## Agent Instructions +> For Fireworks Nexus, start at https://docs.fireworks.ai/nexus. +> Use https://docs.fireworks.ai/nexus/quickstart for coding harnesses, custom agents, APIs, SDKs, and LLM gateways. +> Use https://docs.fireworks.ai/nexus/firerouter for how model routers work, the supported model list, composition, closed-model credentials, and pricing. +> Prefer canonical short model IDs such as firerouter/opus. In LiteLLM litellm_params.model, use the full path fireworks_ai/accounts/fireworks/routers/firerouter/opus. +> Family names such as opus track the latest evaluated family version; do not describe them as fixed model versions. + # Changelog + + Inference + + # Serverless pricing update: DeepSeek V4.1 Flash + + On **October 1, 2026 at 00:00 UTC**, serverless pricing for [DeepSeek V4.1 Flash](https://app.fireworks.ai/models/fireworks/deepseek-v4p1-flash) changes (uncached input / cached input / output price per 1M tokens): + + * **Standard:** \$0.22 / \$0.007 / \$0.66 → **\$0.30 / \$0.006 / \$1.20** + * **Priority:** \$0.275 / \$0.00875 / \$0.825 → **\$0.375 / \$0.0075 / \$1.50** + + This adjustment brings our pricing in line with current market rates for this model. It applies only to serverless usage. If you run DeepSeek V4.1 Flash on a dedicated deployment or use Reserved Throughput, your pricing is unaffected. + + We are also rolling out infrastructure improvements designed to improve cache hit rate, minimize cost per task, and deliver a faster, more reliable experience across the board. + + See [Serverless pricing](/serverless/pricing) for the full rate card. + + + + Inference + + # Serverless deprecation: DeepSeek V4 Pro (0813), DeepSeek V4 Flash (0731), and related models + + The serverless deprecation announced for **September 25, 2026** is now in effect. The models below are no longer available on public serverless, including Fast and US-only serverless endpoints where those existed. Dedicated deployments are unaffected. + + ## **Recommended migrations** + + * **[DeepSeek V4 Pro (0813)](https://app.fireworks.ai/models/fireworks/deepseek-v4-pro-0813)** — migrate to **[DeepSeek V4.1 Flash](https://app.fireworks.ai/models/fireworks/deepseek-v4p1-flash)** + * **[DeepSeek V4 Flash (0731)](https://app.fireworks.ai/models/fireworks/deepseek-v4-flash-0731)** — migrate to **[DeepSeek V4.1 Flash](https://app.fireworks.ai/models/fireworks/deepseek-v4p1-flash)** + * **[DeepSeek V4 Flash Vision Exp](https://app.fireworks.ai/models/fireworks/deepseek-v4-flash-vision-exp)** — migrate to **[DeepSeek V4.1 Flash](https://app.fireworks.ai/models/fireworks/deepseek-v4p1-flash)** + * **[Muse Glimmer 30B](https://app.fireworks.ai/models/fireworks/muse-glimmer-30b)** — migrate to **[NVIDIA Nemotron 3.5 Lightning 30B A3B](https://app.fireworks.ai/models/fireworks/nemotron-lightning-3p5-30b-a3b)** + * **[Kimi K2.6](https://app.fireworks.ai/models/fireworks/kimi-k2p6)** — migrate to **[GLM 5.3](https://app.fireworks.ai/models/fireworks/glm-5p3)** or **[Kimi K3](https://app.fireworks.ai/models/fireworks/kimi-k3)** + * **[Kimi K2.7 Code](https://app.fireworks.ai/models/fireworks/kimi-k2p7-code)** — migrate to **[GLM 5.3](https://app.fireworks.ai/models/fireworks/glm-5p3)** or **[Kimi K3](https://app.fireworks.ai/models/fireworks/kimi-k3)** + * **[GLM 5.2](https://app.fireworks.ai/models/fireworks/glm-5p2)**, including **GLM 5.2 Fast**, **GLM 5.2 Fast US**, and **GLM 5.2 US** — migrate to **[GLM 5.3](https://app.fireworks.ai/models/fireworks/glm-5p3)** + + See [Serverless pricing](/serverless/pricing) and [Which model should I use?](/guides/recommended-models). + + + + Platform + + # New deployment creation flags: `deploymentShape: "default"` and `acceptShapelessRisk` + + Two new options are available on the [Create Deployment](/api-reference/create-deployment) API, in firectl (`--deployment-shape default` / `--accept-shapeless-risk`), and in the Python SDK (`deployment_shape="default"` / `accept_shapeless_risk=True`): + + * **`deploymentShape: "default"`** — Fireworks picks a validated deployment shape for the model and creates the deployment from it. If every compatible shape conflicts with fields in your request, the request fails with an error naming the conflicting fields and compatible shapes; the pick never silently overrides your settings or falls back to creating without a shape. + * **`acceptShapelessRisk=true`** — an explicit opt-out that creates the deployment without a shape, preserving current behavior. It cannot be combined with a shape. + + Deployments created without a shape skip shape validation and are the most common cause of failed deployment creations. Enforcement is coming soon: shapeless creation will then require the explicit opt-in, so start passing a shape (or `default`) now. The opt-out is for advanced users only. If you have a workload no existing shape covers, [contact us](https://fireworks.ai/contact) and we'll help you find or add one. + + + + Inference + + # Upcoming Serverless deprecation: older DeepSeek, GLM, Muse, and Kimi models + + Several older Serverless models will be decommissioned on **September 25, 2026** to better serve newer, higher-performance replacements. This applies **only to serverless endpoints**, including Fast and US-only Serverless endpoints for models that have those variants. **Dedicated deployments are unaffected.** + + ## **Action required** + + If you use any of the models below on serverless, migrate to a recommended replacement **before September 25, 2026**. After that date, they will no longer be available via serverless endpoints. + + ## **Recommended migrations** + + * **[DeepSeek V4 Flash (0731)](https://app.fireworks.ai/models/fireworks/deepseek-v4-flash-0731)** — migrate to **[DeepSeek V4.1 Flash](https://app.fireworks.ai/models/fireworks/deepseek-v4p1-flash)** + * **[DeepSeek V4 Pro (0813)](https://app.fireworks.ai/models/fireworks/deepseek-v4-pro-0813)** — migrate to **[DeepSeek V4.1 Flash](https://app.fireworks.ai/models/fireworks/deepseek-v4p1-flash)** + * **[DeepSeek V4 Flash Vision Exp](https://app.fireworks.ai/models/fireworks/deepseek-v4-flash-vision-exp)** — migrate to **[DeepSeek V4.1 Flash](https://app.fireworks.ai/models/fireworks/deepseek-v4p1-flash)** + * **[GLM 5.2](https://app.fireworks.ai/models/fireworks/glm-5p2)** — migrate to **[GLM 5.3](https://app.fireworks.ai/models/fireworks/glm-5p3)** + * **[Muse Glimmer 30B](https://app.fireworks.ai/models/fireworks/muse-glimmer-30b)** — migrate to **[NVIDIA Nemotron 3.5 Lightning 30B A3B](https://app.fireworks.ai/models/fireworks/nemotron-lightning-3p5-30b-a3b)** + * **[Kimi K2.6](https://app.fireworks.ai/models/fireworks/kimi-k2p6)** — migrate to **[GLM 5.3](https://app.fireworks.ai/models/fireworks/glm-5p3)** or **[Kimi K3](https://app.fireworks.ai/models/fireworks/kimi-k3)** + * **[Kimi K2.7 Code](https://app.fireworks.ai/models/fireworks/kimi-k2p7-code)** — migrate to **[GLM 5.3](https://app.fireworks.ai/models/fireworks/glm-5p3)** or **[Kimi K3](https://app.fireworks.ai/models/fireworks/kimi-k3)** + + On official benchmarks, DeepSeek V4.1 Flash outperforms DeepSeek V4 Pro (0813). DeepSeek V4.1 Flash is also multimodal, with the same vision capability as DeepSeek V4 Flash Vision Exp. + + If you want to switch to a dedicated deployment, see the [Serverless model list](https://fireworks.ai/models?modelTypes=Serverless) and the [on-demand deployment quickstart](/getting-started/ondemand-quickstart). + + Training @@ -73,8 +156,8 @@ * **[MiniMax M2.7](https://app.fireworks.ai/models/fireworks/minimax-m2p7)** — migrate to **[MiniMax M3](https://app.fireworks.ai/models/fireworks/minimax-m3)** * **[GPT OSS 20B](https://app.fireworks.ai/models/fireworks/gpt-oss-20b)** — migrate to **[GPT OSS 120B](https://app.fireworks.ai/models/fireworks/gpt-oss-120b)** or **[Qwen3 8B](https://app.fireworks.ai/models/fireworks/qwen3-8b)** for lower-latency workloads - * **[Kimi K2.6 Turbo / Fast](https://app.fireworks.ai/models/fireworks/kimi-k2p6)** — migrate to **[Kimi K2.6](https://app.fireworks.ai/models/fireworks/kimi-k2p6)** (standard serving path) - * **[Kimi K2.7 Code Fast](https://app.fireworks.ai/models/fireworks/kimi-k2p7-code)** — migrate to **[Kimi K2.7 Code](https://app.fireworks.ai/models/fireworks/kimi-k2p7-code)** (standard serving path) + * **[Kimi K2.6 Turbo / Fast](https://app.fireworks.ai/models/fireworks/kimi-k2p6)** — migrate to **[Kimi K2.6](https://app.fireworks.ai/models/fireworks/kimi-k2p6)** (standard mode) + * **[Kimi K2.7 Code Fast](https://app.fireworks.ai/models/fireworks/kimi-k2p7-code)** — migrate to **[Kimi K2.7 Code](https://app.fireworks.ai/models/fireworks/kimi-k2p7-code)** (standard mode) * **[DeepSeek V4 Pro](https://app.fireworks.ai/models/fireworks/deepseek-v4-pro)** — migrate to **[DeepSeek V4 Pro (0813)](https://app.fireworks.ai/models/fireworks/deepseek-v4-pro-0813)** diff --git a/snapshots/google/deprecations.md b/snapshots/google/deprecations.md index 63cb110..23577f2 100644 --- a/snapshots/google/deprecations.md +++ b/snapshots/google/deprecations.md @@ -1,6 +1,6 @@ # Gemini deprecations -This page lists the known deprecation schedules for [stable (GA)](/gemini-api/docs/models#stable) and [preview](/gemini-api/docs/models#preview) models in the Gemini API. A "**deprecation**" is the announcement that we no longer provide support for a model, and that it will be "**shut down**" in the near future. Once a model is "**shutdown**", it is completely turned off, and the endpoint is no longer available. +This page lists the known deprecation schedules for [stable (GA)](/gemini-api/docs/models#stable) and [preview](/gemini-api/docs/models#preview) models and for managed agents in the Gemini API. A "**deprecation**" is the announcement that we no longer provide support for a model, and that it will be "**shut down**" in the near future. Once a model is "**shutdown**", it is completely turned off, and the endpoint is no longer available. Deprecation announcements are made on the [Release notes](/gemini-api/docs/changelog) page, and the announced earliest shutdown dates are tracked on this page. Already-shutdown models are indicated with gray backgrounds. @@ -8,36 +8,46 @@ Deprecation announcements are made on the [Release notes](/gemini-api/docs/chang ## Gemini 3 models -| **Model** | **Release date** | **Shutdown date** | **Recommended replacement** | -| ------------------------------ | ----------------- | -------------------------- | --------------------------- | -| gemini-3.8-flash | September 2, 2026 | No shutdown date announced | | -| gemini-3.7-flash | August 13, 2026 | No shutdown date announced | | -| gemini-3.6-flash | July 21, 2026 | No shutdown date announced | | -| gemini-3.5-flash-lite | July 21, 2026 | No shutdown date announced | | -| gemini-3.5-flash | May 19, 2026 | No shutdown date announced | | -| gemini-3.1-flash-image | May 28, 2026 | No shutdown date announced | | -| gemini-3-pro-image | May 28, 2026 | No shutdown date announced | | -| gemini-3.1-flash-lite | May 7, 2026 | May 7, 2027 | gemini-3.5-flash-lite | -| Preview models | | | | -| gemini-3.1-flash-image-preview | February 26, 2026 | June 25, 2026 | gemini-3.1-flash-image | -| gemini-3.1-pro-preview | February 19, 2026 | No shutdown date announced | | -| gemini-3-pro-image-preview | November 20, 2025 | June 25, 2026 | gemini-3-pro-image | -| gemini-3-flash-preview | December 17, 2025 | No shutdown date announced | gemini-3.6-flash | -| gemini-3-pro-preview | November 18, 2025 | March 9, 2026 | gemini-3.1-pro-preview | -| gemini-3.1-flash-lite-preview | March 3, 2026 | May 25, 2026 | gemini-3.1-flash-lite | +| **Model** | **Release date** | **Shutdown date** | **Recommended replacement** | +| --------------------------------- | ------------------ | -------------------------- | ------------------------------------------------- | +| gemini-3.8-flash-tts | September 22, 2026 | No shutdown date announced | | +| gemini-3.8-flash-lite-tts | September 22, 2026 | No shutdown date announced | | +| gemini-3.8-live | September 15, 2026 | No shutdown date announced | | +| gemini-3.8-live-extended-thinking | September 15, 2026 | No shutdown date announced | | +| gemini-3.8-flash | September 2, 2026 | No shutdown date announced | | +| gemini-3.7-flash | August 13, 2026 | No shutdown date announced | | +| gemini-3.6-flash | July 21, 2026 | No shutdown date announced | | +| gemini-3.5-flash-lite | July 21, 2026 | No shutdown date announced | | +| gemini-3.5-flash | May 19, 2026 | No shutdown date announced | | +| gemini-3.1-flash-image | May 28, 2026 | No shutdown date announced | | +| gemini-3-pro-image | May 28, 2026 | No shutdown date announced | | +| gemini-3.1-flash-lite | May 7, 2026 | May 7, 2027 | gemini-3.5-flash-lite | +| Preview models | | | | +| gemini-3.1-flash-tts-preview | February 26, 2026 | No shutdown date announced | gemini-3.8-flash-tts or gemini-3.8-flash-lite-tts | +| gemini-3.1-flash-image-preview | February 26, 2026 | June 25, 2026 | gemini-3.1-flash-image | +| gemini-3.1-pro-preview | February 19, 2026 | No shutdown date announced | | +| gemini-3-pro-image-preview | November 20, 2025 | June 25, 2026 | gemini-3-pro-image | +| gemini-3-flash-preview | December 17, 2025 | No shutdown date announced | gemini-3.6-flash | +| gemini-3-pro-preview | November 18, 2025 | March 9, 2026 | gemini-3.1-pro-preview | +| gemini-3.1-flash-lite-preview | March 3, 2026 | May 25, 2026 | gemini-3.1-flash-lite | ## Gemini 2.5 Pro models -| **Model** | **Release date** | **Shutdown date** | **Recommended replacement** | -| ---------------------------- | ---------------- | -------------------------- | --------------------------- | -| gemini-2.5-pro | June 17, 2025 | No shutdown date announced | | -| Preview models | | | | -| gemini-2.5-pro-preview-03-25 | March 3, 2025 | December 2, 2025 | gemini-3.1-pro-preview | -| gemini-2.5-pro-preview-05-06 | May 6, 2025 | December 2, 2025 | gemini-3.1-pro-preview | -| gemini-2.5-pro-preview-06-05 | June 5, 2025 | December 2, 2025 | gemini-3.1-pro-preview | +**Note:** To ensure reliable performance for everyone, we are limiting access to the 2.5 models to users who have actively used them in the past. These models are not deprecated and will continue to be served until further notice through the API. For any new projects, use our latest models: 3.5 Flash-Lite or 3.8 Flash. This helps us maintain sufficient capacity for both ongoing legacy workflows and new applications. + +| **Model** | **Release date** | **Shutdown date** | **Recommended replacement** | +| --------------------------------------- | ---------------- | -------------------------- | --------------------------- | +| gemini-2.5-pro | June 17, 2025 | No shutdown date announced | | +| Preview models | | | | +| gemini-2.5-computer-use-preview-10-2025 | October 7, 2025 | July 28, 2026 | gemini-3.8-flash | +| gemini-2.5-pro-preview-03-25 | March 3, 2025 | December 2, 2025 | gemini-3.1-pro-preview | +| gemini-2.5-pro-preview-05-06 | May 6, 2025 | December 2, 2025 | gemini-3.1-pro-preview | +| gemini-2.5-pro-preview-06-05 | June 5, 2025 | December 2, 2025 | gemini-3.1-pro-preview | ## Gemini 2.5 Flash models +**Note:** To ensure reliable performance for everyone, we are limiting access to the 2.5 models to users who have actively used them in the past. These models are not deprecated and will continue to be served until further notice through the API. For any new projects, use our latest models: 3.5 Flash-Lite or 3.8 Flash. This helps us maintain sufficient capacity for both ongoing legacy workflows and new applications. + | **Model** | **Release date** | **Shutdown date** | **Recommended replacement** | | ------------------------------------- | ------------------ | -------------------------- | ------------------------------ | | gemini-2.5-flash | June 17, 2025 | No shutdown date announced | | @@ -64,25 +74,26 @@ Deprecation announcements are made on the [Release notes](/gemini-api/docs/chang ## Live API models -| **Model** | **Release date** | **Shutdown date** | **Recommended replacement** | -| --------------------------------------------- | ----------------- | -------------------------- | ----------------------------- | -| gemini-3.5-transcribe-live | August 2026 | No shutdown date announced | | -| gemini-2.0-flash-live-001 | April 9, 2025 | December 9, 2025 | gemini-3.1-flash-live-preview | -| Preview models | | | | -| gemini-3.5-live-translate-preview | June 2026 | No shutdown date announced | | -| gemini-3.1-flash-live-preview | March 11, 2026 | No shutdown date announced | | -| gemini-2.5-flash-native-audio-preview-12-2025 | December 12, 2025 | No shutdown date announced | gemini-3.1-flash-live-preview | -| gemini-live-2.5-flash-preview | June 17, 2025 | December 9, 2025 | gemini-3.1-flash-live-preview | +| **Model** | **Release date** | **Shutdown date** | **Recommended replacement** | +| --------------------------------------------- | ------------------ | -------------------------- | --------------------------- | +| gemini-3.8-live | September 15, 2026 | No shutdown date announced | | +| gemini-3.8-live-extended-thinking | September 15, 2026 | No shutdown date announced | | +| gemini-3.5-transcribe-live | August 2026 | No shutdown date announced | | +| gemini-2.0-flash-live-001 | April 9, 2025 | December 9, 2025 | gemini-3.8-live | +| Preview models | | | | +| gemini-3.5-live-translate-preview | June 2026 | No shutdown date announced | | +| gemini-3.1-flash-live-preview | March 11, 2026 | No shutdown date announced | gemini-3.8-live | +| gemini-2.5-flash-native-audio-preview-12-2025 | December 12, 2025 | No shutdown date announced | gemini-3.8-live | +| gemini-live-2.5-flash-preview | June 17, 2025 | December 9, 2025 | gemini-3.8-live | ## Audio models -| **Model** | **Release date** | **Shutdown date** | **Recommended replacement** | -| ---------------------------- | ---------------- | -------------------------- | ---------------------------- | -| gemini-3.5-transcribe | August 2026 | No shutdown date announced | | -| Preview models | | | | -| gemini-3.1-flash-tts-preview | April 13, 2026 | No shutdown date announced | | -| gemini-2.5-flash-preview-tts | May 20, 2025 | No shutdown date announced | gemini-3.1-flash-tts-preview | -| gemini-2.5-pro-preview-tts | May 20, 2025 | No shutdown date announced | gemini-3.1-flash-tts-preview | +| **Model** | **Release date** | **Shutdown date** | **Recommended replacement** | +| ---------------------------- | ---------------- | -------------------------- | ------------------------------------------------- | +| gemini-3.5-transcribe | August 2026 | No shutdown date announced | | +| Preview models | | | | +| gemini-2.5-flash-preview-tts | May 20, 2025 | No shutdown date announced | gemini-3.8-flash-tts or gemini-3.8-flash-lite-tts | +| gemini-2.5-pro-preview-tts | May 20, 2025 | No shutdown date announced | gemini-3.8-flash-tts or gemini-3.8-flash-lite-tts | ## Embedding models @@ -112,31 +123,30 @@ Deprecation announcements are made on the [Release notes](/gemini-api/docs/chang ## Veo models -| **Model** | **Release date** | **Shutdown date** | **Recommended replacement** | -| ----------------------------- | ----------------- | -------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -| veo-3.0-generate-001 | September 9, 2025 | June 30, 2026 | veo-3.1-generate-preview or the GA models on the [Gemini Enterprise Agent Platform](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/veo/3-1-generate) | -| veo-3.0-fast-generate-001 | September 9, 2025 | June 30, 2026 | veo-3.1-fast-generate-preview or the GA models on the [Gemini Enterprise Agent Platform](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/veo/3-1-generate) | -| veo-2.0-generate-001 | April 9, 2025 | June 30, 2026 | veo-3.1-generate-preview or the GA models on the [Gemini Enterprise Agent Platform](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/veo/3-1-generate) | -| Preview models | | | | -| veo-3.1-lite-generate-preview | March 31, 2026 | No shutdown date announced | | -| veo-3.1-generate-preview | October 15, 2025 | No shutdown date announced | | -| veo-3.1-fast-generate-preview | October 15, 2025 | No shutdown date announced | | -| veo-3.0-generate-preview | July 31, 2025 | November 12, 2025 | veo-3.1-generate-preview | -| veo-3.0-fast-generate-preview | July 31, 2025 | November 12, 2025 | veo-3.1-fast-generate-preview | +| **Model** | **Release date** | **Shutdown date** | **Recommended replacement** | +| ----------------------------- | ----------------- | ----------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| veo-3.0-generate-001 | September 9, 2025 | June 30, 2026 | veo-3.1-generate-preview or the GA models on the [Gemini Enterprise Agent Platform](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/veo/3-1-generate) | +| veo-3.0-fast-generate-001 | September 9, 2025 | June 30, 2026 | veo-3.1-fast-generate-preview or the GA models on the [Gemini Enterprise Agent Platform](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/veo/3-1-generate) | +| veo-2.0-generate-001 | April 9, 2025 | June 30, 2026 | veo-3.1-generate-preview or the GA models on the [Gemini Enterprise Agent Platform](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/veo/3-1-generate) | +| Preview models | | | | +| veo-3.1-lite-generate-preview | March 31, 2026 | October 22, 2026 | gemini-omni-1.1-flash | +| veo-3.1-generate-preview | October 15, 2025 | October 22, 2026 | gemini-omni-1.1-flash | +| veo-3.1-fast-generate-preview | October 15, 2025 | October 22, 2026 | gemini-omni-1.1-flash | +| veo-3.0-generate-preview | July 31, 2025 | November 12, 2025 | veo-3.1-generate-preview | +| veo-3.0-fast-generate-preview | July 31, 2025 | November 12, 2025 | veo-3.1-fast-generate-preview | ## Gemini Omni Flash models -| **Model** | **Release date** | **Shutdown date** | **Recommended replacement** | -| ------------------------- | ---------------- | -------------------------- | --------------------------- | -| gemini-omni-1.1-flash | August 27, 2026 | No shutdown date announced | | -| Deprecated models | | | | -| gemini-omni-flash-preview | June 30, 2026 | September 30, 2026 | gemini-omni-1.1-flash | +| **Model** | **Release date** | **Shutdown date** | **Recommended replacement** | +| --------------------- | ---------------- | -------------------------- | --------------------------- | +| gemini-omni-1.1-flash | August 27, 2026 | No shutdown date announced | | ## Lyria models | **Model** | **Release date** | **Shutdown date** | **Recommended replacement** | | -------------------- | ----------------- | -------------------------- | --------------------------- | | lyria-3.5 | September 3, 2026 | No shutdown date announced | | +| Preview models | | | | | lyria-3-clip-preview | March 25, 2026 | No shutdown date announced | | | lyria-3-pro-preview | March 25, 2026 | No shutdown date announced | lyria-3.5 | | lyria-realtime-exp | May 20, 2025 | No shutdown date announced | | @@ -148,3 +158,11 @@ Deprecation announcements are made on the [Release notes](/gemini-api/docs/chang | Preview models | | | | | gemini-robotics-er-1.6-preview | April 14, 2026 | August 31, 2026 | gemini-robotics-er-2-preview | | gemini-robotics-er-1.5-preview | September 25, 2025 | April 30, 2026 | gemini-robotics-er-1.6-preview | + +## Managed agents + +| **Agent** | **Release date** | **Shutdown date** | **Recommended replacement** | +| --------------------------- | ------------------ | -------------------------- | --------------------------- | +| Preview agents | | | | +| antigravity-preview-09-2026 | September 17, 2026 | No shutdown date announced | | +| antigravity-preview-05-2026 | May 19, 2026 | October 5, 2026 | antigravity-preview-09-2026 | diff --git a/snapshots/groq/deprecations.md b/snapshots/groq/deprecations.md index 9d09343..7511b61 100644 --- a/snapshots/groq/deprecations.md +++ b/snapshots/groq/deprecations.md @@ -58,6 +58,23 @@ When a model is marked for deprecation, we follow this standardized process: ## [Deprecation History](#deprecation-history) +### [September 21, 2026: groq/compound and groq/compound-mini](#september-21-2026-groqcompound-and-groqcompoundmini) + +On August 24, 2026, we announced the deprecation of `groq/compound` and `groq/compound-mini`. Both systems will be decommissioned on September 21, 2026\. Beginning on that date, requests to these model IDs will return errors. Historical overviews are available for [Compound](https://console.groq.com/docs/compound/systems/compound) and [Compound Mini](https://console.groq.com/docs/compound/systems/compound-mini), along with the [Compound changelog](https://console.groq.com/docs/changelog/compound). + +| Deprecated Model | Shutdown Date | Recommended Replacement Model ID | +| ------------------ | ------------- | -------------------------------- | +| groq/compound | 09/21/26 | — | +| groq/compound-mini | 09/21/26 | — | + +### [September 14, 2026: qwen/qwen3.6-27b](#september-14-2026-qwenqwen3627b) + +In line with our commitment to bringing you cutting-edge models, we announced the deprecation of `qwen/qwen3.6-27b` in favor of `qwen/qwen3.8-27b`. Qwen 3.8 27B is the direct successor: a 27B multimodal model with the same 131K context window, thinking and instruct modes, tunable reasoning effort, tool use, and JSON mode. This deprecation applies to free and developer-tier usage; enterprise customers with a committed-spend contract are not affected. + +| Deprecated Model | Shutdown Date | Recommended Replacement Model ID | +| ---------------- | ------------- | -------------------------------- | +| qwen/qwen3.6-27b | 09/14/26 | qwen/qwen3.8-27b | + ### [August 16, 2026: llama-3.1-8b-instant and llama-3.3-70b-versatile](#august-16-2026-llama318binstant-and-llama3370bversatile) In line with our commitment to bringing you cutting-edge models, on June 17, 2026, we emailed users to announce the deprecation of `llama-3.1-8b-instant` and `llama-3.3-70b-versatile`. We recommend migrating to `openai/gpt-oss-20b` (for Llama 3.1 8B Instant) and `openai/gpt-oss-120b` or `qwen/qwen3.6-27b` (for Llama 3.3 70B Versatile), which deliver exceptional performance with faster inference. This deprecation applies to free and developer-tier usage; enterprise customers with a committed-spend contract are not affected. diff --git a/snapshots/minimax/api-overview.md b/snapshots/minimax/api-overview.md index eadad84..31baf89 100644 --- a/snapshots/minimax/api-overview.md +++ b/snapshots/minimax/api-overview.md @@ -9,31 +9,38 @@ ## Get API Key * **Pay-as-you-go**：Visit [API Keys > Create new secret key](https://platform.minimax.io/user-center/basic-information/interface-key) to get your **API Key** - Pay-as-you-go supports all modality models, including language, Video, Speech, and Image. -* **Token Plan**：Visit [Billing > Token Plan](https://platform.minimax.io/user-center/payment/token-plan) to view your **Subscription Key** - The Subscription Key is used for Token Plan subscriptions and purchased Credits. It is separate from pay-as-you-go API Keys. See [Token Plan Overview](/docs/token-plan/intro) for details. +* **M Plan**：Visit [Billing > M Plan](https://platform.minimax.io/user-center/payment/token-plan) to view your **Subscription Key** + The Subscription Key is used for M Plan subscriptions and purchased Credits. It is separate from pay-as-you-go API Keys. See [M Plan Overview](https://platform.minimax.io/docs/m-plan/intro) for details. *** ## Large Language Model -The Large Language Model API uses **MiniMax M3**, **MiniMax M2.7**, **MiniMax M2.7 highspeed**, **MiniMax M2.5**, **MiniMax M2.5 highspeed**, **MiniMax M2.1**, **MiniMax M2.1 highspeed**, and **MiniMax M2** to generate conversational content and trigger tool calls based on the provided context. +The Large Language Model API uses **MiniMax M3.1-Flash-Preview**, **MiniMax M3**, **MiniMax M2.7**, **MiniMax M2.7 highspeed**, **MiniMax M2.5**, **MiniMax M2.5 highspeed**, **MiniMax M2.1**, **MiniMax M2.1 highspeed**, and **MiniMax M2** to generate conversational content and trigger tool calls based on the provided context. + +MiniMax-M3.1-Flash-Preview is available only through M Plan and MiniMax Code for now. It can be accessed via **HTTP requests**, the **Anthropic SDK** (Recommended), or the **OpenAI SDK**. **Supported Models** -| Model Name | Context Window | Description | -| :--------------------- | :------------- | :-------------------------------------------------------------------------------------------------------------------------------------------- | -| MiniMax-M3 | 1,000,000 | **Latest M-series language model for agentic reasoning, tool use, coding, and long-context tasks** (output speed approximately 100+ tps) | -| MiniMax-M2.7 | 204,800 | **Beginning the journey of recursive self-improvement. (output speed approximately 60 tps)** | -| MiniMax-M2.7-highspeed | 204,800 | **M2.7 highspeed: Same performance, faster and more agile (output speed approximately 100 tps)** | -| MiniMax-M2.5 | 204,800 | **Peak Performance. Ultimate Value. Master the Complex (output speed approximately 60 tps)** | -| MiniMax-M2.5-highspeed | 204,800 | **M2.5 highspeed: Same performance, faster and more agile (output speed approximately 100 tps)** | -| MiniMax-M2.1 | 204,800 | **Powerful Multi-Language Programming Capabilities with Comprehensively Enhanced Programming Experience (output speed approximately 60 tps)** | -| MiniMax-M2.1-highspeed | 204,800 | **Faster and More Agile (output speed approximately 100 tps)** | -| MiniMax-M2 | 204,800 | **Agentic capabilities, Advanced reasoning** | +| Model Name | Context Window | Description | +| :- | :- | :- | +| MiniMax-M3.1-Flash-Preview | 1,000,000 | **Frontier multimodal coding model with 1M context window and tunable thinking depth** | +| MiniMax-M3 | 1,000,000 | **Frontier multimodal coding model with 1M context window** (output speed approximately 100+ tps) | +| MiniMax-M2.7 | 204,800 | **Beginning the journey of recursive self-improvement. (output speed approximately 60 tps)** | +| MiniMax-M2.7-highspeed | 204,800 | **M2.7 highspeed: Same performance, faster and more agile (output speed approximately 100 tps)** | + + + | Model Name | Context Window | Description | + | :- | :- | :- | + | MiniMax-M2.5 | 204,800 | **Peak Performance. Ultimate Value. Master the Complex (output speed approximately 60 tps)** | + | MiniMax-M2.5-highspeed | 204,800 | **M2.5 highspeed: Same performance, faster and more agile (output speed approximately 100 tps)** | + | MiniMax-M2.1 | 204,800 | **Powerful Multi-Language Programming Capabilities with Comprehensively Enhanced Programming Experience (output speed approximately 60 tps)** | + | MiniMax-M2.1-highspeed | 204,800 | **Faster and More Agile (output speed approximately 100 tps)** | + | MiniMax-M2 | 204,800 | **Agentic capabilities, Advanced reasoning** | + Please note: The maximum token count refers to the total number of input and output tokens. @@ -55,10 +62,10 @@ This API supports video generation from multimodal input (text, images, video, a **Supported Models** -| Model | Description | -| :------------- | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -| MiniMax-H3 | Multimodal video generation model supporting text / image / first-and-last-frame / reference input, 768P / 2K resolution, 4–15s duration. | -| MiniMax-H3-Max | Fast generation model. Supports text-to-video and image-to-video (first / last frame) only; reference input is not supported. 480P / 768P resolution (no 2K), 5–15s duration. | +| Model | Description | +| :- | :- | +| MiniMax-H3 | Multimodal video generation model supporting text / image / first-and-last-frame / reference input, 768P / 2K resolution, 4–15s duration. | +| MiniMax-H3-Max | Fast generation model supporting text-to-video, image-to-video (first / last frame), and reference input. 480P / 768P resolution (no 2K), 5–15s duration. | **API Usage Guide** @@ -104,14 +111,14 @@ All interfaces are stateless: each call only processes the provided input, does **Supported Models** -| Model | Description | -| :--------------- | :------------------------------------------------------------------------------------------------------- | -| speech-2.8-hd | Latest HD model. Ultra-realistic quality featuring sound tags. | -| speech-2.8-turbo | Latest Turbo model. Seamless speed meets natural flow. | -| speech-2.6-hd | HD model with outstanding prosody and excellent cloning similarity. | -| speech-2.6-turbo | Turbo model with support for 40 languages. | -| speech-02-hd | Superior rhythm and stability, with outstanding performance in replication similarity and sound quality. | -| speech-02-turbo | Superior rhythm and stability, with enhanced multilingual capabilities and excellent performance. | +| Model | Description | +| :- | :- | +| speech-2.8-hd | Latest HD model. Ultra-realistic quality featuring sound tags. | +| speech-2.8-turbo | Latest Turbo model. Seamless speed meets natural flow. | +| speech-2.6-hd | HD model with outstanding prosody and excellent cloning similarity. | +| speech-2.6-turbo | Turbo model with support for 40 languages. | +| speech-02-hd | Superior rhythm and stability, with outstanding performance in replication similarity and sound quality. | +| speech-02-turbo | Superior rhythm and stability, with enhanced multilingual capabilities and excellent performance. | **API Overview** @@ -127,22 +134,22 @@ Four capabilities share the models above: - | Support Languages | | | - | ----------------- | ------------- | ------------- | - | 1. Chinese | 15. Turkish | 28. Malay | - | 2. Cantonese | 16. Dutch | 29. Persian | - | 3. English | 17. Ukrainian | 30. Slovak | - | 4. Spanish | 18. Thai | 31. Swedish | - | 5. French | 19. Polish | 32. Croatian | - | 6. Russian | 20. Romanian | 33. Filipino | - | 7. German | 21. Greek | 34. Hungarian | - | 8. Portuguese | 22. Czech | 35. Norwegian | - | 9. Arabic | 23. Finnish | 36. Slovenian | - | 10. Italian | 24. Hindi | 37. Catalan | - | 11. Japanese | 25. Bulgarian | 38. Nynorsk | - | 12. Korean | 26. Danish | 39. Tamil | - | 13. Indonesian | 27. Hebrew | 40. Afrikaans | - | 14. Vietnamese | | | + | Support Languages | | | + | - | - | - | + | 1. Chinese | 15. Turkish | 28. Malay | + | 2. Cantonese | 16. Dutch | 29. Persian | + | 3. English | 17. Ukrainian | 30. Slovak | + | 4. Spanish | 18. Thai | 31. Swedish | + | 5. French | 19. Polish | 32. Croatian | + | 6. Russian | 20. Romanian | 33. Filipino | + | 7. German | 21. Greek | 34. Hungarian | + | 8. Portuguese | 22. Czech | 35. Norwegian | + | 9. Arabic | 23. Finnish | 36. Slovenian | + | 10. Italian | 24. Hindi | 37. Catalan | + | 11. Japanese | 25. Bulgarian | 38. Nynorsk | + | 12. Korean | 26. Danish | 39. Tamil | + | 13. Indonesian | 27. Hebrew | 40. Afrikaans | + | 14. Vietnamese | | | @@ -187,8 +194,8 @@ You can generate images by creating an image generation task using text prompts **Model List** -| Model | Description | -| :------- | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| Model | Description | +| :- | :- | | image-01 | A high-quality image generation model that produces fine-grained details. Supports both text-to-image and image-to-image generation (with subject reference for people). | @@ -215,8 +222,8 @@ This API generates a vocal song based on a music description (prompt) and lyrics **Models** -| Model | Usage | -| :-------- | :--------------------------------------------------------------------------------------------------------------------- | +| Model | Usage | +| :- | :- | | music-3.0 | The latest music generation model. Supports user-provided musical inspiration and lyrics to create AI-generated music. | diff --git a/snapshots/mistral/models.md b/snapshots/mistral/models.md index 15d14db..b3804b8 100644 --- a/snapshots/mistral/models.md +++ b/snapshots/mistral/models.md @@ -12,7 +12,7 @@ Featured Models ## Featured Models -[![Mistral Medium 3.5 icon](/assets/models/Mistral_Medium_3.svg)Mistral Medium 3.5Our frontier-class multimodal model optimized for agentic and coding use cases.](/models/mistral-medium-3-5-26-04)[![OCR 4.1 icon](/assets/models/OCR.svg)OCR 4.1Our latest OCR service with paragraph-level bounding boxes, structural block labels, and block-level confidence scores.](/models/ocr-4-1)[![Z.ai GLM 5.2 icon](/assets/models/Zai_GLM.svg)Z.ai GLM 5.2A third-party open source text model from Z.ai with a 1M-token context window.](/models/zai-glm-5-2)[![Mistral Small 4 icon](/assets/models/Mistral_Small_3.1.svg)Mistral Small 4Hybrid model unifying instruct, reasoning, and coding in a single efficient model.](/models/mistral-small-4-0-26-03)[![Voxtral Mini Transcribe 2 icon](/assets/models/Voxtral.svg)Voxtral Mini Transcribe 2An efficient audio input model, pre-trained and optimized for transcription purposes.](/models/voxtral-mini-transcribe-26-02)[![Voxtral Mini Transcribe Realtime icon](/assets/models/Voxtral.svg)Voxtral Mini Transcribe RealtimeAn efficient audio input model, pre-trained and optimized for live transcription purposes.](/models/voxtral-mini-transcribe-realtime-26-02) +[![Mistral Medium 3.5 icon](/assets/models/Mistral_Medium_3.svg)Mistral Medium 3.5Our frontier-class multimodal model optimized for agentic and coding use cases.](/models/mistral-medium-3-5-26-04)[![OCR 4.1 icon](/assets/models/OCR.svg)OCR 4.1Our latest OCR service with paragraph-level bounding boxes, structural block labels, and block-level confidence scores.](/models/ocr-4-1)[![Z.ai GLM 5.3 icon](/assets/models/Zai_GLM.svg)Z.ai GLM 5.3A third-party open weight text model from Z.ai with a 1M-token context window.](/models/zai-glm-5-3)[![Mistral Small 4 icon](/assets/models/Mistral_Small_3.1.svg)Mistral Small 4Hybrid model unifying instruct, reasoning, and coding in a single efficient model.](/models/mistral-small-4-0-26-03)[![Voxtral Mini Transcribe 2 icon](/assets/models/Voxtral.svg)Voxtral Mini Transcribe 2An efficient audio input model, pre-trained and optimized for transcription purposes.](/models/voxtral-mini-transcribe-26-02)[![Voxtral Mini Transcribe Realtime icon](/assets/models/Voxtral.svg)Voxtral Mini Transcribe RealtimeAn efficient audio input model, pre-trained and optimized for live transcription purposes.](/models/voxtral-mini-transcribe-realtime-26-02) All models @@ -26,7 +26,7 @@ Generalist models Text and multimodal models for broad reasoning, coding, tool use, and agentic tasks. -[![Z.ai GLM 5.2 icon](/assets/models/Zai_GLM.svg)Z.ai GLM 5.2A third-party open source text model from Z.ai with a 1M-token context window.v5.2](/models/zai-glm-5-2)[![Mistral Medium 3.5 icon](/assets/models/Mistral_Medium_3.svg)Mistral Medium 3.5Our frontier-class multimodal model optimized for agentic and coding use cases.v26.04](/models/mistral-medium-3-5-26-04)[![Mistral Small 4 icon](/assets/models/Mistral_Small_3.1.svg)Mistral Small 4Hybrid model unifying instruct, reasoning, and coding in a single efficient model.v26.03](/models/mistral-small-4-0-26-03)[![Mistral Large 3 icon](/assets/models/Mistral_Large_2.svg)Mistral Large 3A state-of-the-art, open-weight, general-purpose multimodal model.v25.12](/models/mistral-large-3-25-12)[![Ministral 3 14B icon](/assets/models/Ministral.svg)Ministral 3 14BA powerful model offering best-in-class text and vision capabilities.v25.12](/models/ministral-3-14b-25-12)[![Ministral 3 8B icon](/assets/models/Ministral.svg)Ministral 3 8BA powerful and efficient model offering best-in-class text and vision capabilities.v25.12](/models/ministral-3-8b-25-12)[![Ministral 3 3B icon](/assets/models/Ministral.svg)Ministral 3 3BA tiny and efficient model offering best-in-class text and vision capabilities.v25.12](/models/ministral-3-3b-25-12) +[![Z.ai GLM 5.3 icon](/assets/models/Zai_GLM.svg)Z.ai GLM 5.3A third-party open weight text model from Z.ai with a 1M-token context window.v5.3](/models/zai-glm-5-3)[![Mistral Medium 3.5 icon](/assets/models/Mistral_Medium_3.svg)Mistral Medium 3.5Our frontier-class multimodal model optimized for agentic and coding use cases.v26.04](/models/mistral-medium-3-5-26-04)[![Mistral Small 4 icon](/assets/models/Mistral_Small_3.1.svg)Mistral Small 4Hybrid model unifying instruct, reasoning, and coding in a single efficient model.v26.03](/models/mistral-small-4-0-26-03)[![Mistral Large 3 icon](/assets/models/Mistral_Large_2.svg)Mistral Large 3A state-of-the-art, open-weight, general-purpose multimodal model.v25.12](/models/mistral-large-3-25-12)[![Ministral 3 14B icon](/assets/models/Ministral.svg)Ministral 3 14BA powerful model offering best-in-class text and vision capabilities.v25.12](/models/ministral-3-14b-25-12)[![Ministral 3 8B icon](/assets/models/Ministral.svg)Ministral 3 8BA powerful and efficient model offering best-in-class text and vision capabilities.v25.12](/models/ministral-3-8b-25-12)[![Ministral 3 3B icon](/assets/models/Ministral.svg)Ministral 3 3BA tiny and efficient model offering best-in-class text and vision capabilities.v25.12](/models/ministral-3-3b-25-12) OCR models @@ -34,7 +34,7 @@ OCR models Models for document understanding, text extraction, and structured OCR outputs. -[![OCR 4.1 icon](/assets/models/OCR.svg)OCR 4.1Our latest OCR service with paragraph-level bounding boxes, structural block labels, and block-level confidence scores.v4.1](/models/ocr-4-1)[![OCR 4.0 icon](/assets/models/OCR.svg)OCR 4.0Our latest OCR service with paragraph-level bounding boxes and structural block labels.v4.0](/models/ocr-4-0)[![OCR 3 icon](/assets/models/OCR.svg)OCR 3Our OCR service powering our Document AI stack. OCR 4 is available as the newer model. OCR 3 remains available for existing integrations and production workloads.v25.12](/models/ocr-3-25-12) +[![OCR 4.1 icon](/assets/models/OCR.svg)OCR 4.1Our latest OCR service with paragraph-level bounding boxes, structural block labels, and block-level confidence scores.v4.1](/models/ocr-4-1)[![OCR 3 icon](/assets/models/OCR.svg)OCR 3Our OCR service powering our Document AI stack. OCR 4 is available as the newer model. OCR 3 remains available for existing integrations and production workloads.v25.12](/models/ocr-3-25-12) Audio models @@ -68,14 +68,6 @@ Models for safety filtering, moderation, and policy checks. [![Shieldstral 1.0 icon](/assets/models/Shieldstral.svg)Shieldstral 1.0Compact multimodal moderation model for text and image safety classification.v1.0](/models/shieldstral-1-0)[![Mistral Moderation 2 icon](/assets/models/Moderation.svg)Mistral Moderation 2Our latest moderation model with 128k context window and jailbreaking detection.v26.03](/models/mistral-moderation-26-03) -Other specialist models - -### Other specialist models - -Specialized models for focused domains and task-specific workloads. - -[![Leanstral 1.5 icon](/assets/models/Leanstral.svg)Leanstral 1.5Updated code agent for Lean 4 formal proof engineering and automated theorem proving.v1.5](/models/leanstral-1-5) - Deprecated ### Deprecated @@ -86,9 +78,12 @@ Older models that have been deprecated or retired. | Model | Version | API | Deprecation | Retirement | Alternative | | ------------------------------------------------------------------ | ------- | --------------------------- | ----------- | ---------- | ------------------------------------------------------------------ | +| [Z.ai GLM 5.2 ↗](/models/zai-glm-5-2) | 5.2 | zai-glm-5-2 | 9/29/2026 | 10/31/2026 | [Z.ai GLM 5.3](/models/zai-glm-5-3) | +| [Leanstral 1.5 ↗](/models/leanstral-1-5) | 1.5 | labs-leanstral-1-5 | 9/29/2026 | 9/30/2026 | | | [Leanstral ↗](/models/leanstral-26-03) | 26.03 | labs-leanstral-2603 | 5/22/2026 | 6/30/2026 | [Leanstral 1.5](/models/leanstral-1-5) | | [Mistral Medium 3.1 ↗](/models/mistral-medium-3-1-25-08) | 25.08 | mistral-medium-2508 | 5/22/2026 | 8/31/2026 | [Mistral Medium 3.5](/models/mistral-medium-3-5-26-04) | | [Mistral Small 3.2 ↗](/models/mistral-small-3-2-25-06) | 25.06 | mistral-small-2506 | 4/30/2026 | 7/31/2026 | [Mistral Small 4](/models/mistral-small-4-0-26-03) | +| [OCR 4.0 ↗](/models/ocr-4-0) | 4.0 | mistral-ocr-4-0 | 9/29/2026 | 9/30/2026 | [OCR 4.1](/models/ocr-4-1) | | [Voxtral Mini Transcribe ↗](/models/voxtral-mini-transcribe-25-07) | 25.07 | voxtral-mini-2507 | 2/27/2026 | 5/31/2026 | [Voxtral Mini Transcribe 2](/models/voxtral-mini-transcribe-26-02) | | [Devstral 2 ↗](/models/devstral-2-25-12) | 25.12 | devstral-2512 | 5/22/2026 | 7/31/2026 | [Mistral Medium 3.5](/models/mistral-medium-3-5-26-04) | | [Magistral Medium 1.1 ↗](/models/magistral-medium-1-1-25-07) | 25.07 | magistral-medium-2507 | 10/31/2025 | 11/30/2025 | [Mistral Medium 3.5](/models/mistral-medium-3-5-26-04) | diff --git a/snapshots/moonshot/models.md b/snapshots/moonshot/models.md index d51b326..1846121 100644 --- a/snapshots/moonshot/models.md +++ b/snapshots/moonshot/models.md @@ -8,18 +8,14 @@ Click [here](pricing/chat) to see more details of model price. - - The `kimi-k2.5` and `moonshot-v1` series were officially retired on August 31, 2026. Calls to these models now return a 404 (model not found) error. Please migrate to [kimi-k3](/docs/guide/kimi-k3-quickstart) or other latest models. - - ## Multi-modal Model -| Model Name | Description | -| -------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -| `kimi-k3` | Kimi's most capable model to date, with 2.8 trillion parameters, native visual understanding, and a 1M-token context window, designed for frontier intelligence scenarios such as software engineering, knowledge work, and deep reasoning. | -| `kimi-k2.7-code` | Kimi's dedicated coding model. It follows instructions more reliably in long contexts, completes coding tasks with higher success rates. Context 256k | -| `kimi-k2.7-code-highspeed` | High-Speed version of Kimi K2.7 Code model, with output speed of approximately 180 Tokens/s and up to 260 Tokens/s in short context scenarios, delivering a more extreme coding experience. | -| `kimi-k2.6` | Supports both visual and text input, thinking and non-thinking modes, and dialogue and Agent tasks. Context 256k | +| Model Name | Description | +| - | - | +| `kimi-k3` | Kimi's most capable model to date, with 2.8 trillion parameters, native visual understanding, and a 1M-token context window, designed for frontier intelligence scenarios such as software engineering, knowledge work, and deep reasoning. | +| `kimi-k2.7-code` | Kimi's dedicated coding model. It follows instructions more reliably in long contexts, completes coding tasks with higher success rates. Context 256k | +| `kimi-k2.7-code-highspeed` | High-Speed version of Kimi K2.7 Code model, with output speed of approximately 180 Tokens/s and up to 260 Tokens/s in short context scenarios, delivering a more extreme coding experience. | +| `kimi-k2.6` | Supports both visual and text input, thinking and non-thinking modes, and dialogue and Agent tasks. Context 256k | ## Deprecated Models @@ -29,21 +25,21 @@ Click [here](pricing/chat) to see more details of model price. > The `kimi-k2` series models were officially discontinued on **May 25, 2026** and are no longer maintained or supported. Please use the latest Kimi model [kimi-k3](/docs/guide/kimi-k3-quickstart) for continued support and enhanced reasoning capabilities. -| Model Name | Description | -| --------------------------------- | ----------- | -| `kimi-k2.5` | Deprecated | -| `moonshot-v1-8k` | Deprecated | -| `moonshot-v1-32k` | Deprecated | -| `moonshot-v1-128k` | Deprecated | -| `moonshot-v1-auto` | Deprecated | -| `moonshot-v1-8k-vision-preview` | Deprecated | -| `moonshot-v1-32k-vision-preview` | Deprecated | -| `moonshot-v1-128k-vision-preview` | Deprecated | -| `kimi-k2-0905-preview` | Deprecated | -| `kimi-k2-0711-preview` | Deprecated | -| `kimi-k2-turbo-preview` | Deprecated | -| `kimi-k2-thinking` | Deprecated | -| `kimi-k2-thinking-turbo` | Deprecated | +| Model Name | Description | +| - | - | +| `kimi-k2.5` | Deprecated | +| `moonshot-v1-8k` | Deprecated | +| `moonshot-v1-32k` | Deprecated | +| `moonshot-v1-128k` | Deprecated | +| `moonshot-v1-auto` | Deprecated | +| `moonshot-v1-8k-vision-preview` | Deprecated | +| `moonshot-v1-32k-vision-preview` | Deprecated | +| `moonshot-v1-128k-vision-preview` | Deprecated | +| `kimi-k2-0905-preview` | Deprecated | +| `kimi-k2-0711-preview` | Deprecated | +| `kimi-k2-turbo-preview` | Deprecated | +| `kimi-k2-thinking` | Deprecated | +| `kimi-k2-thinking-turbo` | Deprecated | > `kimi-latest` was officially discontinued on **January 28, 2026** and is no longer maintained or supported. Please use the latest Kimi model [kimi-k3](/docs/guide/kimi-k3-quickstart) for continued support and enhanced reasoning capabilities. diff --git a/snapshots/openai/deprecations.md b/snapshots/openai/deprecations.md index 70df17d..cda9025 100644 --- a/snapshots/openai/deprecations.md +++ b/snapshots/openai/deprecations.md @@ -34,6 +34,14 @@ We use the term "legacy" to refer to models and endpoints that no longer receive Upcoming deprecations are listed below, with the most recent announcements at the top. +### 2026-09-11: GPT-5.4-Cyber + +The `gpt-5.4-cyber` model is deprecated and will be removed from the API on October 1, 2026. Migrate to the most capable cyber model available to you before the shutdown date. + +| Shutdown date | Model / system | Recommended replacement | +| ------------- | --------------- | ---------------------------------------------- | +| Oct 1, 2026 | `gpt-5.4-cyber` | The most capable cyber model available to you. | + ### 2026-08-26: Transcription models On August 26, 2026, we notified developers using `whisper-1`, `gpt-4o-transcribe`, `gpt-4o-mini-transcribe`, and `gpt-4o-transcribe-diarize` of their deprecation and removal from the API on February 26, 2027. @@ -116,11 +124,11 @@ See [Migrate from Agent Builder](https://developers.openai.com/api/docs/guides/a On June 2, 2026, we notified developers using older GPT Image models of their deprecation and removal from the API on December 1, 2026. -| Shutdown date | Model / system | Recommended replacement | -| ------------- | ---------------------- | ----------------------- | -| Dec 1, 2026 | `gpt-image-1-mini` | `gpt-image-2` | -| Dec 1, 2026 | `gpt-image-1.5` | `gpt-image-2` | -| Dec 1, 2026 | `chatgpt-image-latest` | `gpt-image-2` | +| Shutdown date | Model / system | Recommended replacement | +| ------------- | ---------------------- | ------------------------------------------------- | +| Dec 1, 2026 | `gpt-image-1-mini` | `gpt-image-2.5-sunburst` or `gpt-image-2.5-flare` | +| Dec 1, 2026 | `gpt-image-1.5` | `gpt-image-2.5-sunburst` or `gpt-image-2.5-flare` | +| Dec 1, 2026 | `chatgpt-image-latest` | `gpt-image-2.5-sunburst` or `gpt-image-2.5-flare` | ### Update to OpenAI’s self-serve fine-tuning @@ -134,24 +142,37 @@ Inference on fine-tuned models will continue to be available until the base mode | July 2, 2026 | Creating fine-tuning jobs is no longer available to organizations that have not run inference on a fine-tuned model in the past 60 days. | | Jan 6, 2027 | Active existing customers will no longer be able to create new fine-tuning jobs on this date. Inference on fine-tuned models will be disabled only when the underlying base model is deprecated. | +## Past deprecations + +Past deprecations are listed below, with the most recent announcements at the top. + +### 2026-05-08: `gpt-5.2-chat-latest` and `gpt-5.3-chat-latest` model snapshots + +On May 8th, 2026, we notified developers using `gpt-5.2-chat-latest` and `gpt-5.3-chat-latest` model snapshots of their deprecation and removal from the API. + +| Shutdown date | Model / system | Recommended replacement | +| ------------- | --------------------- | ----------------------- | +| Aug 10, 2026 | `gpt-5.2-chat-latest` | `gpt-5.6-sol` | +| Aug 10, 2026 | `gpt-5.3-chat-latest` | `gpt-5.6-sol` | + ### 2026-04-22: Legacy GPT model snapshots To improve reliability and make it easier for developers to choose the right models, we are deprecating a set of older OpenAI models. Access to these models will be shut down on the dates below. -| Shutdown date | Model snapshot | Substitute model | -| ---------------- | ---------------------------------------------------------------------- | ------------------------------------- | -| October 23, 2026 | `gpt-3.5-turbo-0125` \| `gpt-3.5-turbo`, `gpt-3.5-turbo-completions` | `gpt-5.6-terra` | -| October 23, 2026 | `gpt-4-0613` \| `gpt-4`, `gpt-4-0613-completions`, `gpt-4-completions` | `gpt-5.6-sol` | -| October 23, 2026 | `gpt-4-1106-preview` | `gpt-5.6-sol` | -| October 23, 2026 | `gpt-4-turbo` \| `gpt-4-turbo-2024-04-09`, `gpt-4-turbo-completions` | `gpt-5.6-sol` | -| October 23, 2026 | `gpt-4.1-nano` \| `gpt-4.1-nano-2025-04-14` | `gpt-5.6-luna` | -| October 23, 2026 | `gpt-4o-2024-05-13` | `gpt-5.6-sol` | -| October 23, 2026 | `gpt-image-1` | `gpt-image-2` | -| October 23, 2026 | `o1-2024-12-17` \| `o1` | `gpt-5.6-sol` | -| October 23, 2026 | `o1-pro-2025-03-19` \| `o1-pro` | `gpt-5.6-sol` (`reasoning.mode: pro`) | -| October 23, 2026 | `o3-mini-2025-01-31` \| `o3-mini` | `gpt-5.6-sol` | -| October 23, 2026 | `ft-o4-mini-2025-04-16` | `gpt-5.6-terra` | -| October 23, 2026 | `o4-mini-2025-04-16` \| `o4-mini` | `gpt-5.6-terra` | +| Shutdown date | Model snapshot | Substitute model | +| ---------------- | ---------------------------------------------------------------------- | ------------------------------------------------- | +| October 23, 2026 | `gpt-3.5-turbo-0125` \| `gpt-3.5-turbo`, `gpt-3.5-turbo-completions` | `gpt-5.6-terra` | +| October 23, 2026 | `gpt-4-0613` \| `gpt-4`, `gpt-4-0613-completions`, `gpt-4-completions` | `gpt-5.6-sol` | +| October 23, 2026 | `gpt-4-1106-preview` | `gpt-5.6-sol` | +| October 23, 2026 | `gpt-4-turbo` \| `gpt-4-turbo-2024-04-09`, `gpt-4-turbo-completions` | `gpt-5.6-sol` | +| October 23, 2026 | `gpt-4.1-nano` \| `gpt-4.1-nano-2025-04-14` | `gpt-5.6-luna` | +| October 23, 2026 | `gpt-4o-2024-05-13` | `gpt-5.6-sol` | +| October 23, 2026 | `gpt-image-1` | `gpt-image-2.5-sunburst` or `gpt-image-2.5-flare` | +| October 23, 2026 | `o1-2024-12-17` \| `o1` | `gpt-5.6-sol` | +| October 23, 2026 | `o1-pro-2025-03-19` \| `o1-pro` | `gpt-5.6-sol` (`reasoning.mode: pro`) | +| October 23, 2026 | `o3-mini-2025-01-31` \| `o3-mini` | `gpt-5.6-sol` | +| October 23, 2026 | `ft-o4-mini-2025-04-16` | `gpt-5.6-terra` | +| October 23, 2026 | `o4-mini-2025-04-16` \| `o4-mini` | `gpt-5.6-terra` | We are also removing fine-tuned versions as below: @@ -163,43 +184,6 @@ We are also removing fine-tuned versions as below: | October 23, 2026 | `ft-babbage-002` | `gpt-5.6-terra` | | October 23, 2026 | `ft-davinci-002` | `gpt-5.6-terra` | -### 2026-03-24: Sora 2 video generation models and Videos API - -On March 24th, 2026, we notified developers using the Videos API and Sora 2 video generation model aliases and snapshots of their deprecation and removal from the API on September 24, 2026. - -| Shutdown date | Model / system | Recommended replacement | -| ------------- | ----------------------- | ----------------------- | -| 2026-09-24 | Videos API | --- | -| 2026-09-24 | `sora-2` | --- | -| 2026-09-24 | `sora-2-pro` | --- | -| 2026-09-24 | `sora-2-2025-10-06` | --- | -| 2026-09-24 | `sora-2-2025-12-08` | --- | -| 2026-09-24 | `sora-2-pro-2025-10-06` | --- | - -### 2025-09-26: Legacy GPT model snapshots - -To improve reliability and make it easier for developers to choose the right models, we are deprecating a set of older OpenAI models with declining usage over the next six to twelve months. Access to these models will be shut down on the dates below. - -| Shutdown date | Model / system | Recommended replacement | -| ------------- | ------------------------ | ----------------------- | -| 2026-09-28 | `gpt-3.5-turbo-instruct` | `gpt-5.6-terra` | -| 2026-09-28 | `babbage-002` | `gpt-5.6-terra` | -| 2026-09-28 | `davinci-002` | `gpt-5.6-terra` | -| 2026-09-28 | `gpt-3.5-turbo-1106` | `gpt-5.6-terra` | - -## Past deprecations - -Past deprecations are listed below, with the most recent announcements at the top. - -### 2026-05-08: gpt-5.2-chat-latest and gpt-5.3-chat-latest model snapshots - -On May 8th, 2026, we notified developers using `gpt-5.2-chat-latest` and `gpt-5.3-chat-latest` model snapshots of their deprecation and removal from the API. - -| Shutdown date | Model / system | Recommended replacement | -| ------------- | --------------------- | ----------------------- | -| Aug 10, 2026 | `gpt-5.2-chat-latest` | `gpt-5.6-sol` | -| Aug 10, 2026 | `gpt-5.3-chat-latest` | `gpt-5.6-sol` | - ### 2026-04-22: Legacy GPT model snapshots (July 2026 shutdown) On April 22, 2026, we announced the deprecation of the following older OpenAI models. Access to these models was shut down on July 23, 2026. @@ -221,7 +205,20 @@ On April 22, 2026, we announced the deprecation of the following older OpenAI mo | July 23, 2026 | `o4-mini-deep-research-2025-06-26` \| `o4-mini-deep-research` | `gpt-5.6-sol` | | July 23, 2026 | `gpt-5.2-codex` | `gpt-5.6-sol` | -### 2025-11-18: chatgpt-4o-latest snapshot +### 2026-03-24: Sora 2 video generation models and Videos API + +On March 24th, 2026, we notified developers using the Videos API and Sora 2 video generation model aliases and snapshots of their deprecation and removal from the API on September 24, 2026. + +| Shutdown date | Model / system | Recommended replacement | +| ------------- | ----------------------- | ----------------------- | +| 2026-09-24 | Videos API | --- | +| 2026-09-24 | `sora-2` | --- | +| 2026-09-24 | `sora-2-pro` | --- | +| 2026-09-24 | `sora-2-2025-10-06` | --- | +| 2026-09-24 | `sora-2-2025-12-08` | --- | +| 2026-09-24 | `sora-2-pro-2025-10-06` | --- | + +### 2025-11-18: `chatgpt-4o-latest` snapshot On November 18th, 2025, we notified developers using `chatgpt-4o-latest` model snapshot of its deprecation and removal from the API on February 17, 2026. @@ -229,7 +226,7 @@ On November 18th, 2025, we notified developers using `chatgpt-4o-latest` model s | ------------- | ------------------- | ----------------------- | | 2026-02-17 | `chatgpt-4o-latest` | `gpt-5.1-chat-latest` | -### 2025-11-17: codex-mini-latest model snapshot +### 2025-11-17: `codex-mini-latest` model snapshot On November 17th, 2025, we notified developers using `codex-mini-latest` model of its deprecation and removal from the API on February 12, 2026. As part of this deprecation, we will no longer support our legacy local shell tool, which is only available for use with `codex-mini-latest`. For new use cases, please use our latest shell tool. @@ -246,6 +243,17 @@ On November 14th, 2025, we notified developers using DALL·E model snapshots of | 2026-05-12 | `dall-e-2` | `gpt-image-2`, `gpt-image-1`, or `gpt-image-1-mini` | | 2026-05-12 | `dall-e-3` | `gpt-image-2`, `gpt-image-1`, or `gpt-image-1-mini` | +### 2025-09-26: Legacy GPT model snapshots + +To improve reliability and make it easier for developers to choose the right models, we are deprecating a set of older OpenAI models with declining usage over the next six to twelve months. Access to these models will be shut down on the dates below. + +| Shutdown date | Model / system | Recommended replacement | +| ------------- | ------------------------ | ----------------------- | +| 2026-09-28 | `gpt-3.5-turbo-instruct` | `gpt-5.6-terra` | +| 2026-09-28 | `babbage-002` | `gpt-5.6-terra` | +| 2026-09-28 | `davinci-002` | `gpt-5.6-terra` | +| 2026-09-28 | `gpt-3.5-turbo-1106` | `gpt-5.6-terra` | + ### 2025-09-26: Legacy GPT model snapshots (March 2026 shutdown) To improve reliability and make it easier for developers to choose the right models, we deprecated a set of older OpenAI models with declining usage. Access to these models was shut down on March 26, 2026. @@ -262,24 +270,24 @@ To improve reliability and make it easier for developers to choose the right mod The Realtime API Beta was deprecated and removed from the API on May 12, 2026. -There are a few key differences between the interfaces in the Realtime beta API and the released GA API. See [the migration guide](https://developers.openai.com/api/docs/guides/realtime#beta-to-ga-migration) for the current GA interface and related Realtime docs. +The interfaces in the Realtime beta API and the released GA API have a few key differences. See [the migration guide](https://developers.openai.com/api/docs/guides/realtime#beta-to-ga-migration) for the current GA interface and related Realtime docs. | Shutdown date | Model / system | Recommended replacement | | ------------- | ------------------------ | ----------------------- | | 2026‑05‑12 | OpenAI-Beta: realtime=v1 | Realtime API | -### 2025-09-15: gpt-4o-realtime-preview models +### 2025-09-15: `gpt-4o-realtime-preview` models -In September, 2025, we notified developers using gpt-4o-realtime-preview models of their deprecation and removal from the API in six months. +In September, 2025, we notified developers using `gpt-4o-realtime-preview` models of their deprecation and removal from the API in six months. -| Shutdown date | Model / system | Recommended replacement | -| ------------- | ---------------------------------- | ----------------------- | -| 2026-05-07 | gpt-4o-realtime-preview | gpt-realtime-1.5 | -| 2026-05-07 | gpt-4o-realtime-preview-2025-06-03 | gpt-realtime-1.5 | -| 2026-05-07 | gpt-4o-realtime-preview-2024-12-17 | gpt-realtime-1.5 | -| 2026-05-07 | gpt-4o-mini-realtime-preview | gpt-realtime-mini | -| 2026-05-07 | gpt-4o-audio-preview | gpt-audio-1.5 | -| 2026-05-07 | gpt-4o-mini-audio-preview | gpt-audio-mini | +| Shutdown date | Model / system | Recommended replacement | +| ------------- | ------------------------------------ | ----------------------- | +| 2026-05-07 | `gpt-4o-realtime-preview` | `gpt-realtime-1.5` | +| 2026-05-07 | `gpt-4o-realtime-preview-2025-06-03` | `gpt-realtime-1.5` | +| 2026-05-07 | `gpt-4o-realtime-preview-2024-12-17` | `gpt-realtime-1.5` | +| 2026-05-07 | `gpt-4o-mini-realtime-preview` | `gpt-realtime-mini` | +| 2026-05-07 | `gpt-4o-audio-preview` | `gpt-audio-1.5` | +| 2026-05-07 | `gpt-4o-mini-audio-preview` | `gpt-audio-mini` | ### 2025-08-20: Assistants API @@ -293,15 +301,15 @@ See the Assistants to Conversations [migration guide](https://developers.openai. | ------------- | -------------- | ----------------------------------- | | 2026‑08‑26 | Assistants API | Responses API and Conversations API | -### 2025-06-10: gpt-4o-realtime-preview-2024-10-01 +### 2025-06-10: `gpt-4o-realtime-preview-2024-10-01` -On June 10th, 2025, we notified developers using gpt-4o-realtime-preview-2024-10-01 of its deprecation and removal from the API in three months. +On June 10th, 2025, we notified developers using `gpt-4o-realtime-preview-2024-10-01` of its deprecation and removal from the API in three months. -| Shutdown date | Model / system | Recommended replacement | -| ------------- | ---------------------------------- | ----------------------- | -| 2025-10-10 | gpt-4o-realtime-preview-2024-10-01 | gpt-realtime-1.5 | +| Shutdown date | Model / system | Recommended replacement | +| ------------- | ------------------------------------ | ----------------------- | +| 2025-10-10 | `gpt-4o-realtime-preview-2024-10-01` | `gpt-realtime-1.5` | -### 2025-06-10: gpt-4o-audio-preview-2024-10-01 +### 2025-06-10: `gpt-4o-audio-preview-2024-10-01` On June 10th, 2025, we notified developers using `gpt-4o-audio-preview-2024-10-01` of its deprecation and removal from the API in three months. @@ -309,7 +317,7 @@ On June 10th, 2025, we notified developers using `gpt-4o-audio-preview-2024-10-0 | ------------- | --------------------------------- | ----------------------- | | 2025-10-10 | `gpt-4o-audio-preview-2024-10-01` | `gpt-audio-1.5` | -### 2025-04-28: text-moderation +### 2025-04-28: `text-moderation` On April 28th, 2025, we notified developers using `text-moderation` of its deprecation and removal from the API in six months. @@ -319,7 +327,7 @@ On April 28th, 2025, we notified developers using `text-moderation` of its depre | 2025-10-27 | `text-moderation-stable` | `omni-moderation` | | 2025-10-27 | `text-moderation-latest` | `omni-moderation` | -### 2025-04-28: o1-preview and o1-mini +### 2025-04-28: `o1-preview` and `o1-mini` On April 28th, 2025, we notified developers using `o1-preview` and `o1-mini` of their deprecations and removal from the API in three months and six months respectively. diff --git a/snapshots/perplexity/changelog.md b/snapshots/perplexity/changelog.md index 1572863..b2a3ec5 100644 --- a/snapshots/perplexity/changelog.md +++ b/snapshots/perplexity/changelog.md @@ -4,10 +4,108 @@ # Changelog +> Updates to the Perplexity API platform. + Looking ahead? Check out our [Feature Roadmap](/docs/resources/feature-roadmap) to see what's coming next. + + **GPT-6.1 Sol** + + The Agent API now supports `openai/gpt-6.1-sol`. See the [Agent API Models reference](/docs/agent-api/models). + + + + **Claude Sonnet 5.5** + + The Agent API now supports `anthropic/claude-sonnet-5-5`. See the [Agent API Models reference](/docs/agent-api/models). + + + + **xhigh preset uses Claude Opus 5.5** + + The Agent API `xhigh` preset now uses Claude Opus 5.5: + + | Preset | Previous model | New model | + | - | - | - | + | `xhigh` | `openai/gpt-5.6-sol` | `anthropic/claude-opus-5-5` | + + Prompts, reasoning effort, tools, token budgets, and step limits are unchanged. + + + + **Low, medium, and high presets use GPT-6** + + The Agent API `low`, `medium`, and `high` presets now use the GPT-6 model family: + + | Preset | Previous model | New model | + | - | - | - | + | `low` | `openai/gpt-5.6-luna` | `openai/gpt-6-luna` | + | `medium` | `openai/gpt-5.6-luna` | `openai/gpt-6-luna` | + | `high` | `openai/gpt-5.6-sol` | `openai/gpt-6-sol` | + + Prompts, reasoning effort, tools, token budgets, and step limits are unchanged. + + + + **Upcoming retirement of older OpenAI models** + + On October 24, 2026 at 00:00 UTC, the Agent API and Router API will retire these model IDs: + + * `openai/gpt-5.4` + * `openai/gpt-5.4-mini` + * `openai/gpt-5.4-nano` + * `openai/gpt-5.2` + * `openai/gpt-5.1` + * `openai/gpt-5` + * `openai/gpt-5-mini` + + Update direct model selections and fallback chains before the cutoff. The models remain available until then. After the cutoff, the retired IDs will no longer be accepted or returned by model-list endpoints. + + For new integrations, choose a current OpenAI model in the [Agent API Models reference](/docs/agent-api/models). + + + + **Fast preset uses Fast Search** + + The Agent API `fast` preset now uses Fast Search (`search_type: "fast"`). `web_search` drops from \$2.50 to \$1.00 per 1,000 invocations, and search is about 800 ms faster. See [Agent API Web Search](/docs/agent-api/tools/web-search#search-type). + + + + **Fast Search** + + Set `search_type: "fast"` on the Search API or the Agent API `web_search` tool to use a lower-latency search path. Fast Search costs \$1.00 per 1,000 Search API requests or `web_search` invocations, with model tokens billed separately for Agent API. Set `search_type: "web"` for standard web search. See [Search API Fast Search](/docs/search/fast-search) or [Agent API Web Search](/docs/agent-api/tools/web-search#search-type). + + + + **GPT-6 Sol** + + The Agent API now supports `openai/gpt-6-sol`. See the [Agent API Models reference](/docs/agent-api/models). + + **GPT-6 Luna** + + The Agent API now supports `openai/gpt-6-luna`. See the [Agent API Models reference](/docs/agent-api/models). + + **Claude Opus 5.5** + + The Agent API now supports `anthropic/claude-opus-5-5`. See the [Agent API Models reference](/docs/agent-api/models). + + **Grok 4.7** + + The Agent API now supports `xai/grok-4.7`. See the [Agent API Models reference](/docs/agent-api/models). + + + + **Custom connectors: Bring your own MCP server** + + Register a remote MCP server once on your [Project connectors page](https://console.perplexity.ai/project/connectors). + Perplexity stores the server's credential, so your application does not need to store or send it with each request. + Use the generated connector ID with `type: "connector"` in Agent API requests. + Custom connectors are available to all Projects and support API-key or no authentication, with Streamable HTTP or SSE transport. + See [Add a custom connector](/docs/agent-api/tools/connectors#add-a-custom-connector). + + **Sign in with Perplexity for the remote MCP server** @@ -41,7 +139,7 @@ **Fast preset updated** - The Agent API `fast` preset now uses `openai/gpt-5.6-luna` with `minimal` reasoning effort and priority processing. Dynamic `fast` preset requests pick up the change automatically. If you use a [frozen configuration](/docs/agent-api/presets#current-preset-values), update the model and reasoning effort and set `service_tier` to `priority`. Priority processing uses 2× the model's standard token prices. + The Agent API `fast` preset now uses `openai/gpt-6-luna` with reasoning effort set to `none` and priority processing. Dynamic `fast` preset requests pick up the change automatically. If you use a [frozen configuration](/docs/agent-api/presets#current-preset-values), update the model and reasoning effort and set `service_tier` to `priority`. Priority processing uses 2× the model's standard token prices. @@ -62,18 +160,6 @@ The Agent API and Router API now support `perplexity/nemotron-3-ultra-550b-a55b` at \$0.25 per million input or cached-input tokens and \$2.50 per million output tokens. See the [Agent API Models reference](/docs/agent-api/models) or the [Router model catalog](/docs/router/models). - - **NVIDIA Nemotron 3.5 Lightning** - - The Agent API and Router API now support `perplexity/nemotron-3.5-lightning-30b-a3b`, a fast, efficient open-weight reasoning model, at \$0.0115 per million input tokens, \$0.00115 per million cached-input tokens, and \$0.17 per million output tokens. See the [Agent API Models reference](/docs/agent-api/models) or the [Router model catalog](/docs/router/models). - - - - **DeepSeek V4 Flash 0731** - - The Agent API and Router API now support `perplexity/deepseek-v4-flash-0731`, a fast, efficient open reasoning model with a 1M-token context window. See pricing in the [Agent API Models reference](/docs/agent-api/models) or the [Router model catalog](/docs/router/models). - - **GPT-5.6 price cuts and Sol Fast mode** @@ -162,7 +248,6 @@ The Agent API expanded model coverage this month, all with direct first-party token pricing. See the full list in the [Agent API Models reference](/docs/agent-api/models). * **Claude Sonnet 5** — `anthropic/claude-sonnet-5`, Anthropic's latest Sonnet model. - * **GLM 5.2** — `perplexity/glm-5.2`, Z.AI's flagship reasoning model. * **Kimi K2.7 Code** — `perplexity/kimi-k2.7-code`, Moonshot AI's coding and agentic model. * **Nemotron 3 Super** — `nvidia/nemotron-3-super-120b-a12b`, NVIDIA's open-weight reasoning model. @@ -272,7 +357,7 @@ * **Context-aware**: Perfect for educational content, geographic queries, processes, and demonstrations * **Configurable control**: Enable/disable and override media types as needed - Available exclusively with `sonar-pro`, the Media Classifier enhances responses for visual concepts, locations, step-by-step processes, and educational content. [Learn more →](/docs/sonar/media) + Available exclusively with `sonar-pro`, the Media Classifier enhances responses for visual concepts, locations, step-by-step processes, and educational content. **Search API Enhancements** @@ -299,8 +384,6 @@ * **Automatic classification**: Use `search_type: "auto"` to let the system intelligently route queries based on complexity * **Built-in tools**: Access `web_search` and `fetch_url_content` tools that the model uses automatically - Learn more about Pro Search in our [Pro Search Quickstart](/docs/sonar/pro-search/quickstart) guide. - **MCP Server: One-Click Installation** The [Perplexity MCP Server](/docs/getting-started/integrations/mcp-server) now supports **one-click installation** for popular AI development environments: @@ -334,7 +417,7 @@ * Streaming support with async iterators * Automatic environment variable handling for API keys - Get started with our [SDK Quickstart Guide](/docs/sdk/overview) and explore the [Sonar API Guide](/docs/sonar/quickstart) for detailed usage examples. + Get started with our [SDK Quickstart Guide](/docs/sdk/overview). **Interactive Search API Playground** @@ -364,8 +447,6 @@ * **Multi-language Support**: Analyze documents in various languages Upload documents either via publicly accessible URLs using the `file_url` content type, similar to our existing image upload functionality. - - Get started with our comprehensive [File Attachments Guide](/docs/sonar/media#sending-files). @@ -598,9 +679,6 @@ "reasoning_effort": "low" }' ``` - - For detailed documentation and implementation examples, please see: - [Sonar Deep Research Documentation](/docs/sonar/models/sonar-deep-research) @@ -617,9 +695,6 @@ 3. `GET https://api.perplexity.ai/v1/async/sonar/{request_id}` - Retrieves the status and result of a specific asynchronous chat completion job **Note:** Async requests have a time-to-live (TTL) of 7 days. After this period, the request and its results will no longer be accessible. - - For detailed documentation and implementation examples, please see: - [Sonar Deep Research Documentation](/docs/sonar/models/sonar-deep-research) diff --git a/snapshots/vertex/model-versions.md b/snapshots/vertex/model-versions.md index e8e0a60..21f6fb5 100644 --- a/snapshots/vertex/model-versions.md +++ b/snapshots/vertex/model-versions.md @@ -12,76 +12,79 @@ The following table lists the models that will be available for at least 12 mont ### Gemini models -| Model ID | Release date | Retirement date | Replacement model | -| ---------------------------------- | ----------------- | ---------------------- | ---------------------------------------------- | -| gemini-3.5-flash-lite | July 21, 2026 | July 21, 2027 or later | | -| gemini-3.5-flash | May 19, 2026 | May 19, 2027 or later | | -| gemini-3.1-flash-lite | May 7, 2026 | May 7, 2027 or later | | -| gemini-2.5-pro | June 17, 2025 | October 20, 2026 | Gemini 3.5 Flash | -| gemini-2.5-flash | June 17, 2025 | October 20, 2026 | Gemini 3.5 Flash-Lite or Gemini 3.1 Flash-Lite | -| gemini-2.5-flash-lite | July 22, 2025 | October 20, 2026 | Gemini 3.1 Flash-Lite or Gemma 4 | -| gemini-live-2.5-flash-native-audio | December 12, 2025 | December 13, 2026 | | +| Model ID | Release date | Retirement date | Replacement model ID | +| -------------------------------------------------------------------------------------------------------- | ----------------- | ---------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| [gemini-3.5-flash-lite](/gemini-enterprise-agent-platform/models/gemini/3-5-flash-lite) | July 21, 2026 | July 21, 2027 or later | | +| [gemini-3.5-flash](/gemini-enterprise-agent-platform/models/gemini/3-5-flash) | May 19, 2026 | May 19, 2027 or later | | +| [gemini-3.1-flash-lite](/gemini-enterprise-agent-platform/models/gemini/3-1-flash-lite) | May 7, 2026 | May 7, 2027 or later | | +| [gemini-2.5-pro](/gemini-enterprise-agent-platform/models/gemini/2-5-pro) | June 17, 2025 | October 20, 2026 | [gemini-3.8-flash](/gemini-enterprise-agent-platform/models/gemini/3-8-flash) or [gemini-3.5-flash](/gemini-enterprise-agent-platform/models/gemini/3-5-flash) | +| [gemini-2.5-flash](/gemini-enterprise-agent-platform/models/gemini/2-5-flash) | June 17, 2025 | October 20, 2026 | [gemini-3.8-flash](/gemini-enterprise-agent-platform/models/gemini/3-8-flash) or [gemini-3.5-flash-lite](/gemini-enterprise-agent-platform/models/gemini/3-5-flash-lite) or [gemini-3.1-flash-lite](/gemini-enterprise-agent-platform/models/gemini/3-1-flash-lite) | +| [gemini-2.5-flash-lite](/gemini-enterprise-agent-platform/models/gemini/2-5-flash-lite) | July 22, 2025 | October 20, 2026 | [gemini-3.8-flash](/gemini-enterprise-agent-platform/models/gemini/3-8-flash) or [gemini-3.1-flash-lite](/gemini-enterprise-agent-platform/models/gemini/3-1-flash-lite) or [Gemma 4](https://console.cloud.google.com/agent-platform/publishers/google/model-garden/gemma4) | +| [gemini-live-2.5-flash-native-audio](/gemini-enterprise-agent-platform/models/gemini/2-5-flash-live-api) | December 12, 2025 | December 13, 2026 | | ### Gemini image models -| Model ID | Release date | Retirement date | Replacement model | -| --------------------------- | --------------- | ---------------------------- | --------------------------- | -| gemini-3.1-flash-lite-image | June 23, 2026 | No retirement date announced | | -| gemini-3-pro-image | May 28, 2026 | May 28, 2027 or later | | -| gemini-3.1-flash-image | May 28, 2026 | May 28, 2027 or later | | -| gemini-2.5-flash-image | October 2, 2025 | October 2, 2026 | Gemini 3.1 Flash-Lite Image | +| Model ID | Release date | Retirement date | Replacement model ID | +| --------------------------------------------------------------------------------------------------- | --------------- | ---------------------- | --------------------------------------------------------------------------------------------------- | +| [gemini-3.1-flash-lite-image](/gemini-enterprise-agent-platform/models/gemini/3-1-flash-lite-image) | June 23, 2026 | June 28, 2027 or later | | +| [gemini-3-pro-image](/gemini-enterprise-agent-platform/models/gemini/3-pro-image) | May 28, 2026 | May 28, 2027 or later | | +| [gemini-3.1-flash-image](/gemini-enterprise-agent-platform/models/gemini/3-1-flash-image) | May 28, 2026 | May 28, 2027 or later | | +| [gemini-2.5-flash-image](/gemini-enterprise-agent-platform/models/gemini/2-5-flash-image) | October 2, 2025 | March 15, 2027 | [gemini-3.1-flash-lite-image](/gemini-enterprise-agent-platform/models/gemini/3-1-flash-lite-image) | ### Veo models -| Model ID | Release date | Retirement date | Replacement model | -| ------------------------- | ----------------- | -------------------------- | ------------------------- | -| veo-3.0-generate-001 | July 29, 2025 | June 30, 2026 | veo-3.1-generate-001 | -| veo-3.0-fast-generate-001 | July 29, 2025 | June 30, 2026 | veo-3.1-fast-generate-001 | -| veo-3.1-generate-001 | November 17, 2025 | November 17, 2026 or later | | -| veo-3.1-fast-generate-001 | November 17, 2025 | November 17, 2026 or later | | +| Model ID | Release date | Retirement date | Replacement model ID | +| ------------------------------------------------------------------------------------------------------------ | ----------------- | -------------------------- | ------------------------------------------------------------------------------------------------------------ | +| [veo-3.0-generate-001](/gemini-enterprise-agent-platform/models/veo/3-0-generate#3.0-generate-001) | July 29, 2025 | June 30, 2026 | [veo-3.1-generate-001](/gemini-enterprise-agent-platform/models/veo/3-1-generate#3.1-generate-001) | +| [veo-3.0-fast-generate-001](/gemini-enterprise-agent-platform/models/veo/3-0-generate#3.0-fast-generate-001) | July 29, 2025 | June 30, 2026 | [veo-3.1-fast-generate-001](/gemini-enterprise-agent-platform/models/veo/3-1-generate#3.1-fast-generate-001) | +| [veo-3.1-generate-001](/gemini-enterprise-agent-platform/models/veo/3-1-generate#3.1-generate-001) | November 17, 2025 | November 17, 2026 or later | | +| [veo-3.1-fast-generate-001](/gemini-enterprise-agent-platform/models/veo/3-1-generate#3.1-fast-generate-001) | November 17, 2025 | November 17, 2026 or later | | ### Embeddings models -| Model ID | Release date | Retirement date | Replacement model | -| ------------------------------- | ----------------- | --------------------------- | ----------------- | -| gemini-embedding-2 | April 22, 2026 | | | -| gemini-embedding-001 | May 20, 2025 | No sooner than May 20, 2028 | | -| text-embedding-005 | November 18, 2024 | April 1, 2027 | | -| text-embedding-004 | May 14, 2024 | April 1, 2027 | | -| text-multilingual-embedding-002 | May 14, 2024 | April 1, 2027 | | -| multimodalembedding@001 | February 12, 2024 | April 1, 2027 | | +| Model ID | Release date | Retirement date | Replacement model ID | +| ---------------------------------------------------------------------------------------------------------- | ----------------- | --------------------------- | -------------------- | +| [gemini-embedding-2](/gemini-enterprise-agent-platform/models/gemini/embedding-2) | April 22, 2026 | | | +| [gemini-embedding-001](/gemini-enterprise-agent-platform/models/embeddings/get-text-embeddings) | May 20, 2025 | No sooner than May 20, 2028 | | +| [text-embedding-005](/gemini-enterprise-agent-platform/models/embeddings/get-text-embeddings) | November 18, 2024 | April 1, 2027 | | +| [text-embedding-004](/gemini-enterprise-agent-platform/models/embeddings/get-text-embeddings) | May 14, 2024 | April 1, 2027 | | +| [text-multilingual-embedding-002](/gemini-enterprise-agent-platform/models/embeddings/get-text-embeddings) | May 14, 2024 | April 1, 2027 | | +| [multimodalembedding@001](/gemini-enterprise-agent-platform/models/embeddings/get-multimodal-embeddings) | February 12, 2024 | April 1, 2027 | | ### Models available for shorter availability periods -Short-term availability models retire 45 days after a replacement model is released. The following table lists models available for shorter terms: +Short-term availability models remain active until a replacement model is released and a retirement date is announced. When we schedule a model for retirement, we post a fixed date in the following table that gives you at least 45 days to migrate. Even after a replacement launches, a model remains active until we announce its retirement date. -| Model ID | Release date | Retirement date | Replacement model | -| ---------------- | ----------------- | ---------------------------- | ----------------- | -| gemini-3.8-flash | September 2, 2026 | No retirement date announced | | -| gemini-3.7-flash | August 13, 2026 | No retirement date announced | | -| gemini-3.6-flash | July 21, 2026 | No retirement date announced | | +The following table lists models available for shorter terms: + +| Model ID | Release date | Retirement date | Replacement model ID | +| ----------------------------------------------------------------------------------------- | ------------------ | ---------------------------- | ----------------------------------------------------------------------------- | +| [gemini-3.8-flash-cyber](/gemini-enterprise-agent-platform/models/gemini/3-8-flash-cyber) | September 16, 2026 | No retirement date announced | | +| [gemini-3.8-flash](/gemini-enterprise-agent-platform/models/gemini/3-8-flash) | September 2, 2026 | No retirement date announced | | +| [gemini-3.7-flash](/gemini-enterprise-agent-platform/models/gemini/3-7-flash) | August 13, 2026 | No retirement date announced | [gemini-3.8-flash](/gemini-enterprise-agent-platform/models/gemini/3-8-flash) | +| [gemini-3.6-flash](/gemini-enterprise-agent-platform/models/gemini/3-6-flash) | July 21, 2026 | No retirement date announced | [gemini-3.8-flash](/gemini-enterprise-agent-platform/models/gemini/3-8-flash) | ### Retired models -| Model ID | Release date | Retirement date | Recommended upgrade | -| ------------------------------------ | ------------------ | ------------------ | ---------------------- | -| gemini-2.0-flash | February 5, 2025 | June 1, 2026 | gemini-3.1-flash-lite | -| gemini-2.0-flash-lite | February 25, 2025 | June 1, 2026 | gemini-3.1-flash-lite | -| gemini-1.5-pro-001 | May 24, 2024 | May 24, 2025 | gemini-2.5-flash | -| gemini-1.5-pro-002 | September 24, 2024 | September 24, 2025 | gemini-2.5-flash | -| gemini-1.5-flash-001 | May 24, 2024 | May 24, 2025 | gemini-2.5-flash-lite | -| gemini-1.5-flash-002 | September 24, 2024 | September 24, 2025 | gemini-2.5-flash-lite | -| textembedding-gecko@003\* | December 12, 2023 | May 24, 2025 | gemini-embedding-001 | -| textembedding-gecko-multilingual@001 | November 2, 2023 | May 24, 2025 | gemini-embedding-001 | -| gemini-1.0-pro-001 | February 15, 2024 | April 21, 2025 | gemini-2.5-flash | -| gemini-1.0-pro-002 | April 9, 2024 | April 21, 2025 | gemini-2.5-flash | -| gemini-1.0-pro-vision-001 | February 15, 2024 | April 21, 2025 | gemini-2.5-flash | -| text-bison | May 2023 | April 21, 2025 | gemini-2.5-flash-lite | -| chat-bison | May 2023 | April 21, 2025 | gemini-2.5-flash-lite | -| code-gecko | May 2023 | April 21, 2025 | gemini-2.5-flash-lite | -| textembedding-gecko@002 | November 2, 2023 | April 21, 2025 | gemini-embedding-001 | -| textembedding-gecko@001 | June 7, 2023 | April 21, 2025 | gemini-embedding-001 | -| imagetext | June 7, 2023 | September 24, 2025 | gemini-2.5-flash-image | +| Model ID | Release date | Retirement date | Recommended upgrade | +| ------------------------------------ | ------------------ | ------------------ | ----------------------------------------------------------------------------------------------- | +| gemini-2.0-flash | February 5, 2025 | June 1, 2026 | [gemini-3.1-flash-lite](/gemini-enterprise-agent-platform/models/gemini/3-1-flash-lite) | +| gemini-2.0-flash-lite | February 25, 2025 | June 1, 2026 | [gemini-3.1-flash-lite](/gemini-enterprise-agent-platform/models/gemini/3-1-flash-lite) | +| gemini-1.5-pro-001 | May 24, 2024 | May 24, 2025 | [gemini-2.5-flash](/gemini-enterprise-agent-platform/models/gemini/2-5-flash) | +| gemini-1.5-pro-002 | September 24, 2024 | September 24, 2025 | [gemini-2.5-flash](/gemini-enterprise-agent-platform/models/gemini/2-5-flash) | +| gemini-1.5-flash-001 | May 24, 2024 | May 24, 2025 | [gemini-2.5-flash-lite](/gemini-enterprise-agent-platform/models/gemini/2-5-flash-lite) | +| gemini-1.5-flash-002 | September 24, 2024 | September 24, 2025 | [gemini-2.5-flash-lite](/gemini-enterprise-agent-platform/models/gemini/2-5-flash-lite) | +| textembedding-gecko@003\* | December 12, 2023 | May 24, 2025 | [gemini-embedding-001](/gemini-enterprise-agent-platform/models/embeddings/get-text-embeddings) | +| textembedding-gecko-multilingual@001 | November 2, 2023 | May 24, 2025 | [gemini-embedding-001](/gemini-enterprise-agent-platform/models/embeddings/get-text-embeddings) | +| gemini-1.0-pro-001 | February 15, 2024 | April 21, 2025 | [gemini-2.5-flash](/gemini-enterprise-agent-platform/models/gemini/2-5-flash) | +| gemini-1.0-pro-002 | April 9, 2024 | April 21, 2025 | [gemini-2.5-flash](/gemini-enterprise-agent-platform/models/gemini/2-5-flash) | +| gemini-1.0-pro-vision-001 | February 15, 2024 | April 21, 2025 | [gemini-2.5-flash](/gemini-enterprise-agent-platform/models/gemini/2-5-flash) | +| text-bison | May 2023 | April 21, 2025 | [gemini-2.5-flash-lite](/gemini-enterprise-agent-platform/models/gemini/2-5-flash-lite) | +| chat-bison | May 2023 | April 21, 2025 | [gemini-2.5-flash-lite](/gemini-enterprise-agent-platform/models/gemini/2-5-flash-lite) | +| code-gecko | May 2023 | April 21, 2025 | [gemini-2.5-flash-lite](/gemini-enterprise-agent-platform/models/gemini/2-5-flash-lite) | +| textembedding-gecko@002 | November 2, 2023 | April 21, 2025 | [gemini-embedding-001](/gemini-enterprise-agent-platform/models/embeddings/get-text-embeddings) | +| textembedding-gecko@001 | June 7, 2023 | April 21, 2025 | [gemini-embedding-001](/gemini-enterprise-agent-platform/models/embeddings/get-text-embeddings) | +| imagetext | June 7, 2023 | September 24, 2025 | [gemini-2.5-flash-image](/gemini-enterprise-agent-platform/models/gemini/2-5-flash-image) | ## Migrate to a latest available model diff --git a/snapshots/xiaomi/deprecations.md b/snapshots/xiaomi/deprecations.md index d25b7d0..8a852c5 100644 --- a/snapshots/xiaomi/deprecations.md +++ b/snapshots/xiaomi/deprecations.md @@ -12,9 +12,16 @@ With the continuous iteration of the MiMo model, the new version has comprehensi - Access [ Bill Details ](https://platform.xiaomimimo.com/console/usage), check if there are any models pending offline; - Refer to the system replacement model in the table below to complete your code self-check and replacement. It is recommended to fully test and verify before the official switch. +### Deprecated model on 2026.10.21 + +| Offline Model | Deprecated Time | Note | +| ------------- | ----------------------------- | ---------------------------------------------------------------------------- | +| mimo-v2.5-pro | Beijing Time 2026.10.21 10:00 | **No system replacement model; will be directly deprecated upon expiration** | +| mimo-v2.5 | Beijing Time 2026.10.21 10:00 | **No system replacement model; will be directly deprecated upon expiration** | + ### Deprecated model on 2026.6.30 -| Deprecated Model | Offline Time | System replacement time | System Replacement Model | Replacement Impact | +| Deprecated Model | Deprecated Time | System replacement time | System Replacement Model | Replacement Impact | | ---------------- | ---------------------------- | ---------------------------- | ------------------------ | --------------------------------------------------------------------------------------------- | | mimo-v2-pro | Beijing Time 2026.6.30 00:00 | Beijing Time 2026.6.1 00:00 | mimo-v2.5-pro | API parameters are fully adapted | | mimo-v2-omni | Beijing Time 2026.6.30 00:00 | Beijing Time 2026.6.1 00:00 | mimo-v2.5 | API parameters are fully adapted | diff --git a/snapshots/z-ai/pricing.md b/snapshots/z-ai/pricing.md index 92065df..fb2e0a9 100644 --- a/snapshots/z-ai/pricing.md +++ b/snapshots/z-ai/pricing.md @@ -12,76 +12,77 @@ Prices per 1M tokens. -| Model | Input | Cached Input | Cached Input Storage | Output | -| :------------ | :----- | :----------- | :------------------- | :----- | -| GLM-5.3-Flash | \$0.15 | \$0.03 | Limited-time Free | \$0.50 | -| GLM-5.3 | \$1.4 | \$0.26 | Limited-time Free | \$4.4 | -| GLM-5.2 | \$1.4 | \$0.26 | Limited-time Free | \$4.4 | +| Model | Input | Cached Input | Cached Input Storage | Output | +| :- | :- | :- | :- | :- | +| GLM-5.3-Flash | \$0.15 | \$0.03 | Limited-time Free | \$0.50 | +| GLM-5.3-FlashX | \$0.37 | \$0.075 | Limited-time Free | \$1.25 | +| GLM-5.3 | \$1.4 | \$0.26 | Limited-time Free | \$4.4 | +| GLM-5.2 | \$1.4 | \$0.26 | Limited-time Free | \$4.4 | ### Text Models Prices per 1M tokens. -| Model | Input | Cached Input | Cached Input Storage | Output | -| :------------------ | :----- | :----------- | :------------------- | :----- | -| GLM-5.1 | \$1.4 | \$0.26 | Limited-time Free | \$4.4 | -| GLM-5 | \$1 | \$0.2 | Limited-time Free | \$3.2 | -| GLM-4.7 | \$0.6 | \$0.11 | Limited-time Free | \$2.2 | -| GLM-4.7-FlashX | \$0.07 | \$0.01 | Limited-time Free | \$0.4 | -| GLM-4.6 | \$0.6 | \$0.11 | Limited-time Free | \$2.2 | -| GLM-4.5 | \$0.6 | \$0.11 | Limited-time Free | \$2.2 | -| GLM-4.5-X | \$2.2 | \$0.45 | Limited-time Free | \$8.9 | -| GLM-4.5-Air | \$0.2 | \$0.03 | Limited-time Free | \$1.1 | -| GLM-4.5-AirX | \$1.1 | \$0.22 | Limited-time Free | \$4.5 | -| GLM-4-32B-0414-128K | \$0.1 | - | - | \$0.1 | -| GLM-4.7-Flash | Free | Free | Free | Free | -| GLM-4.5-Flash | Free | Free | Free | Free | +| Model | Input | Cached Input | Cached Input Storage | Output | +| :- | :- | :- | :- | :- | +| GLM-5.1 | \$1.4 | \$0.26 | Limited-time Free | \$4.4 | +| GLM-5 | \$1 | \$0.2 | Limited-time Free | \$3.2 | +| GLM-4.7 | \$0.6 | \$0.11 | Limited-time Free | \$2.2 | +| GLM-4.7-FlashX | \$0.07 | \$0.01 | Limited-time Free | \$0.4 | +| GLM-4.6 | \$0.6 | \$0.11 | Limited-time Free | \$2.2 | +| GLM-4.5 | \$0.6 | \$0.11 | Limited-time Free | \$2.2 | +| GLM-4.5-X | \$2.2 | \$0.45 | Limited-time Free | \$8.9 | +| GLM-4.5-Air | \$0.2 | \$0.03 | Limited-time Free | \$1.1 | +| GLM-4.5-AirX | \$1.1 | \$0.22 | Limited-time Free | \$4.5 | +| GLM-4-32B-0414-128K | \$0.1 | - | - | \$0.1 | +| GLM-4.7-Flash | Free | Free | Free | Free | +| GLM-4.5-Flash | Free | Free | Free | Free | ### Vision Models Prices per 1M tokens. -| Model | Input | Cached Input | Cached Input Storage | Output | -| :-------------- | :----- | :----------- | :------------------- | :----- | -| GLM-4.6V | \$0.3 | \$0.05 | Limited-time Free | \$0.9 | -| GLM-OCR | \$0.03 | \\ | \\ | \$0.03 | -| GLM-4.6V-FlashX | \$0.04 | \$0.004 | Limited-time Free | \$0.4 | -| GLM-4.5V | \$0.6 | \$0.11 | Limited-time Free | \$1.8 | -| GLM-4.6V-Flash | Free | Free | Free | Free | +| Model | Input | Cached Input | Cached Input Storage | Output | +| :- | :- | :- | :- | :- | +| GLM-4.6V | \$0.3 | \$0.05 | Limited-time Free | \$0.9 | +| GLM-OCR | \$0.03 | \\ | \\ | \$0.03 | +| GLM-4.6V-FlashX | \$0.04 | \$0.004 | Limited-time Free | \$0.4 | +| GLM-4.5V | \$0.6 | \$0.11 | Limited-time Free | \$1.8 | +| GLM-4.6V-Flash | Free | Free | Free | Free | ### Built-in Tools -| Tool | Cost | -| :--------- | :----------- | +| Tool | Cost | +| :- | :- | | Web Search | \$0.01 / use | ### Image Generation Models Prices per image. -| Model | Price | -| :-------- | :------ | +| Model | Price | +| :- | :- | | GLM-Image | \$0.015 | -| CogView-4 | \$0.01 | +| CogView-4 | \$0.01 | ### Video Generation Models Prices per video. -| Model | Price | -| :---------- | :---- | +| Model | Price | +| :- | :- | | CogVideoX-3 | \$0.2 | ### Audio Models -| Model | Price | -| :----------- | :---------------------------------------------------------- | +| Model | Price | +| :- | :- | | GLM-ASR-2512 | \$0.03 / MTok (equivalent to approximately \$0.0024/minute) | ### Agents -| Agent | Price | -| :-------------------------------------- | :------------ | -| GLM Slide/Poster Agent(beta) | \$0.7 / MTok | -| General-Purpose Translation | \$3 / MTok | +| Agent | Price | +| :- | :- | +| GLM Slide/Poster Agent(beta) | \$0.7 / MTok | +| General-Purpose Translation | \$3 / MTok | | Popular Special Effects Video Templates | \$0.2 / video |