Skip to content

docs: update model references to newer versions #32

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
erikhoward merged 1 commit into from
May 13, 2026
Merged

docs: update model references to newer versions #32

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
45 changes: 29 additions & 16 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -118,8 +118,8 @@ func main() {
// Create a client
client := core.NewClient(provider)

// Send a chat request
resp, err := client.Chat("claude-sonnet-4-5").
// Send a chat request (using latest Claude Sonnet 4.6)
resp, err := client.Chat("claude-sonnet-4-6").
System("You are a helpful assistant.").
User("What is the capital of France?").
GetResponse(context.Background())
Expand Down Expand Up @@ -646,13 +646,13 @@ resp, _ := provider.EditImage(ctx, &core.ImageEditRequest{
| `dall-e-3` | High quality (deprecated May 2026) |
| `dall-e-2` | Lower cost, inpainting (deprecated May 2026) |

### Using the Responses API (GPT-5)
### Using the Responses API (GPT-5.4)

GPT-5 models automatically use OpenAI's Responses API, which provides advanced features like reasoning, built-in tools, and response chaining.
GPT-5+ models automatically use OpenAI's Responses API, which provides advanced features like reasoning, built-in tools, and response chaining.

```go
// GPT-5 uses the Responses API automatically
resp, err := client.Chat("gpt-5").
// GPT-5.4 uses the Responses API automatically
resp, err := client.Chat("gpt-5.4").
Instructions("You are a helpful research assistant.").
User("What are the latest developments in quantum computing?").
ReasoningEffort(core.ReasoningEffortHigh).
Expand All @@ -673,7 +673,7 @@ if resp.Reasoning != nil {
}

// Response chaining - continue from a previous response
followUp, err := client.Chat("gpt-5").
followUp, err := client.Chat("gpt-5.4").
ContinueFrom(resp.ID).
User("Can you elaborate on the most promising approach?").
GetResponse(ctx)
Expand All @@ -694,7 +694,7 @@ iris keys set ollama # Only needed for Ollama Cloud
iris chat --provider openai --model gpt-4o --prompt "Hello, world!"

# Chat with Anthropic Claude
iris chat --provider anthropic --model claude-sonnet-4-5 --prompt "Hello, world!"
iris chat --provider anthropic --model claude-sonnet-4-6 --prompt "Hello, world!"

# Chat with Google Gemini
iris chat --provider gemini --model gemini-2.5-flash --prompt "Hello, world!"
Expand All @@ -713,7 +713,7 @@ iris chat --provider openai --model gpt-5 --prompt "Explain quantum entanglement

# Stream responses
iris chat --provider openai --model gpt-4o --prompt "Tell me a story" --stream
iris chat --provider anthropic --model claude-sonnet-4-5 --prompt "Tell me a story" --stream
iris chat --provider anthropic --model claude-sonnet-4-6 --prompt "Tell me a story" --stream

# Get JSON output
iris chat --provider openai --model gpt-4o --prompt "Hello" --json
Expand Down Expand Up @@ -753,7 +753,7 @@ Iris looks for configuration at `~/.iris/config.yaml`:

```yaml
default_provider: openai
default_model: gpt-5 # or gpt-4o for older models
default_model: gpt-5.4 # or gpt-4o for older models

providers:
openai:
Expand Down Expand Up @@ -821,20 +821,28 @@ See [docs/SECURITY.md](docs/SECURITY.md) for comprehensive security documentatio

| Model ID | Features |
|----------|----------|
| `grok-3` | Chat, Streaming, Tools, Reasoning |
| `grok-3-mini` | Chat, Streaming, Tools, Reasoning (exposes reasoning_content) |
| `grok-4` | Chat, Streaming, Tools, Reasoning (latest) |
| `grok-4.20-multi-agent-beta-0309` | Chat, Streaming, Tools, Reasoning (multi-agent beta) |
| `grok-4.20-beta-0309-reasoning` | Chat, Streaming, Tools, Reasoning (beta) |
| `grok-4.20-beta-0309-non-reasoning` | Chat, Streaming, Tools (beta) |
| `grok-4.1` | Chat, Streaming, Tools |
| `grok-4-1-fast-non-reasoning` | Chat, Streaming, Tools (default for CLI) |
| `grok-4-1-fast-reasoning` | Chat, Streaming, Tools, Reasoning |
| `grok-4` | Chat, Streaming, Tools, Reasoning |
| `grok-4-fast-non-reasoning` | Chat, Streaming, Tools |
| `grok-4-fast-reasoning` | Chat, Streaming, Tools, Reasoning |
| `grok-3` | Chat, Streaming, Tools, Reasoning |
| `grok-3-mini` | Chat, Streaming, Tools, Reasoning (exposes reasoning_content) |
| `grok-code-fast` | Chat, Streaming, Tools (code-optimized) |
| `grok-4-1-fast-non-reasoning` | Chat, Streaming, Tools (default for CLI) |
| `grok-4-1-fast-reasoning` | Chat, Streaming, Tools, Reasoning |

### Z.ai GLM Models

| Model ID | Features |
|----------|----------|
| `glm-4.7` | Chat, Streaming, Tools, Thinking (latest flagship) |
| `glm-5.1` | Chat, Streaming, Tools, Thinking (latest) |
| `glm-5` | Chat, Streaming, Tools, Thinking |
| `glm-5-turbo` | Chat, Streaming, Tools, Thinking |
| `glm-5v-turbo` | Chat, Streaming, Tools, Thinking, Vision |
| `glm-4.7` | Chat, Streaming, Tools, Thinking |
| `glm-4.7-flash` | Chat, Streaming, Tools (default for CLI) |
| `glm-4.7-flashx` | Chat, Streaming, Tools |
| `glm-4.6` | Chat, Streaming, Tools, Thinking |
Expand All @@ -847,6 +855,7 @@ See [docs/SECURITY.md](docs/SECURITY.md) for comprehensive security documentatio
| `glm-4.5-air` | Chat, Streaming, Tools |
| `glm-4.5-airx` | Chat, Streaming, Tools |
| `glm-4.5-flash` | Chat, Streaming, Tools |
| `glm-for-coding` | Chat, Streaming, Tools, Thinking (code-optimized) |
| `glm-4-32b-0414-128k` | Chat, Streaming, Tools (128K context) |

### Perplexity Models
Expand All @@ -862,11 +871,15 @@ See [docs/SECURITY.md](docs/SECURITY.md) for comprehensive security documentatio

| Model ID | Features |
|----------|----------|
| `gemini-3.1-flash-image-preview` | Chat, Streaming, Image Generation |
| `gemini-3-pro-preview` | Chat, Streaming, Tools, Reasoning (thinkingLevel) |
| `gemini-3-flash-preview` | Chat, Streaming, Tools, Reasoning (thinkingLevel) |
| `gemini-3-pro-image-preview` | Image Generation (Nano Banana Pro) |
| `gemini-2.5-pro` | Chat, Streaming, Tools, Reasoning (thinkingBudget) |
| `gemini-2.5-flash` | Chat, Streaming, Tools, Reasoning (thinkingBudget) |
| `gemini-2.5-flash-lite` | Chat, Streaming, Tools, Reasoning (thinkingBudget) |
| `gemini-2.5-flash-image` | Image Generation (Nano Banana) |
| `gemini-2.0-flash-lite` | Chat, Streaming |

### Ollama Models

Expand Down
69 changes: 57 additions & 12 deletions docs/PROVIDERS.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,22 +34,35 @@ This document provides a comprehensive comparison of the AI providers supported

| Model | Display Name | Reasoning | Built-in Tools | Notes |
|-------|--------------|-----------|----------------|-------|
| gpt-5.2 | GPT-5.2 | Yes | Yes | Latest flagship |
| gpt-5.4 | GPT-5.4 | Yes | Yes | Latest flagship |
| gpt-5.4-pro | GPT-5.4 Pro | Yes | Yes | Enhanced capabilities |
| gpt-5.4-mini | GPT-5.4 Mini | Yes | Yes | Smaller, faster |
| gpt-5.4-nano | GPT-5.4 Nano | Yes | Yes | Lightweight |
| gpt-5.2 | GPT-5.2 | Yes | Yes | |
| gpt-5.2-pro | GPT-5.2 Pro | Yes | Yes | Enhanced capabilities |
| gpt-5.2-codex | GPT-5.2 Codex | Yes | Yes | Code specialized |
| gpt-5.1 | GPT-5.1 | Yes | Yes | |
| gpt-5.1-codex | GPT-5.1 Codex | Yes | Yes | Code specialized |
| gpt-5.1-codex-mini | GPT-5.1 Codex Mini | Yes | Yes | Smaller codex |
| gpt-5.1-codex-max | GPT-5.1 Codex Max | Yes | Yes | Largest codex |
| gpt-5 | GPT-5 | Yes | Yes | |
| gpt-5-mini | GPT-5 Mini | Yes | Yes | Smaller, faster |
| gpt-5-nano | GPT-5 Nano | No | Yes | Lightweight |
| gpt-5-codex | GPT-5 Codex | Yes | Yes | Code specialized |
| gpt-5-thinking | GPT-5 Thinking | Yes | Yes | Extended reasoning |
| gpt-4.1 | GPT-4.1 | No | Yes | |
| gpt-4.1-mini | GPT-4.1 Mini | No | Yes | |
| gpt-4.1-nano | GPT-4.1 Nano | No | Yes | |
| gpt-4o | GPT-4o | No | No | Multimodal |
| gpt-4o-mini | GPT-4o Mini | No | No | Cost-effective |
| o4-mini | o4-mini | Yes | Yes | Reasoning focused |
| o4-mini-deep-research | o4-mini Deep Research | Yes | Yes | Research focused |
| o3 | o3 | Yes | Yes | Reasoning focused |
| o3-mini | o3-mini | Yes | Yes | Smaller reasoning |
| o1 | o1 | Yes | No | Reasoning focused |
| o1-pro | o1 Pro | Yes | No | Enhanced reasoning |

**Image Generation Models**: gpt-image-1.5, gpt-image-1, dall-e-3, dall-e-2
**Image Generation Models**: gpt-image-1.5, gpt-image-1, gpt-image-1-mini, dall-e-3, dall-e-2, chatgpt-image-latest

**Usage Example**:
```go
Expand All @@ -71,23 +84,32 @@ resp, err := client.Chat(openai.ModelGPT4o).

**Models**:

| Model | Display Name | Notes |
|-------|--------------|-------|
| claude-sonnet-4-5 | Claude Sonnet 4.5 | Balanced performance |
| claude-haiku-4-5 | Claude Haiku 4.5 | Fast, cost-effective |
| claude-opus-4-5 | Claude Opus 4.5 | Most capable |
| Model | Display Name | Reasoning | Notes |
|-------|--------------|-----------|-------|
| claude-opus-4-7 | Claude Opus 4.7 | Yes | Latest flagship |
| claude-sonnet-4-6 | Claude Sonnet 4.6 | Yes | Balanced performance |
| claude-sonnet-4-6-thinking | Claude Sonnet 4.6 (Thinking) | Yes | Extended reasoning |
| claude-opus-4-6 | Claude Opus 4.6 | Yes | High capability |
| claude-opus-4-6-thinking | Claude Opus 4.6 (Thinking) | Yes | Extended reasoning |
| claude-sonnet-4-5 | Claude Sonnet 4.5 | Yes | Balanced performance |
| claude-sonnet-4-5-thinking | Claude Sonnet 4.5 (Thinking) | Yes | Extended reasoning |
| claude-haiku-4-5 | Claude Haiku 4.5 | Yes | Fast, cost-effective |
| claude-opus-4-5 | Claude Opus 4.5 | Yes | High capability |
| claude-opus-4-5-thinking | Claude Opus 4.5 (Thinking) | Yes | Extended reasoning |
| claude-3-5-haiku-latest | Claude 3.5 Haiku | No | Legacy fast model |

**Special Features**:
- Extended context windows
- Strong instruction following
- Built-in safety guardrails
- Thinking/reasoning modes

**Usage Example**:
```go
provider := anthropic.New(os.Getenv("ANTHROPIC_API_KEY"))
client := core.NewClient(provider)

resp, err := client.Chat(anthropic.ModelClaudeSonnet45).
resp, err := client.Chat(anthropic.ModelClaudeSonnet46).
System("You are a helpful assistant.").
User("Explain quantum computing.").
GetResponse(ctx)
Expand All @@ -105,13 +127,17 @@ resp, err := client.Chat(anthropic.ModelClaudeSonnet45).

| Model | Display Name | Reasoning | Notes |
|-------|--------------|-----------|-------|
| gemini-3.1-flash-image-preview | Gemini 3.1 Flash Image Preview | No | Image generation |
| gemini-3-pro-preview | Gemini 3 Pro Preview | Yes | Latest preview |
| gemini-3-flash-preview | Gemini 3 Flash Preview | Yes | Fast preview |
| gemini-3-pro-image-preview | Gemini 3 Pro Image Preview | No | Image generation (Nano Banana Pro) |
| gemini-2.5-pro | Gemini 2.5 Pro | Yes | Production ready |
| gemini-2.5-flash | Gemini 2.5 Flash | Yes | Fast, efficient |
| gemini-2.5-flash-lite | Gemini 2.5 Flash Lite | Yes | Lightweight |
| gemini-2.5-flash-image | Gemini 2.5 Flash Image | No | Image generation (Nano Banana) |
| gemini-2.0-flash-lite | Gemini 2.0 Flash Lite | No | Legacy lightweight |

**Image Generation Models**: gemini-2.5-flash-image, gemini-3-pro-image-preview (Nano Banana)
**Image Generation Models**: gemini-3.1-flash-image-preview, gemini-3-pro-image-preview, gemini-2.5-flash-image (Nano Banana)

**Special Features**:
- Native multimodal support
Expand Down Expand Up @@ -140,17 +166,23 @@ resp, err := client.Chat(gemini.ModelGemini25Flash).

| Model | Display Name | Reasoning | Notes |
|-------|--------------|-----------|-------|
| grok-4 | Grok 4 | Yes | Latest flagship |
| grok-4.20-multi-agent-beta-0309 | Grok 4.20 Multi-Agent Beta | Yes | Multi-agent beta |
| grok-4.20-beta-0309-reasoning | Grok 4.20 Beta (Reasoning) | Yes | Beta with reasoning |
| grok-4.20-beta-0309-non-reasoning | Grok 4.20 Beta (Non-Reasoning) | No | Beta without reasoning |
| grok-4.1 | Grok 4.1 | No | Latest stable |
| grok-4-1-fast-non-reasoning | Grok 4.1 Fast (Non-Reasoning) | No | Fast without reasoning |
| grok-4-1-fast-reasoning | Grok 4.1 Fast (Reasoning) | Yes | Fast with reasoning |
| grok-4 | Grok 4 | Yes | Flagship |
| grok-4-fast-reasoning | Grok 4 Fast (Reasoning) | Yes | Fast with reasoning |
| grok-4-fast-non-reasoning | Grok 4 Fast (Non-Reasoning) | No | Fast without reasoning |
| grok-4-1-fast-reasoning | Grok 4.1 Fast (Reasoning) | Yes | Newest fast model |
| grok-3 | Grok 3 | Yes | Previous generation |
| grok-3-mini | Grok 3 Mini | Yes | Smaller model |
| grok-code-fast | Grok Code Fast | No | Code specialized |

**Special Features**:
- Real-time information access
- Distinct reasoning modes
- Multi-agent capabilities (beta)

**Usage Example**:
```go
Expand Down Expand Up @@ -206,18 +238,31 @@ resp, err := client.Chat(perplexity.ModelSonarPro).

| Model | Display Name | Reasoning | Vision | Notes |
|-------|--------------|-----------|--------|-------|
| glm-4.7 | GLM-4.7 | Yes | No | Latest flagship |
| glm-5.1 | GLM-5.1 | Yes | No | Latest flagship |
| glm-5 | GLM-5 | Yes | No | |
| glm-5-turbo | GLM-5 Turbo | Yes | No | Fast |
| glm-5v-turbo | GLM-5V Turbo | Yes | Yes | Vision capable |
| glm-4.7 | GLM-4.7 | Yes | No | |
| glm-4.7-flash | GLM-4.7 Flash | No | No | Fast |
| glm-4.7-flashx | GLM-4.7 FlashX | No | No | Extra fast |
| glm-4.6 | GLM-4.6 | Yes | No | |
| glm-4.6v | GLM-4.6V | Yes | Yes | Vision capable |
| glm-4.6v-flash | GLM-4.6V Flash | No | Yes | Fast vision |
| glm-4.6v-flashx | GLM-4.6V FlashX | No | Yes | Extra fast vision |
| glm-4.5 | GLM-4.5 | Yes | No | |
| glm-4.5v | GLM-4.5V | Yes | Yes | Vision capable |
| glm-4.5-x | GLM-4.5-X | No | No | Extended |
| glm-4.5-air | GLM-4.5 Air | No | No | Lightweight |
| glm-4.5-airx | GLM-4.5 AirX | No | No | Extra lightweight |
| glm-4.5-flash | GLM-4.5 Flash | No | No | Fast |
| glm-for-coding | GLM for Coding | Yes | No | Code specialized |
| glm-4-32b-0414-128k | GLM-4 32B | No | No | Large context |

**Special Features**:
- Vision models for image understanding
- Chinese language optimization
- Large context windows
- Code-specialized model

**Usage Example**:
```go
Expand Down
16 changes: 8 additions & 8 deletions examples/chat/responses-api/main.go
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
// Example: OpenAI Responses API
//
// This example demonstrates the new Responses API features available
// with newer OpenAI models like GPT-5.2, including:
// with newer OpenAI models like GPT-5.4, including:
// - Reasoning with configurable effort levels
// - Built-in tools (web search, code interpreter)
// - Response chaining (continuing from previous responses)
Expand Down Expand Up @@ -41,9 +41,9 @@ func main() {
defer cancel()

// Example 1: Basic Responses API usage
// GPT-5.2 automatically uses the Responses API
// GPT-5.4 automatically uses the Responses API
fmt.Println("=== Example 1: Basic Responses API ===")
resp, err := client.Chat(openai.ModelGPT52).
resp, err := client.Chat(openai.ModelGPT54).
Instructions("You are a helpful assistant.").
User("What is the capital of France?").
GetResponse(ctx)
Expand All @@ -59,7 +59,7 @@ func main() {

// Example 2: Using reasoning with high effort
fmt.Println("=== Example 2: Reasoning with High Effort ===")
resp, err = client.Chat(openai.ModelGPT52).
resp, err = client.Chat(openai.ModelGPT54).
Instructions("You are a math tutor. Show your reasoning.").
User("What is 15% of 240?").
ReasoningEffort(core.ReasoningEffortHigh).
Expand All @@ -81,7 +81,7 @@ func main() {

// Example 3: Using built-in web search
fmt.Println("=== Example 3: Built-in Web Search ===")
resp, err = client.Chat(openai.ModelGPT52).
resp, err = client.Chat(openai.ModelGPT54).
Instructions("Use web search to find current information.").
User("What are the top news stories today?").
WebSearch().
Expand All @@ -97,7 +97,7 @@ func main() {

// Example 4: Response chaining
fmt.Println("=== Example 4: Response Chaining ===")
firstResp, err := client.Chat(openai.ModelGPT52).
firstResp, err := client.Chat(openai.ModelGPT54).
Instructions("You are a storyteller.").
User("Start a short story about a robot.").
GetResponse(ctx)
Expand All @@ -111,7 +111,7 @@ func main() {
fmt.Println()

// Continue from the previous response
secondResp, err := client.Chat(openai.ModelGPT52).
secondResp, err := client.Chat(openai.ModelGPT54).
ContinueFrom(firstResp.ID).
User("Continue the story with an unexpected twist.").
GetResponse(ctx)
Expand All @@ -126,7 +126,7 @@ func main() {

// Example 5: Streaming with Responses API
fmt.Println("=== Example 5: Streaming with Responses API ===")
stream, err := client.Chat(openai.ModelGPT52).
stream, err := client.Chat(openai.ModelGPT54).
Instructions("You are a poet.").
User("Write a haiku about programming.").
Stream(ctx)
Expand Down
Loading