DeepSeek V4.1 Flash examples use the 1017 id

agents.mdx

@@ -103,7 +103,7 @@ const client = new OpenAI({ baseURL: 'https://api.pre.dev/v1', apiKey: process.e
 
 const { data: completion, response } = await client.chat.completions
   .create({
-    model: 'deepseek/deepseek-v4.1-flash',
+    model: 'deepseek/deepseek-v4.1-flash-1017',
     messages: [{ role: 'user', content: 'Write a one-line welcome message for a todo app.' }],
   })
   .withResponse();
@@ -119,7 +119,7 @@ from openai import OpenAI
 client = OpenAI(base_url="https://api.pre.dev/v1", api_key=os.environ["PREDEV_API_KEY"])
 
 raw = client.chat.completions.with_raw_response.create(
-    model="deepseek/deepseek-v4.1-flash",
+    model="deepseek/deepseek-v4.1-flash-1017",
     messages=[{"role": "user", "content": "Write a one-line welcome message for a todo app."}],
 )
 print(raw.parse().choices[0].message.content)

ai-gateway/api/chat-completions.mdx

@@ -12,7 +12,7 @@ curl --fail-with-body -i https://api.pre.dev/v1/chat/completions \
   -H "Authorization: Bearer $PREDEV_API_KEY" \
   -H "Content-Type: application/json" \
   -d '{
-    "model": "deepseek/deepseek-v4.1-flash",
+    "model": "deepseek/deepseek-v4.1-flash-1017",
     "messages": [
       { "role": "system", "content": "Answer in one sentence." },
       { "role": "user", "content": "Why is the sky blue?" }
@@ -26,7 +26,7 @@ const client = new OpenAI({ baseURL: 'https://api.pre.dev/v1', apiKey: process.e
 
 const { data: completion, response } = await client.chat.completions
   .create({
-    model: 'deepseek/deepseek-v4.1-flash',
+    model: 'deepseek/deepseek-v4.1-flash-1017',
     messages: [
       { role: 'system', content: 'Answer in one sentence.' },
       { role: 'user', content: 'Why is the sky blue?' },
@@ -43,7 +43,7 @@ from openai import OpenAI
 client = OpenAI(base_url="https://api.pre.dev/v1", api_key=os.environ["PREDEV_API_KEY"])
 
 raw = client.chat.completions.with_raw_response.create(
-    model="deepseek/deepseek-v4.1-flash",
+    model="deepseek/deepseek-v4.1-flash-1017",
     messages=[
         {"role": "system", "content": "Answer in one sentence."},
         {"role": "user", "content": "Why is the sky blue?"},
@@ -79,7 +79,7 @@ The body is the standard chat completion response. `id` is the pre.dev generatio
 {
   "id": "pdg-7c1e4b52-9a3d-4f8e-b0c6-2d5a8e913f47",
   "object": "chat.completion",
-  "model": "deepseek/deepseek-v4.1-flash",
+  "model": "deepseek/deepseek-v4.1-flash-1017",
   "choices": [
     {
       "index": 0,

ai-gateway/api/usage.mdx

@@ -33,7 +33,7 @@ curl --fail-with-body "https://api.pre.dev/v1/usage?days=30" \
   "totals": { "requests": 1840, "credits": 87.5 },
   "by_model": [
     {
-      "model": "deepseek/deepseek-v4.1-flash",
+      "model": "deepseek/deepseek-v4.1-flash-1017",
       "path": "/chat/completions",
       "requests": 1702,
       "credits": 41.2,

ai-gateway/models.mdx

@@ -5,7 +5,7 @@ description: "Use any model id from the pre.dev catalog and read credit prices f
 
 The gateway serves hundreds of models from every major lab. Use the model id exactly as listed by [`GET /v1/models`](/ai-gateway/api/models): if the catalog lists it, `model: "<author>/<slug>"` works here.
 
-Example ids: `anthropic/claude-sonnet-5`, `deepseek/deepseek-v4.1-flash`, `google/gemini-3.8-flash`, and `openai/gpt-6-luna`.
+Example ids: `anthropic/claude-sonnet-5`, `deepseek/deepseek-v4.1-flash-1017`, `google/gemini-3.8-flash`, and `openai/gpt-6-luna`.
 
 Some models also have variant ids in the catalog, such as a `:free` or `:batch` suffix; use them exactly as listed. Append `:online` to a model id to add web search, the same as the `web` plugin. See [fallbacks and advanced options](/ai-gateway/routing-and-fallbacks).
 
@@ -20,8 +20,8 @@ Each row describes the model (`id`, `name`, `context_length`, supported modaliti
 
 ```json
 {
-  "id": "deepseek/deepseek-v4.1-flash",
-  "name": "DeepSeek: DeepSeek V4.1 Flash",
+  "id": "deepseek/deepseek-v4.1-flash-1017",
+  "name": "DeepSeek: DeepSeek V4.1 Flash 1017",
   "context_length": 1048576,
   "predev": {
     "credits_per_m_input": 2.5,

ai-gateway/overview.mdx

@@ -39,7 +39,7 @@ The pre.dev AI Gateway is an OpenAI-compatible API for hundreds of models from e
 
 ## What you send
 
-Model ids are `<author>/<slug>` strings exactly as listed by [`GET /v1/models`](/ai-gateway/api/models), for example `anthropic/claude-sonnet-5`, `deepseek/deepseek-v4.1-flash`, `google/gemini-3.8-flash`, or `openai/gpt-6-luna`. There are no separate pre.dev-specific model names.
+Model ids are `<author>/<slug>` strings exactly as listed by [`GET /v1/models`](/ai-gateway/api/models), for example `anthropic/claude-sonnet-5`, `deepseek/deepseek-v4.1-flash-1017`, `google/gemini-3.8-flash`, or `openai/gpt-6-luna`. There are no separate pre.dev-specific model names.
 
 The standard chat completion fields (`messages`, `temperature`, `max_tokens`, `stop`, and so on) work as you would expect. The pre.dev AI API also supports these options, described on [fallbacks and advanced options](/ai-gateway/routing-and-fallbacks):
 

ai-gateway/quickstart.mdx

@@ -6,7 +6,7 @@ description: "Send a chat completion through api.pre.dev/v1 with curl or a stock
 
 import ApiKeyLocation from "/snippets/api-key-location.mdx";
 
-Send one chat completion to `deepseek/deepseek-v4.1-flash` and read the credits it charged.
+Send one chat completion to `deepseek/deepseek-v4.1-flash-1017` and read the credits it charged.
 
 ## Before you start
 
@@ -23,7 +23,7 @@ Store it as `PREDEV_API_KEY`. A Free workspace can spend 5 credits on gateway ca
       -H "Authorization: Bearer $PREDEV_API_KEY" \
       -H "Content-Type: application/json" \
       -d '{
-        "model": "deepseek/deepseek-v4.1-flash",
+        "model": "deepseek/deepseek-v4.1-flash-1017",
         "messages": [{ "role": "user", "content": "Say hello in five words." }]
       }'
     ```
@@ -40,7 +40,7 @@ Store it as `PREDEV_API_KEY`. A Free workspace can spend 5 credits on gateway ca
     });
 
     const completion = await client.chat.completions.create({
-      model: 'deepseek/deepseek-v4.1-flash',
+      model: 'deepseek/deepseek-v4.1-flash-1017',
       messages: [{ role: 'user', content: 'Say hello in five words.' }],
     });
     console.log(completion.choices[0].message.content);
@@ -59,7 +59,7 @@ Store it as `PREDEV_API_KEY`. A Free workspace can spend 5 credits on gateway ca
     )
 
     completion = client.chat.completions.create(
-        model="deepseek/deepseek-v4.1-flash",
+        model="deepseek/deepseek-v4.1-flash-1017",
         messages=[{"role": "user", "content": "Say hello in five words."}],
     )
     print(completion.choices[0].message.content)
@@ -78,7 +78,7 @@ Store it as `PREDEV_API_KEY`. A Free workspace can spend 5 credits on gateway ca
     });
 
     const { text } = await generateText({
-      model: predev('deepseek/deepseek-v4.1-flash'),
+      model: predev('deepseek/deepseek-v4.1-flash-1017'),
       prompt: 'Say hello in five words.',
     });
     console.log(text);

ai-gateway/routing-and-fallbacks.mdx

@@ -11,7 +11,7 @@ Send `models` instead of a single `model`. The gateway tries each in order, and
 
 ```json
 {
-  "models": ["anthropic/claude-sonnet-5", "openai/gpt-6-luna", "deepseek/deepseek-v4.1-flash"],
+  "models": ["anthropic/claude-sonnet-5", "openai/gpt-6-luna", "deepseek/deepseek-v4.1-flash-1017"],
   "route": "fallback",
   "messages": [{ "role": "user", "content": "Summarize the plot of Dune in two sentences." }]
 }

ai-gateway/tools-and-structured-output.mdx

@@ -164,7 +164,7 @@ Add the `response-healing` plugin to repair near-valid JSON from models without
 
 ```json
 {
-  "model": "deepseek/deepseek-v4.1-flash",
+  "model": "deepseek/deepseek-v4.1-flash-1017",
   "plugins": [{ "id": "response-healing" }],
   "response_format": { "type": "json_object" },
   "messages": [{ "role": "user", "content": "Return {\"ok\": true} as JSON." }]