@ai-sdk/cerebras 3.0.29 → 3.0.31

package/CHANGELOG.md

@@ -1,5 +1,21 @@
 # @ai-sdk/cerebras
 
+## 3.0.31
+
+### Patch Changes
+
+- Updated dependencies [86892f3]
+  - @ai-sdk/openai-compatible@3.0.31
+
+## 3.0.30
+
+### Patch Changes
+
+- f563df6: Update Cerebras model ID autocomplete and package documentation to the current public model catalog.
+- Updated dependencies [7fbfc6d]
+  - @ai-sdk/provider-utils@5.0.27
+  - @ai-sdk/openai-compatible@3.0.30
+
 ## 3.0.29
 
 ### Patch Changes

package/README.md

@@ -40,7 +40,7 @@ import { cerebras } from '@ai-sdk/cerebras';
 import { generateText } from 'ai';
 
 const { text } = await generateText({
-  model: cerebras('llama-3.3-70b'),
+  model: cerebras('gpt-oss-120b'),
   prompt: 'Write a JavaScript function that sorts a list:',
 });
 ```
@@ -51,5 +51,3 @@ For more information about Cerebras' high-speed inference capabilities and API d
 
 - [Cerebras Inference Documentation](https://inference-docs.cerebras.ai/introduction)
 - [Cerebras Website](https://cerebras.ai)
-
-Note: Due to high demand in the early launch phase, context windows are temporarily limited to 8192 tokens in the Free Tier.

package/dist/index.d.ts

@@ -2,7 +2,7 @@ import { ProviderV4, LanguageModelV4 } from '@ai-sdk/provider';
 import { FetchFunction } from '@ai-sdk/provider-utils';
 import { z } from 'zod/v4';
 
-type CerebrasChatModelId = 'llama3.1-8b' | 'gpt-oss-120b' | 'qwen-3-235b-a22b-instruct-2507' | 'qwen-3-235b-a22b-thinking-2507' | 'zai-glm-4.6' | 'zai-glm-4.7' | (string & {});
+type CerebrasChatModelId = 'gpt-oss-120b' | 'gemma-4-31b' | 'zai-glm-4.7' | (string & {});
 
 declare const cerebrasErrorSchema: z.ZodObject<{
     message: z.ZodString;

package/dist/index.js

@@ -96,7 +96,7 @@ var CerebrasChatLanguageModel = class _CerebrasChatLanguageModel extends OpenAIC
 import { z } from "zod/v4";
 
 // src/version.ts
-var VERSION = true ? "3.0.29" : "0.0.0-test";
+var VERSION = true ? "3.0.31" : "0.0.0-test";
 
 // src/cerebras-provider.ts
 var cerebrasErrorSchema = z.object({

package/docs/40-cerebras.mdx

@@ -62,7 +62,7 @@ import { cerebras } from '@ai-sdk/cerebras';
 import { generateText } from 'ai';
 
 const { text } = await generateText({
-  model: cerebras('llama3.1-8b'),
+  model: cerebras('gpt-oss-120b'),
   prompt: 'Write a vegetarian lasagna recipe for 4 people.',
 });
 ```
@@ -70,22 +70,22 @@ const { text } = await generateText({
 Cerebras language models can be used in the `streamText` function
 (see [AI SDK Core](/docs/ai-sdk-core)).
 
-You can create Cerebras language models using a provider instance. The first argument is the model ID, e.g. `llama-3.3-70b`:
+You can create Cerebras language models using a provider instance. The first argument is the model ID, e.g. `gpt-oss-120b`:
 
 ```ts
-const model = cerebras('llama-3.3-70b');
+const model = cerebras('gpt-oss-120b');
 ```
 
 You can also use the `.languageModel()` and `.chat()` methods:
 
 ```ts
-const model = cerebras.languageModel('llama-3.3-70b');
-const model = cerebras.chat('llama-3.3-70b');
+const model = cerebras.languageModel('gpt-oss-120b');
+const model = cerebras.chat('gpt-oss-120b');
 ```
 
 ### Reasoning Models
 
-Cerebras offers several reasoning models including `gpt-oss-120b`, `qwen-3-32b`, and `zai-glm-4.7` that generate intermediate thinking tokens before their final response. The reasoning output is streamed through the standard AI SDK reasoning parts.
+Cerebras offers reasoning models including `gpt-oss-120b`, `zai-glm-4.7`, and `gemma-4-31b` that generate intermediate thinking tokens before their final response. The reasoning output is streamed through the standard AI SDK reasoning parts.
 
 For `gpt-oss-120b`, you can control the reasoning depth using the `reasoningEffort` provider option:
 
@@ -132,21 +132,8 @@ The following optional provider options are available for Cerebras language mode
 
 ## Model Capabilities
 
-| Model                            | Image Input | Object Generation | Tool Usage | Tool Streaming | Reasoning |
-| -------------------------------- | ----------- | ----------------- | ---------- | -------------- | --------- |
-| `llama3.1-8b`                    | <Cross />   | <Check />         | <Check />  | <Check />      | <Cross /> |
-| `llama-3.3-70b`                  | <Cross />   | <Check />         | <Check />  | <Check />      | <Cross /> |
-| `gpt-oss-120b`                   | <Cross />   | <Check />         | <Check />  | <Check />      | <Check /> |
-| `qwen-3-32b`                     | <Cross />   | <Check />         | <Check />  | <Check />      | <Check /> |
-| `qwen-3-235b-a22b-instruct-2507` | <Cross />   | <Check />         | <Check />  | <Check />      | <Cross /> |
-| `qwen-3-235b-a22b-thinking-2507` | <Cross />   | <Check />         | <Check />  | <Check />      | <Cross /> |
-| `zai-glm-4.6`                    | <Cross />   | <Check />         | <Check />  | <Check />      | <Cross /> |
-| `zai-glm-4.7`                    | <Cross />   | <Check />         | <Check />  | <Check />      | <Check /> |
-
-<Note>
-  The models `qwen-3-32b` and `llama-3.3-70b` are scheduled for deprecation on
-  February 16, 2026. Please see the [Cerebras
-  docs](https://inference-docs.cerebras.ai/introduction) for more details about
-  the available models and migration guidance. You can also pass any available
-  provider model ID as a string if needed.
-</Note>
+| Model          | Image Input | Object Generation | Tool Usage | Tool Streaming | Reasoning |
+| -------------- | ----------- | ----------------- | ---------- | -------------- | --------- |
+| `gpt-oss-120b` | <Cross />   | <Check />         | <Check />  | <Check />      | <Check /> |
+| `zai-glm-4.7`  | <Cross />   | <Check />         | <Check />  | <Check />      | <Check /> |
+| `gemma-4-31b`  | <Check />   | <Check />         | <Check />  | <Check />      | <Check /> |

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@ai-sdk/cerebras",
-  "version": "3.0.29",
+  "version": "3.0.31",
   "type": "module",
   "license": "Apache-2.0",
   "sideEffects": false,
@@ -29,9 +29,9 @@
     }
   },
   "dependencies": {
-    "@ai-sdk/openai-compatible": "3.0.29",
+    "@ai-sdk/openai-compatible": "3.0.31",
     "@ai-sdk/provider": "4.0.7",
-    "@ai-sdk/provider-utils": "5.0.26"
+    "@ai-sdk/provider-utils": "5.0.27"
   },
   "devDependencies": {
     "@types/node": "22.19.19",

package/src/cerebras-chat-options.ts

@@ -1,11 +1,8 @@
 // https://inference-docs.cerebras.ai/models/overview
 export type CerebrasChatModelId =
   // production
-  | 'llama3.1-8b'
   | 'gpt-oss-120b'
+  | 'gemma-4-31b'
   // preview
-  | 'qwen-3-235b-a22b-instruct-2507'
-  | 'qwen-3-235b-a22b-thinking-2507'
-  | 'zai-glm-4.6'
   | 'zai-glm-4.7'
   | (string & {});