release: 0.31.0 (#238)

stainless-app[bot] · web-flow · commit 15d5c16d717e · 2025-09-02T16:19:20.000Z
Co-authored-by: stainless-app[bot] &lt;142633134+stainless-app[bot]@users.noreply.github.com&gt;
diff --git a/.release-please-manifest.json b/.release-please-manifest.json
@@ -1,3 +1,3 @@
 {
-  ".": "0.30.0"
+  ".": "0.31.0"
 }
diff --git a/.stats.yml b/.stats.yml
@@ -1,4 +1,4 @@
 configured_endpoints: 17
-openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/groqcloud%2Fgroqcloud-4543b558a0a546fc45d3300535b9b535f9cf251f4284bc255d3bc337727e5a50.yml
-openapi_spec_hash: 09235cb11f84f84a07819c2b3f0a6d6a
-config_hash: 6b1c374dcc1ffa3165dd22f52a77ff89
+openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/groqcloud%2Fgroqcloud-a95a90928412afdb9cf5101b7fbb67ef2abbc4ecaa51ff18fa04643f9e8d2c95.yml
+openapi_spec_hash: d2e5cb1562a2b2beb8673256252b9bf5
+config_hash: 961b4995e909aef11a454befa56ad3d2
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -1,5 +1,32 @@
 # Changelog
 
+## 0.31.0 (2025-09-02)
+
+Full Changelog: [v0.30.0...v0.31.0](https://github.com/groq/groq-typescript/compare/v0.30.0...v0.31.0)
+
+### Features
+
+* **api:** api update ([be48d38](https://github.com/groq/groq-typescript/commit/be48d38f749dc4599ab71633ff226583f6e74b02))
+* **api:** api update ([44424c2](https://github.com/groq/groq-typescript/commit/44424c26018f43b69682bebca7e9c734b5d0f1e0))
+* **api:** api update ([f772446](https://github.com/groq/groq-typescript/commit/f772446f655ff905c14f40f45cafc4109ef7f912))
+* **api:** api update ([2e12bd1](https://github.com/groq/groq-typescript/commit/2e12bd1022f8cd168d41b62d753615b3900ee1f1))
+* **api:** api update ([61a9e99](https://github.com/groq/groq-typescript/commit/61a9e99c984e43432d823388435893408d84ce0f))
+
+
+### Bug Fixes
+
+* update example model from decommissioned models to gpt-oss-20b ([1c69897](https://github.com/groq/groq-typescript/commit/1c69897c7fe09a0d0df5f041749a17a95ed878cd))
+
+
+### Chores
+
+* **deps:** update dependency node-fetch to v2.6.13 ([4938496](https://github.com/groq/groq-typescript/commit/49384963049a83b196e87595046e7686fcdfcca0))
+* **internal:** formatting change ([a287d5e](https://github.com/groq/groq-typescript/commit/a287d5e41f1b6bba338b0cc3e1b9212a35b4e824))
+* **internal:** move publish config ([5fe1890](https://github.com/groq/groq-typescript/commit/5fe1890402075a67d6ea4472b6196273cd0b0f9e))
+* **internal:** update comment in script ([2a69a41](https://github.com/groq/groq-typescript/commit/2a69a4195d773bd0c6c1dcc0e49824ed6f50b24d))
+* update @stainless-api/prism-cli to v5.15.0 ([35cd683](https://github.com/groq/groq-typescript/commit/35cd68309611e5e77f04974ce18b516116f3346d))
+* update CI script ([e863bc0](https://github.com/groq/groq-typescript/commit/e863bc04c0324e2b5cdf2fab8abe36e2c4469907))
+
 ## 0.30.0 (2025-08-05)
 
 Full Changelog: [v0.29.0...v0.30.0](https://github.com/groq/groq-typescript/compare/v0.29.0...v0.30.0)
diff --git a/README.md b/README.md
@@ -28,7 +28,7 @@ const client = new Groq({
 
 const chatCompletion = await client.chat.completions.create({
   messages: [{ role: 'user', content: 'Explain the importance of low latency LLMs' }],
-  model: 'llama3-8b-8192',
+  model: 'openai/gpt-oss-20b',
 });
 
 console.log(chatCompletion.choices[0].message.content);
@@ -51,7 +51,7 @@ const params: Groq.Chat.CompletionCreateParams = {
     { role: 'system', content: 'You are a helpful assistant.' },
     { role: 'user', content: 'Explain the importance of low latency LLMs' },
   ],
-  model: 'llama3-8b-8192',
+  model: 'openai/gpt-oss-20b',
 };
 const chatCompletion: Groq.Chat.ChatCompletion = await client.chat.completions.create(params);
 ```
@@ -117,7 +117,7 @@ const chatCompletion = await client.chat.completions
       { role: 'system', content: 'You are a helpful assistant.' },
       { role: 'user', content: 'Explain the importance of low latency LLMs' },
     ],
-    model: 'llama3-8b-8192',
+    model: 'openai/gpt-oss-20b',
   })
   .catch(async (err) => {
     if (err instanceof Groq.APIError) {
@@ -159,7 +159,7 @@ const client = new Groq({
 });
 
 // Or, configure per-request:
-await client.chat.completions.create({ messages: [{ role: 'system', content: 'You are a helpful assistant.' }, { role: 'user', content: 'Explain the importance of low latency LLMs' }], model: 'llama3-8b-8192' }, {
+await client.chat.completions.create({ messages: [{ role: 'system', content: 'You are a helpful assistant.' }, { role: 'user', content: 'Explain the importance of low latency LLMs' }], model: 'openai/gpt-oss-20b' }, {
   maxRetries: 5,
 });
 ```
@@ -176,7 +176,7 @@ const client = new Groq({
 });
 
 // Override per-request:
-await client.chat.completions.create({ messages: [{ role: 'system', content: 'You are a helpful assistant.' }, { role: 'user', content: 'Explain the importance of low latency LLMs' }], model: 'llama3-8b-8192' }, {
+await client.chat.completions.create({ messages: [{ role: 'system', content: 'You are a helpful assistant.' }, { role: 'user', content: 'Explain the importance of low latency LLMs' }], model: 'openai/gpt-oss-20b' }, {
   timeout: 5 * 1000,
 });
 ```
@@ -203,7 +203,7 @@ const response = await client.chat.completions
       { role: 'system', content: 'You are a helpful assistant.' },
       { role: 'user', content: 'Explain the importance of low latency LLMs' },
     ],
-    model: 'llama3-8b-8192',
+    model: 'openai/gpt-oss-20b',
   })
   .asResponse();
 console.log(response.headers.get('X-My-Header'));
@@ -215,7 +215,7 @@ const { data: chatCompletion, response: raw } = await client.chat.completions
       { role: 'system', content: 'You are a helpful assistant.' },
       { role: 'user', content: 'Explain the importance of low latency LLMs' },
     ],
-    model: 'llama3-8b-8192',
+    model: 'openai/gpt-oss-20b',
   })
   .withResponse();
 console.log(raw.headers.get('X-My-Header'));
@@ -329,7 +329,7 @@ await client.chat.completions.create(
       { role: 'system', content: 'You are a helpful assistant.' },
       { role: 'user', content: 'Explain the importance of low latency LLMs' },
     ],
-    model: 'llama3-8b-8192',
+    model: 'openai/gpt-oss-20b',
   },
   {
     httpAgent: new http.Agent({ keepAlive: false }),
diff --git a/bin/publish-npm b/bin/publish-npm
@@ -58,4 +58,4 @@ else
 fi
 
 # Publish with the appropriate tag
-yarn publish --access public --tag "$TAG"
+yarn publish --tag "$TAG"
diff --git a/package.json b/package.json
@@ -1,6 +1,6 @@
 {
   "name": "groq-sdk",
-  "version": "0.30.0",
+  "version": "0.31.0",
   "description": "The official TypeScript library for the Groq API",
   "author": "Groq <support@groq.com>",
   "types": "dist/index.d.ts",
@@ -13,6 +13,9 @@
     "**/*"
   ],
   "private": false,
+  "publishConfig": {
+    "access": "public"
+  },
   "scripts": {
     "test": "./scripts/test",
     "build": "./scripts/build",
diff --git a/scripts/mock b/scripts/mock
@@ -21,7 +21,7 @@ echo "==> Starting mock server with URL ${URL}"
 
 # Run prism mock on the given spec
 if [ "$1" == "--daemon" ]; then
-  npm exec --package=@stainless-api/prism-cli@5.8.5 -- prism mock "$URL" &> .prism.log &
+  npm exec --package=@stainless-api/prism-cli@5.15.0 -- prism mock "$URL" &> .prism.log &
 
   # Wait for server to come online
   echo -n "Waiting for server"
@@ -37,5 +37,5 @@ if [ "$1" == "--daemon" ]; then
 
   echo
 else
-  npm exec --package=@stainless-api/prism-cli@5.8.5 -- prism mock "$URL"
+  npm exec --package=@stainless-api/prism-cli@5.15.0 -- prism mock "$URL"
 fi
diff --git a/scripts/test b/scripts/test
@@ -43,7 +43,7 @@ elif ! prism_is_running ; then
   echo -e "To run the server, pass in the path or url of your OpenAPI"
   echo -e "spec to the prism command:"
   echo
-  echo -e "  \$ ${YELLOW}npm exec --package=@stoplight/prism-cli@~5.3.2 -- prism mock path/to/your.openapi.yml${NC}"
+  echo -e "  \$ ${YELLOW}npm exec --package=@stainless-api/prism-cli@5.15.0 -- prism mock path/to/your.openapi.yml${NC}"
   echo
 
   exit 1
diff --git a/scripts/utils/upload-artifact.sh b/scripts/utils/upload-artifact.sh
@@ -12,7 +12,7 @@ if [[ "$SIGNED_URL" == "null" ]]; then
   exit 1
 fi
 
-UPLOAD_RESPONSE=$(tar -cz dist | curl -v -X PUT \
+UPLOAD_RESPONSE=$(tar -cz "${BUILD_PATH:-dist}" | curl -v -X PUT \
   -H "Content-Type: application/gzip" \
   --data-binary @- "$SIGNED_URL" 2>&1)
 
diff --git a/src/index.ts b/src/index.ts
@@ -218,6 +218,7 @@ Groq.Audio = Audio;
 Groq.Models = Models;
 Groq.Batches = Batches;
 Groq.Files = Files;
+
 export declare namespace Groq {
   export type RequestOptions = Core.RequestOptions;
 
diff --git a/src/resources/chat/completions.ts b/src/resources/chat/completions.ts
@@ -1409,9 +1409,10 @@ export namespace ChatCompletionTokenLogprob {
 
 export interface ChatCompletionTool {
   /**
-   * The type of the tool. Currently, only `function` is supported.
+   * The type of the tool. `function`, `browser_search`, and `code_interpreter` are
+   * supported.
    */
-  type: 'function' | 'browser_search' | 'code_interpreter';
+  type: 'function' | 'browser_search' | 'code_interpreter' | (string & {});
 
   function?: Shared.FunctionDefinition;
 }
@@ -1487,6 +1488,17 @@ export interface ChatCompletionCreateParamsBase {
     | 'llama3-70b-8192'
     | 'llama3-8b-8192';
 
+  /**
+   * Custom configuration of models and tools for Compound.
+   */
+  compound_custom?: CompletionCreateParams.CompoundCustom | null;
+
+  /**
+   * A list of documents to provide context for the conversation. Each document
+   * contains text that can be referenced by the model.
+   */
+  documents?: Array<CompletionCreateParams.Document> | null;
+
   /**
    * @deprecated Deprecated: Use search_settings.exclude_domains instead. A list of
    * domains to exclude from the search results when the model uses a web search
@@ -1495,9 +1507,9 @@ export interface ChatCompletionCreateParamsBase {
   exclude_domains?: Array<string> | null;
 
   /**
-   * Number between -2.0 and 2.0. Positive values penalize new tokens based on their
-   * existing frequency in the text so far, decreasing the model's likelihood to
-   * repeat the same line verbatim.
+   * This is not yet supported by any of our models. Number between -2.0 and 2.0.
+   * Positive values penalize new tokens based on their existing frequency in the
+   * text so far, decreasing the model's likelihood to repeat the same line verbatim.
    */
   frequency_penalty?: number | null;
 
@@ -1580,15 +1592,18 @@ export interface ChatCompletionCreateParamsBase {
   parallel_tool_calls?: boolean | null;
 
   /**
-   * Number between -2.0 and 2.0. Positive values penalize new tokens based on
-   * whether they appear in the text so far, increasing the model's likelihood to
-   * talk about new topics.
+   * This is not yet supported by any of our models. Number between -2.0 and 2.0.
+   * Positive values penalize new tokens based on whether they appear in the text so
+   * far, increasing the model's likelihood to talk about new topics.
    */
   presence_penalty?: number | null;
 
   /**
-   * this field is only available for qwen3 models. Set to 'none' to disable
-   * reasoning. Set to 'default' or null to let Qwen reason.
+   * qwen3 models support the following values Set to 'none' to disable reasoning.
+   * Set to 'default' or null to let Qwen reason.
+   *
+   * openai/gpt-oss-20b and openai/gpt-oss-120b support 'low', 'medium', or 'high'.
+   * 'medium' is the default value.
    */
   reasoning_effort?: 'none' | 'default' | 'low' | 'medium' | 'high' | null;
 
@@ -1707,6 +1722,34 @@ export interface ChatCompletionCreateParamsBase {
 }
 
 export namespace CompletionCreateParams {
+  /**
+   * Custom configuration of models and tools for Compound.
+   */
+  export interface CompoundCustom {
+    models?: CompoundCustom.Models | null;
+  }
+
+  export namespace CompoundCustom {
+    export interface Models {
+      /**
+       * Custom model to use for answering.
+       */
+      answering_model?: string | null;
+
+      /**
+       * Custom model to use for reasoning.
+       */
+      reasoning_model?: string | null;
+    }
+  }
+
+  export interface Document {
+    /**
+     * The text content of the document.
+     */
+    text: string;
+  }
+
   /**
    * @deprecated
    */
diff --git a/src/version.ts b/src/version.ts
@@ -1 +1 @@
-export const VERSION = '0.30.0'; // x-release-please-version
+export const VERSION = '0.31.0'; // x-release-please-version
diff --git a/tests/api-resources/chat/completions.test.ts b/tests/api-resources/chat/completions.test.ts
@@ -27,6 +27,8 @@ describe('resource completions', () => {
     const response = await client.chat.completions.create({
       messages: [{ content: 'string', role: 'system', name: 'name' }],
       model: 'meta-llama/llama-4-scout-17b-16e-instruct',
+      compound_custom: { models: { answering_model: 'answering_model', reasoning_model: 'reasoning_model' } },
+      documents: [{ text: 'text' }],
       exclude_domains: ['string'],
       frequency_penalty: -2,
       function_call: 'none',
diff --git a/yarn.lock b/yarn.lock

Original file line number	Diff line number	Diff line change
`@@ -1,3 +1,3 @@`
`1`	`1`	`{`
`2`		`- ".": "0.30.0"`
	`2`	`+ ".": "0.31.0"`
`3`	`3`	`}`