browserbase · antonvishal · Sep 11, 2026
diff --git a/.changeset/remove-groq-cerebras.md b/.changeset/remove-groq-cerebras.md
@@ -0,0 +1,9 @@
+---
+"@browserbasehq/stagehand-protocol": major
+"@browserbasehq/stagehand-extension": patch
+"@browserbasehq/stagehand-python": patch
+"@browserbasehq/stagehand-go": patch
+"@browserbasehq/stagehand": patch
+---
+
+Remove native Groq and Cerebras provider support.
@@ -35,7 +35,6 @@ Set up your API keys before configuring Stagehand:
 OPENAI_API_KEY=your_openai_key_here
 ANTHROPIC_API_KEY=your_anthropic_key_here
 GOOGLE_API_KEY=your_google_key_here
-GROQ_API_KEY=your_groq_key_here
 ```
 </CodeGroup>
 
@@ -54,10 +53,8 @@ Stagehand supports major LLM providers with structured output capabilities:
 ### Additional Providers
 
 <Expandable title="More Providers">
-- **Groq** - `llama-3.3-70b-versatile` (Good for speed critical applications)
 - **xAI** - `grok-beta` (Good for complex reasoning)
 - **Azure** - Enterprise OpenAI deployment
-- **Cerebras** - High-speed inference
 - **TogetherAI** - Open-source models
 - **Mistral** - `mixtral-8x7b-32768` (European option)
 - **DeepSeek** - Cost-effective alternative
@@ -302,4 +299,4 @@ For each provider, use their latest models that meet these requirements. Some ex
 <Card title="Cache Results" href="/v2/best-practices/caching" icon="database">
   Store successful patterns using our Caching Guide
 </Card>
-</CardGroup>
+</CardGroup>
@@ -340,24 +340,6 @@ For Microsoft Entra ID authentication, pass the bearer token explicitly in `auth
 [View all supported Azure models →](https://ai.azure.com/catalog)
 </Tab>
 
-<Tab title="Cerebras">
-<CodeGroup>
-```typescript TypeScript
-import { Stagehand } from "@browserbasehq/stagehand";
-
-const stagehand = new Stagehand({
-  env: "BROWSERBASE",
-  model: "cerebras/llama-4-scout"
-  // API key auto-loads from CEREBRAS_API_KEY - set in your .env
-});
-
-await stagehand.init();
-```
-
-</CodeGroup>
-[View all supported Cerebras models →](https://inference-docs.cerebras.ai/models/overview)
-</Tab>
-
 <Tab title="DeepSeek">
 
 <CodeGroup>
@@ -377,26 +359,6 @@ await stagehand.init();
 [View all supported DeepSeek models →](https://api-docs.deepseek.com/quick_start/pricing)
 </Tab>
 
-<Tab title="Groq">
-
-
-<CodeGroup>
-```typescript TypeScript
-import { Stagehand } from "@browserbasehq/stagehand";
-
-const stagehand = new Stagehand({
-  env: "BROWSERBASE",
-  model: "groq/llama-3.1-8b-instant"
-  // API key auto-loads from GROQ_API_KEY - set in your .env
-});
-
-await stagehand.init();
-```
-
-</CodeGroup>
-[View all supported Groq models →](https://console.groq.com/docs/models)
-</Tab>
-
 <Tab title="Mistral">
 
 <CodeGroup>
@@ -1003,19 +965,6 @@ The following models work without the `provider/` prefix in the model parameter
 - `gpt-4o-2024-08-06`
 - `o1-preview`
 
-</Accordion>
-<Accordion title="Cerebras">
-
-- `cerebras-llama-3.3-70b`
-- `cerebras-llama-3.1-8b`
-
-</Accordion>
-<Accordion title="Groq">
-
-- `groq-llama-3.3-70b-versatile`
-- `groq-llama-3.3-70b-specdec`
-- `moonshotai/kimi-k2-instruct`
-
 </Accordion>
 </AccordionGroup>
 
@@ -1042,9 +991,7 @@ The following models work without the `provider/` prefix in the model parameter
 | Anthropic  | `ANTHROPIC_API_KEY`            |
 | OpenAI     | `OPENAI_API_KEY`               |
 | Azure      | `AZURE_API_KEY`                |
-| Cerebras   | `CEREBRAS_API_KEY`             |
 | DeepSeek   | `DEEPSEEK_API_KEY`             |
-| Groq       | `GROQ_API_KEY`                 |
 | Mistral    | `MISTRAL_API_KEY`              |
 | Ollama     | None (local)                   |
 | Perplexity | `PERPLEXITY_API_KEY`           |

@@ -538,136 +538,6 @@ OpenAI models are called through the Responses API.
 [View all supported OpenAI models →](https://platform.openai.com/docs/models)
 </Tab>
 
-<Tab title="Groq">
-
-<Tabs>
-<Tab title="TypeScript">
-```typescript
-import { browserbase, Stagehand } from "@browserbasehq/stagehand";
-
-const stagehand = await Stagehand.create({
-  browser: await browserbase.launch({ apiKey: process.env.BROWSERBASE_API_KEY }),
-  model: {
-    modelName: "groq/llama-3.3-70b-versatile",
-  },
-});
-```
-</Tab>
-
-<Tab title="Python">
-```python
-import os
-
-from stagehand import Stagehand, browserbase
-
-browser = await browserbase.launch(api_key=os.environ["BROWSERBASE_API_KEY"])
-
-stagehand = await Stagehand.create(
-    browser=browser,
-    model="groq/llama-3.3-70b-versatile",
-    model_api_key=os.environ["GROQ_API_KEY"],
-)
-```
-</Tab>
-
-<Tab title="Go">
-```go
-apiKey := os.Getenv("BROWSERBASE_API_KEY")
-modelAPIKey := os.Getenv("GROQ_API_KEY")
-model := stagehand.ModelConfig{
-	ModelName: "groq/llama-3.3-70b-versatile",
-	APIKey:    &modelAPIKey,
-}
-
-browser, err := stagehand.LaunchBrowserbase(ctx, stagehand.BrowserbaseLaunchOptions{
-	APIKey: apiKey,
-})
-if err != nil {
-	return err
-}
-
-client, err := stagehand.Create(ctx, stagehand.CreateOptions{
-	Browser: browser,
-	Model:   &model,
-})
-if err != nil {
-	return err
-}
-defer func() { err = errors.Join(err, client.Close(ctx)) }()
-```
-</Tab>
-</Tabs>
-
-Commonly used: `groq/llama-3.3-70b-versatile`, `groq/openai/gpt-oss-120b`, `groq/moonshotai/kimi-k2-instruct-0905`, `groq/qwen/qwen3-32b`.
-
-[View all supported Groq models →](https://console.groq.com/docs/models)
-</Tab>
-
-<Tab title="Cerebras">
-
-<Tabs>
-<Tab title="TypeScript">
-```typescript
-import { browserbase, Stagehand } from "@browserbasehq/stagehand";
-
-const stagehand = await Stagehand.create({
-  browser: await browserbase.launch({ apiKey: process.env.BROWSERBASE_API_KEY }),
-  model: {
-    modelName: "cerebras/gpt-oss-120b",
-  },
-});
-```
-</Tab>
-
-<Tab title="Python">
-```python
-import os
-
-from stagehand import Stagehand, browserbase
-
-browser = await browserbase.launch(api_key=os.environ["BROWSERBASE_API_KEY"])
-
-stagehand = await Stagehand.create(
-    browser=browser,
-    model="cerebras/gpt-oss-120b",
-    model_api_key=os.environ["CEREBRAS_API_KEY"],
-)
-```
-</Tab>
-
-<Tab title="Go">
-```go
-apiKey := os.Getenv("BROWSERBASE_API_KEY")
-modelAPIKey := os.Getenv("CEREBRAS_API_KEY")
-model := stagehand.ModelConfig{
-	ModelName: "cerebras/gpt-oss-120b",
-	APIKey:    &modelAPIKey,
-}
-
-browser, err := stagehand.LaunchBrowserbase(ctx, stagehand.BrowserbaseLaunchOptions{
-	APIKey: apiKey,
-})
-if err != nil {
-	return err
-}
-
-client, err := stagehand.Create(ctx, stagehand.CreateOptions{
-	Browser: browser,
-	Model:   &model,
-})
-if err != nil {
-	return err
-}
-defer func() { err = errors.Join(err, client.Close(ctx)) }()
-```
-</Tab>
-</Tabs>
-
-Commonly used: `cerebras/gpt-oss-120b`, `cerebras/qwen-3-235b-a22b-instruct-2507`, `cerebras/zai-glm-4.7`, `cerebras/llama3.1-8b`.
-
-[View all supported Cerebras models →](https://inference-docs.cerebras.ai/models/overview)
-</Tab>
-
 </Tabs>
 
 ---
@@ -1744,8 +1614,6 @@ You pinned a `model` but gave it no `apiKey`, and the browser is not a Browserba
 | Google     | `GOOGLE_GENERATIVE_AI_API_KEY` or `GEMINI_API_KEY` |
 | Anthropic  | `ANTHROPIC_API_KEY`            |
 | OpenAI     | `OPENAI_API_KEY`               |
-| Groq       | `GROQ_API_KEY`                 |
-| Cerebras   | `CEREBRAS_API_KEY`             |
 | Bring your own LLM | None; your callback owns its credentials |
 
 </Accordion>
@@ -1756,7 +1624,7 @@ You pinned a `model` but gave it no `apiKey`, and the browser is not a Browserba
 **Solutions:**
 
 - Use the `provider/model` format: `openai/gpt-5`. The prefix is required; bare model names are rejected
-- Use one of the five supported providers: `openai`, `anthropic`, `google`, `groq`, `cerebras`
+- Use one of the three supported providers: `openai`, `anthropic`, `google`
 - Check the model ID against the lists on this page. Stagehand validates the whole name, so a typo fails at `Stagehand.create()` rather than on the first inference
 - Upgrade the SDK if the model shipped after your installed version
 - For a provider outside that list, use the [bring-your-own-LLM callback](#custom-models)

diff --git a/packages/evals/initStagehand.ts b/packages/evals/initStagehand.ts
@@ -33,8 +33,6 @@ const PROVIDER_API_KEY_ENV: Record<string, string[]> = {
   openai: ["OPENAI_API_KEY"],
   anthropic: ["ANTHROPIC_API_KEY"],
   google: ["GOOGLE_GENERATIVE_AI_API_KEY", "GEMINI_API_KEY"],
-  groq: ["GROQ_API_KEY"],
-  cerebras: ["CEREBRAS_API_KEY"],
 };
 
 type StagehandLogEvent = Parameters<NonNullable<StagehandClientLoggingConfig["onLog"]>>[0];

diff --git a/packages/evals/taskConfig.ts b/packages/evals/taskConfig.ts
@@ -46,16 +46,6 @@ const ALL_EVAL_MODELS = [
   // TOGETHER - DEEPSEEK
   "deepseek-ai/DeepSeek-V3",
   "Qwen/Qwen2.5-7B-Instruct-Turbo",
-  // GROQ
-  "groq/meta-llama/llama-4-scout-17b-16e-instruct",
-  "groq/llama-3.3-70b-versatile",
-  "groq/llama3-70b-8192",
-  "groq/qwen-qwq-32b",
-  "groq/qwen-2.5-32b",
-  "groq/deepseek-r1-distill-qwen-32b",
-  "groq/deepseek-r1-distill-llama-70b",
-  // CEREBRAS
-  "cerebras/llama3.3-70b",
 ];
 
 // ---------------------------------------------------------------------------

diff --git a/packages/extension/llm/LLMClient.ts b/packages/extension/llm/LLMClient.ts
@@ -101,7 +101,7 @@ export interface LLMParsedResponse<T> {
 }
 
 export abstract class LLMClient {
-  public abstract type: "openai" | "anthropic" | "cerebras" | "groq" | (string & {});
+  public abstract type: "openai" | "anthropic" | (string & {});
   public modelName: ModelName;
   public hasVision = false;
   // Compile-only bridge: provider SDK option types diverge from V3's shared options.

diff --git a/packages/extension/llm/LLMProvider.ts b/packages/extension/llm/LLMProvider.ts
@@ -10,8 +10,6 @@ import { LLMClient } from "./LLMClient.js";
 import { createOpenAI } from "@ai-sdk/openai";
 import { createAnthropic } from "@ai-sdk/anthropic";
 import { createGoogleGenerativeAI } from "@ai-sdk/google";
-import { createGroq } from "@ai-sdk/groq";
-import { createCerebras } from "@ai-sdk/cerebras";
 import { wrapLanguageModel } from "ai";
 
 // Compile-only bridge: current AI SDK providers return mixed v2/v3/v4 model
@@ -23,8 +21,6 @@ const AISDKProviderFactories: Record<ModelProvider, AISDKProviderFactory> = {
   openai: createOpenAI as AISDKProviderFactory,
   anthropic: createAnthropic as AISDKProviderFactory,
   google: createGoogleGenerativeAI as AISDKProviderFactory,
-  groq: createGroq as AISDKProviderFactory,
-  cerebras: createCerebras as AISDKProviderFactory,
 };
 
 type AISDKProviderClientOptions = ClientOptions & Record<string, unknown>;

diff --git a/packages/extension/llm/aiSdkClient.ts b/packages/extension/llm/aiSdkClient.ts
@@ -1,17 +1,13 @@
 import { createAnthropic } from "@ai-sdk/anthropic";
-import { createCerebras } from "@ai-sdk/cerebras";
 import { createGoogleGenerativeAI } from "@ai-sdk/google";
-import { createGroq } from "@ai-sdk/groq";
 import { createOpenAI } from "@ai-sdk/openai";
 import { generateText, jsonSchema, Output } from "ai";
 import type { LanguageModel, ModelMessage, ToolSet } from "ai";
 import { z } from "zod/v4";
 import {
   AnthropicModelIdSchema,
-  CerebrasModelIdSchema,
   createLLMGenerateResultSchema,
   GoogleModelIdSchema,
-  GroqModelIdSchema,
   LLMGenerateParamsSchema,
   LLMMessageSchema,
   LLMGenerateResultSchema,
@@ -163,10 +159,6 @@ export function createAiSdkLanguageModel(
       })(AnthropicModelIdSchema.parse(modelId));
     case "google":
       return createGoogleGenerativeAI(connection)(GoogleModelIdSchema.parse(modelId));
-    case "groq":
-      return createGroq(connection)(GroqModelIdSchema.parse(modelId));
-    case "cerebras":
-      return createCerebras(connection)(CerebrasModelIdSchema.parse(modelId));
   }
 }
 

diff --git a/packages/extension/llm/aisdk.ts b/packages/extension/llm/aisdk.ts
@@ -181,16 +181,6 @@ export class AISdkClient extends LLMClient {
           structuredOutputs: true,
         };
         break;
-      case "groq":
-        providerOptions.groq = {
-          structuredOutputs: true,
-        };
-        break;
-      case "cerebras":
-        providerOptions.cerebras = {
-          strictJsonSchema: true,
-        };
-        break;
       case "mistral":
         providerOptions.mistral = {
           structuredOutputs: true,

diff --git a/packages/extension/package.json b/packages/extension/package.json
@@ -11,9 +11,7 @@
   },
   "dependencies": {
     "@ai-sdk/anthropic": "catalog:",
-    "@ai-sdk/cerebras": "catalog:",
     "@ai-sdk/google": "catalog:",
-    "@ai-sdk/groq": "catalog:",
     "@ai-sdk/openai": "catalog:",
     "@ai-sdk/provider": "catalog:",
     "@opentelemetry/api": "catalog:",