Add Cerebras provider support

- Add CerebrasProvider using OpenAI SDK for Cerebras's OpenAI-compatible API
- Support for Llama 3.3, Qwen 3, GPT-OSS, and GLM models
- Add cerebras optional dependency group
- Add documentation with usage examples and UTM tracking

Author: sebastiand-cerebras

docs/models/cerebras.md

@@ -0,0 +1,83 @@
+# Cerebras
+
+Cerebras provides ultra-fast inference using their Wafer-Scale Engine (WSE), delivering predictable performance for any workload.
+
+## Installation
+
+To use Cerebras, you need to either install `pydantic-ai`, or install `pydantic-ai-slim` with the `cerebras` optional group:
+
+```bash
+# pip
+pip install "pydantic-ai-slim[cerebras]"
+
+# uv
+uv add "pydantic-ai-slim[cerebras]"
+```
+
+## Configuration
+
+To use Cerebras, go to [cloud.cerebras.ai](https://cloud.cerebras.ai/?utm_source=3pi_pydantic-ai&utm_campaign=partner_doc) to get an API key.
+
+### Environment Variable
+
+Set your API key as an environment variable:
+
+```bash
+export CEREBRAS_API_KEY='your-api-key'
+```
+
+### Available Models
+
+Cerebras supports the following models:
+
+- `llama-3.3-70b` (recommended) - Latest Llama 3.3 model
+- `llama-3.1-8b` - Llama 3.1 8B (faster, smaller)
+- `qwen-3-235b-a22b-instruct-2507` - Qwen 3 235B
+- `qwen-3-32b` - Qwen 3 32B
+- `gpt-oss-120b` - GPT-OSS 120B
+- `zai-glm-4.6` - GLM 4.6 model
+
+
+See the [Cerebras documentation](https://inference-docs.cerebras.ai/introduction?utm_source=3pi_pydantic-ai&utm_campaign=partner_doc) for the latest models.
+
+## Usage
+
+### Simple Usage (Recommended)
+
+```python
+from pydantic_ai import Agent
+
+agent = Agent('cerebras:llama-3.3-70b')
+result = agent.run_sync('What is the capital of France?')
+print(result.output)
+#> The capital of France is Paris.
+```
+
+### Async Usage
+
+```python
+import asyncio
+from pydantic_ai import Agent
+
+agent = Agent('cerebras:llama-3.3-70b')
+
+async def main():
+    result = await agent.run('What is the capital of France?')
+    print(result.output)
+    #> The capital of France is Paris.
+
+asyncio.run(main())
+```
+
+## Why Cerebras?
+
+- **Ultra-fast inference** - Powered by the world's largest AI chip (WSE)
+- **Predictable performance** - Consistent latency for any workload
+- **OpenAI-compatible** - Drop-in replacement for OpenAI API
+- **Cost-effective** - Competitive pricing with superior performance
+
+## Resources
+
+- [Cerebras Inference Documentation](https://inference-docs.cerebras.ai?utm_source=3pi_pydantic-ai&utm_campaign=partner_doc)
+- [Get API Key](https://cloud.cerebras.ai/?utm_source=3pi_pydantic-ai&utm_campaign=partner_doc)
+- [Model Pricing](https://cerebras.ai/pricing?utm_source=3pi_pydantic-ai&utm_campaign=partner_doc)

mkdocs.yml

@@ -30,6 +30,7 @@ nav:
           - models/anthropic.md
           - models/google.md
           - models/bedrock.md
+          - models/cerebras.md
           - models/cohere.md
           - models/groq.md
           - models/mistral.md

pydantic_ai_slim/pydantic_ai/providers/cerebras.py

@@ -10,7 +10,6 @@
 from pydantic_ai.models import cached_async_http_client
 from pydantic_ai.profiles.harmony import harmony_model_profile
 from pydantic_ai.profiles.meta import meta_model_profile
-from pydantic_ai.profiles.openai import OpenAIJsonSchemaTransformer, OpenAIModelProfile
 from pydantic_ai.profiles.qwen import qwen_model_profile
 from pydantic_ai.providers import Provider
 
@@ -39,27 +38,18 @@ def client(self) -> AsyncOpenAI:
         return self._client
 
     def model_profile(self, model_name: str) -> ModelProfile | None:
-        prefix_to_profile = {'llama': meta_model_profile, 'qwen': qwen_model_profile, 'gpt-oss': harmony_model_profile}
+        prefix_to_profile = {
+            'llama': meta_model_profile,
+            'qwen': qwen_model_profile,
+            'gpt-oss': harmony_model_profile,
+        }
 
-        profile = None
         for prefix, profile_func in prefix_to_profile.items():
             model_name = model_name.lower()
             if model_name.startswith(prefix):
-                profile = profile_func(model_name)
-
-        # According to https://inference-docs.cerebras.ai/resources/openai#currently-unsupported-openai-features,
-        # Cerebras doesn't support some model settings.
-        unsupported_model_settings = (
-            'frequency_penalty',
-            'logit_bias',
-            'presence_penalty',
-            'parallel_tool_calls',
-            'service_tier',
-        )
-        return OpenAIModelProfile(
-            json_schema_transformer=OpenAIJsonSchemaTransformer,
-            openai_unsupported_model_settings=unsupported_model_settings,
-        ).update(profile)
+                return profile_func(model_name)
+
+        return None
 
     @overload
     def __init__(self) -> None: ...

pydantic_ai_slim/pyproject.toml

@@ -72,6 +72,7 @@ cohere = ["cohere>=5.18.0; platform_system != 'Emscripten'"]
 vertexai = ["google-auth>=2.36.0", "requests>=2.32.2"]
 google = ["google-genai>=1.51.0"]
 anthropic = ["anthropic>=0.70.0"]
+cerebras = ["openai>=1.107.2"]
 groq = ["groq>=0.25.0"]
 mistral = ["mistralai>=1.9.10"]
 bedrock = ["boto3>=1.40.14"]