API compatibility - 6 documented limits

Cerebras Inference API compatibility

Cerebras Inference documents an OpenAI-compatible API at https://api.cerebras.ai/v1 (chat/completions). Its docs do not mention an Anthropic-compatible endpoint. The docs list 6 limitations: 6 for the OpenAI-compatible layer.

Verified October 18, 2026 against Cerebras Inference's own documentation. Not documented means the docs read that day do not say; it never means No.

Compare every provider in the API compatibility matrix.

OpenAI-compatible API

Supported

Base URL

https://api.cerebras.ai/v1

Endpoints

chat/completions

Auth

CEREBRAS_API_KEY passed as the OpenAI client's api_key

Notes

Compatible 'for many common workflows'. With Shared Inference the model field is an exact Cerebras model ID; with Dedicated Inference it is your endpoint ID. Cerebras-specific parameters (reasoning_format, clear_thinking) go through extra_body. Cerebras also ships its own Python and TypeScript SDKs.

From the docs

The Cerebras API is compatible with OpenAI client libraries for many common workflows. Existing applications can use Cerebras by changing the API key, base URL, and inference target.

inference-docs.cerebras.ai/resources/openai

Anthropic-compatible API

Not documented

Notes: The Cerebras OpenAI compatibility page read today does not mention an Anthropic-compatible endpoint.

Checked: inference-docs.cerebras.ai/resources/openai

Documented limitations

Parameters, content types and features Cerebras Inference's docs say its compatibility layers ignore, reject or change, each with the line it comes from. A layer with nothing listed may still differ in ways the docs do not spell out.

OpenAI-compatible layer6

n must be 1
n | Only n: 1 is supported
inference-docs.cerebras.ai/resources/openai
service_tier unavailable on Shared Inference
service_tier | Not available with Shared Inference or Kimi K2.7 Code customer trials
inference-docs.cerebras.ai/resources/openai
external image URLs and image_url.detail unsupported
External HTTPS image URLs and image_url.detail are not supported.
inference-docs.cerebras.ai/resources/openai
do not send tool_stream
Use standard streaming with stream: true. Do not send tool_stream.
inference-docs.cerebras.ai/resources/openai
tools + response_format combination model-dependent; gpt-oss-120b rejects it
gpt-oss-120b rejects requests containing both fields.
inference-docs.cerebras.ai/resources/openai
system and developer roles both act at developer level (gpt-oss-120b)
On Cerebras, both roles act at the developer level, meaning they may have stronger influence than system messages in OpenAI's API.
inference-docs.cerebras.ai/resources/openai

Example from Cerebras Inference's docs

Copied verbatim from the provider's documentation, placeholders included.

Provider example

import os
import openai

client = openai.OpenAI(
    base_url="https://api.cerebras.ai/v1",
    api_key=os.environ.get("CEREBRAS_API_KEY")
)

response = client.chat.completions.create(
    model="qwen-3.8-27b",
    messages=[{"role": "user", "content": "Explain this code."}],
)

Newsletter

One email per week. New models, new endpoints and the compatibility changes that break a base URL, and what they mean for your stack.