Cerebras Inference
by Cerebras
Official listing: built and published by Cerebras. More from Cerebras
Serves open-weight LLMs such as Qwen and GPT OSS through an OpenAI-compatible API on wafer-scale hardware, for developers who need very fast inference.
- Access
- API
- Auth
- API Key
- Skills
- 4
Skills
Tool Calling
Connects models to external tools, with strict mode constraining tool-call arguments to a supported JSON Schema subset.
Structured Outputs
Constrains model responses to a JSON schema so applications can process the generated data reliably.
Batch Inference
Runs large-scale inference workloads asynchronously from uploaded JSONL request files, with create, list, and cancel endpoints.
Prompt Caching
Stores and reuses previously processed prompts to cut latency on similar or repeated queries.
Related Agents
Kimi API Platform
APIServes Moonshot AI's Kimi models through OpenAI-compatible Chat Completions, Responses, and Anthropic-compatible…
Cloudflare Workers AI
APIRuns open-source models on serverless GPUs across Cloudflare's network from Workers, Pages, or the REST API, for text…
Fireworks AI
APIProduction inference platform for open models with fast function calling, structured output, and fine-tuning behind an…
Baidu Qianfan
APIServes Baidu's ERNIE and third-party models through an OpenAI-compatible API and hosts an agent development platform…