Is the Model API compatible with OpenAI?

Yes, for Chat Completions. Point an OpenAI SDK at https://api.gateway.clatterlabs.xyz/v1, add the X-Clatter-Account header, and use a SuperCosmos model id.

What works#

• POST /v1/chat/completions, streamed or not
• Tools (tools, tool_choice, tool_calls)
• usage on every response, and in streams with stream_options.include_usage
• GET /v1/models and GET /v1/models/{id}
• Common parameters: max_tokens / max_completion_tokens, temperature, top_p, stop, seed, presence_penalty, frequency_penalty, reasoning_effort
• The OpenAI error shape

What's different#

• An extra header: X-Clatter-Account.
• Not supported: image input, n > 1, logprobs.
• Not available: embeddings, images, audio, files, responses (404 not_supported).
• Extra fields: effort on requests, reasoning_content on Max and Heavy replies.

See Moving from another OpenAI-compatible API.

Good to know#

• Model ids: supercosmos-flash, supercosmos-max, supercosmos-heavy (SuperCosmos 1.1). Which to call
• If calls fail unexpectedly, check status.clatterlabs.com before debugging further.
• Every response has an X-Request-Id; log it so a request can be found later. Why log it

Still need help?#

• General support: support@clatterlabs.com or team@clatterlabs.xyz
• Infrastructure questions, or permanent deletion of your data (your whole account or one service): infrastructure@clatterlabs.xyz

We usually reply within the first hour, and always within 24 hours. A full support team is with you.