OpenAI Compatible

Anthropic Messages API on a SpicyAPI text model

Accepts an Anthropic Messages request (model, system, messages with text / image / tool_use / tool_result blocks, max_tokens, temperature, top_p, top_k, stop_sequences, tools, tool_choice, stream) and translates it to a chat completion internally. stop_sequences becomes the model's stop field, and tool_choice.disable_parallel_tool_use: true becomes parallel_tool_calls: false; a model that does not declare the target field rejects the request with 400 instead of ignoring it. Non-streaming calls return an Anthropic message object. Streaming calls emit message_start, content_block_start, content_block_delta, content_block_stop, message_delta and message_stop events. Errors use the Anthropic {type:"error",error:{type,message}} shape.

post/v1/messages

Request

  • Base URL: https://api.spicyapi.ai
  • URL: https://api.spicyapi.ai/v1/messages
  • Auth: HTTP bearer

Headers

Idempotency-Keystring

Stable key for one logical task submission; retained for 24 hours per account and bound to both the submitting API key and normalized request fingerprint. A sibling key receives 409 without the original task ID.

Request body

modelstring required
max_tokensinteger required
temperaturenumber
top_pnumber
top_kinteger
stop_sequencesstring[]
toolsobject[]
tool_choiceobject

disable_parallel_tool_use: true is translated to parallel_tool_calls: false.

streamboolean

Response

One Anthropic message object, or an SSE stream when stream is true.

idstring required
type'message' required
role'assistant' required
modelstring required
stop_reason'end_turn' | 'max_tokens' | 'tool_use' required
stop_sequenceunknown

Changes

No recorded changes to this operation across all 1 revision of this API.