LLM Chat (Anthropic-Compatible)
Compatible with the Anthropic Messages protocol, with optional built-in octen_broad_search and octen_search tools.
Authorizations
Bearer token used for request authentication. Alternatively, you can send the API key in the x-api-key header. Note: A payment method is required to use the API.
Headers
Anthropic protocol version, e.g. 2023-06-01. Sent automatically by the Anthropic SDK. Defaults to 2023-06-01 if omitted.
Body
Request body for the Messages API. Some parameters apply only to certain models; unsupported parameters are ignored.
The model to use. Anthropic models also accept their native ids (e.g. claude-opus-4-8), which map to anthropic/claude-opus-4.8.
openai/gpt-5.6-sol, openai/gpt-5.6-terra, openai/gpt-5.6-luna, openai/gpt-5.5-pro, openai/gpt-5.5, openai/gpt-5.4, anthropic/claude-fable-5, anthropic/claude-opus-5, anthropic/claude-opus-4.8, anthropic/claude-opus-4.6, anthropic/claude-sonnet-5, anthropic/claude-sonnet-4.6, anthropic/claude-haiku-4.5, google/gemini-3.5-flash, google/gemini-3.1-pro-preview, google/gemini-3.1-flash-lite, google/gemini-3-flash-preview, moonshotai/kimi-k3, moonshotai/kimi-k2.6, moonshotai/kimi-k2.5, minimax/minimax-m2.5, qwen/qwen3.6-plus, deepseek/deepseek-v4-pro, deepseek/deepseek-v4-flash Maximum number of tokens to generate, including thinking and visible output tokens.
x >= 1The conversation so far, in chronological order.
System prompt. A plain string or an array of text blocks supporting cache_control.
A tool definition. One of a custom tool, the built-in octen_broad_search tool, or the octen_search tool.
- Option 1
- Option 2
- Option 3
Controls whether and how the model calls tools.
Whether to enable streaming output.
Controls randomness.
0 <= x <= 1Nucleus sampling. If unset, no nucleus truncation is applied. Set only one of temperature and top_p.
x <= 1Sample only from the top K tokens. If unset, top-k filtering is disabled.
x >= 0Stop sequences.
Thinking options for reasoning models.
Request metadata.
Controls how the model produces its output.
Top-level prompt caching marker. Sets a cache breakpoint on the last cacheable content block in the request, equivalent to setting cache_control on that block directly.
Response
Successful message response. When stream=false, returns a single message object. When stream=true, returns an Anthropic SSE event stream.
- Option 1
- Option 2
A non-streaming response. Returned when stream=false.
The unique identifier for this request.
The response type. message on success.
message, error Always assistant.
assistant The model used for this response.
The response content, as a list of content blocks.
Why the model stopped.
end_turn, max_tokens, stop_sequence, tool_use, pause_turn, refusal Token usage information.
Additional detail about why the model stopped. Returned only when stop_reason is refusal.
The stop sequence that was hit, or null.