Create a message

Anthropic Messages compatible — anthropic-native clients such as Claude Code connect as-is. Internally it runs through the same chat pipeline and supports stream.

Body

modelstringYes

Model ID

messagesarrayYes

role is user / assistant. content is a string or an array of blocks (text, image, tool_use, tool_result, thinking, document)

max_tokensintegerYes

1–200000 (required by the Anthropic spec)

systemstring | arrayNo

A string or an array of text blocks

temperaturenumberNo

0–1

top_pnumberNo

0–1

top_kintegerNo

Positive integer

stop_sequencesstring[]No

Up to 8

streambooleanNo

Defaults to false

toolsarrayNo

{name, description, input_schema}

tool_choiceobjectNo

{"type":"auto"|"any"|"none"} or {"type":"tool","name":"..."}

metadataobjectNo

{"user_id": "..."}

thinkingobjectNo

{"type":"enabled","budget_tokens":N} (N < max_tokens) · {"type":"adaptive"} · {"type":"disabled"}

everyaisobjectNo

Gateway caching options

If you attach cache_control directly to a block, it is passed through as-is (see prompt caching).

Model-specific thinking and tools

Check capabilities and limits in GET /v1/models. Omitted fields mean unverified support; unsupported options and combinations return 400. See the model table under Chat options.

• Latest models such as Claude Opus 5 use thinking: {"type":"adaptive"}. Manual thinking: {"type":"enabled","budget_tokens":N} is not universal. Opus/Sonnet 4.6 support both modes.
• Manual budgets require 1024 ≤ budget_tokens < max_tokens. Unsupported manual budgets are not resized or converted to adaptive thinking. Fable/Mythos reject thinking: {"type":"disabled"} with 400.
• Latest Claude on Bedrock rejects explicit temperature, top_p, and top_k with 400. Check capabilities.sampling before setting sampling options.
• tool_choice.disable_parallel_tool_use: true disables parallel calls. Claude native strict tools require capabilities.structured_outputs: true; for other models, see the strict function-tool restrictions in the Chat documentation; unsupported strict: true returns 400.
• Web search is exclusive to /v1/chat/completions. Messages tools are client-executed function tools.

POST /v1/messages/count_tokens

Estimates the input token count before you send a request. Claude Code calls this endpoint automatically.

• Free — no credit is deducted.
• Returns a heuristic estimate without calling the upstream provider (it may differ from the exact tokenizer result).
• The request body takes the same shape as /v1/messages.

{
  "input_tokens": 1234
}