> ## Documentation Index
> Fetch the complete documentation index at: https://gomodel-docs-benchmark-writeup-and-tooling.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Anthropic Messages API

> Accept Anthropic-style /v1/messages requests and route them to any provider.

## Overview

GoModel accepts the **Anthropic Messages API** request dialect at `POST /v1/messages`,
in addition to its OpenAI-compatible API. Clients and SDKs that speak the Anthropic
format can point at GoModel unchanged.

The request is translated to GoModel's canonical chat type at ingress and runs through
the same pipeline as `/v1/chat/completions` — so virtual models, workflow policy,
budgets, failover, the response cache, usage/cost tracking, and audit logging all
apply. Because every provider implements chat completion, an Anthropic-format request
can be routed to **any** configured provider (OpenAI, Gemini, Bedrock, and others),
not only Anthropic.

This differs from the [passthrough API](/features/passthrough-api): `/p/anthropic/v1/messages`
forwards bytes verbatim to the Anthropic upstream only, while the managed `/v1/messages`
endpoint routes anywhere and is fully managed.

## Supported endpoints

| Endpoint                         | Behavior                                                                                                                  |
| -------------------------------- | ------------------------------------------------------------------------------------------------------------------------- |
| `POST /v1/messages`              | Creates a message through translated model routing. Supports streaming (`stream: true`) with Anthropic-format SSE events. |
| `POST /v1/messages/count_tokens` | Returns a heuristic input token estimate.                                                                                 |

## Example

```bash theme={null}
curl https://your-gateway/v1/messages \
  -H "Authorization: Bearer $GOMODEL_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-4-6",
    "max_tokens": 256,
    "system": "Be concise.",
    "messages": [{"role": "user", "content": "Hello"}]
  }'
```

The response uses the Anthropic Messages shape (`type: "message"`, `content` blocks,
`stop_reason`, `usage`). Errors use the Anthropic error envelope
(`{"type": "error", "error": {...}}`). `max_tokens` is required, as in the Anthropic API.

Streaming responses emit the Anthropic SSE event sequence (`message_start`,
`content_block_start`/`content_block_delta`/`content_block_stop`, `message_delta`,
`message_stop`).

## Cost tracking and audit logs

`/v1/messages` requests are tracked and audited exactly like the OpenAI-compatible
routes. Cost is computed from the actual provider that served the request, and usage
is recorded under the `/v1/messages` endpoint so it can be filtered in the dashboard.

## Limitations

`/v1/messages` translates through GoModel's canonical chat type. Anthropic-specific
features that have no canonical equivalent are not preserved end to end:

* **`cache_control` breakpoints** are dropped — prompt-caching cost benefits are not
  carried through the canonical hop.
* **Extended-thinking signatures** and `thinking` blocks on input messages are dropped.
* **Server/built-in tools** (web search, code execution, …) are rejected with a clear
  `400`; only custom tools (`type` absent or `"custom"`) translate.
* **`top_k`** is dropped — it has no portable OpenAI-compatible equivalent, and
  OpenAI-family providers reject unknown request fields. `temperature` and `top_p`
  are forwarded.
* **`document` and other non-text/image content blocks** are rejected with a clear
  `400` error rather than silently dropped.
* **`stop_sequences`** are honored, but a stop-sequence-triggered completion reports
  `stop_reason: "end_turn"` instead of `"stop_sequence"` (the output is still truncated
  correctly).
* **`count_tokens`** returns a provider-agnostic heuristic estimate (≈ characters / 4),
  not a tokenizer-exact count. Use it for budgeting and UX sizing, not hard
  context-limit decisions.

For byte-exact Anthropic fidelity (including prompt-cache breakpoints), use the
`/p/anthropic/v1/messages` passthrough route instead.

See [ADR-0007](https://github.com/ENTERPILOT/GoModel/blob/main/docs/adr/0007-anthropic-messages-ingress.md)
for the design rationale and tradeoffs.