> ## 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

> Configure Anthropic (Claude) in GoModel and understand how reasoning effort maps to Claude's adaptive thinking and effort control.

Anthropic setup is just an API key. This page exists for one quirk: how
GoModel maps the OpenAI-style `reasoning.effort` knob onto Claude's native
thinking and effort controls, which differ by model generation.

## Configure

```bash theme={null}
ANTHROPIC_API_KEY=sk-ant-...
# ANTHROPIC_BASE_URL=https://api.anthropic.com/v1   # optional override
# ANTHROPIC_DEFAULT_MAX_TOKENS=4096                 # injected when callers omit max_tokens
```

Or in `config.yaml`:

```yaml theme={null}
providers:
  anthropic:
    type: anthropic
    api_key: "${ANTHROPIC_API_KEY}"
```

<Note>
  Anthropic's `/v1/messages` requires `max_tokens` on every request. GoModel
  injects `ANTHROPIC_DEFAULT_MAX_TOKENS` (default `4096`) when a caller omits
  it, keeping the OpenAI-compatible surface lenient.
</Note>

## Reasoning effort mapping

GoModel accepts the OpenAI-shaped `"reasoning": {"effort": "..."}` object as
well as the Chat Completions string form `"reasoning_effort": "..."` (a
non-empty `reasoning.effort` wins when both are present; an empty object falls
back to the string form) and translates them to Claude's native controls. The
five accepted levels are `low`, `medium`, `high`, `xhigh`, and `max`; values
are matched case-insensitively and any other value is downgraded to `low` and
logged. The translation
depends on whether the model supports **adaptive thinking**.

| Model generation                                                                                                                        | Thinking config                                 | Effort destination                      |
| --------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------- | --------------------------------------- |
| Adaptive — `claude-fable-5`, `claude-opus-4-8`, `claude-opus-4-7`, `claude-opus-4-6`, `claude-sonnet-4-6` (and dated snapshots of each) | `thinking: {type: "adaptive"}`                  | `output_config.effort` (passed through) |
| Legacy (everything else, e.g. `claude-opus-4-5`, `claude-3-5-sonnet`)                                                                   | `thinking: {type: "enabled", budget_tokens: N}` | mapped to a token budget                |

<Note>
  Adaptive routing is an explicit allowlist, not a version comparison. New
  model IDs are treated as legacy until added to the list. For pre-4.7 models
  the legacy fallback keeps working via `budget_tokens`; models from Opus 4.7
  onward reject `budget_tokens` outright, so a new adaptive-only model ID
  fails with an upstream 400 until it is added to the allowlist.
</Note>

For legacy models the effort string maps to a thinking budget; `max_tokens` is
bumped above the budget when needed. `xhigh` and `max` are adaptive-only levels,
so on legacy models they are capped at the `high` budget rather than inflating
`max_tokens` past what those models can emit:

| Effort                   | Budget tokens |
| ------------------------ | ------------- |
| `low`                    | 5000          |
| `medium`                 | 10000         |
| `high` / `xhigh` / `max` | 20000         |

<Note>
  Omit `reasoning` to leave thinking off. On the adaptive models above, GoModel
  only sets `thinking: {type: "adaptive"}` when you pass `reasoning.effort`;
  without it those models do not engage extended thinking. Effort is a separate
  control that governs overall token spend (text and tool calls) whether or not
  thinking is engaged, and Anthropic defaults it to `high` when unset. It is a
  behavioral signal for depth and verbosity, not a hard budget — actual usage
  varies per request and is bounded by `max_tokens`.
</Note>

<Note>
  Effort levels are model-gated upstream: `xhigh` is only available on Fable 5
  and Opus 4.8/4.7, and `max` on Fable 5, Opus 4.8/4.7/4.6, and Sonnet 4.6.
  GoModel forwards the level you send; Anthropic rejects it with a 400 if the
  target model does not support it. Manual `budget_tokens` thinking is rejected
  on Fable 5 and Opus 4.7/4.8, which is why GoModel uses adaptive thinking for
  those models.
</Note>

When extended thinking is engaged, Anthropic requires `temperature = 1`. GoModel
drops any other temperature value (and logs it) rather than failing the request.

## Native passthrough

To send Claude-native request fields that have no OpenAI-compatible equivalent
(for example inline mid-task `system` entries in the `messages` array), use the
passthrough route `/p/anthropic/messages`, which forwards the body verbatim.