> ## Documentation Index
> Fetch the complete documentation index at: https://docs.comfy.org/llms.txt
> Use this file to discover all available pages before exploring further.

# Use Claude Fable 5.2 with Comfy Router

> Call anthropic/claude-fable-5-2 through Comfy Router: endpoint, request shape and the response Router returns.

API Reference for `anthropic/claude-fable-5-2`, served by Comfy Router from Anthropic.

**Input:** Text, Image · **Output:** Text

## Quick start

Create a key in [your Comfy workspace](https://platform.comfy.org/profile/api-keys?onboarding=router) and export it as `COMFY_API_KEY`. The Python and TypeScript snippets use the Comfy SDKs (`pip install comfy-sdk` and `npm install @comfyorg/sdk`); the cURL snippet is the same call over raw HTTP.

**Model ID:** `anthropic/claude-fable-5-2`

**Endpoint:** `POST https://api.comfy.org/v2/models/anthropic/claude-fable-5-2`

> [tab] Wait for the result
>
> ```python Python theme={null}
> from comfy_sdk import Comfy
>
> # Reads COMFY_API_KEY from the environment.
> # The SDK automatically creates an idempotency key and reuses it for automatic retries.
> with Comfy() as client:
>     result = client.models.run(
>         "anthropic/claude-fable-5-2",
>         {
>             "max_tokens": 16,
>             "messages": [
>                 {
>                     "content": "Reply with the single word: ok",
>                     "role": "user",
>                 },
>             ],
>         },
>     )
>
> print(result)
> ```
>
> ```typescript TypeScript theme={null}
> import { comfy } from "@comfyorg/sdk";
>
> // Reads COMFY_API_KEY from the environment.
> // The SDK automatically creates an idempotency key and reuses it for automatic retries.
> const { data } = await comfy.models.run("anthropic/claude-fable-5-2", {
>   max_tokens: 16,
>   messages: [
>     {
>       content: "Reply with the single word: ok",
>       role: "user",
>     },
>   ],
> });
>
> console.log(data);
> ```
>
> ```bash cURL theme={null}
> curl https://api.comfy.org/v2/models/anthropic/claude-fable-5-2 \
>   -H "X-API-Key: $COMFY_API_KEY" \
>   -H "Idempotency-Key: $(uuidgen)" \
>   -H "Content-Type: application/json" \
>   -d "{\"max_tokens\": 16, \"messages\": [{\"content\":\"Reply with the single word: ok\",\"role\":\"user\"}]}"
> ```

> [tab] Queue and collect later
>
> The same body, sent to `POST https://api.comfy.org/v2/models/anthropic/claude-fable-5-2/requests`. Router answers `201` with a `request_id` as soon as the run is admitted, and the result is collected once it is ready, from this process or another one. [Queued delivery](https://docs.comfy.org/development/comfy-router/queue.md) walks through status, cancellation and collection.
>
> ```python Python theme={null}
> import asyncio
> from comfy_sdk import AsyncComfy
>
> # Reads COMFY_API_KEY from the environment.
> # Each submit() call mints its own Idempotency-Key and reuses it for automatic retries.
> async def main():
>     async with AsyncComfy() as client:
>         handle = await client.models.submit(
>             "anthropic/claude-fable-5-2",
>             {
>                 "max_tokens": 16,
>                 "messages": [
>                     {
>                         "content": "Reply with the single word: ok",
>                         "role": "user",
>                     },
>                 ],
>             },
>         )
>         print("request_id:", handle.request_id)  # with the model ID, all another process needs
>
>         # Poll until the request completes, waiting the Retry-After the server names.
>         async for update in handle.iter_events():
>             print(update.status, update.queue_position)
>
>         # The provider's own payload, the same value models.run() returns.
>         # A request that failed or was cancelled raises the typed Router error here.
>         result = await handle.get()
>
>     print(result)
>
> asyncio.run(main())
> ```
>
> ```typescript TypeScript theme={null}
> import { comfy } from "@comfyorg/sdk";
>
> // Reads COMFY_API_KEY from the environment.
> // Each submit() call mints its own Idempotency-Key and reuses it for automatic retries.
> const handle = await comfy.models.submit("anthropic/claude-fable-5-2", {
>   max_tokens: 16,
>   messages: [
>     {
>       content: "Reply with the single word: ok",
>       role: "user",
>     },
>   ],
> });
> console.log("requestId:", handle.requestId); // with the model ID, all another process needs
>
> // Poll until the request completes, waiting the Retry-After the server names.
> for await (const update of handle.events()) {
>   console.log(update.status, update.queuePosition);
> }
>
> // The same result models.run() returns. A request that failed or was cancelled rejects here.
> const result = await handle.get();
>
> console.log(result.data);
> ```
>
> ```bash cURL theme={null}
> # 1. Submit. Router answers 201 with request_id, status_url, response_url and cancel_url.
> curl https://api.comfy.org/v2/models/anthropic/claude-fable-5-2/requests \
>   -H "X-API-Key: $COMFY_API_KEY" \
>   -H "Idempotency-Key: $(uuidgen)" \
>   -H "Content-Type: application/json" \
>   -d "{\"max_tokens\": 16, \"messages\": [{\"content\":\"Reply with the single word: ok\",\"role\":\"user\"}]}"
>
> # 2. Poll until status is COMPLETED, waiting the Retry-After seconds each response names.
> REQUEST_ID="<request_id from the 201 body>"
> curl -i https://api.comfy.org/v2/models/anthropic/claude-fable-5-2/requests/$REQUEST_ID/status \
>   -H "X-API-Key: $COMFY_API_KEY"
>
> # 3. Collect. 200 with the model's native output, 202 with the status body while it is still running.
> curl https://api.comfy.org/v2/models/anthropic/claude-fable-5-2/requests/$REQUEST_ID \
>   -H "X-API-Key: $COMFY_API_KEY"
> ```

## Schema

### Input

**max\_tokens** `integer` *required*

Maximum number of tokens to generate before stopping.

**messages** `object[]` *required*

Conversation turns. See Anthropic Messages API docs for the full content-block taxonomy.

**messages\[].content** `object` *required*

Either a string shorthand or an array of content blocks (text, image, document, tool\_use, tool\_result, ...).

**messages\[].role** `string` *required*

Possible values: `user`, `assistant`

**model** `string`

Anthropic model identifier (e.g. `claude-sonnet-4-5`, `claude-opus-4-7`).

**stream** `boolean`

On the Comfy Router route `POST /v2/models/anthropic/{model}`, `stream` is INERT: Router SETTLES it to `false` before dispatch and always returns the completed message as one JSON document. On the v1 `POST /proxy/anthropic/v1/messages` route, `true` makes the response a `text/event-stream` of Anthropic message events instead of a single JSON body. Send `stream` false or omit it on Router; the `text/event-stream` half of the `/proxy/` operation's 200 has no Router counterpart.

**system** `object`

Top-level system prompt. Either a string or an array of content blocks; both reach Anthropic unchanged.

Generated from the schema Router serves at `GET /v2/models/anthropic/claude-fable-5-2/openapi.json`, the same document it validates a call against before the request reaches the provider.

### Output

**id** `string`

**model** `string`

**role** `string`

**stop\_reason** `string`

**stop\_sequence** `string`

**type** `string`

**usage** `object`

Token usage for an Anthropic Messages API call.

**usage.cache\_creation** `object`

Per-TTL breakdown of cache-write input tokens for an Anthropic Messages API call.

**usage.cache\_creation.ephemeral\_1h\_input\_tokens** `integer`

**usage.cache\_creation.ephemeral\_5m\_input\_tokens** `integer`

**usage.cache\_creation\_input\_tokens** `integer`

**usage.cache\_read\_input\_tokens** `integer`

**usage.input\_tokens** `integer`

**usage.output\_tokens** `integer`

**content** `object[]` *required*

The reply's content blocks, in order. Present on every completed message; empty when the turn produced nothing.

**content\[].text** `string`

The block's text. Present on `text` blocks and absent on every other kind.

**content\[].type** `string`

The block kind. `text` is the one that carries `text`; `thinking`, `redacted_thinking`, `tool_use`, `server_tool_use` and the tool-result blocks are the others Anthropic sends today, and the list is open.

## Examples

### Input

```json theme={null}
{
  "max_tokens": 16,
  "messages": [
    {
      "content": "Reply with the single word: ok",
      "role": "user"
    }
  ]
}
```

### Output

```json theme={null}
{
  "content": [
    {
      "text": "ok",
      "type": "text"
    }
  ],
  "id": "msg_01ExampleInvalidPlaceholder",
  "model": "claude-fable-5-2",
  "role": "assistant",
  "stop_reason": "end_turn",
  "stop_sequence": null,
  "type": "message",
  "usage": {
    "input_tokens": 16,
    "output_tokens": 3
  }
}
```

## Before you ship

The SDKs create an `Idempotency-Key` and reuse it for automatic retries. For manual retries, reuse the original key. Router can hold the connection for up to 10 minutes.

When a request fails, Router sends an `X-Comfy-Error-Type` response header explaining why. A `422` means Router rejected the input before calling the provider, and a `413` means the request body was larger than Router accepts. Download generated assets promptly because [result URLs can expire](https://docs.comfy.org/development/comfy-router/reference.md#result-assets).

Any size limit named in a field description above is the provider's own bound on that field, quoted from the provider's specification. Router applies a separate cap to the whole request body, which base64-encoded media counts against: see [request body size](https://docs.comfy.org/development/comfy-router/limitations.md#request-bodies-are-capped).

This page documents one partner model called through Comfy Router. The same `comfy-sdk` / `@comfyorg/sdk` package also ships a second client, for running a whole ComfyUI workflow graph on Comfy Cloud: `Comfy(api_key=...)` / `new Comfy({ apiKey })`, with `client.workflows`, `client.assets` and `client.jobs`. See [Comfy SDKs](https://docs.comfy.org/development/api-development/sdks.md).

> [card] [Headers](https://docs.comfy.org/development/comfy-router/headers.md)
>
> Authentication, idempotency, request IDs, error buckets, retry pacing, spend limits.

> [card] [Using the Router API](https://docs.comfy.org/development/comfy-router/api.md)
>
> Model discovery, validation errors, retries, and billing.

> [card] [Limitations](https://docs.comfy.org/development/comfy-router/limitations.md)
>
> What Router does not do today, and what to use instead.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.