# Claude Fable 5.1

> Run Claude Fable 5.1 by anthropic online or via API. From $10.00 per 1M tokens, no setup.

**URL:** https://inference.sh/apps/anthropic/claude-fable-5-1
**Last updated:** 2026-10-13

---

Claude Fable 5.1 — Anthropic's most capable model for demanding reasoning and long-horizon agents. 1M context, 128k output, always-on thinking with effort, vision, tool use. Direct API.

- app: `anthropic/claude-fable-5-1`
- maker: [anthropic](https://inference.sh/apps/anthropic.md)
- category: [chat](https://inference.sh/apps/category/chat.md)
- tasks: [vision](https://inference.sh/apps/tag/vision.md), [reasoning](https://inference.sh/apps/tag/reasoning.md), [coding](https://inference.sh/apps/tag/coding.md)
- price: $10.00/M input, $50.00/M output, $0.25/M cache read, $12.50/M cache write
- runs via: api, javascript and python sdk, belt cli, mcp

## claude-fable-5-1 API Guide

### About
claude fable 5.1 — anthropic's most capable model for demanding reasoning and long-horizon agents. 1m context, 128k output, always-on thinking with effort, vision, tool use. direct api.

### 1. Calling the API

#### Install the Client

```bash
pip install inferencesh
```

#### Setup Your API Key
Set `INFERENCE_API_KEY` as an environment variable. Get your key from settings → api keys.

```bash
export INFERENCE_API_KEY="inf_your_key"
```

#### Run and Get Result

```python
import os
from inferencesh import inference

client = inference(api_key=os.environ["INFERENCE_API_KEY"])


result = client.run({
        "app": "anthropic/claude-fable-5-1@4a756jj1",
        "input": {}
    })

print(result["output"])
```

#### Stream Live Updates

```python
import os
from inferencesh import inference

client = inference(api_key=os.environ["INFERENCE_API_KEY"])


## stream=True yields updates as they arrive
for update in client.run({
        "app": "anthropic/claude-fable-5-1@4a756jj1",
        "input": {}
    }, stream=True):
    if update.get("progress"):
        print(f"progress: {update['progress']}%")
    if update.get("output"):
        print(f"output: {update['output']}")
```

### 2. Authentication
The API uses API keys for authentication. See the authentication docs for detailed setup instructions.

### 3. Files

#### Automatic Upload

```python
## local file paths are automatically uploaded
result = client.run({
    "app": "anthropic/claude-fable-5-1@4a756jj1",
    "input": {
        "image": "/path/to/local/image.png",  # detected & uploaded
        "audio": "https://example.com/audio.mp3",  # url passed through
    }
})
```

#### Manual Upload

```python
## upload and get a hosted URL
file = client.files.upload("/path/to/file.png")
print(file.uri)  # https://cloud.inference.sh/...
```

### 4. Schema

#### Input
- **context_size** (integer): The context size for the model.
- **stream** (boolean): Stream the response or return complete response
- **temperature** (number): Temperature
- **top_p** (number): Top P
- **top_k** (integer): Top K
- **min_p** (number): Min P
- **frequency_penalty** (number): Frequency Penalty
- **presence_penalty** (number): Presence Penalty
- **repetition_penalty** (number): Repetition Penalty
- **seed** (integer): Seed
- **stop** (array): Stop
- **max_tokens** (integer): Max Tokens
- **reasoning_effort** (string): ReasoningEffortEnum
- **reasoning_max_tokens** (integer): Reasoning Max Tokens
- **system_prompt** (string): System Prompt
- **tools** (array): Tools
- **tool_choice** (object): ToolChoice
- **response_format** (object): ResponseFormat
- **context** (array): Context
- **role** (string): ChatMessageRole
- **text** (string): Text
- **reasoning** (string): Reasoning
- **attachments** (array): Attachments
- **images** (array): Images
- **files** (array): Files
- **tool_call_id** (string): Tool Call Id

#### Output
- **reasoning** (string): Reasoning
- **reasoning_state** (object): Reasoning State
- **response** (string): Response
- **tool_calls** (array): Tool Calls
- **usage** (object): LLMUsage

## other chat apps

- [GPT-6 Sol](https://inference.sh/apps/openai/gpt-6-sol.md): $2.00/M input, $0.20/M cached input, $10.00/M output
- [GPT-6 Luna](https://inference.sh/apps/openai/gpt-6-luna.md): $0.10/M input, $0.01/M cached, $0.50/M output
- [GPT-6.1 Sol](https://inference.sh/apps/openai/gpt-6-1-sol.md): $2.00/M input, $0.10/M cached, $10.00/M output
- [Claude Haiku 5.5](https://inference.sh/apps/anthropic/claude-haiku-5-5.md): $0.10/M input, $0.50/M output (<=100K tokens); $0.50/M input, $2.50/M output (>100K)
- [Claude Sonnet 5.5](https://inference.sh/apps/anthropic/claude-sonnet-5-5.md): $2.00/M input, $10.00/M output, $0.20/M cache read, $2.50/M cache write

## faq

### how much does Claude Fable 5.1 cost?

$10.00/M input, $50.00/M output, $0.25/M cache read, $12.50/M cache write. you pay per run from your inference shell credits. no subscription is required.

### how do I run Claude Fable 5.1 via api?

call anthropic/claude-fable-5-1 with the javascript or python sdk, the rest api, or `belt app run anthropic/claude-fable-5-1` from a terminal. the api reference on this page lists every input.

### who makes Claude Fable 5.1?

Claude Fable 5.1 is made by anthropic and runs on inference shell. every anthropic app is listed at https://inference.sh/apps/anthropic.

### can my agent use Claude Fable 5.1?

yes. agents call it as a tool through the inference shell mcp server (https://api.inference.sh/mcp), the belt cli or the sdk, and pay per run like you do.

### what are the alternatives to Claude Fable 5.1?

other chat apps on inference shell include GPT-6 Sol, GPT-6 Luna, GPT-6.1 Sol, Claude Haiku 5.5. they run through the same api, so switching is a one-line change.