# claude-fable-5 — API, Pricing & Context Window | Vivgrid

> Source: https://vivgrid.com/docs/models/claude-fable-5

Run Anthropic's claude-fable-5 on Vivgrid: the first Fable-tier Claude, with a 1M-token context window, 128K max output, and global acceleration.

`claude-fable-5` opened Anthropic's Fable tier — the frontier above Opus — for demanding reasoning and long-running agentic workloads. It offers a **1M-token context window**, **128K-token max output**, and always-on adaptive thinking, at the same per-token price as its successor `claude-fable-5-1`.

On Vivgrid, `claude-fable-5` is geo-distributed across **AMER, EMEA, and APAC** and reachable two ways with the same unified API key: the native **Messages API** (`/messages`) for Claude-compatible coding clients, and **Chat Completions** (`/chat/completions`) for agent projects and OpenAI-shaped SDKs.

## Specifications

| Field | Value |
| --- | --- |
| Provider | Anthropic |
| Model ID | `claude-fable-5` |
| Best for | Coding |
| Available on | Chat Completions, Vibe coding |
| Context window | 1,000,000 tokens |
| Max output | 128,000 tokens |
| Modalities | Text, Image |
| Tool / function calling | Yes |
| Knowledge cutoff | 2026-06 |
| Acceleration | Geo-distributed — AMER, EMEA, APAC |

## Pricing

Pricing in USD per 1M tokens.

| Input | Cached input | Output |
| --- | --- | --- |
| $10.00 | $1.25 | $50.00 |

### What one request costs

The rates above applied to a 20K-token prompt with a 2K-token reply — a typical single agent turn, small enough that every request is billed at the base rate.

| Request | Cost |
| --- | --- |
| Cold prompt, nothing cached | $0.3000 |
| Warm prompt, 90% of the input served from cache | $0.1425 |


Prompt caching is billed at **$12.50 per 1M cache-write tokens** on the 5-minute TTL and **$20.00 per 1M** on the 1-hour TTL, with cached reads at $1.25.

## API surfaces

The Vivgrid Console catalogs `claude-fable-5` on 2 surfaces, all behind the same API key. The endpoint shown is the one the Console previews for that surface.

| Surface | Primary endpoint | Use it for |
| --- | --- | --- |
| Chat Completions | `/chat/completions` | Agent projects, where Vivgrid injects the model, system prompt and tools server-side, and Model API calls that name the model per request. |
| Vibe coding | `/messages` | Coding CLIs and IDE agents that drive the model themselves — point the tool at Vivgrid and keep your own loop. |

## Quick start

Get an API key from the Vivgrid Console (https://console.vivgrid.com), then call `claude-fable-5` directly.

### `/chat/completions`

```bash
curl https://api.vivgrid.com/v1/chat/completions \
  -H "Authorization: Bearer $VIVGRID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-fable-5",
    "messages": [
      { "role": "user", "content": "Say hello in English, Chinese and Spanish." }
    ],
    "stream": true
  }'
```

### `/messages`

```bash
curl https://api.vivgrid.com/v1/messages \
  -H "Authorization: Bearer $VIVGRID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-fable-5",
    "max_tokens": 1024,
    "messages": [
      { "role": "user", "content": "Say hello in English, Chinese and Spanish." }
    ],
    "stream": true
  }'
```


## Ideal use cases

- Frontier coding agents and autonomous software development
- Long-context analysis and refactoring within a 1M-token budget
- Complex planning and reasoning across long agent sessions
- Workloads already tuned for Fable-tier behavior

## Related models

- [claude-fable-5-1](/docs/models/claude-fable-5-1) — the newer Fable release with cheaper cache reads
- [claude-opus-5-5](/docs/models/claude-opus-5-5) — the latest Opus model at a lower price
- [claude-sonnet-5-5](/docs/models/claude-sonnet-5-5) — a faster, lower-cost Claude model