claude-fable-5 API

At provider list price streamingvisionfunction-callingreasoning

claude-fable-5 is Anthropic's most capable widely released model, built for long-running agent work. On CaMeL Hub you call it with any OpenAI SDK by setting base_url to https://api.camel-hub.com/v1 — $10 per 1M input tokens, $50 per 1M output tokens. It ships with a 1M-token context window, up to 128K output tokens, and adaptive reasoning that is always on, so the model decides how deeply to think on each request without you managing a thinking budget.

Pricing

per 1M input tokensper 1M output tokens
CaMeL Hub$10.00$50.00
Provider list price$10.00$50.00

Prices are the public default-group rate in USD per 1M tokens; input and output are billed separately. · Provider list price · verified 2026-07-11

Specifications

Provider
Anthropic
Context window
1000000 tokens
Max output
128000 tokens
Capabilities
streaming, vision, function-calling, reasoning
Endpoints
anthropic, openai
Claude Fable 5 (API ID claude-fable-5) became generally available on June 9, 2026 as the top-capability tier of the Claude family, positioned by Anthropic as "next-generation intelligence for long-running agents." It pairs a 1M-token context window with a 128K-token maximum output and a January 2026 knowledge cutoff. Unlike earlier Claude generations, there is no extended-thinking toggle: adaptive reasoning is always on, and the model allocates its own deliberation per request. Its trade-off is deliberate: comparative latency is slower than the Opus, Sonnet, and Haiku tiers, and at $10/$50 per 1M tokens it sits at the top of the Claude price ladder. That makes it the wrong default for latency-sensitive chat, and the right choice when answer quality on hard, multi-step work dominates — agents that run for hours, plans that must survive contact with failing tool calls, or analysis where a wrong conclusion costs far more than the tokens. One cost note worth knowing before you migrate: it uses the tokenizer introduced with Claude Opus 4.7, so the same text produces roughly 30% more tokens than on pre-4.7 Claude models — budget accordingly when porting long prompts. On CaMeL Hub, claude-fable-5 is exposed on both the OpenAI-compatible endpoint (/v1/chat/completions — just change base_url in your existing OpenAI SDK code) and the native Anthropic Messages endpoint (/v1/messages), so tools built against either format work unchanged. Streaming, vision input, and function calling are all supported, and billing meters input and output tokens separately at the rates above.

What it is good for

Quickstart

OpenAI-compatible: set base_url to https://api.camel-hub.com/v1 and use your CaMeL Hub API key. No SDK changes needed.

cURL

curl https://api.camel-hub.com/v1/chat/completions \
  -H "Authorization: Bearer $CAMEL_HUB_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-fable-5",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Python

from openai import OpenAI

client = OpenAI(
    api_key="$CAMEL_HUB_KEY",
    base_url="https://api.camel-hub.com/v1",  # <-- the only change vs. the OpenAI default
)

resp = client.chat.completions.create(
    model="claude-fable-5",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)

Node.js

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.CAMEL_HUB_KEY,
  baseURL: "https://api.camel-hub.com/v1", // <-- the only change vs. the OpenAI default
});

const resp = await client.chat.completions.create({
  model: "claude-fable-5",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(resp.choices[0].message.content);

Get an API key Browse integration guides

Frequently asked questions

How is claude-fable-5 billed on CaMeL Hub?

Per token, with input and output metered separately: $10 per 1M input tokens and $50 per 1M output tokens. Streaming responses are billed at the same rates as non-streaming — you pay for tokens, not for connection time.

Does claude-fable-5 support streaming, function calling, and image input?

Yes to all three. You can stream tokens as they generate, define tools/functions for the model to call, and send images (screenshots, diagrams, photos) as input. Reasoning is also built in — adaptive thinking is always on for this model.

What are the context window and maximum output length?

The context window is 1M tokens and the maximum output is 128K tokens per request, per Anthropic's official model documentation. Note that claude-fable-5 uses the tokenizer introduced with Claude Opus 4.7, so identical text tokenizes to roughly 30% more tokens than on older Claude models.

Do I need Anthropic-specific code to call it?

No. CaMeL Hub serves claude-fable-5 through an OpenAI-compatible API, so any OpenAI SDK works — set base_url to https://api.camel-hub.com/v1 and pass your CaMeL Hub key. If your tooling speaks the native Anthropic Messages format instead, that endpoint is available too.

How do I get started?

Create an account at https://api.camel-hub.com/console, generate an API key, then point your existing OpenAI or Anthropic SDK at https://api.camel-hub.com/v1 with model "claude-fable-5". Top up by card, Alipay, or WeChat Pay, or pick a subscription plan.

More from Anthropic

Compare with other models