Claude Fable 5 API
Call Claude Fable 5 with one TokenMilo API key. Anthropic’s top Claude tier — for the hardest reasoning, research and long agentic tasks. Billed per token at 78% below the official Anthropic price.
| Model ID | claude-fable-5 |
|---|---|
| Provider | Anthropic |
| Family | Claude Fable |
| Discount | 78% off official |
Claude Fable 5 pricing
USD per 1M tokens. Prices updated 2026-11-13.
| TokenMilo | Official Anthropic | You save | |
|---|---|---|---|
| Input | $2.23 | $10 | −78% |
| Output | $11.18 | $50 | −78% |
| Cache read | $0.225 | $1 | −78% |
| Cache write (5 min) | $2.8 | $12.5 | −78% |
| Cache write (1 hour) | $2.8 | $20 | −86% |
Official cache prices follow Anthropic’s published multipliers (read 0.1×, 5-min write 1.25×, 1-hour write 2× the input price). On TokenMilo, 1-hour cache writes cost the same as 5-minute writes.
What it costs in practice
| Workload | TokenMilo | Official | You save |
|---|---|---|---|
| 1,000 requests × 2,000 in / 500 out tokens | $10.05 | $45.00 | $34.95 |
| 1,000 requests × 50,000 in / 2,000 out tokens | $134 | $600 | $466 |
Claude Fable price comparison: TokenMilo vs official
| Model | TokenMilo in / out | Official in / out | Saved |
|---|---|---|---|
| Claude Fable 5.2 | $1.79 / $8.95 | $8 / $40 | −78% |
| Claude Fable 5.1 | $2.23 / $11.18 | $10 / $50 | −78% |
| Claude Fable 5 (this page) | $2.23 / $11.18 | $10 / $50 | −78% |
Claude Fable 5 use cases
Hard reasoning and research
Multi-step maths, science and strategy problems where cheaper models get it wrong. Worth it when one correct answer saves hours.
Long-running autonomous agents
Agents that plan, call tools and self-correct over dozens of steps without losing track of the goal.
Large codebase refactors
Cross-file migrations and architecture changes in Claude Code, where understanding the whole repository matters.
High-stakes writing and analysis
Legal, financial and technical documents where accuracy and nuance matter more than cost.
Supported endpoints
| Anthropic Messages · recommended | POST https://api.tokenmilo.com/v1/messages |
| OpenAI Chat Completions | POST https://api.tokenmilo.com/v1/chat/completions |
Base URL and API key are the same for every format. API guide →
Code examples
curl
curl https://api.tokenmilo.com/v1/messages \
-H "x-api-key: $TOKENMILO_API_KEY" \
-H "anthropic-version: 2023-06-01" \
-H "content-type: application/json" \
-d '{
"model": "claude-fable-5",
"max_tokens": 1024,
"messages": [{"role": "user", "content": "Hello, Claude Fable 5!"}]
}'Python
# pip install anthropic
import os, anthropic
client = anthropic.Anthropic(
base_url="https://api.tokenmilo.com",
api_key=os.environ["TOKENMILO_API_KEY"],
)
msg = client.messages.create(
model="claude-fable-5",
max_tokens=1024,
messages=[{"role": "user", "content": "Explain prompt caching in one paragraph."}],
)
print(msg.content[0].text)Use Claude Fable 5 in your tools
- Claude Code setup — Run Claude Code with a TokenMilo key on macOS, Linux and Windows.
- DeepSeek Harness (dsh) setup with Claude & GPT — Add TokenMilo as a custom provider in DeepSeek’s open-source agent harness.
- WorkBuddy custom model setup — Use Claude and GPT in Tencent’s WorkBuddy desktop agent via a custom API.
- CC Switch one-click setup (Claude Code & Codex) — The easiest way: import TokenMilo into Claude Code and Codex with one click.
- OpenCode setup — Add TokenMilo as a custom provider in the OpenCode terminal agent.
- OpenClaw setup — Run the OpenClaw personal agent on Claude and GPT via TokenMilo.
- Aider setup — Pair-program in your terminal with Claude or GPT via TokenMilo.
- Cursor setup — Add Claude and GPT models to Cursor with your own key.
- Cline setup (VS Code) — Configure the Cline coding agent with Claude via TokenMilo.
- Kilo Code setup — Add a TokenMilo custom provider to the Kilo Code agent.
- Roo Code setup (VS Code) — Use Claude 5.x and GPT-6 in Roo Code via the OpenAI Compatible provider.
- Continue setup (VS Code & JetBrains) — Configure Claude and GPT in Continue’s config.yaml.
- Trae custom model setup — Add Claude and GPT to the Trae IDE as custom models.
- Zed setup — Use TokenMilo models in the Zed editor’s agent panel.
- Chatbox setup — Chat with Claude and GPT in Chatbox on desktop and mobile.
- Cherry Studio setup — Chat with Claude and GPT in the Cherry Studio desktop app.
More Anthropic models
- Claude Opus 5.5 — $0.855 / $4.26
- Claude Opus 5 — $1.06 / $5.33
- Claude Opus 4.8 — $1.06 / $5.33
- Claude Opus 4.7 — $1.06 / $5.33
- Claude Opus 4.6 — $1.06 / $5.33
- Claude Sonnet 5.5 — $0.423 / $2.13
Common Claude Fable 5 API errors and how to fix them
Most errors come from the key, the base URL or the model ID. Check these first:
401 Unauthorized / invalid API key
Cause: The key is wrong, has an extra space or line break, was deleted, or is an official Anthropic/OpenAI key instead of a TokenMilo key.
Fix: Copy the key again from the Tokens page of the console (it starts with sk-). In Claude Code, set it as ANTHROPIC_AUTH_TOKEN or ANTHROPIC_API_KEY — not both with different values.
The response is an HTML page, or "Unexpected token <" / JSON parse error
Cause: The base URL points at the website instead of the API, or has a typo.
Fix: Anthropic format: use https://api.tokenmilo.com (SDKs add /v1/messages themselves). OpenAI format: use https://api.tokenmilo.com/v1. If a tool asks for a single URL, https://api.tokenmilo.com/v1 works for both.
model_not_found / "no available channel for model"
Cause: The model name is misspelled, has the wrong case, or includes a vendor prefix.
Fix: Use the exact model ID claude-fable-5 — lowercase, with no prefix such as anthropic/ or openai/.
Insufficient quota / balance
Cause: Your account balance is used up, or the key has its own spending limit that has been reached.
Fix: Top up in the console, or edit the key and raise or remove its quota limit.
Connection error, timeout, ECONNRESET or "fetch failed"
Cause: A local proxy (for example Clash in fake-ip mode) or a firewall is intercepting the connection.
Fix: Set api.tokenmilo.com to DIRECT in your proxy rules, or turn the proxy off. TokenMilo does not need a proxy.
429 Too Many Requests
Cause: Too many concurrent requests in a short time.
Fix: Retry with exponential backoff and lower the concurrency of batch jobs.
Context too long ("prompt is too long" / context_length_exceeded)
Cause: The conversation plus attached files exceeds the model’s context window.
Fix: Start a new session or run /compact in Claude Code, attach fewer files, and trim long tool outputs.
400 "max_tokens: Field required"
Cause: The Anthropic Messages API requires max_tokens on every request.
Fix: Add max_tokens (for example 1024 or more) to the request body. OpenAI-format requests don’t need it.
400 tool_choice not supported
Cause: Some newer Claude models (for example Claude Sonnet 5.5) only accept tool_choice "auto"; forcing a specific tool or "any" is rejected upstream.
Fix: Use tool_choice "auto" (or omit it), or switch to a model that supports forced tool use, such as claude-sonnet-4-6.
500 / 502 / 503 upstream error
Cause: A temporary error from the upstream model provider.
Fix: Retry after a few seconds. If it keeps failing for several minutes, contact support with the time and request ID.
Still stuck? Ask in our Telegram support group and we will help, including remote setup. Telegram →
FAQ
Is this the real Claude Fable 5?
Yes. Requests with model ID claude-fable-5 are served by the genuine Anthropic model — no quantized, swapped or downgraded variant. Response quality is the same as calling Anthropic directly.
How much does Claude Fable 5 cost on TokenMilo?
$2.23 per 1M input tokens and $11.18 per 1M output tokens, compared with $10 / $50 officially — 78% less. There is no subscription or monthly minimum.
Which API format should I use for Claude Fable 5?
The Anthropic Messages API (https://api.tokenmilo.com/v1/messages) is recommended and supports every Claude feature, including prompt caching, tool use and extended thinking. The OpenAI-compatible Chat Completions endpoint also works for simple chat.
Does Claude Fable 5 support prompt caching?
Yes. Cache reads are billed at $0.225 per 1M tokens, which makes long system prompts and coding-agent sessions much cheaper.
Start using Claude Fable 5
Sign up, top up, create a key — and point your SDK at TokenMilo.