Claude Fable 5.1

AnthropicChatIDGlobal
Claude Fable 5.1 is Anthropic's model for demanding reasoning and long-horizon agentic work, with adaptive thinking always on, a 1M-token context window and up to 128K output tokens; list price $10.00 in / $50.00 out per 1M tokens, provider list as at 1 November 2026.
Seedrise is an independent provider and is not affiliated with or endorsed by Anthropic. Claude is a trademark of Anthropic, PBC.

Provider list price

Claude Fable 5.1Per 1M tokens, as at 1 November 2026
Token typePrice
Input10.00
Output50.00
Cached input0.25
AUD is shown at a reference rate of 1 USD = 1.53 AUD; invoices use the rate on the day.

Your Seedrise rate is quoted per account against this list price. Request a rate card.

Specifications

Model IDclaude-fable-5-1
ProviderAnthropic
TypeChat
Context window1M tokens (1,000,000)
Max output128K tokens (128,000)
ModalitiesTextVisionToolsReasoning
RegionGlobal Provider global routing
EndpointsOpenAI Chat Completions: https://api.seedrise.ai/v1
Anthropic Messages: https://api.seedrise.ai
Prices checked1 November 2026

Global: runs on the provider's global routing only and cannot be pinned to an Australian region. Fable 5.1 is enabled per key on request, and prompts and outputs may be retained on the provider side for up to 30 days for safety review.

Strengths

  • Adaptive thinking is always on, with high as the default effort level
  • 1M-token context window and up to 128K output tokens per request
  • Cache reads list at $0.25 per 1M tokens, which lowers the cost of long agent runs that resend the same context
  • Text and image input with tool use

Typical use cases

  • Multi-step agents that plan and execute over long sessions
  • Hard reasoning and analysis where Claude Opus 5.5 at higher effort still falls short
  • Reviewing and refactoring large codebases in one context
  • Research synthesis across long documents

Quickstart

A first request with curl. Replace sk-... with your Seedrise key.

curl
curl https://api.seedrise.ai/v1/chat/completions \
  -H "Authorization: Bearer sk-..." \
  -H "Content-Type: application/json" \
  -d '{"model":"claude-fable-5-1","messages":[{"role":"user","content":"Hello"}]}'

OpenAI SDK, Python

python
from openai import OpenAI

client = OpenAI(base_url="https://api.seedrise.ai/v1", api_key="sk-...")

r = client.chat.completions.create(
    model="claude-fable-5-1",
    messages=[{"role": "user", "content": "Summarise this contract in three bullets."}],
)
print(r.choices[0].message.content)

Claude Code

Claude Code talks Anthropic Messages, so it points at the root URL. Set the environment once and start it as usual.

bash
export ANTHROPIC_BASE_URL="https://api.seedrise.ai"
export ANTHROPIC_AUTH_TOKEN="sk-..."                     # your Seedrise key
export ANTHROPIC_API_KEY=""                             # clear any personal key
export ANTHROPIC_DEFAULT_OPUS_MODEL="claude-opus-5-5"
export ANTHROPIC_DEFAULT_SONNET_MODEL="claude-sonnet-5-5"
export ANTHROPIC_DEFAULT_HAIKU_MODEL="claude-haiku-5-5"
export CLAUDE_CODE_SUBAGENT_MODEL="claude-sonnet-5-5"
export CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC=1
export ANTHROPIC_DEFAULT_FABLE_MODEL="claude-fable-5-1"
claude

Fable 5.1 is available on keys that have it enabled.

Full guide with team settings and troubleshooting: Claude Code on Seedrise

Where it runs

Global Served on the provider's global routing. Australian-region pinning is not on the rate card for this model; ask if you need it.

Questions about Claude Fable 5.1

What is the model ID for Claude Fable 5.1? +
Use claude-fable-5-1 as the model field, with no vendor prefix. It works on the OpenAI-compatible endpoint at https://api.seedrise.ai/v1 and on Anthropic Messages at https://api.seedrise.ai. GET /v1/models returns the IDs your key can call.
How does the Seedrise rate for Claude Fable 5.1 compare to the list price? +
Anthropic's list price as at 1 November 2026 is US$10.00 per 1M input tokens and US$50.00 per 1M output tokens. Seedrise quotes rates per account against the provider's published list price for the same routing. Volume and committed tiers sit below list.
What is the context window and max output of Claude Fable 5.1? +
Claude Fable 5.1 has a context window of 1,000,000 tokens and a maximum output of 128,000 tokens, per the provider documentation checked on 1 November 2026.
Can Claude Fable 5.1 run in Australia? +
Not at present. Claude Fable 5.1 is served on the provider's global routing. Models marked AU in the model library can be pinned to Sydney or Melbourne on request.
Can Claude Fable 5.1 be pinned to Sydney or Melbourne? +
No. Fable 5.1 runs on global routing only. If inference must stay in Australia, use Claude Opus 5.5, Sonnet 5.5 or Haiku 5.5, which can be pinned to Sydney or Melbourne on request.
How does Claude Fable 5.1 compare with Claude Opus 5.5 on price? +
At provider list as at 1 November 2026, Fable 5.1 is $10.00 in / $50.00 out per 1M tokens and Opus 5.5 is $4.00 in / $20.00 out. Anthropic suggests starting with Opus 5.5 and moving to Fable 5.1 for demanding reasoning and long-horizon agentic work.

Get a rate for Claude Fable 5.1

Per-model rates in writing within one business day, then a console login and a trial key.

Request a rate card →