New Sign up free, 10 calls on us. Up to $1, no card needed.

Claude Fable 5.1

Released 2026-09-01

invited beta chatCodeReasoningTool callingVisionPrompt caching

Claude Fable 5.1 is Anthropic's current top-capability model, released on 1 September 2026 and positioned for demanding reasoning and long-horizon agentic work.

Input
text image $10/M
Output
text $50/M
Cache read
$0.25/M
Context
1M
Knowledge cutoff
2026-06

Benchmarks

Above averageNo peer higher7 / 77 / 7
Claude Fable 5.1 other models measured peer average no peer scored higher
Terminal-bench 4.0
no peer scored higher 55.8%
OSWorld 2.0 partial
77.9%
GDPval-AA v2 Elo · 1711-1853 per Anthropic · 2026-09-05
no peer scored higher 1853
Humanity's Last Exam no tools
no peer scored higher 60.9%
AutomationBench
no peer scored higher 31.4%

Vendor-published: Alibaba (Qwen) Anthropic DeepSeek Google MiniMax Moonshot OpenAI Z.ai

Price in context

Where the price sits among 65 comparable models

Input$10/M
$0.05 · Qwen3 VL Flash GPT-5.4 Pro · $30
Output$50/M
$0.275 · DeepSeek V4 Flash GPT-5.4 Pro · $180
Cached read$0.25/M
$0.0028 · DeepSeek V4 Flash GPT-5.4 Pro · $15

The bar shows how this model’s price compares with every other model of the same kind on Synthorai. The cheapest and the most expensive are named at each end. These are base rates; batch, region and cache-write discounts are on the pricing page.

Specs & limits

Tokens

Context window (vendor spec) 1,000,000
Max output (vendor spec) 128,000
Knowledge cutoff 2026-06

Prompt caching

How it caches explicit (opt-in)
Min prefix 1,024
Lifetime 5m default, 1h option
Write cost 1.25x (5m) / 2x (1h)

Thinking

Vendor control output_config.effort (thinking is adaptive-only and always on)
Accepted values effort low · medium · high · xhigh · max
Default thinking always on (adaptive); effort high applied when the request sets nothing
Can be turned off No
Thinking behaviour Effort can be changed per message mid-conversation without invalidating the prompt cache (beta). Turn-scoped system messages and readable progress updates between tool calls are the other additions, both beta.
Parameter reasoning_effort
Values minimal · low · medium · high the gateway's parameter surface - the vendor mapping above applies

Model

Modalities text + image → text
  • Extends Claude Fable 5 at the same input and output prices with cache reads at a quarter of the cost
  • three changes break callers moving from Fable 5, because forced tool use returns an error, thinking blocks are tied to the model that produced them, and editing an earlier turn invalidates them

per Anthropic official docs ↗

Use Claude Fable 5.1 in 30 seconds

OpenAI-compatible: swap the base_url, keep your SDK. POST /v1/chat/completions

from openai import OpenAI

client = OpenAI(
    base_url="https://synthorai.io/v1",
    api_key="sk-syn-...",
)

resp = client.chat.completions.create(
    model="claude-fable-5-1",
    messages=[{"role": "user", "content": "Summarize this diff"}],
    reasoning_effort="medium",
)
print(resp.choices[0].message.content)

About Claude Fable 5.1

  • Anthropic's own guidance still starts most workloads on Claude Opus 5 and reserves this tier for cases where Opus 5 at higher effort still falls short.
  • It keeps the shape of Claude Fable 5 exactly: a 1M-token context window, 128K output tokens, text and image in and text out, and adaptive thinking that is always on with effort defaulting to high.
  • The reason to move up is cost behaviour and agentic endurance rather than a larger window.
  • Input and output stay at $10 and $50 per million tokens while cache reads drop to a quarter of the earlier rate, and Anthropic reports roughly 25% lower cost on a typical workload and about 45% on a highly agentic one.
  • Three changes are breaking for callers coming from Fable 5: forced tool use now returns an error, thinking blocks are tied to the model that produced them so earlier Claude models cannot read them, and editing an earlier turn invalidates them.
  • The additions are backward compatible, and three of the five are in beta: per-message effort, turn-scoped system messages, and readable progress updates between tool calls; the lower cache read price and content provenance are generally available.
  • Claude Mythos 5.1 offers the same capabilities to Project Glasswing participants only.
  • Synthorai serves it through the OpenAI-compatible chat endpoint as an invite-only beta.

FAQ

Is the Claude Fable 5.1 API free to try?

Claude Fable 5.1 is currently in invited beta: access is application-based rather than open signup. Apply from the Synthorai console; once approved, standard pay-as-you-go pricing applies with no subscription.

What is Claude Fable 5.1 best at?

1M-token context window and 128K output; cache reads at a quarter of Fable 5's rate; forced tool use is no longer supported. See the About section for the full picture from the vendor's own release notes.

How much does Claude Fable 5.1 cost?

Claude Fable 5.1 costs $10 per million input tokens and $50 per million output tokens on Synthorai. That is the provider's list price, with no platform markup. Cached input tokens bill at $0.25/M.

Does Claude Fable 5.1 support prompt caching?

Yes, via opt-in: mark stable prefixes with cache_control breakpoints. Cached input tokens bill at $0.25/M vs $10/M uncached; prompts need a 1,024-token stable prefix to cache (TTL 5m default, 1h option). Prompt caching guide →

How do I get access to Claude Fable 5.1?

Claude Fable 5.1 is in invited beta: request access from the Synthorai console. Once approved it works like every other model: point your OpenAI SDK at base_url="https://synthorai.io/v1" and set model="claude-fable-5-1".

What is Claude Fable 5.1's knowledge cutoff?

Claude Fable 5.1's knowledge cutoff is 2026-06, per the vendor's official documentation (as of 2026-09-05).

Related models

Compare

Every value on this page is transcribed from the vendor's own documentation, linked above, and carries the date it was checked. Prices are compared across the catalogue; specification values that vendors define differently are shown with the difference stated rather than charted. Nothing here is measured by us, and nothing is scored.

Get your API key Compare your cost →