Claude Fable 5.1 · Anthropic

What does Claude Fable 5.1 cost to run in a coding agent?

Claude Fable 5.1 costs about $0.24 per average coding-agent request on our measured traffic, at list prices of $10 per million input and $50 per million output tokens. It ranks #2 on Scale's SWE-Bench Pro V2.

List prices: Anthropic pricing, checked 2026-10-13. Request costs: Standard Compute gateway data, 79,301 coding-agent requests from 75 users, Sep 13 to Oct 12, 2026. Benchmark: Scale SWE-Bench Pro V2. How we compute this

Run Claude Fable 5.1 in your agent from $19/month

See plans

What Fable 5.1 costs per coding-agent request

Cost at list price	Fable 5.1
Prompt under 100K tokens50% of requests, 87% of input cached	$0.12
Prompt of 100K to 272K39% of requests, 88% of input cached	$0.28
Prompt over 272K tokens11% of requests, 86% of input cached	$0.63
Average request	$0.24
100 requests	$23.76
Median session16 requests; a session ends after 10 idle minutes	$3.26
A month of regular usemedian of 20 users active on 5+ days	$332

Each logged request priced at the vendor's list rates for its own token counts, including cache reads and any higher rate for long prompts. Average output: 698 tokens per request.

What to watch for

Fable 5.1 costs 2.2x Opus 5.5 per request ($0.24 vs $0.11) and scores lower on Terminal-Bench 4.0 (57.9% vs 64.9%). Its cache reads cost $0.25 per million, a quarter of Fable 5's, which is why it comes out 27% cheaper than Fable 5 per request on our traffic.

About Claude Fable 5.1

Claude Fable 5.1 is Anthropic's premium model, released September 1, 2026 alongside the limited-access Mythos 5.1. Anthropic says it is about 25% cheaper than Fable 5 on typical work and up to 45% cheaper on agentic work, thanks to a lower cache-read price. It scores 53 on the Artificial Analysis Intelligence Index, 57.9% on the Terminal-Bench 4.0 leaderboard, and ranks #2 on Scale's SWE-Bench Pro V2. Three weeks after launch, Anthropic said Opus 5.5 performs at Fable 5.1's level on most work, which makes Fable a narrower pick than it was.

Sources: Anthropic announcement · Artificial Analysis · Terminal-Bench 4.0 · SWE-Bench Pro V2

Claude Fable 5.1 FAQ

How much does Claude Fable 5.1 cost per coding-agent request?

$0.24 on average at list price, $23.76 per 100 requests, and $3.26 for a median 16-request session. That is 79,301 real coding-agent requests (Sep 13 to Oct 12, 2026) priced at Anthropic's list rates; the median request sent 99,534 input tokens, 87% of input was read from cache, and requests returned 698 output tokens on average.

Does Claude Fable 5.1 charge more for long prompts?

No. Claude Fable 5.1 bills the same rate per token up to its 1M-token context window.

Is Claude Fable 5.1 good for AI agents?

Teams already standardized on Fable that want the newest premium Claude. On our editorial scoring it rates 9.7/10 for agentic ability and 9.7/10 for output quality. #2 on Scale's SWE-Bench Pro V2 (99.1, Claude Code harness).

What is Claude Fable 5.1's context window?

Claude Fable 5.1 has a 1M-token context window — large enough to hold sizeable codebases or document sets in a single run. Anthropic is the maker.

Can I self-host Claude Fable 5.1?

No — Claude Fable 5.1 is a proprietary, hosted-only model from Anthropic. You access it through an API (e.g. OpenRouter) rather than running the weights yourself.

What are the downsides of Claude Fable 5.1?

The main trade-offs: Opus 5.5 scores higher on Artificial Analysis and Terminal-Bench 4.0 at less than half the price; Slow: about 67 output tokens/s at max effort. It's strongest for teams already standardized on Fable that want the newest premium Claude.