← Models

Claude Fable 5.1 vs Claude Sonnet 5

Compare Claude Fable 5.1 from Anthropic and Claude Sonnet 5 from Anthropic on key metrics including benchmarks, price, context length, and other model features. Access both models and hundreds of others through the AIHubMix API.

AnthropicClaude Fable 5.1AnthropicClaude Sonnet 5
Anthropic logo
Claude Fable 5.1
Anthropic · text, image, pdf → text

Claude-fable-5-1 is Anthropic's most capable newly released model, suitable for the most demanding reasoning and long-running agent work. Claude Fable 5.1, while keeping input and output prices the same as Claude Fable 5, reduces cache read prices to one quarter of the original and is more capable for long-running agent programming, multi-step research, and document, spreadsheet, and slide processing. (The model is extremely expensive and not recommended for casual use.)

Input$11 /M
Output$55 /M
Cache read$0.275 /M
Anthropic logo
Claude Sonnet 5
Anthropic · text, image, pdf → text

Claude Sonnet 5 is the next generation of Anthropic's Sonnet model family. It is a drop-in upgrade for Claude Sonnet 4.6 with three behavior changes: adaptive thinking is on by default, manual extended thinking now returns a 400 error (it was deprecated on Claude Sonnet 4.6), and setting sampling parameters (temperature, top_p, top_k) to non-default values returns a 400 error

Input$2 /M
Output$10 /M

Pricing & Specifications

Prices are per million tokens. Time to First Token and throughput are rolling averages measured on AIHubMix.

Claude Fable 5.1
Claude Sonnet 5
Input
$11 /M
$2 /M
Output
$55 /M
$10 /M
Cache read
$0.275 /M
-
Context length
1,000,000
1,000,000
Max output
128,000
128,000
Time to First Token
27.9 s
0.8 s
Throughput
69.5 tok/s
7839.1 tok/s
Modalities
textimagepdf
textimagepdf
Supported Parameters
thinkingtoolsfunction callingstructured outputs
thinkingtoolsfunction callingstructured outputs
API Formats
chat_completions · claude_api
chat_completions · gemini_api · claude_api
Released
September 2, 2026
June 30, 2026

Promotional prices show the discounted rate; see each model page for promotion windows.

Activity Past 30 Days

Daily traffic served through AIHubMix — how demand for each model is trending.

claude-fable-5-1claude-sonnet-5

Tokens / day

-

Requests / day

-

Performance Past 3 Days

Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.

claude-fable-5-1claude-sonnet-5

Throughput (tok/s)

-

TTFT (s)

-

Uptime (%)

-

LMArena Benchmarks

LMArena ratings by capability (Bradley-Terry, commonly called Elo). Higher is better.

Text
claude-fable-5-1claude-sonnet-5
1400146015201580
Overall
14611503
Coding
15201533
Math
14721527
Hard prompts
14901521
Instruction following
14671500
Multi-turn
14731486
Creative writing
14341490
Longer query
14811509
Chinese
14971563
English
14711501
Vision
claude-fable-5-1claude-sonnet-5
1240128013201360
Overall
12611289
OCR
12801305
Diagram
12921326
Homework
13031328
WebDev Arena
claude-fable-5-1claude-sonnet-5
14801580168017801880
Overall
15391742
React
15391788
HTML
15261681
Gaming
15751845
Simulations
15541822
Data analytics
15031616

Source: LMArena (arena.ai) leaderboard, imported by AIHubMix. Models without published ratings are omitted per chart.

Cost calculator

Estimate your monthly bill for the same workload on each model.

Claude Sonnet 5
$270 /mo
Claude Fable 5.1
$1,485 /mo

Monthly = daily × 30. Discounted rates applied where a promotion is active.

FAQ

Which is cheaper: Claude Fable 5.1, Claude Sonnet 5?

Claude Sonnet 5: $10/M output tokens; Claude Fable 5.1: $55/M. Use the cost calculator above to estimate your own workload.

How do their coding arena scores compare?

Claude Fable 5.1: 1533; Claude Sonnet 5: 1520 (LMArena coding leaderboard).

Which responds faster?

Claude Sonnet 5: 0.8s time to first token measured on AIHubMix; see the live performance charts above for how each model behaves across the day.

How large is each context window?

Claude Fable 5.1 accepts 1,000,000 and Claude Sonnet 5 accepts 1,000,000 input tokens. Maximum output per request is 128,000 tokens on Claude Fable 5.1 and 128,000 tokens on Claude Sonnet 5.

Which one generates tokens faster?

Claude Sonnet 5 at 7839.1 tok/s and Claude Fable 5.1 at 69.5 tok/s, measured as output throughput on AIHubMix — a separate metric from time to first token.

What inputs and capabilities does each model support?

Claude Fable 5.1 accepts text, image and PDF input and supports thinking, tool calling, function calling and structured outputs; Claude Sonnet 5 accepts text, image and PDF input and supports thinking, tool calling, function calling and structured outputs.

Can I call Claude Fable 5.1 and Claude Sonnet 5 with the same API key?

Yes. AIHubMix serves every model on this page behind one OpenAI-compatible endpoint, so switching between them is a one-line change to the model field — no second account, key or SDK.

Popular comparisons

Related model match-ups readers also look at.