AIHubMixAIHubMix
← Models

Anthropic Opus 4.6 vs Claude 3.7 Sonnet

Compare Anthropic Opus 4.6 from Anthropic and Claude 3.7 Sonnet 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.

AnthropicAnthropic Opus 4.6AnthropicClaude 3.7 Sonnet
+ Add model · 2/4
Anthropic logo
Anthropic Opus 4.6
Anthropic · text, image → text

Claude Opus 4.6 is Anthropic’s latest state-of-the-art reasoning model. It features an adaptive “thinking” mode that dynamically decides when to think and how much to think. At the default effort level (high), Claude will almost always engage in thinking. At lower effort levels, it may skip thinking for simple problems. ⚠️ The minimum cache token for claude-opus-4-6 has been increased from 1,024 to 4,096 tokens.

Input$5 /M
Output$25 /M
Cache read$0.5 /M
Details
Anthropic logo
Claude 3.7 Sonnet
Anthropic · text, image → text

Support for the thinking parameter through the original Claude SDK.

Input$3.3 /M
Output$16.5 /M
Details

Pricing & Specifications

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

Anthropic Opus 4.6
Claude 3.7 Sonnet
Input /M
$5
$3.3
Output /M
$25
$16.5
Cache read /M
$0.5
-
Context length
200,000
200,000
Max output
32,000
128,000
Time to First Token
3.1 s
0.6 s
Throughput
39.7 tok/s
57.3 tok/s
Modalities
textimage
textimage
Supported Parameters
thinkingtoolsfunction callingstructured outputs
thinkingtoolsfunction callingstructured outputs
API Formats
Released
-
-

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.

anthropic-opus-4-6claude-3-7-sonnet

Tokens / day

-

Requests / day

-

Performance Past 3 Days

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

anthropic-opus-4-6claude-3-7-sonnet

Throughput (tok/s)

-

TTFT (s)

-

Uptime (%)

-

LMArena Benchmarks

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

Text
anthropic-opus-4-6claude-3-7-sonnet
13401400146015201580
Overall
13711499
Coding
14301548
Math
13621504
Hard prompts
13981528
Instruction following
13841501
Multi-turn
13961510
Creative writing
13761478
Longer query
14101519
Chinese
13811549
English
13851508
Vision
anthropic-opus-4-6claude-3-7-sonnet
1140120012601320
Overall
11751297
OCR
11831313
Diagram
11891333
Homework
12241314

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 3.7 Sonnet
$446 /mo
Anthropic Opus 4.6
$675 /mo

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

FAQ

Which is cheaper: Anthropic Opus 4.6, Claude 3.7 Sonnet?

Claude 3.7 Sonnet: $16.5/M output tokens; Anthropic Opus 4.6: $25/M. Use the cost calculator above to estimate your own workload.

How do their coding arena scores compare?

Anthropic Opus 4.6: 1548; Claude 3.7 Sonnet: 1430 (LMArena coding leaderboard).

Which responds faster?

Claude 3.7 Sonnet: 0.6s 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?

Anthropic Opus 4.6 accepts 200,000 and Claude 3.7 Sonnet accepts 200,000 input tokens. Maximum output per request is 32,000 tokens on Anthropic Opus 4.6 and 128,000 tokens on Claude 3.7 Sonnet.

Which one generates tokens faster?

Claude 3.7 Sonnet at 57.3 tok/s and Anthropic Opus 4.6 at 39.7 tok/s, measured as output throughput on AIHubMix — a separate metric from time to first token.

What inputs and capabilities does each model support?

Anthropic Opus 4.6 accepts text and image input and supports thinking, tool calling, function calling and structured outputs; Claude 3.7 Sonnet accepts text and image input and supports thinking, tool calling, function calling and structured outputs.

Can I call Anthropic Opus 4.6 and Claude 3.7 Sonnet 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.

Kimi K3vsQwen3.8 Max PreviewClaude Opus 5vsGPT 5.6 LunaClaude Opus 5vsClaude Sonnet 5Gemini 3.1 Pro PreviewvsGPT 5.5GLM 5.2vsKimi K3Gemini 3.6 FlashvsQwen3.8 MaxDeepSeek V4 FlashvsGLM 5.2Claude Opus 5vsGrok 4.5
AIHubMix

© 2023 - 2026 AIHubMix, LLC

Product

Company

Developer

Connect