Flagship Claude model for deep reasoning, coding, and long-horizon agents
Specification
anthropic listing
Context
200K
Max output
64K
Released
2025-11-24
Knowledge cutoff
2025-05
Retires
2026-11-24
Open weights
no
Input
text, image, pdf
Output
text
Price
US dollars per million tokens · anthropic list price
Input
$5.00
Output
$25.00
Cache read
$0.50
Cache write
$6.25
Batch and priority prices
US dollars per million tokens · per listing
| Price | Listing | $/M |
|---|---|---|
| Cache write, 1 hour | bedrock_converse | $10.00 |
| Cache write, 1 hour | bedrock_converse · us | $11.00 |
Quality
11 benchmarks · 2 sources
Composite
55th
percentile of 334 scored models
Rank
151 / 334
±0.06 sd
Evidence
11 × 2
3 or more benchmarks, from 2 or more sources
Effort range
3.3
points between effort settings
reasoning64th4/4 bench
math48th5/7 bench
knowledge56th1/1 bench
general29th1/1 bench
By reasoning effort
every setting placed on the same scale as the leaderboard
| Setting | Composite | Benchmarks behind it |
|---|---|---|
| 16k | 76th | 4 |
| 48k | 61st | 1 |
| 32k | 59th | 8 |
| high+64k | 39th | 1 |
| 128k | 33rd | 1 |
Every score
one row per source and configuration — nothing averaged away
| Benchmark | Score | Configuration | Source | Run |
|---|---|---|---|---|
| GPQA diamond | 86.0 ±2.1 | 32k | Epoch AI | 2025-11-24 |
| ↳ | 85.5 ±2.2 | 16k | Epoch AI | 2025-11-25 |
| Settings differ by 0.5 points on this benchmark. | ||||
| OTIS Mock AIME 2024-2025 | 86.1 ±4.3 | 32k | Epoch AI | 2025-11-24 |
| ↳ | 81.7 ±5.0 | 16k | Epoch AI | 2025-11-24 |
| Settings differ by 4.4 points on this benchmark. | ||||
| SimpleQA Verified | 45.7 ±1.6 | 32k | Epoch AI | 2026-08-27 |
| FrontierMath-v1 | 30.2 ±16.3 | 16k · 2 runs | Epoch AI | 2025-11-25 |
| ↳ | 20.7 ±2.4 | 32k | Epoch AI | 2025-11-25 |
| Settings differ by 9.5 points on this benchmark. | ||||
| Mystery Game Puzzles | 22.0 ±4.2 | 48k | Epoch AI | 2026-07-25 |
| Chess Puzzles | 12.0 ±3.3 | 32k | Epoch AI | 2025-12-08 |
| FrontierMath-Tier-4-2025-07-01 | 4.2 ±2.9 | 32k | Epoch AI | 2025-11-25 |
| ↳ | 2.1 ±2.1 | 16k | Epoch AI | 2025-11-25 |
| Settings differ by 2.1 points on this benchmark. | ||||
| FrontierMath-Tiers-1-3-v2 | 34.4 ±2.8 | 32k | Epoch AI | 2026-06-11 |
| LiveBench | 72.9 | high+64k · 23 runs | LiveBench | 2026-06-25 |
| EBR-bench | 14.3 | 128k | Epoch AI | 2026-06-25 |
| FrontierMath-Tier-4-v2 | 4.9 ±3.4 | 32k | Epoch AI | 2026-06-11 |
The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.
Available from 49 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| anthropicvendor | $5.00 | $25.00 | $0.50 | $6.25 | 200K | 64K | 2026-11-24 |
| qihang-ai | $0.71 | $3.57 | — | — | 200K | 32K | — |
| poe | $4.30 | $21.00 | $0.43 | $5.30 | 197K | 64K | — |
| jiekou | $4.50 | $22.50 | — | — | 200K | 66K | — |
| 302ai | $5.00 | $25.00 | — | — | 200K | 64K | — |
| abacus | $5.00 | $25.00 | — | — | 200K | 64K | — |
| amazon-bedrock | $5.00 | $25.00 | $0.50 | $6.25 | 200K | 64K | — |
| amazon-bedrock · global | $5.00 | $25.00 | $0.50 | $6.25 | 200K | 64K | — |
| amazon-bedrock · us | $5.00 | $25.00 | $0.50 | $6.25 | 200K | 64K | — |
| azure | $5.00 | $25.00 | $0.50 | $6.25 | 200K | 64K | — |
| azure_ai | $5.00 | $25.00 | $0.50 | $6.25 | 200K | 64K | 2026-10-19 |
| azure-cognitive-services | $5.00 | $25.00 | $0.50 | $6.25 | 200K | 64K | — |
| bedrock_converse | $5.00 | $25.00 | $0.50 | $6.25 | 200K | 64K | — |
| bedrock_converse · eu | $5.00 | $25.00 | $0.50 | $6.25 | 200K | 64K | — |
| bedrock_converse · global | $5.00 | $25.00 | $0.50 | $6.25 | 200K | 64K | — |
| cloudflare-ai-gateway | $5.00 | $25.00 | $0.50 | $6.25 | 200K | 64K | — |
| databricks | $5.00 | $25.00 | $0.50 | $6.25 | 200K | 64K | — |
| edenai | $5.00 | $25.00 | $0.50 | $6.25 | 200K | 64K | — |
| gmi · gmi | $5.00 | $25.00 | — | — | 410K | 32K | — |
| google-vertex | $5.00 | $25.00 | $0.50 | $6.25 | 200K | 64K | — |
| google-vertex-anthropic | $5.00 | $25.00 | $0.50 | $6.25 | 200K | 64K | — |
| impossibl | $5.00 | $25.00 | $0.50 | $6.25 | 200K | 64K | — |
| kilo | $5.00 | $25.00 | $0.50 | $6.25 | 200K | 64K | — |
| llmgateway | $5.00 | $25.00 | $0.50 | $6.25 | 200K | 64K | — |
| llmgateway-providers | $5.00 | $25.00 | $0.50 | $6.25 | 200K | 32K | — |
| llmgateway-providers · aws-bedrock | $5.00 | $25.00 | $0.50 | $6.25 | 200K | 32K | — |
| llmgateway-providers · vertex-anthropic | $5.00 | $25.00 | $0.50 | — | 200K | 32K | — |
| merge-gateway | $5.00 | $25.00 | $0.50 | $6.25 | 200K | 64K | — |
| nano-gpt | $5.00 | $25.00 | $0.50 | — | 200K | 64K | — |
| nano-gpt · thinking | $5.00 | $25.00 | $0.50 | — | 200K | 64K | — |
| neon | $5.00 | $25.00 | $0.50 | $6.25 | 200K | 64K | — |
| ofox | $5.00 | $25.00 | $0.50 | $6.25 | 200K | 64K | — |
| opencode | $5.00 | $25.00 | $0.50 | $6.25 | 200K | 64K | — |
| openrouter | $5.00 | $25.00 | $0.50 | $6.25 | 200K | 64K | — |
| opper | $5.00 | $25.00 | $0.50 | $6.25 | 200K | 64K | — |
| orcarouter | $5.00 | $25.00 | $0.50 | $6.25 | 200K | 64K | — |
| perplexity | $5.00 | $25.00 | $0.50 | — | — | — | — |
| perplexity-agent | $5.00 | $25.00 | $0.50 | — | 200K | 64K | — |
| pioneer | $5.00 | $25.00 | $0.50 | $6.25 | 200K | 64K | — |
| requesty | $5.00 | $25.00 | $0.50 | $6.25 | 200K | 64K | — |
| vercel | $5.00 | $25.00 | $0.50 | $6.25 | 200K | 64K | — |
| vercel_ai_gateway · vercel-ai-gateway | $5.00 | $25.00 | $0.50 | $6.25 | 200K | 64K | — |
| vertex_ai-anthropic_models | $5.00 | $25.00 | $0.50 | $6.25 | 200K | 64K | 2026-11-24 |
| zenmux | $5.00 | $25.00 | $0.50 | $6.25 | 200K | 64K | — |
| amazon-bedrock · eu | $5.50 | $27.50 | $0.55 | $6.875 | 200K | 64K | — |
| bedrock_converse · us | $5.50 | $27.50 | $0.55 | $6.875 | 200K | 64K | — |
| venice | $6.00 | $30.00 | $0.60 | $7.50 | 198K | 33K | — |
| github_copilot · github-copilot | — | — | — | — | 128K | 16K | — |
| snowflake-cortex | — | — | — | — | 200K | 64K | — |
Other listings of this model
same model, different key
More from Anthropic
most-hosted first