Flagship Claude model for deep reasoning, coding, and long-horizon agents
Specification
anthropic listing
Context
200K
Max output
32K
Released
2025-08-05
Knowledge cutoff
2025-03-31
Retires
2026-08-05
Open weights
no
Input
text, image, pdf
Output
text
Price
US dollars per million tokens · anthropic list price
Input
$15.00
Output
$75.00
Cache read
$1.50
Cache write
$18.75
Batch and priority prices
US dollars per million tokens · per listing
| Price | Listing | $/M |
|---|---|---|
| Batch input | vertex_ai-anthropic_models | $7.50 |
| Batch output | vertex_ai-anthropic_models | $37.50 |
| Cache write, 1 hour | azure_ai | $30.00 |
Batch input is 50% below the interactive input price at the same listing.
Quality
10 benchmarks · 1 source
Composite
43rd
percentile of 334 scored models
Rank
190 / 334
±0.06 sd
Evidence
10 × 1
one source, or fewer than 3 benchmarks
Effort range
4.0
points between effort settings
coding77th1/3 bench
reasoning49th4/4 bench
math30th5/7 bench
By reasoning effort
every setting placed on the same scale as the leaderboard
| Setting | Composite | Benchmarks behind it |
|---|---|---|
| 24k | 58th | 1 |
| 16k | 57th | 3 |
| 27k | 57th | 4 |
| 32k | 16th | 2 |
Every score
one row per source and configuration — nothing averaged away
| Benchmark | Score | Configuration | Source | Run |
|---|---|---|---|---|
| SWE-Bench verified | 73.3 ±2.0 | default | Epoch AI | 2026-02-11 |
| GPQA diamond | 77.3 ±3.0 | 16k | Epoch AI | 2025-08-05 |
| ↳ | 76.8 ±3.0 | 27k | Epoch AI | 2025-08-05 |
| ↳ | 73.2 ±3.2 | default | Epoch AI | 2025-08-05 |
| Settings differ by 4.1 points on this benchmark. | ||||
| OTIS Mock AIME 2024-2025 | 68.9 ±7.0 | 27k | Epoch AI | 2025-08-05 |
| ↳ | 64.4 ±7.2 | 16k | Epoch AI | 2025-08-05 |
| ↳ | 40.0 ±7.4 | default | Epoch AI | 2025-08-05 |
| Settings differ by 28.9 points on this benchmark. | ||||
| Mystery Game Puzzles | 21.0 ±4.1 | 24k | Epoch AI | 2026-07-25 |
| FrontierMath-Tier-4-2025-07-01 | 4.2 ±2.9 | 27k | Epoch AI | 2025-08-05 |
| Chess Puzzles | 7.0 ±2.6 | default | Epoch AI | 2026-07-20 |
| FrontierMath-v1 | 3.6 ±1.5 | 27k · 2 runs | Epoch AI | 2025-08-05 |
| ↳ | 2.9 ±1.4 | default · 2 runs | Epoch AI | 2025-08-05 |
| ↳ | 0.0 ±0.0 | 16k | Epoch AI | 2025-08-05 |
| Settings differ by 3.6 points on this benchmark. | ||||
| EBR-bench | 7.9 | default | Epoch AI | 2026-06-25 |
| FrontierMath-Tier-4-v2 | 2.4 ±2.4 | 32k | Epoch AI | 2026-06-11 |
| FrontierMath-Tiers-1-3-v2 | 12.6 ±2.0 | 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 32 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| anthropicvendor | $15.00 | $75.00 | $1.50 | $18.75 | 200K | 32K | 2026-08-05 |
| poe | $13.00 | $64.00 | $1.30 | $16.00 | 197K | 32K | — |
| jiekou | $13.50 | $67.50 | — | — | 200K | 32K | — |
| 302ai | $15.00 | $75.00 | — | — | 200K | 32K | — |
| abacus | $15.00 | $75.00 | — | — | 200K | 32K | — |
| amazon-bedrock | $15.00 | $75.00 | $1.50 | $18.75 | 200K | 32K | — |
| amazon-bedrock · us | $15.00 | $75.00 | $1.50 | $18.75 | 200K | 32K | — |
| azure | $15.00 | $75.00 | $1.50 | $18.75 | 200K | 32K | — |
| azure_ai | $15.00 | $75.00 | $1.50 | $18.75 | 200K | 32K | 2026-08-05 |
| azure-cognitive-services | $15.00 | $75.00 | $1.50 | $18.75 | 200K | 32K | — |
| bedrock_converse | $15.00 | $75.00 | $1.50 | $18.75 | 200K | 32K | 2027-01-08 |
| bedrock_converse · eu | $15.00 | $75.00 | $1.50 | $18.75 | 200K | 32K | 2027-01-08 |
| bedrock_converse · us | $15.00 | $75.00 | $1.50 | $18.75 | 200K | 32K | 2027-01-08 |
| databricks | $15.00 | $75.00 | $1.50 | $18.75 | 200K | 32K | — |
| fastrouter | $15.00 | $75.00 | $1.50 | $18.75 | 200K | 32K | — |
| google-vertex | $15.00 | $75.00 | $1.50 | $18.75 | 200K | 32K | — |
| google-vertex-anthropic | $15.00 | $75.00 | $1.50 | $18.75 | 200K | 32K | — |
| helicone | $15.00 | $75.00 | $1.50 | $18.75 | 200K | 32K | — |
| kilo | $15.00 | $75.00 | $1.50 | $18.75 | 200K | 32K | — |
| llmgateway | $15.00 | $75.00 | $1.50 | $18.75 | 200K | 32K | — |
| llmgateway-providers · aws-bedrock | $15.00 | $75.00 | $1.50 | $18.75 | 200K | 32K | — |
| merge-gateway | $15.00 | $75.00 | $1.50 | $18.75 | 200K | 32K | — |
| nano-gpt | $15.00 | $75.00 | $1.50 | — | 200K | 32K | — |
| nano-gpt · thinking | $15.00 | $75.00 | $1.50 | — | 200K | 32K | — |
| neon | $15.00 | $75.00 | $1.50 | $18.75 | 200K | 32K | — |
| opencode | $15.00 | $75.00 | $1.50 | $18.75 | 200K | 32K | — |
| openrouter | $15.00 | $75.00 | $1.50 | $18.75 | 200K | 32K | — |
| pioneer | $15.00 | $75.00 | $1.50 | $18.75 | 200K | 32K | — |
| requesty | $15.00 | $75.00 | $1.50 | $18.75 | 200K | 32K | — |
| vercel_ai_gateway · vercel-ai-gateway | $15.00 | $75.00 | $1.50 | $18.75 | 200K | 32K | — |
| vertex_ai-anthropic_models | $15.00 | $75.00 | $1.50 | $18.75 | 200K | 32K | 2026-08-05 |
| zenmux | $15.00 | $75.00 | $1.50 | $18.75 | 200K | 64K | — |
Other listings of this model
same model, different key
More from Anthropic
most-hosted first