Claude 3 Opus
anthropic-claude-3-opus
Legacy model retained for compatibility with older integrations
Specification
most-agreed values
Context
200K
Max output
4K
Released
2024-02-29
Knowledge cutoff
2023-08
Retires
—
Open weights
no
Input
text, image
Output
text
Price
US dollars per million tokens · most-agreed
Input
$15.00
Output
$75.00
Cache read
$1.50
Cache write
$18.75
Quality
6 benchmarks · 2 sources
Composite
14th
percentile of 334 scored models
Rank
286 / 334
±0.05 sd
Evidence
6 × 2
3 or more benchmarks, from 2 or more sources
Effort range
—
one configuration only
coding2nd1/3 bench
reasoning30th2/4 bench
math18th2/7 bench
knowledge7th1/1 bench
Every score
one row per source and configuration — nothing averaged away
| Benchmark | Score | Configuration | Source | Run |
|---|---|---|---|---|
| MATH level 5 | 37.5 ±1.1 | default | Epoch AI | 2025-01-27 |
| Chess Puzzles | 5.0 ±2.2 | default | Epoch AI | 2026-07-15 |
| GPQA diamond | 47.2 ±2.6 | default | Epoch AI | 2025-01-27 |
| OTIS Mock AIME 2024-2025 | 4.7 ±2.0 | default | Epoch AI | 2025-02-25 |
| SimpleQA Verified | 12.6 ±1.1 | default | Epoch AI | 2026-08-31 |
| SWE-Bench verified | 11.4 | default · RAG baseline · 2 runs | SWE-bench | — |
The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.
Available from 3 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| digitalocean | $15.00 | $75.00 | $1.50 | $18.75 | 200K | 4K | — |
| gradient_ai · gradient-ai | $15.00 | $75.00 | — | — | 200K | 1K | — |
| sap-ai-core | $15.00 | $75.00 | $1.50 | $18.75 | 200K | 4K | — |
Other listings of this model
this page is one of them
The corpus files Claude 3 Opus under several keys. This page is the anthropic-claude-3-opus listing. The full record — every host, every price and every benchmark score — is on the main Claude 3 Opus page.