Anthropic

Claude 3 Opus 2024-02-29

Type
language model
Context
200K tokens
Max output
4K
API string
claude-3-opus-20240229

The provider has deprecated this model. It still responds, but it is not a good choice for new projects.

Prices by provider

Provider Input, $ per 1M Output, $ per 1M In our data since
Amazon Bedrock $15 $75 2 Aug 2026
Anthropic $15 $75 1 Aug 2026

Only the base tier and only per-token prices are shown. Batch, discounted and cached rates, as well as prices per image or per second of video, do not go into this table: they cannot stand in the same column as a price per million tokens.

The date in the last column is the day this price first entered our collection. The price may well be older: before that day we simply were not recording it. It has not changed since — otherwise a new row with a new date would stand in its place.

Measurement results

Task set Result Run conditions Measured by
Arena Score in Russian 1,279.06 1,272–1,286
Arena Score, multi-turn dialogue 1,275.39 1,269–1,281
Arena Score in French 1,273.88 1,255–1,293
Arena Score, mathematics 1,272.58 1,266–1,279
Arena Score, programming 1,264.67 1,259–1,271
Arena Score in English 1,262.98 1,259–1,267
Arena Score, overall 1,262.17 1,259–1,265
Arena Score, long queries 1,259.32 1,253–1,266
Arena Score, instruction following 1,248.74 1,244–1,253
Arena Score, hard prompts 1,245.74 1,241–1,251
Arena Score in Spanish 1,245.51 1,227–1,264
Arena Score, creative writing 1,235.21 1,229–1,242
Arena Score, expert questions 1,222.21 1,213–1,232
Arena Score, working with images 1,023.06 1,013–1,033
MATH, difficulty level five 37.48 % · with a tuned harness Epoch evaluations
GPQA Diamond — graduate-level questions 29.55 % · with a tuned harness Epoch evaluations
WeirdML — unusual machine learning tasks 23.18 % WeirdML Leaderboard
Cybench — cybersecurity tasks 10 % · with a tuned harness Cybench leaderboard
SimpleBench — trick questions 8.2 % SimpleBench Leaderboard
Mock AIME 2024–2025 — olympiad problems 4.63 % · with a tuned harness Epoch evaluations
Chess puzzles 0.04 % Epoch evaluations