LLM

Claude Opus 4

by Anthropic

Prices last updated October 4, 2026

Claude Opus 4, a proprietary Anthropic model available via OpenRouter.

Context
200k
Providers
1
Cheapest Input
$15.00
Function Calling Streaming Chat / Instruct

Price Comparison

Compare pricing across 1 provider serving Claude Opus 4

Provider Input $/1M Output $/1M Context Speed TTFT Status
OpenRouter
OpenRouter
$15.00 ● $75.00 200k — — Down
● Cheapest ● Fastest Prices in USD per 1M tokens

Benchmarks

Independent results for Claude Opus 4, as each source publishes them. Where a source tested several versions (effort levels, thinking modes, dated snapshots), the best one is shown and named under "As tested". Scores from different sources use different scales and aren't comparable with each other.

BenchmarkScoreRankAs tested
Overall
One score combining a model's results across many benchmarks, on a common scale.
142.8±1.6
#110 of 258
Claude Opus 4
Reasoning
GPQA DiamondEpoch AI
Graduate-level multiple-choice questions in biology, physics and chemistry, written to be hard to look up.
76.3%±5.9
#110 of 232
claude-opus-4-20250514_16K
May 2025
Math
Competition maths problems from the OTIS mock AIME exams (2024-2025).
64.4%±14.1
#124 of 215
claude-opus-4-20250514_27K
May 2025
MATH Level 5Epoch AI
The hardest level of the MATH competition-problem dataset.
85.0%±1.9
#22 of 94
claude-opus-4-20250514
May 2025
Coding
Real GitHub issues from Python projects; the model must write a patch that passes the project's tests. Epoch's own runs.
70.7%±4.1
#24 of 32
claude-opus-4-20250514
Feb 2026
Text Arena votes on coding prompts only.
1,498±8
6,580 votes
#91 of 421
Claude Opus 4 (Thinking 16K, 20250514)
Nov 2026
Chat
Text ArenaLMArena
Human votes on chat answers across all kinds of prompts (style-controlled).
1,426±4
35,833 votes
#128 of 426
Claude Opus 4 (Thinking 16K, 20250514)
Nov 2026
Vision
Human votes on answers to prompts that include images (style-controlled).
1,208±16
1,288 votes
#90 of 168
Claude Opus 4 (Thinking 16K, 20250514)
Nov 2026

Epoch AI: Epoch runs each benchmark itself on the models it evaluates, with the same harness for every model. The Epoch Capabilities Index combines many benchmarks into one score. Data: Epoch AI, 'Capabilities & benchmarking', epoch.ai/benchmarks (CC BY 4.0).

LMArena: People compare two anonymous models side by side and vote for the better answer; ratings come from those votes (Bradley-Terry, style-controlled for text and vision). Data: LMArena (arena.ai) leaderboard dataset (CC BY 4.0).

Rank is among all models the source ranks, including ones we don't list.

Claude Opus 4 guides

Subscribe to our newsletter

News and updates, 1–2 emails per month. No spam.