Skip to main content
Back to Explore

Claude Opus 5 (Adaptive Reasoning, Medium Effort)

Anthropic·Released 2026-07-24
Multimodal
Comparison data ready73% coverage12/12 fields directly observedUpdated Jul 24, 2026, 11:39 PM

Pricing

Input

$5.00

per 1M tokens

Output

$25.00

per 1M tokens

Blended

$10.00

per 1M tokens

Cheaper than 7% of models. Median price is $0.69/1M tokens.

Cost Calculator

Tokens per day1M
100K100M

Daily

$10.00

Monthly

$300.00

vs. Similar Models

GPT-5.6 Sol (high)Q:-0.4
$11.25+13%
Anthropic: Claude Opus 4.8Q:-0.6
$10.000%
MoonshotAI: Kimi K3Q:+0.8
$6.00-40%
OpenAI: GPT-5.6 TerraQ:-1.3
$5.63-44%

Performance

56

tokens/sec

Faster than 19% of models

9.66

seconds

Faster than 16% of models

9.66

seconds

Faster than 42% of models

Market Median

95 tok/s

42% slower

Median TTFT

1.19s

714% slower

Throughput/Dollar

6

tok/s per $/1M

Speed Comparison

Qwen2.5 Instruct 72B
56 tok/s-0%
Llama Nemotron Super 49B v1.5 (Non-reasoning)
56 tok/s+0%
xAI: Grok 4.5
56 tok/s+0%

Benchmarks

MMLU-ProNot evaluated
GPQA Diamond
91.9%
HLE
49.2%
LiveCodeBenchNot evaluated
SciCode
50.7%
TerminalBench HardNot evaluated
MATH-500Not evaluated
AIMENot evaluated
AIME 2025Not evaluated
IFBenchNot evaluated
Long Context Recall
69.0%
Tau2Not evaluated
Market AverageTop Score

Quick Compare

Similar Models

Compare all 7 models