The Known Good Updated 25 Jul 2026
Providers· First-party endpoint· 14 tracked models

Anthropic — pricing & performance

Compare models All providers Data sources
Models served
14
of 908 tracked models
Mean output speed
54
tokens per second, averaged over
13 measured endpoints
Mean latency
2.0s
time to first token, averaged over
13 measured endpoints
Cheapest blended
$2.00
per 1M tokens at a 3:1
input:output blend
Output speed on Anthropic

Median output tokens per second for each model this host serves, derived from OpenRouter endpoint telemetry. Higher is better. We do not run these measurements ourselves.

12 of 14 models +Add model from specific provider
The Known Good
14 models on Anthropic
Full leaderboard →
Model Creator Input $/M Output $/M Blended Speed TTFT Context
Anthropic: Claude Fable 5 Anthropic $10.00 $50.00 $20.00 40 4.3s 1.00M
Anthropic: Claude Haiku 4.5 Anthropic $1.00 $5.00 $2.00 67 0.7s 200k
Anthropic: Claude Opus 4.1 Anthropic $15.00 $75.00 $30.00 26 1.8s 200k
Anthropic: Claude Opus 4.5 Anthropic $5.00 $25.00 $10.00 32 1.2s 200k
Anthropic: Claude Opus 4.6 Anthropic $5.00 $25.00 $10.00 37 1.8s 1.00M
Anthropic: Claude Opus 4.7 Anthropic $5.00 $25.00 $10.00 45 1.6s 1.00M
Anthropic: Claude Opus 4.7 (Fast) Anthropic $30.00 $150.00 $60.00 1.00M
Anthropic: Claude Opus 4.8 Anthropic $5.00 $25.00 $10.00 63 3.4s 1.00M
Anthropic: Claude Opus 4.8 (Fast) Anthropic $10.00 $50.00 $20.00 99 1.0s 1.00M
Anthropic: Claude Sonnet 4.5 Anthropic $3.00 $15.00 $6.00 44 1.6s 1.00M
Anthropic: Claude Sonnet 4.6 Anthropic $3.00 $15.00 $6.00 38 1.1s 1.00M
Anthropic: Claude Sonnet 5 Anthropic $2.00 $10.00 $4.00 63 2.2s 1.00M
Claude Opus 5 Anthropic $5.00 $25.00 $10.00 70 3.4s 1.00M
Claude Opus 5 (Fast) Anthropic $10.00 $50.00 $20.00 77 2.3s 1.00M
The Known Good
Source. Prices, endpoint availability and throughput for Anthropic are ingested from OpenRouter; model metadata is enriched from models.dev. A blank cell means the figure was not published for that endpoint — it never means zero. Blended price is (3 × input + output) ÷ 4, the same 3:1 blend used everywhere on this site; see methodology. Quality scores are not provider-specific: a model scores the same wherever it is hosted, so quality lives on the model pages.