The Known Good Updated 9 Sep 2026 Subscribe
Providers· Inference host· 9 tracked models

Claude Platform on AWS — pricing & performance

Compare models All providers Data sources
Models served
9
of 1,111 tracked models
Mean output speed
47
tokens per second, averaged over
9 measured endpoints
Mean latency
3.2s
time to first token, averaged over
9 measured endpoints
Cheapest blended
$4.00
per 1M tokens at a 3:1
input:output blend
Output speed on Claude Platform on AWS

Output tokens per second for all 9 models on Claude Platform on AWS with published throughput telemetry, the most recent figure OpenRouter publishes for each host. Higher is better. We do not run these measurements ourselves.

All 9 of 9 models⇩
70
52
52
49
48
45
39
35
33
The Known Good
9 models on Claude Platform on AWS
Full leaderboard →
Model Creator Input $/M Output $/M Blended Speed TTFT Context
Anthropic: Claude Fable 5 Anthropic $10.00 $50.00 $20.00 48 8.3s 1.00M
Anthropic: Claude Opus 4.5 Anthropic $5.00 $25.00 $10.00 70 1.8s 200k
Anthropic: Claude Opus 4.6 Anthropic $5.00 $25.00 $10.00 35 1.8s 1.00M
Anthropic: Claude Opus 4.7 Anthropic $5.00 $25.00 $10.00 45 1.6s 1.00M
Anthropic: Claude Opus 4.8 Anthropic $5.00 $25.00 $10.00 52 1.8s 1.00M
Anthropic: Claude Sonnet 4.5 Anthropic $3.00 $15.00 $6.00 33 1.6s 1.00M
Anthropic: Claude Sonnet 4.6 Anthropic $3.00 $15.00 $6.00 39 1.2s 1.00M
Anthropic: Claude Sonnet 5 Anthropic $2.00 $10.00 $4.00 49 5.3s 1.00M
Claude Opus 5 Anthropic $5.00 $25.00 $10.00 52 5.7s 1.00M
The Known Good
Source. Prices, endpoint availability and throughput for Claude Platform on AWS 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.