Anthropic — pricing & performance
Models served
24
of 947 tracked models
Mean output speed
57
tokens per second, averaged over
13 measured endpoints
13 measured endpoints
Mean latency
2.2s
time to first token, averaged over
13 measured endpoints
13 measured endpoints
Cheapest blended
$1.00
per 1M tokens at a 3:1
input:output blend
input:output blend
Output speed on Anthropic
Median output tokens per second for the 13 of 24 models on Anthropic with published throughput telemetry from OpenRouter. The full table below lists all 24, measured or not. Higher is better. We do not run these measurements ourselves.
The Known Good
24 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 | 36 | 5.2s | 1.00M |
|
Anthropic: Claude Fable 5 (batch)
|
Anthropic | $5.00 | $25.00 | $10.00 | — | — | 1.00M |
|
Anthropic: Claude Haiku 4.5
|
Anthropic | $1.00 | $5.00 | $2.00 | 76 | 0.7s | 200k |
|
Anthropic: Claude Haiku 4.5 (batch)
|
Anthropic | $0.50 | $2.50 | $1.00 | — | — | 200k |
|
Anthropic: Claude Opus 4.1
|
Anthropic | $15.00 | $75.00 | $30.00 | 21 | 2.1s | 200k |
|
Anthropic: Claude Opus 4.1 (batch)
|
Anthropic | $7.50 | $37.50 | $15.00 | — | — | 200k |
|
Anthropic: Claude Opus 4.5
|
Anthropic | $5.00 | $25.00 | $10.00 | 35 | 1.2s | 200k |
|
Anthropic: Claude Opus 4.5 (batch)
|
Anthropic | $2.50 | $12.50 | $5.00 | — | — | 200k |
|
Anthropic: Claude Opus 4.6
|
Anthropic | $5.00 | $25.00 | $10.00 | 31 | 2.5s | 1.00M |
|
Anthropic: Claude Opus 4.6 (batch)
|
Anthropic | $2.50 | $12.50 | $5.00 | — | — | 1.00M |
|
Anthropic: Claude Opus 4.7
|
Anthropic | $5.00 | $25.00 | $10.00 | 44 | 1.8s | 1.00M |
|
Anthropic: Claude Opus 4.7 (batch)
|
Anthropic | $2.50 | $12.50 | $5.00 | — | — | 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 | 62 | 1.5s | 1.00M |
|
Anthropic: Claude Opus 4.8 (batch)
|
Anthropic | $2.50 | $12.50 | $5.00 | — | — | 1.00M |
|
Anthropic: Claude Opus 4.8 (Fast)
|
Anthropic | $10.00 | $50.00 | $20.00 | 144 | 2.6s | 1.00M |
|
Anthropic: Claude Sonnet 4.5
|
Anthropic | $3.00 | $15.00 | $6.00 | 37 | 1.3s | 1.00M |
|
Anthropic: Claude Sonnet 4.5 (batch)
|
Anthropic | $1.50 | $7.50 | $3.00 | — | — | 1.00M |
|
Anthropic: Claude Sonnet 4.6
|
Anthropic | $3.00 | $15.00 | $6.00 | 38 | 1.5s | 1.00M |
|
Anthropic: Claude Sonnet 5
|
Anthropic | $2.00 | $10.00 | $4.00 | 54 | 2.7s | 1.00M |
|
Anthropic: Claude Sonnet 5 (batch)
|
Anthropic | $1.00 | $5.00 | $2.00 | — | — | 1.00M |
|
Claude Opus 5
|
Anthropic | $5.00 | $25.00 | $10.00 | 56 | 2.6s | 1.00M |
|
Claude Opus 5 (batch)
|
Anthropic | $2.50 | $12.50 | $5.00 | — | — | 1.00M |
|
Claude Opus 5 (Fast)
|
Anthropic | $10.00 | $50.00 | $20.00 | 111 | 2.8s | 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.