DeepSeek — pricing & performance
Models served
5
of 1,094 tracked models
Mean output speed
63
tokens per second, averaged over
5 measured endpoints
5 measured endpoints
Mean latency
1.0s
time to first token, averaged over
5 measured endpoints
5 measured endpoints
Cheapest blended
$0.33
per 1M tokens at a 3:1
input:output blend
input:output blend
Output speed on DeepSeek
Output tokens per second for all 5 models on DeepSeek with published throughput telemetry, the most recent figure OpenRouter publishes for each host. Higher is better. We do not run these measurements ourselves.
All 5 of 5 models⇩
The Known Good
5 models on DeepSeek
Full leaderboard →
| Model | Creator | Input $/M | Output $/M | Blended | Speed | TTFT | Context |
|---|---|---|---|---|---|---|---|
DeepSeek: DeepSeek V4 Flash 0423
|
DeepSeek | $0.22 | $0.66 | $0.33 | 88 | 0.8s | 1.05M |
|
DeepSeek: DeepSeek V4 Flash 0731
|
DeepSeek | $0.44 | $1.32 | $0.66 | 80 | 0.8s | 1.05M |
|
DeepSeek: DeepSeek V4 Flash Vision Exp
|
DeepSeek | $0.44 | $1.32 | $0.66 | 90 | 1.3s | 1.05M |
|
DeepSeek: DeepSeek V4 Pro 0423
|
DeepSeek | $0.66 | $1.98 | $0.99 | 31 | 1.3s | 1.05M |
|
DeepSeek: DeepSeek V4 Pro 0813
|
DeepSeek | $1.32 | $3.96 | $1.98 | 25 | 1.1s | 1.05M |
The Known Good
Source. Prices, endpoint availability and throughput for DeepSeek 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.