OpenInference — pricing & performance
Models served
8
of 1,299 tracked models
Mean output speed
50
tokens per second, averaged over
8 measured endpoints
8 measured endpoints
Mean latency
0.9s
time to first token, averaged over
8 measured endpoints
8 measured endpoints
Cheapest blended
$0.000
per 1M tokens at a 3:1
input:output blend
input:output blend
Output speed on OpenInference
Output tokens per second for all 8 models on OpenInference with published throughput telemetry, the most recent figure OpenRouter publishes for each host. Higher is better. We do not run these measurements ourselves.
All 8 of 8 models⇩
The Known Good
8 models on OpenInference
Full leaderboard →
| Model | Creator | Input $/M | Output $/M | Blended | Speed | TTFT | Context |
|---|---|---|---|---|---|---|---|
DeepSeek: DeepSeek V4 Flash 0423
|
DeepSeek | $0.040 | $0.14 | $0.064 | 12 | 1.4s | 1.05M |
|
DeepSeek: DeepSeek V4 Flash 0731
|
DeepSeek | $0.015 | $0.14 | $0.046 | 20 | 1.5s | 1.05M |
|
DeepSeek: DeepSeek V4 Flash 0731 (free)
|
DeepSeek | $0.000 | $0.000 | $0.000 | 32 | 1.2s | 1.05M |
|
DeepSeek: DeepSeek V4.1 Flash
|
DeepSeek | $0.020 | $1.00 | $0.27 | 68 | 0.7s | 1.05M |
|
DeepSeek: DeepSeek V4.1 Flash 1017
|
DeepSeek | $0.020 | $1.00 | $0.27 | 59 | 0.8s | 1.05M |
Google: Gemma 4 31B
|
$0.070 | $0.35 | $0.14 | 50 | 0.4s | 262k | |
Z.ai: GLM 5.3
|
Z.ai | $0.040 | $3.21 | $0.83 | 79 | 0.5s | 1.05M |
|
Z.ai: GLM 5.3 Flash
|
Z.ai | $0.032 | $0.30 | $0.099 | 82 | 0.6s | 1.05M |
The Known Good
Source. Prices, endpoint availability and throughput for OpenInference 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.