BaseTen — pricing & performance
Models served
6
of 908 tracked models
Mean output speed
158
tokens per second, averaged over
5 measured endpoints
5 measured endpoints
Mean latency
0.7s
time to first token, averaged over
5 measured endpoints
5 measured endpoints
Cheapest blended
$0.20
per 1M tokens at a 3:1
input:output blend
input:output blend
Output speed on BaseTen
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.
5 of 6 models ▾
☰⚙⇩
+Add model from specific provider
The Known Good
6 models on BaseTen
Full leaderboard →
| Model | Creator | Input $/M | Output $/M | Blended | Speed | TTFT | Context |
|---|---|---|---|---|---|---|---|
DeepSeek: DeepSeek V4 Pro
|
DeepSeek | $1.74 | $3.48 | $2.17 | 110 | 0.7s | 262k |
MoonshotAI: Kimi K2.6
|
Moonshot AI | $0.95 | $4.00 | $1.71 | — | — | 262k |
NVIDIA: Nemotron 3 Ultra
|
NVIDIA | $0.60 | $2.40 | $1.05 | 176 | 0.4s | 203k |
OpenAI: gpt-oss-120b
|
OpenAI | $0.10 | $0.50 | $0.20 | 285 | 0.2s | 128k |
| TM Thinking Machines: Inkling | Thinking Machines | $1.00 | $4.05 | $1.76 | 101 | 0.4s | 1.05M |
Z.ai: GLM 5.2
|
Z.ai | $1.40 | $4.40 | $2.15 | 120 | 1.8s | 524k |
The Known Good
Source. Prices, endpoint availability and throughput for BaseTen 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.