SambaNova — pricing & performance
Models served
6
of 947 tracked models
Mean output speed
142
tokens per second, averaged over
6 measured endpoints
6 measured endpoints
Mean latency
1.5s
time to first token, averaged over
6 measured endpoints
6 measured endpoints
Cheapest blended
$0.34
per 1M tokens at a 3:1
input:output blend
input:output blend
Output speed on SambaNova
Median output tokens per second for all 6 models on SambaNova with published throughput telemetry from OpenRouter. Higher is better. We do not run these measurements ourselves.
All 6 of 6 models⇩
The Known Good
6 models on SambaNova
Full leaderboard →
| Model | Creator | Input $/M | Output $/M | Blended | Speed | TTFT | Context |
|---|---|---|---|---|---|---|---|
DeepSeek: DeepSeek V3.1
|
DeepSeek | $0.65 | $1.50 | $0.86 | 57 | 0.8s | 131k |
|
DeepSeek: DeepSeek V3.2
|
DeepSeek | $3.00 | $4.50 | $3.38 | 23 | 2.3s | 33k |
Google: Gemma 4 31B
|
$0.38 | $1.15 | $0.57 | 115 | 3.0s | 131k | |
Meta: Llama 3.3 70B Instruct
|
Meta | $0.45 | $0.90 | $0.56 | 65 | 0.7s | 16k |
MiniMax: MiniMax M2.7
|
MiniMax | $0.30 | $1.50 | $0.60 | 227 | 1.3s | 197k |
OpenAI: gpt-oss-120b
|
OpenAI | $0.14 | $0.95 | $0.34 | 367 | 1.1s | 131k |
The Known Good
Source. Prices, endpoint availability and throughput for SambaNova 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.