Cerebras — pricing & performance
Models served
3
of 947 tracked models
Mean output speed
280
tokens per second, averaged over
3 measured endpoints
3 measured endpoints
Mean latency
0.3s
time to first token, averaged over
3 measured endpoints
3 measured endpoints
Cheapest blended
$0.45
per 1M tokens at a 3:1
input:output blend
input:output blend
Output speed on Cerebras
Median output tokens per second for all 3 models on Cerebras with published throughput telemetry from OpenRouter. Higher is better. We do not run these measurements ourselves.
All 3 of 3 models⇩
The Known Good
3 models on Cerebras
Full leaderboard →
| Model | Creator | Input $/M | Output $/M | Blended | Speed | TTFT | Context |
|---|---|---|---|---|---|---|---|
Google: Gemma 4 31B
|
$0.99 | $1.49 | $1.11 | 29 | 0.3s | 131k | |
OpenAI: gpt-oss-120b
|
OpenAI | $0.35 | $0.75 | $0.45 | 501 | 0.2s | 131k |
Z.ai: GLM 4.7
|
Z.ai | $2.25 | $2.75 | $2.38 | 310 | 0.3s | 131k |
The Known Good
Source. Prices, endpoint availability and throughput for Cerebras 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.