← Hosted open-model inference
Cerebras
gpt-oss-120B (Cerebras)
Wafer-scale inference with very high token rates. Sample entry; the fetched pricing page showed no per-model table.
USD per 1M output tokens
$0.69
- input
- $0.25
- output
- $0.69
Unverified sample
#4 cheapest of 15 in Hosted open-model inference
Official pricing ↗Capabilities, explained
What this API can do, and what each capability means for your project.
Model
gpt-oss
Which open-weight model family is served.
Output speed
2,500 tok/s
How fast text is generated.
Precision
—
Numerical precision served. bf16 is the reference quality.
Context window
—
Context length offered by this host.
Price history
Only one price recorded so far. The chart appears once the price changes.