Text model
gpt-oss-120b pricing
Cerebras charges $0.35 per million input tokens and $0.75 per million output tokens for gpt-oss-120b. Below: every rate that applies, what common workloads cost, and cheaper options.
- Input
- $0.35/ 1M
- Output
- $0.75/ 1M
- Context
- 131.1Ktokens
All rates
| Tier | Input | Output | Cache read | Cache write |
|---|---|---|---|---|
| Standard | $0.35 | $0.75 | — | — |
USD per million tokens. Long-context tiers apply when the whole prompt, cached tokens included, passes the threshold.
Work it out
What common workloads cost
| Workload | Per call | Cost per call | Calls a month | Per month |
|---|---|---|---|---|
| Chat reply | 1,500 input and 400 output tokens | $0.000825 | 100,000 | $82.50 |
| RAG answer, cached context | 2,000 fresh + 4,000 cached input, 500 output | $0.00248 | 100,000 | $247.50 |
| Agent step | 4,000 fresh + 8,000 cached input, 800 output | $0.0048 | 250,000 | $1,200.00 |
| Batch summary | 3,000 input and 300 output tokens via the Batch API | — | 1,000,000 | — |
Planning a mix of models? Simulate a workload with gpt-oss-120b, alongside anything else you run.
Cheaper options
Current models that cost at least 15% less for a typical chat reply. Cheaper isn't always equivalent: test quality on your own prompts, then use veqen diff to see the impact at your volume.
| Model | Chat reply | Saving |
|---|---|---|
| cerebras/llama3.1-8b | $0.00019 | 77% |
| novita/qwen/qwen3-vl-30b-a3b-thinking | $0.0007 | 15% |
| bedrock/qwen.qwen3-235b-a22b-2507-v1:0 | $0.000682 | 17% |
Price history
No price changes since Veqen started tracking this model.
Compare
- gpt-5 vs gpt-oss-120b
- gpt-5-mini vs gpt-oss-120b
- gpt-5.2 vs gpt-oss-120b
- gpt-4o vs gpt-oss-120b
- gpt-4o-mini vs gpt-oss-120b
- gpt-4.1 vs gpt-oss-120b
Last verified with price book 2026-10-22. Sources: Cerebras pricing and LiteLLM's MIT-licensed price file. Track every call to this model, per customer or project: install the SDK.