Text model
openai/gpt-oss-120b pricing
IBM watsonx charges $0.159 per million input tokens and $0.636 per million output tokens for openai/gpt-oss-120b. Below: every rate that applies, what common workloads cost, and cheaper options.
- Input
- $0.159/ 1M
- Output
- $0.636/ 1M
- Context
- 131.1Ktokens
All rates
| Tier | Input | Output | Cache read | Cache write |
|---|---|---|---|---|
| Standard | $0.159 | $0.636 | — | — |
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 | $0.000493 | 100,000 | $49.29 |
| RAG answer, cached context | 2,000 fresh + 4,000 cached input, 500 output | $0.00127 | 100,000 | $127.20 |
| Agent step | 4,000 fresh + 8,000 cached input, 800 output | $0.00242 | 250,000 | $604.20 |
| 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 openai/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 |
|---|---|---|
| watsonx/mistralai/mistral-small-3-1-24b-instruct-2503 | $0.000286 | 42% |
| watsonx/meta-llama/llama-3-2-3b-instruct | $0.000285 | 42% |
| qwen/qwen3.8-flash | $0.000413 | 16% |
| qwen/qwen3.8-omni-flash | $0.000413 | 16% |
Price history
No price changes since Veqen started tracking this model.
Compare
Last verified with price book 2026-10-22. Sources: IBM watsonx pricing and LiteLLM's MIT-licensed price file. Track every call to this model, per customer or project: install the SDK.