gpt-oss-120b vs Granite 4.0 Micro: pricing comparison
Granite 4.0 Micro is the cheaper option at $0.02/$0.11 per 1M input/output tokens — gpt-oss-120b ($0.04/$0.17) costs about 2.2x more per input token. Full spec-by-spec breakdown below.
| gpt-oss-120b | Granite 4.0 Micro | |
|---|---|---|
| Input /1M tokens | $0.04 | $0.02 |
| Output /1M tokens | $0.17 | $0.11 |
| Cache read /1M | — | — |
| Context window | 131K | 131K |
| Provider | OpenAI | Ibm-granite |
| Vision input | No | No |
| Released | Aug 2025 | Oct 2025 |
Real workload costs: gpt-oss-120b vs Granite 4.0 Micro
Cost per single request at common token profiles — the cheapest model for each workload is highlighted.
| Workload | Tokens (in / out) | gpt-oss-120b | Granite 4.0 Micro |
|---|---|---|---|
| Chatbot message | 500 / 300 | <$0.0001 | <$0.0001 |
| RAG query with context | 4,000 / 500 | $0.0002 | $0.0001 |
| Document summarization | 20,000 / 1,000 | $0.0009 | $0.0005 |
| Agent coding session | 100,000 / 5,000 | $0.0046 | $0.0023 |
Frequently asked questions
Which is cheaper: gpt-oss-120b vs Granite 4.0 Micro?
Granite 4.0 Micro is the cheapest on input tokens at $0.02 per 1M, and Granite 4.0 Micro is cheapest on output at $0.11 per 1M. gpt-oss-120b costs about 2.2x more per input token than Granite 4.0 Micro.
How much does gpt-oss-120b cost per 1M tokens?
gpt-oss-120b costs $0.04 per 1M input tokens and $0.17 per 1M output tokens on the OpenAI API, with a 131K-token context window.
How much does Granite 4.0 Micro cost per 1M tokens?
Granite 4.0 Micro costs $0.02 per 1M input tokens and $0.11 per 1M output tokens on the Ibm-granite API, with a 131K-token context window.
What does a typical request cost on gpt-oss-120b vs Granite 4.0 Micro?
For a typical request with 2,000 input and 500 output tokens: gpt-oss-120b costs $0.0002, Granite 4.0 Micro costs <$0.0001. At 1,000 requests/day for a month that is $4.77 for gpt-oss-120b vs $2.70 for Granite 4.0 Micro.
Estimate your own workload with the per-model calculators (gpt-oss-120b, Granite 4.0 Micro), browse all current prices on the live model pricing dashboard, or run these models head-to-head on a real prompt (free account required). Prices may differ from provider list prices for batch or tiered usage.
Pricing data via the OpenRouter models API.