Providers / Novita AI / OpenAI GPT OSS 120B
OpenAI GPT OSS 120B API Cost Calculator
OpenAI GPT OSS 120B costs $0.05 per 1M input tokens and $0.25 per 1M output tokens at Novita AI's gateway (reseller) price — not the model maker's official price — verified 2026-10-25. Estimate your own usage below — the calculator is preset to this model.
Calculate your OpenAI GPT OSS 120B cost →Paste text to count tokens instead
Cost per call
—
Estimated monthly cost
—
Official price vs gateway price
| Where | Input / 1M | Output / 1M |
|---|---|---|
| Novita AI (gateway, affiliate link) | $0.05 | $0.25 |
| OpenAI (open-weight) official API | No official price we could verify — not shown, never estimated | |
OpenAI GPT OSS 120B is an open-weight model; the Novita price is Novita AI's public gateway rate (source), not an official price from the model's maker. The Novita link is an affiliate link: we may earn a commission at no extra cost to you, and it does not affect rankings, which are sorted by price only.Disclosure.
OpenAI GPT OSS 120B price facts
| Input | $0.05 per 1M tokens |
|---|---|
| Output | $0.25 per 1M tokens |
| Cached input | Not published per 1M tokens |
| Batch tier | Not published |
| Context window | 128,000 tokens |
| Released | — |
| Price verified | 2026-10-25 · source |
What OpenAI GPT OSS 120B costs in practice
| Workload | Per call | Per month |
|---|---|---|
| Chat assistant 2,000 input / 500 output tokens per call, 10,000 calls a month | $0.000225 | $2.25 |
| Document processing 50,000 input / 2,000 output tokens per call, 1,000 calls a month | $0.003 | $3.00 |
| Agent loop with prompt caching 10,000 fresh input / 100,000 cached input / 2,000 output tokens per call, 500 calls a month | $0.001 | $0.5 |
Note: this provider has not published a cached-input rate for this model in our sources, so the caching workload above bills cached tokens at $0 in the breakdown — check the provider before budgeting a caching-heavy workload.
Frequently asked questions
How much does OpenAI GPT OSS 120B cost per month?
It depends entirely on token volume. As worked examples: a chat assistant doing 10,000 calls a month costs $2.25, while a document pipeline doing 1,000 long calls costs $3.00. Use the calculator on this page with your own numbers for an exact figure. Prices are gateway (reseller) rates verified 2026-10-25.
Is OpenAI GPT OSS 120B cheaper than OpenAI GPT OSS 20B?
At a blended workload of 1M input and 250K output tokens, OpenAI GPT OSS 120B costs $0.1125 and OpenAI GPT OSS 20B costs $0.0775 — so OpenAI GPT OSS 20B is cheaper at this mix. The answer can flip if your workload is mostly output or mostly cached input.
Does OpenAI GPT OSS 120B have batch or caching discounts?
No published batch rate in our sources. No published cached-input rate in our sources. Prices verified 2026-10-25. We do not invent unpublished rates.
Are these official prices or gateway prices?
OpenAI GPT OSS 120B on this page uses Novita AI's gateway (reseller) price, labeled as such — not the model maker's official API price. Affiliate disclosures (when any) never change the listed rate or sort order.
Related
Related models
Closest in cost for 1M input + 250K output tokens (standard tier), listed by price.
- Claude Haiku 5.5 — $0.1 / $0.5 per 1M tokens ($0.225 for that workload)
- GPT-6 Luna — $0.1 / $0.5 per 1M tokens ($0.225 for that workload)
- GPT-4o Mini — $0.15 / $0.6 per 1M tokens ($0.3 for that workload)
- GPT-5.6 Luna — $0.2 / $1.2 per 1M tokens ($0.5 for that workload)