Inference providers · open weights · OpenAI
gpt-oss-120b
Open-weights model published by OpenAI; the API prices below are set by the 3 hosts that serve it, not by OpenAI. There is no maker's list price to compare with: OpenAI publishes the weights, not a per-token rate. Each figure was read on that host's own pricing page and links to it, with the date it was checked.
What each host charges
3 hosts, every one of them at $0.15 per 1M input tokens and $0.60 per 1M output tokens: no spread at all, within the 1.15× that this site treats as the same price. Pick a host on latency, region or tooling; the bill will be the same.
| Host | Input | Output | Cached input | Context served | Checked | Source |
|---|---|---|---|---|---|---|
| Together AI | $0.15 | $0.60 | — | 131K tokens | October 1, 2026 | docs.together.ai |
| Fireworks AI | $0.15 | $0.60 | — | 131K tokens | October 1, 2026 | docs.fireworks.ai |
| Groq | $0.15 | $0.60 | — | 131K tokens | September 30, 2026 | console.groq.com |
Hosts that no longer price it
Offerings this site tracked and stopped listing, with the date and the reason. They are kept because nobody else records when a host drops a model.
- DeepInfra removed September 6, 2026 · last listed at $0.037 in · $0.17 out Not listed on the official DeepInfra pricing page; previous figure came from OpenRouter.
Recorded price changes
Every change this site has recorded for a host's price of gpt-oss-120b, with the date it took or takes effect and why. Changes of our own rule are listed too, and say so.
-
September 1, 2026 · Fireworks AI (all models on this host) · price up 1.5×
Since September 1, 2026 Fireworks adds a 50% surcharge to the base price of the Serverless models it marks as US-only. The Fireworks prices on this site are the base prices, without the surcharge.
On OpenRouter
On September 15, 2026 OpenRouter listed 24 endpoints for gpt-oss-120b, 18 of them healthy, from $0.03 (AkashML) to $0.35 per 1M input tokens. The figure OpenRouter's catalog shows for the model, $0.037 / $0.17 (DeepInfra), is the 4th cheapest of those 24. None of them is OpenAI: all are resellers, which is why this site shows no OpenRouter price for the model. Together AI and Groq, priced above from their own pages, are among them. DeepInfra, which this site stopped listing on September 6, 2026 because its own pricing page carries no price for the model, serves it 3 times through OpenRouter; that is a reseller listing, not a published price, so the row stays out.
Why the catalog figure is not what a request pays →
Specifications
| Weights published by | OpenAI |
|---|---|
| Context length (maker) | 131K tokens |
| Context served by hosts | 131K tokens |
| API model ids | Together AI: openai/gpt-oss-120b; Fireworks AI: gpt-oss-120b; Groq: openai/gpt-oss-120b |
| Hosts with a verified price | 3 |
Host prices verified between September 30, 2026 and October 1, 2026, each on the host's own pricing page linked in the table above, never from a reseller catalog or a third-party table. Maker and context length from OpenAI's model card, checked September 15, 2026 (max_position_embeddings 131072 in the model's config.json). How the data is checked.
Every open model, every host, one table →
When comparing hosts is worth it, and when it is not →