Inference providers · open weights · OpenAI

gpt-oss-120b

Open-weights model published by OpenAI; the API prices below are set by the 5 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

5 hosts, from $0.05 (Novita AI) to $0.15 (Fireworks AI, Groq and Together AI) per 1M input tokens: a 3.0× spread. Above the 1.15× line AI Signal draws, so the choice of host is a price decision.

Host Input Output Cached input Context served Checked Source
Novita AI $0.05 $0.25 — 131K tokens November 16, 2026 novita.ai
Baseten $0.10 $0.50 — — November 16, 2026 baseten.co
Together AI $0.15 $0.60 — 131K tokens November 16, 2026 docs.together.ai
Fireworks AI $0.15 $0.60 $0.015 131K tokens November 16, 2026 docs.fireworks.ai
Groq $0.15 $0.60 $0.075 131K tokens November 16, 2026 console.groq.com

Novita AI charges $0.05 per 1M input tokens and Fireworks AI, Groq and Together AI $0.15 for the same weights; on output, $0.25 against $0.60.

Hosts that no longer price it

Offerings AI Signal tracked and stopped listing, with the date and the reason. They are kept because nobody else records when a host drops a model.

Mentioned in

4 posts on AI Signal cite gpt-oss-120b. The sentence is the post's own, taken from where it links here.

Recorded price changes

Every change AI Signal 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.

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 AI Signal shows no OpenRouter price for the model. Novita AI, Baseten, Together AI and Groq, priced above from their own pages, are among them. DeepInfra, which AI Signal 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.

From OpenAI's model card

Specifications

Weights published by OpenAI
Context length (maker) 131K tokens
Context served by hosts 131K tokens
API model ids Novita AI: openai/gpt-oss-120b; Baseten: openai/gpt-oss-120b; Together AI: openai/gpt-oss-120b; Fireworks AI: gpt-oss-120b; Groq: openai/gpt-oss-120b
Hosts with a verified price 5

Host prices verified on November 16, 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.