Groq pricing
GPT-OSS 120B (Groq) pricing
GPT-OSS 120B (Groq) bills per million tokens, metered separately for input and output. The current rates are below, along with the parts of the bill a per-token estimate leaves out.
GPT-OSS 120B (Groq) rates in full
All figures are USD per million tokens, taken from Groq’s own pricing documentation. The API model identifier is openai/gpt-oss-120b.
| Per million tokens | Standard |
|---|---|
| Input | $0.15 |
| Output | $0.60 |
Context window: 131.072K tokens, with up to 65.536K tokens of output per request.
What the rate table does not tell you
Groq describes GPT-OSS 120B as “OpenAI's flagship open-weight language model,” running at roughly 500 tokens/sec on Groq's LPU hardware.
Includes built-in browser search and code execution tool support.
A worked monthly example
Take 500,000 calls in a month at 3,000 input tokens and 400 output tokens each. That is 1.5 billion input tokens against 200 million output tokens, so input is 88% of the token volume.
| Line | Tokens | Rate | Cost |
|---|---|---|---|
| Input | 1,500M | $0.15 | $225 |
| Output | 200M | $0.60 | $120 |
| Total | 1,700M | $345 |
Output is 12% of the tokens and 35% of the bill. That inversion is why prompt trimming so often fails to move the invoice, and it is the single most common reason a forecast built on GPT-OSS 120B (Groq) comes in under the real number.
How this page stays current
The rate on this page was read off Groq’s published pricing and recorded with the date it was checked, September 16, 2026. The date changes only when someone checks again, not on each deploy. This model is also in the live model catalog Spendline uses to price API traffic, and our automated checks compare the two and fail if they disagree. At the last build the catalog agreed: $0.15 input and $0.60 output.
Frequently asked questions
How much does the GPT-OSS 120B (Groq) API cost?
GPT-OSS 120B (Groq) is billed per million tokens, metered separately for input and output. As of September 16, 2026 the rate is $0.15 per million input tokens and $0.60 per million output tokens.
Why is my GPT-OSS 120B (Groq) bill higher than the per-token estimate?
Most estimates multiply expected tokens by the input rate and stop there. Output is priced at $0.60 against $0.15 for input, so responses usually dominate the bill even when prompts look larger. Reasoning tokens bill as output. Retries and agent fan-out pay full input cost for calls that produced nothing. And a cache that gets written but never read is pure overhead rather than a saving.
What is the cheapest way to run GPT-OSS 120B (Groq)?
The larger lever is usually routing: sending the requests that do not need this tier to a cheaper model, and capping spend per customer before the call goes out.
How do I track GPT-OSS 120B (Groq) spend per customer or per feature?
Provider reports group usage by model, project or API key. Your application supplies the customer and workflow context needed to see cost per account. That means passing the customer, team or agent with each request from your server and recording the resolved cost against it. Spendline does this for supported requests routed through it, and checks configured budgets before forwarding them. Actual response cost can differ from the pre-call estimate.
See cost per customer, not just per token
A rate card tells you what a token costs. It does not tell you which customer, team or agent spent it. Spendline records attributed cost for supported requests routed through it and checks configured budgets before forwarding them.
Book a 30-minute call Explore a sample account