A rate per million tokens is not a budget. The calculator takes your request volume, prompt size and cache hit rate and gives you a monthly figure.
GPT-OSS 20B (Groq) API pricing (October 2026)
API name openai/gpt-oss-20b. Batch requests bill at the 50% batch rate whether or not they hit the cache.
What it costs at real volumes
A chat-shaped workload: 800 input tokens and 300 output tokens per request, no caching, no batch.
Specifications
- Provider
- Groq
- Context window
- 131K tokens
- Max output
- 66K tokens
- Tier
- small
- Status
- GA
- Blended $/1M (3:1)
- $0.131
- Cache break-even hit rate
- 0%, caching always saves
- Prices verified
- 12 Oct 2026
Source: Groq pricing. Finitizer is not affiliated with Groq.
Similar models
Other gpt-oss models
- GPT-OSS 120B (Groq)+$0.131
Closest prices elsewhere
- GPT-5 nano+$0.00625
- Amazon Nova Lite-$0.026
- GPT-4.1 nano+$0.044
- Gemini 2.5 Flash-Lite+$0.044
Frequently asked questions
How much does GPT-OSS 20B (Groq) cost per 1M tokens?
GPT-OSS 20B (Groq) costs $0.075 per million input tokens and $0.300 per million output tokens at Groq list prices. Output is 4.0x the input rate, so the input:output ratio of your workload drives the real cost more than the headline price.
Does GPT-OSS 20B (Groq) support prompt caching?
Yes. Cached input is billed at $0.037 per million tokens, 2x cheaper than uncached input. There is no cache-write premium, so caching is never a net loss.
What is the batch discount for GPT-OSS 20B (Groq)?
Requests submitted through the asynchronous batch endpoint are billed at 50% off both input and output rates, bringing input to $0.037 and output to $0.150 per million tokens.
What is GPT-OSS 20B (Groq)'s context window?
131K tokens of context with up to 66K output tokens per request. A larger context window raises the ceiling on what you can send, not the price per token, but filling it on every request is one of the most common causes of an unexpected bill.
Running GPT-OSS 20B (Groq) in production?
Finitizer Tokenomics reads what this model actually costs you from your own bills and exports, shows which workload, team or API key is spending it, flags a spike or a new spend source the day your data shows it, and forecasts where the month will land.
See how Finitizer works