GPT OSS 20B pricing, context window and limits
GPT OSS 20B costs $0.075 per million input tokens and $0.3 per million output tokens at Groq list price. It accepts up to 131,072 tokens of context and returns up to 65,536 tokens.
- Model id
groq/openai/gpt-oss-20b - Snapshot
What does GPT OSS 20B cost?
| Input | $0.075 |
|---|---|
| Output | $0.3 |
| Cached input (read) | $0.0375 |
| Cache write | — |
US dollars per million tokens. A dash means no price is published.
How much can GPT OSS 20B read and write?
| Context window | 131,072 |
|---|---|
| Max output | 65,536 |
What can GPT OSS 20B do?
| Vision (image input) | No |
|---|---|
| Tool calling | Yes |
| Structured output | Yes |
| Reasoning | Yes |
| Input | text |
| Output | text |
What does a request to GPT OSS 20B cost?
| A typical request: 1,000 tokens in, 500 out | $0.00022 |
|---|---|
| A long request: 10,000 tokens in, 1,000 out | $0.001 |
| 1,000 typical requests | $0.23 |
| 1 million tokens in and 1 million out | $0.38 |
Input read from the provider's prompt cache costs $0.0375 per million tokens instead of $0.075, 50% less. A request that repeats a 1,000-token prompt from the cache costs $0.00019 instead of $0.00022.
Among 10 Groq models with a published price, GPT OSS 20B is the 5th cheapest by input price. Its context window is the largest of 14. List prices only; discounts, batch prices and prices above 200K tokens are not shown.
How do I call GPT OSS 20B through DVARA?
Configure the groq provider in the DVARA LLM Gateway and send the model id groq/openai/gpt-oss-20b. DVARA, the AI gateway, applies your policies, audit and cost attribution to the call. See LLM cost attribution and budgets.
In DVARA, if you haven't set your own price for a model, its calls are costed at the price in the catalogue that ships with your DVARA version. A price you set in Flightdeck always wins. You can switch catalogue prices off. Then a model with no price you set gets no cost record: its calls count against no budget and appear in no report, and the gateway records the model as unpriced. Every cost record says which price it used.
Which other Groq models are there?
- GPT OSS 120B$0.15 in · $0.6 out · 131K context
- Safety GPT OSS 20B$0.075 in · $0.3 out · 131K context
- Prompt Guard 2 86M$0.04 in · $0.04 out · 512 context
- Qwen3.6 27B$0.6 in · $3 out · 131K context
- Llama Prompt Guard 2 22M$0.03 in · $0.03 out · 512 context
- Qwen3.8 27B$0.8 in · $4 out · 131K context
- Llama 3.3 70B$0.59 in · $0.79 out · 131K context
- Whisper— in · — out · — context
- Llama 3.1 8B$0.05 in · $0.08 out · 131K context
- Whisper Large V3 Turbo— in · — out · — context
- Compound Mini— in · — out · 131K context
- Compound— in · — out · 131K context
Which models from other providers are similar to GPT OSS 20B?
These are the closest in context window and input price, one per provider.
- Qwen2.5 7B InstructAlibaba Qwen · $0.072 in · $0.144 out · 131K context
- gpt-oss-20bAmazon Bedrock · $0.07 in · $0.3 out · 131K context
- Ministral 3 3BMistral AI · $0.1 in · $0.1 out · 131K context
- GLM-4.7-FlashXZhipu GLM · $0.07 in · $0.4 out · 200K context
- Command RCohere · $0.15 in · $0.6 out · 128K context