GPT-OSS 20B
$0.075
Input / MTok
$0.3
Output / MTok
Hosted third-party inference; price is Groq's serverless rate, not OpenAI's own API.
API identifier openai/gpt-oss-20b · Context 131,072 tokens · Max output 65,536
· vendor pricing page
Full price sheet
| Metric | USD / million tokens |
|---|---|
| Input | $0.075 |
| Output | $0.3 |
Price history
| Observed | Metric | Price |
|---|---|---|
| 2026-08-07 19:44:55 | Input | $0.075 |
| 2026-08-07 19:44:55 | Output | $0.3 |
Current prices are free and always will be. The full series — every observation since we started watching, which nobody can reconstruct after the fact — is the part Pro pays for.
Changes affecting this model
coverage
GPT-OSS 20B added to coverage
—
2026-08-07Compare with
Models at a similar price point.
| Model | Input | Output | |
|---|---|---|---|
| DeepSeek V4 Flash | $0.14 | $0.28 | compare → |
| DeepSeek V4 Flash (0731) | $0.14 | $0.28 | compare → |
| Devstral Small 2 | $0.1 | $0.3 | compare → |
| Qwen3.5 9B | $0.17 | $0.25 | compare → |
| Ministral 3 14B | $0.2 | $0.2 | compare → |
| Qwen2.5 7B Instruct Turbo | $0.3 | $0.3 | compare → |