Back to models
retired
OpenAI: gpt-oss-20b
openai/gpt-oss-20bPrices
- Input
$0.07 per 1M tokens
low- Output
$0.30 per 1M tokens
low
Also available on
The same model, sold by someone else. The price above is the maker's own.
| Channel | What | Price |
|---|---|---|
| Amazon Bedrock | Input | $0.07 per 1M tokens |
| Input (batch) (region: us-gov-east-1) | $0.042 per 1M tokens | |
| Input (batch) (region: us-gov-west-1) | $0.042 per 1M tokens | |
| Input (flex) (region: us-gov-east-1) | $0.042 per 1M tokens | |
| Input (flex) (region: us-gov-west-1) | $0.042 per 1M tokens | |
| Input (priority) (region: us-gov-east-1) | $0.147 per 1M tokens | |
| Input (priority) (region: us-gov-west-1) | $0.147 per 1M tokens | |
| Input (region: us-gov-east-1) | $0.084 per 1M tokens | |
| Input (region: us-gov-west-1) | $0.084 per 1M tokens | |
| Output | $0.30 per 1M tokens | |
| Output (batch) (region: us-gov-east-1) | $0.18 per 1M tokens | |
| Output (batch) (region: us-gov-west-1) | $0.18 per 1M tokens | |
| Output (flex) (region: us-gov-east-1) | $0.18 per 1M tokens | |
| Output (flex) (region: us-gov-west-1) | $0.18 per 1M tokens | |
| Output (priority) (region: us-gov-east-1) | $0.63 per 1M tokens | |
| Output (priority) (region: us-gov-west-1) | $0.63 per 1M tokens | |
| Output (region: us-gov-east-1) | $0.36 per 1M tokens | |
| Output (region: us-gov-west-1) | $0.36 per 1M tokens | |
| Databricks | Input | $0.07 per 1M tokens |
| Input (cache write) | $0.07 per 1M tokens | |
| Input (cache write) (region: eu) | $0.07 per 1M tokens | |
| Input (cached read) | $0.007 per 1M tokens | |
| Input (cached read) (region: eu) | $0.007 per 1M tokens | |
| Input (region: eu) | $0.07 per 1M tokens | |
| Output | $0.30 per 1M tokens | |
| Output (region: eu) | $0.30 per 1M tokens | |
| Cloudflare Workers AI | Input | $0.20 per 1M tokens |
| Output | $0.30 per 1M tokens | |
| Fireworks AI · fireworks-ai | Input | $0.07 per 1M tokens |
| Input (cached read) | $0.035 per 1M tokens | |
| Output | $0.30 per 1M tokens | |
| Fireworks AI · impossibl | Input | $0.07 per 1M tokens |
| Input (cached read) | $0.035 per 1M tokens | |
| Output | $0.30 per 1M tokens | |
| OpenRouter · openai | Input | $0.03 per 1M tokens |
| Input (cached read) | $0.03 per 1M tokens | |
| Output | $0.13 per 1M tokens | |
| OpenRouter | Input | $0.075 per 1M tokens |
| Input (cached read) | $0.0375 per 1M tokens | |
| Output | $0.30 per 1M tokens | |
| Other · aimlapi | Input | $0.0794 per 1M tokens |
| Input (cached read) | $0.0397 per 1M tokens | |
| Output | $0.3174 per 1M tokens | |
| Other · cortecs | Input | $0.045 per 1M tokens |
| Output | $0.167 per 1M tokens | |
| Other · darkbloom | Input | $0.0145 per 1M tokens |
| Output | $0.07 per 1M tokens | |
| Other · deepinfra | Input | $0.03 per 1M tokens |
| Input (cached read) | $0.015 per 1M tokens | |
| Output | $0.14 per 1M tokens | |
| Other · digitalocean | Input | $0.05 per 1M tokens |
| Input (cached read) | $0.01 per 1M tokens | |
| Output | $0.45 per 1M tokens | |
| Other · doubleword | Input | $0.04 per 1M tokens |
| Output | $0.30 per 1M tokens | |
| Other · edenai | Input (cached read) (host: deepinfra) | $0.015 per 1M tokens |
| Input (cached read) (host: flexai, region: eu) | $0.0027 per 1M tokens | |
| Input (cached read) (host: flexai) | $0.0027 per 1M tokens | |
| Input (cached read) (host: greenference) | $0.0045 per 1M tokens | |
| Input (cached read) (host: groq) | $0.0375 per 1M tokens | |
| Input (host: deepinfra) | $0.03 per 1M tokens | |
| Input (host: flexai, region: eu) | $0.018 per 1M tokens | |
| Input (host: flexai) | $0.018 per 1M tokens | |
| Input (host: greenference) | $0.009 per 1M tokens | |
| Input (host: groq) | $0.075 per 1M tokens | |
| Input (host: ovhcloud) | $0.05 per 1M tokens | |
| Input (host: together-ai) | $0.05 per 1M tokens | |
| Output (host: deepinfra) | $0.14 per 1M tokens | |
| Output (host: flexai, region: eu) | $0.09 per 1M tokens | |
| Output (host: flexai) | $0.09 per 1M tokens | |
| Output (host: greenference) | $0.045 per 1M tokens | |
| Output (host: groq) | $0.30 per 1M tokens | |
| Output (host: ovhcloud) | $0.18 per 1M tokens | |
| Output (host: together-ai) | $0.20 per 1M tokens | |
| Other · fastrouter | Input | $0.07 per 1M tokens |
| Input (cached read) | $0.007 per 1M tokens | |
| Output | $0.25 per 1M tokens | |
| Other · frogbot | Input | $0.07 per 1M tokens |
| Output | $0.20 per 1M tokens | |
| Other · gmi | Input | $0.04 per 1M tokens |
| Output | $0.15 per 1M tokens | |
| Other · groq | Input | $0.075 per 1M tokens |
| Input (cached read) | $0.0375 per 1M tokens | |
| Output | $0.30 per 1M tokens | |
| Web search (context size: high) | $0.005 per query | |
| Web search (context size: low) | $0.005 per query | |
| Web search (context size: medium) | $0.005 per query | |
| Other · helicone | Input | $0.05 per 1M tokens |
| Output | $0.20 per 1M tokens | |
| Other · huggingface | Input | $0.10 per 1M tokens |
| Output | $0.50 per 1M tokens | |
| Other · huggingface-fireworks-ai | Input | $0.05 per 1M tokens |
| Output | $0.20 per 1M tokens | |
| Other · huggingface-groq | Input | $0.10 per 1M tokens |
| Output | $0.50 per 1M tokens | |
| Other · huggingface-hyperbolic | Input | $0.10 per 1M tokens |
| Output | $0.10 per 1M tokens | |
| Other · huggingface-novita | Input | $0.04 per 1M tokens |
| Output | $0.15 per 1M tokens | |
| Other · huggingface-nscale | Input | $0.05 per 1M tokens |
| Output | $0.20 per 1M tokens | |
| Other · huggingface-ovhcloud | Input | $0.05 per 1M tokens |
| Output | $0.18 per 1M tokens | |
| Other · huggingface-together | Input | $0.05 per 1M tokens |
| Output | $0.20 per 1M tokens | |
| Other · impossibl | Input | $0.075 per 1M tokens |
| Input (cached read) | $0.0375 per 1M tokens | |
| Output | $0.30 per 1M tokens | |
| Other · inferall | Input | $0.00 per 1M tokens |
| Output | $0.00 per 1M tokens | |
| Other · inferenceapis | Input | $0.04 per 1M tokens |
| Output | $0.19 per 1M tokens | |
| Other · io-net | Input | $0.055 per 1M tokens |
| Input (cache write) | $0.06 per 1M tokens | |
| Input (cached read) | $0.0275 per 1M tokens | |
| Output | $0.194 per 1M tokens | |
| Other · kenari | Input | $0.036 per 1M tokens |
| Input (cached read) | $0.003714 per 1M tokens | |
| Output | $0.1543 per 1M tokens | |
| Other · kilo | Input | $0.018 per 1M tokens |
| Input (cached read) | $0.009 per 1M tokens | |
| Output | $0.09 per 1M tokens | |
| Other · llmgateway | Input | $0.04 per 1M tokens |
| Input (cached read) | $0.01 per 1M tokens | |
| Output | $0.19 per 1M tokens | |
| Other · llmgateway-providers | Input (cached read) | $0.01 per 1M tokens |
| Input (host: consensusprotocol) | $0.04 per 1M tokens | |
| Input (host: groq) | $0.10 per 1M tokens | |
| Input (host: together-ai) | $0.05 per 1M tokens | |
| Output (host: consensusprotocol) | $0.19 per 1M tokens | |
| Output (host: groq) | $0.50 per 1M tokens | |
| Output (host: together-ai) | $0.20 per 1M tokens | |
| Other · lmstudio | Input | $0.00 per 1M tokens |
| Output | $0.00 per 1M tokens | |
| Other · lowrouter | Input | $0.113 per 1M tokens |
| Output | $0.4745 per 1M tokens | |
| Other · merge-gateway | Input | $0.04 per 1M tokens |
| Input (cached read) | $0.02 per 1M tokens | |
| Output | $0.15 per 1M tokens | |
| Other · nano-gpt | Input | $0.018 per 1M tokens |
| Input (cached read) | $0.009 per 1M tokens | |
| Input (cached read) (deployment: tee) | $0.02 per 1M tokens | |
| Input (deployment: tee) | $0.04 per 1M tokens | |
| Output | $0.09 per 1M tokens | |
| Output (deployment: tee) | $0.15 per 1M tokens | |
| Other · neon | Input | $0.07 per 1M tokens |
| Output | $0.30 per 1M tokens | |
| Other · novita | Input | $0.04 per 1M tokens |
| Output | $0.15 per 1M tokens | |
| Other · novita-ai | Input | $0.04 per 1M tokens |
| Output | $0.15 per 1M tokens | |
| Other · nvidia | Input | $0.00 per 1M tokens |
| Output | $0.00 per 1M tokens | |
| Other · oci | Input | $0.07 per 1M tokens |
| Output | $0.30 per 1M tokens | |
| Other · openrouter | Input | $0.03 per 1M tokens |
| Input (cached read) | $0.03 per 1M tokens | |
| Output | $0.13 per 1M tokens | |
| Other · opper | Input | $0.1162 per 1M tokens |
| Output | $0.4881 per 1M tokens | |
| Other · ovhcloud | Input | $0.05 per 1M tokens |
| Output | $0.18 per 1M tokens | |
| Other · pioneer | Input | $0.07 per 1M tokens |
| Input (cache write) | $0.07 per 1M tokens | |
| Input (cached read) | $0.035 per 1M tokens | |
| Output | $0.30 per 1M tokens | |
| Other · powerspring | Input | $0.0442 per 1M tokens |
| Output | $0.1658 per 1M tokens | |
| Other · prime | Input | $0.07 per 1M tokens |
| Output | $0.30 per 1M tokens | |
| Other · qiniu-ai | Input | $0.1162 per 1M tokens |
| Input (cached read) | $0.01 per 1M tokens | |
| Output | $0.4881 per 1M tokens | |
| Other · qvac | Input | $0.00 per 1M tokens |
| Output | $0.00 per 1M tokens | |
| Other · regolo-ai | Input | $0.1122 per 1M tokens |
| Output | $0.471 per 1M tokens | |
| Other · replicate | Input | $0.09 per 1M tokens |
| Output | $0.36 per 1M tokens | |
| Other · siliconflow | Input | $0.04 per 1M tokens |
| Output | $0.18 per 1M tokens | |
| Other · sokkan | Input | $0.015 per 1M tokens |
| Input (cached read) | $0.008 per 1M tokens | |
| Output | $0.075 per 1M tokens | |
| Other · stackit | Input | $0.18 per 1M tokens |
| Output | $0.29 per 1M tokens | |
| Other · tempr | Input | $0.075 per 1M tokens |
| Input (cached read) | $0.0375 per 1M tokens | |
| Output | $0.30 per 1M tokens | |
| Other · tensormesh | Input | $0.07 per 1M tokens |
| Input (cached read) | $0.00 per 1M tokens | |
| Output | $0.28 per 1M tokens | |
| Other · thinkingmachines | Input | $0.18 per 1M tokens |
| Input (cached read) | $0.036 per 1M tokens | |
| Output | $0.45 per 1M tokens | |
| Other · together-ai | Input | $0.05 per 1M tokens |
| Output | $0.20 per 1M tokens | |
| Other · togetherai | Input | $0.05 per 1M tokens |
| Output | $0.20 per 1M tokens | |
| Other · vercel | Input | $0.03 per 1M tokens |
| Output | $0.14 per 1M tokens | |
| Other · wandb | Input | $0.03 per 1M tokens |
| Input (cached read) | $0.03 per 1M tokens | |
| Output | $0.13 per 1M tokens |
Specifications
- Provider
- openai
- Context window
- 131,072
- Max output tokens
- 131,072
- Open weights
- yes
- Released
- 08/05/2025
- Retires
- 09/15/2026
- First seen by this tracker
Price history
No price of this model has changed since we started tracking it.
- Input
- 0.07 per 1M tokens, unchanged since 09/17/2026
- Output
- 0.3 per 1M tokens, unchanged since 09/17/2026