OpenAI
GPT OSS 20B
Open-weight GPT model for self-hosted reasoning and instruction-following workloads
Model facts
- Context window
- 131K tokens
- Maximum output
- 33K tokens
- Cheapest paid input
- $0.02 per 1M tokens
- Cheapest paid output
- $0.1 per 1M tokens
- Open weights
- yes
- Providers
- 51
Capabilities and modalities
reasoning, tool calling, structured output, attachments, temperature control, open weights, text, image.
Local hardware estimate
At 4K context: Q4_K_M 13.8 GiB, Q8_0 23.5 GiB, F16 41.8 GiB working memory.
- Parameters
- 20.9 billion
- Architecture
- gptoss
- Model license
- apache-2.0
Planning estimate adapted from the MIT-licensed whichllm estimator using metadata from Hugging Face; not a vendor minimum requirement.
Artificial Analysis benchmarks
Compare this model on the full LLM benchmark leaderboard.
| Configuration | AAI | Coding | Math | Output tokens/s |
|---|---|---|---|---|
| high | 15.2 | 20.7 | 89.3 | 127.7 |
| low | 14.4 | not measured | 62.3 | 146.1 |
Observed price history
- 2026-08-24: $0.03 input / $0.13 output per 1M tokens
- 2026-08-25: $0.02 input / $0.1 output per 1M tokens
API providers
- Kenari — model id gpt-oss-20b; free input / free output per 1M tokens; provider documentation
- LMStudio — model id openai/gpt-oss-20b; free input / free output per 1M tokens; provider documentation
- Nvidia — model id openai/gpt-oss-20b; free input / free output per 1M tokens; provider documentation
- QVAC — model id gpt-oss-20b; free input / free output per 1M tokens; provider documentation
- Eden AI — model id flexai/gpt-oss-20b; $0.02 input / $0.1 output per 1M tokens; provider documentation
- Kilo Gateway — model id openai/gpt-oss-20b; $0.02 input / $0.1 output per 1M tokens; provider documentation
- OpenRouter — model id openai/gpt-oss-20b; $0.03 input / $0.13 output per 1M tokens; provider documentation
- Weights & Biases — model id openai/gpt-oss-20b; $0.03 input / $0.13 output per 1M tokens; provider documentation
- Deep Infra — model id openai/gpt-oss-20b; $0.03 input / $0.14 output per 1M tokens; provider documentation
- Eden AI — model id deepinfra/openai/gpt-oss-20b; $0.03 input / $0.14 output per 1M tokens; provider documentation
- IO.NET — model id openai/gpt-oss-20b; $0.03 input / $0.14 output per 1M tokens; provider documentation
- NovitaAI (OpenAI) — model id openai/gpt-oss-20b; $0.04 input / $0.15 output per 1M tokens; provider documentation
- Cortecs — model id gpt-oss-20b; $0.045 input / $0.167 output per 1M tokens; provider documentation
- SiliconFlow — model id openai/gpt-oss-20b; $0.04 input / $0.18 output per 1M tokens; provider documentation
- Clarifai — model id openai/chat-completion/models/gpt-oss-20b; $0.045 input / $0.18 output per 1M tokens; provider documentation
- Eden AI — model id ovhcloud/gpt-oss-20b; $0.05 input / $0.18 output per 1M tokens; provider documentation
- OVHcloud AI Endpoints — model id gpt-oss-20b; $0.05 input / $0.18 output per 1M tokens; provider documentation
- DevPass (LLM Gateway) — model id gpt-oss-20b; $0.04 input / $0.19 output per 1M tokens; provider documentation
- LLM Gateway (Consensus Protocol) — model id consensusprotocol/gpt-oss-20b; $0.04 input / $0.19 output per 1M tokens; provider documentation
- Merge Gateway — model id openai/gpt-oss-20b; $0.04 input / $0.2 output per 1M tokens; provider documentation
- Helicone — model id gpt-oss-20b; $0.05 input / $0.2 output per 1M tokens; provider documentation
- OpenRouter — model id openai/gpt-oss-20b:batch; $0.05 input / $0.2 output per 1M tokens; provider documentation
- Databricks — model id databricks-gpt-oss-20b; $0.05 input / $0.2 output per 1M tokens; provider documentation
- Eden AI — model id together_ai/openai/gpt-oss-20b; $0.05 input / $0.2 output per 1M tokens; provider documentation
- FastRouter — model id openai/gpt-oss-20b; $0.05 input / $0.2 output per 1M tokens; provider documentation
- LLM Gateway (Together AI) — model id together-ai/gpt-oss-20b; $0.05 input / $0.2 output per 1M tokens; provider documentation
- Together AI — model id openai/gpt-oss-20b; $0.05 input / $0.2 output per 1M tokens; provider documentation
- Vercel AI Gateway — model id openai/gpt-oss-20b; $0.05 input / $0.2 output per 1M tokens; provider documentation
- FrogBot — model id gpt-oss-20b; $0.07 input / $0.2 output per 1M tokens; provider documentation
- Vertex — model id openai/gpt-oss-20b-maas; $0.07 input / $0.25 output per 1M tokens; provider documentation
- Amazon Bedrock — model id openai.gpt-oss-20b; $0.07 input / $0.3 output per 1M tokens; provider documentation
- Amazon Bedrock — model id openai.gpt-oss-20b-1:0; $0.07 input / $0.3 output per 1M tokens; provider documentation
- Impossibl — model id fireworks/gpt-oss-20b; $0.07 input / $0.3 output per 1M tokens; provider documentation
- Neon — model id gpt-oss-20b; $0.07 input / $0.3 output per 1M tokens; provider documentation
- Pioneer — model id openai/gpt-oss-20b; $0.07 input / $0.3 output per 1M tokens; provider documentation
- Eden AI — model id databricks/databricks-gpt-oss-20b; $0.07 input / $0.3 output per 1M tokens; provider documentation
- Eden AI (EU) — model id databricks/databricks-gpt-oss-20b@eu; $0.07 input / $0.3 output per 1M tokens; provider documentation
- Eden AI — model id groq/openai/gpt-oss-20b; $0.075 input / $0.3 output per 1M tokens; provider documentation
- Groq — model id openai/gpt-oss-20b; $0.075 input / $0.3 output per 1M tokens; provider documentation
- Impossibl — model id groq/gpt-oss-20b; $0.075 input / $0.3 output per 1M tokens; provider documentation
- STACKIT — model id openai/gpt-oss-20b; $0.18 input / $0.29 output per 1M tokens; provider documentation
- Cloudflare Workers AI — model id @cf/openai/gpt-oss-20b; $0.2 input / $0.3 output per 1M tokens; provider documentation
- DigitalOcean — model id openai-gpt-oss-20b; $0.05 input / $0.45 output per 1M tokens; provider documentation
- Eden AI — model id cloudflare/@cf/openai/gpt-oss-20b; $0.2 input / $0.3 output per 1M tokens; provider documentation
- NanoGPT — model id openai/gpt-oss-20b; $0.2 input / $0.3 output per 1M tokens; provider documentation
- Hugging Face — model id openai/gpt-oss-20b; $0.1 input / $0.5 output per 1M tokens; provider documentation
- LLM Gateway (Groq) — model id groq/gpt-oss-20b; $0.1 input / $0.5 output per 1M tokens; provider documentation
- Regolo AI — model id gpt-oss-20b; $0.4 input / $1.8 output per 1M tokens; provider documentation
- Arena — model id gpt-oss-20b; not published input / not published output per 1M tokens; provider documentation
- Ollama Cloud — model id gpt-oss:20b; not published input / not published output per 1M tokens; provider documentation
- Qiniu — model id gpt-oss-20b; not published input / not published output per 1M tokens; provider documentation