Last refreshed 2026-06-30. Next refresh: weekly.
Why use gpt-oss-20b on Open Inference?
Open Inference offers gpt-oss-20b with free input token pricing. Open Inference provides an OpenAI-compatible API for hosted text-generation model inference.
Compare gpt-oss-20b across 10 providers to find the best fit for your use caseSetup recipe
Docs fallbackUse the provider REST API or SDKCreate a provider API keymodel: gpt-oss-20bgpt-oss-20bRequest example
Gotchas
No curated gotchas have been sourced for this exact provider/model route yet.
Compare gpt-oss-20b Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| Cloudflare Workers AI | $0.20 | $0.30 |
| OpenRouter | $0.03 | $0.14 |
| Fireworks AI | $0.07 | $0.30 |
| GCP Vertex AI | $0.07 | $0.25 |
| NVIDIA NIM | — | — |
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | Free |
| Output tokens | Free |
Capabilities
About gpt-oss-20b
OpenAI open-weight model with 20 billion parameters. Lightweight, efficient text-only model with reasoning and function calling. Free for self-hosting. Released August 5, 2025.
FAQ
What does gpt-oss-20b cost on Open Inference?
On Open Inference, gpt-oss-20b costs $0 per 1M input tokens and $0 per 1M output tokens.
What is the context window for gpt-oss-20b on Open Inference?
gpt-oss-20b supports a 131k token context window on Open Inference.
How does Open Inference compare to other gpt-oss-20b providers?
gpt-oss-20b is available from 10 providers. The cheapest input pricing is $0/1M tokens from Open Inference.
Who created gpt-oss-20b?
gpt-oss-20b was created by OpenAI as part of the GPT-OSS model family.
Is gpt-oss-20b open source?
gpt-oss-20b is open source under Apache 2.0 according to the seed data.