All Models
GPT-OSS 20B
gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for lower-latency inference and deployability on consumer or single-GPU hardware. The model is trained in OpenAI’s Harmony response format and supports reasoning level configuration, fine-tuning, and agentic capabilities including function calling, tool use, and structured outputs.
Available Providers (21)
| Provider | Model ID | Input Cost | Output Cost | Context | Max Output | Docs |
|---|---|---|---|---|---|---|
 LMStudio | openai/gpt-oss-20b | $0.00/MTok | $0.00/MTok | 131.1K | 32.8K | |
 Chutes | openai/gpt-oss-20b | $0.02/MTok | $0.10/MTok | 131.1K | 131.1K | |
 IO.NET | openai/gpt-oss-20b | $0.03/MTok | $0.14/MTok | 64K | 4.1K | |
 Deep Infra | openai/gpt-oss-20b | $0.03/MTok | $0.14/MTok | 131.1K | 16.4K | |
 NanoGPT | openai/gpt-oss-20b | $0.04/MTok | $0.15/MTok | 128K | 16.4K | |
 Clarifai | openai/chat-completion/models/gpt-oss-20b | $0.04/MTok | $0.18/MTok | 131.1K | 16.4K | |
 FastRouter | openai/gpt-oss-20b | $0.05/MTok | $0.20/MTok | 131.1K | 65.5K | |
 Nebius Token Factory | openai/gpt-oss-20b | $0.05/MTok | $0.20/MTok | 128K | 4.1K | |
 Weights & Biases | openai/gpt-oss-20b | $0.05/MTok | $0.20/MTok | 131.1K | 131.1K | |
 Fireworks AI | accounts/fireworks/models/gpt-oss-20b | $0.05/MTok | $0.20/MTok | 131.1K | 32.8K | |
 OpenRouter | openai/gpt-oss-20b | $0.05/MTok | $0.20/MTok | 131.1K | 32.8K | |
 OVHcloud AI Endpoints | gpt-oss-20b | $0.05/MTok | $0.18/MTok | 131.1K | 131.1K | |
 Amazon Bedrock | openai.gpt-oss-20b-1:0 | $0.07/MTok | $0.30/MTok | 128K | 4.1K | |
 Vertex | openai/gpt-oss-20b-maas | $0.07/MTok | $0.25/MTok | 131.1K | 32.8K | |
 Firmware | gpt-oss-20b | $0.07/MTok | $0.20/MTok | 131.1K | 32.8K | |
 Vercel AI Gateway | openai/gpt-oss-20b | $0.07/MTok | $0.30/MTok | 131.1K | 32.8K | |
 Groq | openai/gpt-oss-20b | $0.07/MTok | $0.30/MTok | 131.1K | 65.5K | |
 Cloudflare AI Gateway | workers-ai/@cf/openai/gpt-oss-20b | $0.20/MTok | $0.30/MTok | 128K | 16.4K | |
 Cloudflare Workers AI | @cf/openai/gpt-oss-20b | $0.20/MTok | $0.30/MTok | 128K | 16.4K | |
 Qiniu | gpt-oss-20b | —/MTok | —/MTok | 128K | 4.1K | |
 Ollama Cloud | gpt-oss:20b | —/MTok | —/MTok | 131.1K | 32.8K |
Capabilities
Reasoning
Tool Calling
Attachments
Open Weights
Structured Output