# GPT-OSS 20B

> OpenAI's open-weight model designed for powerful reasoning, agentic tasks, and versatile developer use cases - optimized for lower latency and specialized use-cases at the edge

**ID**: `openai/gpt-oss-20b`  
**Creator**: OpenAI  
**Category**: text  
**Context**: 131K tokens  
**Pricing**: $0.03 / $0.14 per 1M · billed by your provider (BYOK)  
**Released**: 2025-04-08  
**Web page**: https://anyrouter.dev/model/openai/gpt-oss-20b

**Input modalities**: text  
**Output modalities**: text  

**Tokenizer**: GPT

**Capabilities**: chat, reasoning, function-calling, streaming, coding

## Usage

**Endpoint**: `POST https://anyrouter.dev/api/v1/chat/completions`

```bash
curl https://anyrouter.dev/api/v1/chat/completions \
  -H "Authorization: Bearer $ANYROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "openai/gpt-oss-20b",
  "messages": [
    {
      "role": "user",
      "content": "Say hi in 3 words."
    }
  ]
}'
```

## Providers

| Provider | Input | Output |
| --- | --- | --- |
| aihubmix-byok | $0.03/M (list) | $0.14/M (list) |
| huggingface-byok | $0.03/M (list) | $0.14/M (list) |
| deepinfra-byok | $0.03/M (list) | $0.14/M (list) |
| cline-byok | $0.03/M (list) | $0.14/M (list) |
| openrouter-byok | $0.03/M (list) | $0.14/M (list) |
| ovhcloud-byok | $0.05/M (list) | $0.18/M (list) |
| router-byok | $0.07/M (list) | $0.30/M (list) |
| vercel-byok | $0.03/M (list) | $0.14/M (list) |

BYOK routes are billed by your own provider key — AnyRouter charges $0. Rates marked (list) are the provider's published list price.

## Benchmarks

- **GPQA Diamond**: 0.7
- **HLE**: 0.1
- **τ²-Bench Telecom**: 0.6
- **SciCode**: 0.3

## Source

- Upstream docs: https://developers.cloudflare.com/models/gpt-oss-20b/