OpenAI: gpt-oss-20b (batch)
OpenAIOpen weights
OpenAI: gpt-oss-20b (batch) by OpenAI costs $0.02 per 1M input tokens and $0.11 per 1M output tokens, with a 131K-token context window.
Pricing
Input (per 1M tokens)
$0.02
Output (per 1M tokens)
$0.11
Cached input (per 1M)
—
Specifications
- Provider
- OpenAI
- Context window
- 131K tokens
- Parameters
- 21B
- Released
- Aug 2025
- Open weights
- Yes
- Frontier model
- No
- Hugging Face
- openai/gpt-oss-20b
Benchmarks
- GPQA Diamond
- 60.8
Speed & latency
Time to first token
1.02s
Output speed
944 tok/s
Fastest host: groq (via vercel-ai-gateway).
Compare OpenAI: gpt-oss-20b (batch) with…
OpenAI: gpt-oss-20b (batch) vs Granite 4.0 Micro$0.11/1MOpenAI: gpt-oss-20b (batch) vs Gemma 3 4B$0.10/1MOpenAI: gpt-oss-20b (batch) vs Ministral 8B (latest)$0.10/1MOpenAI: gpt-oss-20b (batch) vs Llama-3.2-1B$0.10/1MOpenAI: gpt-oss-20b (batch) vs Qwen2.5-Coder-0.5B$0.10/1MOpenAI: gpt-oss-20b (batch) vs Granite 4.1 8B$0.10/1M
FAQ
How much does OpenAI: gpt-oss-20b (batch) cost?
OpenAI: gpt-oss-20b (batch) is priced at $0.02 per 1M input tokens and $0.11 per 1M output tokens. Output tokens cost more than input.
What is OpenAI: gpt-oss-20b (batch)'s context window?
OpenAI: gpt-oss-20b (batch) supports a context window of 131K tokens — the maximum prompt plus response length it can handle in a single request.
Is OpenAI: gpt-oss-20b (batch) open weight?
Yes — OpenAI: gpt-oss-20b (batch) has openly available weights.
Data as of 2026-10-15. Source: Pricing via OpenRouter API, openrouter.ai. Pricing is per 1M tokens (USD); confirm with the provider before production use.