gpt-oss-20b pricing & specs
OpenAI · released 2025-08-05 · ● verified 2026-10-11
input / 1M$0.07via Amazon Bedrock
output / 1M$0.30via Amazon Bedrock
context131.1K
max output128K
// price history ($/1M tokens)
// cheaper or similar alternatives
| model | in | out | ctx | vs gpt-oss-20b |
|---|---|---|---|---|
| Gemma 4 E2B IT | $0.04 | $0.08 | 131.1K | −60.8% |
| Qwen3.7 Flash | $0.03 | $0.13 | 1M | −56.9% |
| Qwen Turbo | $0.05 | $0.20 | 1M | −31.4% |
| DeepSeek V4 Flash 0731 | $0.06 | $0.18 | 1.05M | −29.4% |
| GPT OSS 120B | $0.05 | $0.25 | 131.1K | −21.6% |
// price by host
| host | in $/1M | out $/1M |
|---|---|---|
| Amazon Bedrock | $0.07 | $0.30 |
| Cloudflare Workers AI | $0.20 | $0.30 |
// faq
How much does gpt-oss-20b cost?
gpt-oss-20b costs $0.07 per million input tokens and $0.30 per million output tokens (cheapest tracked host: Amazon Bedrock). At 50M input and 10M output tokens per month that is about $6.50.
What is the context window of gpt-oss-20b?
131.1K tokens, with up to 128K output tokens per request.
What are cheaper alternatives to gpt-oss-20b?
Gemma 4 E2B IT ($0.04 in / $0.08 out), Qwen3.7 Flash ($0.03 in / $0.13 out), Qwen Turbo ($0.05 in / $0.20 out) offer the same input types and capabilities for less.
Is gpt-oss-20b open weights?
Yes. It is available from 2 tracked hosts; the cheapest is Amazon Bedrock at $0.07 input and $0.30 output per million tokens.
// spec sheet
- input / 1M
- $0.07
- output / 1M
- $0.30
- blended (3:1)
- $0.1275
- context
- 131.1K
- max output
- 128K
- input types
- text
- reasoning
- yes
- tool calling
- yes
- structured output
- yes
- open weights
- yes
- knowledge cutoff
- n/a
- price source
- Amazon Bedrock
// cost calculator
| model | in $/1M | out $/1M | = monthly |
|---|---|---|---|
| Gemma 4 E2B IT | $0.04 | $0.08 | $2.80 |
| Qwen3.7 Flash | $0.03 | $0.13 | $2.80 |
| Qwen Turbo | $0.05 | $0.20 | $4.50 |
| gpt-oss-20b | $0.07 | $0.30 | $6.50 |
Base-tier list prices. Long-context tiers, caching and batch discounts are not included.