OpenAI: gpt-oss-20b pricing
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… OpenAI: gpt-oss-20b from OpenRouter costs $0.030 per 1M input tokens and $0.130 per 1M output tokens. Cached input is $0.030 per 1M. Context window 131,072 tokens.
API id openai/gpt-oss-20b · OpenRouter · source · updated 2026-11-10 · general-purpose
OpenAI: gpt-oss-20b specifications
- Provider
- OpenRouter
- API id
openai/gpt-oss-20b- Model type
- general-purpose
- Context window
- 131K tokens
- Max output
- 118K tokens
- Currency
- USD
- Price source
- Provider API
- Last checked
- 2026-11-10
OpenAI: gpt-oss-20b across providers
The same model, priced by every seller we track. Ranked by the cost of 1M input + 1M output tokens, standard tier; savings measured against buying from the vendor directly.
| Provider | Input /1M | Cached /1M | Output /1M | 1M in + 1M out | vs vendor |
|---|---|---|---|---|---|
| $0.030 | $0.030 | $0.130 | $0.16 | — | |
DeepInfraHost | $0.030 | — | $0.140 | $0.17 | — |
What OpenAI: gpt-oss-20b costs in practice
| Workload | Input tokens | Output tokens | Estimated cost |
|---|---|---|---|
| Short chat turn | 1,000 | 500 | $0.0001 |
| Document summary | 50,000 | 2,000 | $0.0018 |
| 1M tokens in, 200K out | 1,000,000 | 200,000 | $0.06 |
Estimates use the standard tier and ignore caching discounts, so real bills with repeated prompt prefixes are typically lower.
OpenAI: gpt-oss-20b price history
| Recorded | Input /1M | Output /1M |
|---|---|---|
| 2026-11-01 | $0.030 | $0.130 |
| 2026-09-29 | $0.018 | $0.090 |
| 2026-09-23 | $0.018 | $0.090 |
| 2026-08-27 | $0.030 | $0.140 |
| 2026-08-27 | $0.030 | $0.130 |
Common questions
- How much does OpenAI: gpt-oss-20b cost per 1M tokens?
- OpenAI: gpt-oss-20b costs $0.030 per 1M input tokens and $0.130 per 1M output tokens on the standard tier. Cached input is $0.030 per 1M.
- What is OpenAI: gpt-oss-20b's context window?
- OpenAI: gpt-oss-20b accepts up to 131,072 tokens in a single request, and can return up to 117,964 output tokens.
- Is there a cheaper OpenRouter model than OpenAI: gpt-oss-20b?
- Yes. Free Models Router is free per 1M input tokens versus $0.030 for OpenAI: gpt-oss-20b, with a 200,000 token context window.
- Where does this OpenAI: gpt-oss-20b price come from?
- From the OpenRouter catalogue, because OpenRouter does not publish machine-readable pricing. OpenRouter is a reseller, so its rate can differ from OpenRouter's own — verify before committing spend.
Head-to-head comparisons
Other OpenRouter models
- Nex AGI: Nex-N2.6 $0.120
- Thinking Machines: Inkling 2 Small (free) Free
- Anthropic: Claude Fable 5.2 $8.00
- Meta: Muse Ember $0.100
- LiquidAI: LFM3-1.7B $0.080
- LiquidAI: LFM3-1.7B (free) Free
- Google: Gemini Omni 1.2 Flash $1.50
- Google: Gemini Omni 1.1 Flash $1.50
- Ricursive: Ripple 65B Preview $0.200
- Tencent: Hy4 $0.417
- Z.ai: GLM 5.3 FlashX Legal $0.370
- Particle AI: Particle-1 $0.050
- OpenAI: GPT-6.1 Terra Pro $1.00
- OpenAI: GPT-6.1 Terra $1.00
- MoonshotAI: Kimi K3.1 Pro $2.00
- Recursive: Flint (free) Free