OpenAI · model
gpt-oss-20b
$0.029/1M in · $0.14/1M out · 131K context. That's cheaper than 95% of the 298 models we track, by output price. Here's what it costs, how its price has moved, and where it fits.
- Context
- 131K
- Input / 1M
- $0.029
- Output / 1M
- $0.14
- Modality
- Text only
- Provider
- OpenAI
- Tokenizer
- GPT
Snapshot · source: OpenRouter ↗ · how we measure →
For 1,500 input + 500 output tokens across 200,000 requests/month. That's 3.8× the cheapest tracked option (Ling-2.6-flash, $6.00/mo).
Flat at $0.14 since tracking began 2026-06-14. Full history →
Where it fits
- High-volume, cost-sensitive work — at $0.14/1M output it sits in the cheapest quarter of tracked models.
- Input-heavy jobs like summarization and RAG — input is cheap at $0.029/1M, and these read far more than they write.
Watch for
- Priced from OpenRouter's routed market, not a first-party list price — availability and rate can shift without notice.
- Text-only — no image, audio, or file input.
These notes are derived from price, context and modality — structural facts, not measured quality. Measured cost-to-finish-a-task lives on the real-cost index.
Related models
How to read gpt-oss-20b's pricing
Two numbers decide most of the bill: $0.029/1M for input (everything you send — prompt, context, attachments) and $0.14/1M for output (everything it generates, including hidden reasoning tokens). Output is priced 4.8× the input rate here, so the shape of your workload — how much it reads versus writes — matters as much as the headline figure. This row is OpenRouter's routed market price; it can move as providers and routing change.
Frequently asked questions
How much does gpt-oss-20b cost per million tokens?
gpt-oss-20b is priced at $0.029 per 1M input tokens and $0.14 per 1M output tokens, from OpenRouter's routed market price as of the 2026-06-15 snapshot. Output is the figure that usually drives the bill. Enter your own token volumes in the cost calculator for a monthly estimate.
What is gpt-oss-20b's context window?
gpt-oss-20b has a 131K-token context window — roughly 197 pages of text. Prompt, attachments, conversation and the model's own output all share that budget, and every token you send is billed at the input rate.
Related
- API cost calculator — your monthly cost for gpt-oss-20b and every other model.
- Model comparison — the full sortable table.
- Price history — how token prices move over time.
- LLM pricing explained — input, output, cached and reasoning tokens.