GPT-OSS 20B pricing
GPT-OSS 20B, Small-tier from OpenRouter, costs $0.03 per 1M input tokens and $0.13 per 1M output tokens.
Input$0.03per 1M tokens
Output$0.13per 1M tokens
Context window131Ktokens
TierSmallOpenRouter
Price your own workload against GPT-OSS 20B in the calculator →
Specs and pricing
| Provider | OpenRouter |
| Tier | Small |
| Context window | 131K tokens |
| Max output | 118K tokens |
| Input price | $0.03 / 1M tokens |
| Output price | $0.13 / 1M tokens |
| Cache read | $0.03 / 1M tokens |
| Modalities | text |
Note. OpenRouter's default route for this model.
What it costs at realistic volumes
Assuming a 4:1 input:output token ratio, a common shape for chat and RAG-style workloads:
| Volume (4:1 in:out ratio) | Input cost | Output cost | Total / month |
|---|---|---|---|
| 1,000,000 in / 250,000 out | $0.03 | $0.03 | $0.06 |
| 10,000,000 in / 2,500,000 out | $0.30 | $0.33 | $0.63 |
| 100,000,000 in / 25,000,000 out | $3.00 | $3.25 | $6.25 |
Cheaper alternatives
Same tier (Small), a different provider, and a lower blended cost at the 4:1 ratio used above:
| Model | Provider | $/1M in | $/1M out | At the 4:1 ratio |
|---|---|---|---|---|
| Meta-Llama-3.1-8B-Instruct-Turbo | DeepInfra | $0.02 | $0.04 | 52% cheaper blended |