← All models
Flash — fastest and cheapest, lighter reasoningCommercial API
gpt-oss-20b (batch) Pricing
OpenAI · openai-gpt-oss-20b-batch
Input / 1M tokens
$0.024
Output / 1M tokens
$0.112
Context window
131,072 tokens
≈ 175 pages of text
Max output
117,964 tokens
What it costs in practice
Typical request (1,200 in + 400 out tokens)$0.0001
1,000 requests / month$0.0736/mo10,000 requests / month$0.736/mo100,000 requests / month$7.36/moEstimate your own workloadOpens the calculator with gpt-oss-20b (batch) preloaded — adjust volume and token counts there.
Price history
List price per 1M tokens since we started tracking in Aug 2026. Each step marks a price change — hover a point for the exact date and rate.
What it excels at
Handles high-volume batch text workloads at low cost with 128k context and 118k output capacity.
The business tradeoff
20B scale limits reasoning depth and complex task performance relative to larger models in the same family.
Cheaper from OpenAI
Head-to-head
Vendor list rates, as of Sep 22, 2026 · source: openrouter · per-request examples assume 1,200 input + 400 output tokens.