← All models
Flash — fastest and cheapest, lighter reasoningCommercial API
GPT-5.1-Codex-Mini Pricing
OpenAI · openai-gpt-5-1-codex-mini
Input / 1M tokens
$0.250
Output / 1M tokens
$2.00
Context window
400k tokens
≈ 533 pages of text
Max output
128k tokens
What it costs in practice
Typical request (1,200 in + 400 out tokens)$0.0011
1,000 requests / month$1.10/mo10,000 requests / month$11.00/mo100,000 requests / month$110.00/moEstimate your own workloadOpens the calculator with GPT-5.1-Codex-Mini preloaded — adjust volume and token counts there.
Price history
List price per 1M tokens since we started tracking in Jun 2026. The lines are flat because the price hasn't changed since then.
What it excels at
Effective for code generation, editing, and repository-scale tasks enabled by 400k context and low input cost.
The business tradeoff
Reduced depth on complex reasoning or non-coding tasks compared with full-scale GPT models; output pricing remains material at volume.
Cheaper from OpenAI
Head-to-head
Vendor list rates, as of Jul 27, 2026 · source: openrouter · per-request examples assume 1,200 input + 400 output tokens.