One agent session
1M input tokens and 100K output tokens, no caching.
- Input1M x $0.25 = $0.25
- Output0.1M x $2 = $0.20
$0.45per session
OpenAI - Closed weights
GPT-5 Mini is a closed-weights model from OpenAI that costs $0.25 per 1M input tokens and $2 per 1M output tokens on the first-party API, with a 400K-token context window.
Last verified from developers.openai.com. All sources
| Item | Price / 1M tokens |
|---|---|
| Input | $0.25 |
| Output | $2 |
| Cache read | $0.025 |
| Batch inputBatch requests | $0.125 |
| Batch outputBatch requests | $1 |
| Fast mode inputFast mode requests | $0.45 |
| Fast mode outputFast mode requests | $3.60 |
Note: Maximum input tokens 272,000. Default snapshot gpt-5-mini-2025-08-07.
gpt-5-miniopenai/gpt-5-miniNot stated means the provider's docs do not say either way. It is not the same as No. Checked against provider docs on . Compare capabilities across models.
Worked from the standard list rates above, with the math shown so you can swap in your own token counts.
1M input tokens and 100K output tokens, no caching.
$0.45per session
10,000 requests a day at 2K input and 500 output tokens each.
$15.00per day
$450.00 per 30-day month
90% of the input is read from the prompt cache. The one-time cache write premium is not included.
$0.2475per session
| Model | Input / 1M | Output / 1M |
|---|---|---|
| GPT-5 Mini (this page) | $0.25 | $2 |
| GPT-3.5 Turbo InstructOpenAI | $1.50 | $2 |
| Grok Build 0.1xAI | $1 | $2 |
| Qwen3.5-35B-A3BAlibaba Cloud (Qwen) | $0.25 | $2 |
| Seed 2.0 LiteByteDance Seed | $0.25 | $2 |
| GPT-4.1 MiniOpenAI | $0.40 | $1.60 |
| GPT-3.5 TurboOpenAI | $0.50 | $1.50 |
| GPT-5.4 nanoOpenAI | $0.20 | $1.25 |
| GPT-5.6 LunaOpenAI | $0.20 | $1.20 |
| GPT-4o MiniOpenAI | $0.15 | $0.60 |
Side-by-side pages with both models' prices, specs, cost examples and like-for-like benchmark rows.
GPT-5 Mini costs $0.25 per 1M input tokens and $2 per 1M output tokens on OpenAI's first-party API, per developers.openai.com on October 17, 2026. Per 1M tokens, cache reads cost $0.025, and the batch rate is $0.125 input and $1 output.
GPT-5 Mini has a 400,000-token context window and returns up to 128,000 output tokens per response.
No. GPT-5 Mini is a closed-weights model. You call it through OpenAI's API as gpt-5-mini or through Vercel AI Gateway as openai/gpt-5-mini.
OpenAI released GPT-5 Mini on August 7, 2025.
Last verified from developers.openai.com.
Newsletter
One email per week. New model releases, price cuts and what they mean for your bill.