GPT-4o-mini API Pricing 2026: $0.15/M Tokens
Complete per-million-token pricing for GPT-4o-mini from OpenAI, including cached and batch rates, cost-per-1K/1M/10M breakdowns, a monthly cost calculator, and a head-to-head comparison with Gemini 2.5 Flash, Claude Haiku 3.5, DeepSeek-V3. For full cross-provider rankings, open the main calculator.
GPT-4o-mini headline pricing
Input
$0.15 /M tokens
Output
$0.60 /M tokens
Cached input
$0.075 /M (50% off)
Batch (50% off)
$0.075 in / $0.30 out /M
Context · capabilities
128K context · Chat, Code, Vision · benchmark 7/10
GPT-4o-mini cost per 1K, 1M and 10M tokens
Standard on-demand USD rates. Input assumes prompt tokens; output assumes generated tokens.
| Volume | Input cost | Output cost | Total (1:1) |
|---|---|---|---|
| 1K tokens | $0.0002 | $0.0006 | $0.0007 |
| 1M tokens | $0.15 | $0.60 | $0.75 |
| 10M tokens | $1.50 | $6.00 | $7.50 |
GPT-4o-mini monthly cost calculator
$0.45
per month for 1M in + 500K out
$5.40
per year
Need to weigh it against other models? Use the full cross-provider calculator.
GPT-4o-mini vs Gemini 2.5 Flash vs Claude Haiku 3.5 vs DeepSeek-V3
GPT-4o-mini ranks #2 of 4 by blended per-million-token price in this comparison. Lower input + output is cheaper.
| Model | Input $/M | Output $/M | In+Out | Context |
|---|---|---|---|---|
| Gemini 2.5 FlashGoogle | $0.15 | $0.60 | $0.75 | 1M |
| YOUGPT-4o-miniOpenAI | $0.15 | $0.60 | $0.75 | 128K |
| DeepSeek-V3DeepSeek | $0.27 | $1.10 | $1.37 | 128K |
| Claude Haiku 3.5Anthropic | $0.80 | $4.00 | $4.80 | 200K |
Related pricing pages
GPT-4o-mini pricing FAQ
How much does GPT-4o-mini cost?
GPT-4o-mini is priced at $0.15 per million input tokens and $0.60 per million output tokens on OpenAI. At a typical 2:1 input-to-output ratio, that works out to roughly $0.30 per million blended tokens. Context window is 128K.
Is GPT-4o-mini cheaper than Gemini 2.5 Flash?
GPT-4o-mini and Gemini 2.5 Flash are within ~2% of each other on blended per-million-token price ($0.75 vs $0.75), so the choice should hinge on quality, context window, and feature fit rather than price.
Does GPT-4o-mini support prompt caching?
Yes. OpenAI serves repeated input prefixes on GPT-4o-mini at $0.075/M — a 50% discount versus the standard $0.15/M input rate. Caching is automatic for qualifying prefixes and is most valuable for long system prompts and recurring context.
Can I use GPT-4o-mini with the Batch API?
Yes. GPT-4o-mini supports the OpenAI Batch API at $0.075/M input and $0.30/M output — 50% off standard rates — in exchange for asynchronous (up to 24-hour) completion. Batch is ideal for offline evaluation, classification, and bulk generation.