OpenAI · Updated 2026-07-22

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.

VolumeInput costOutput costTotal (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

1M
500K

$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.

ModelInput $/MOutput $/MIn+OutContext
Gemini 2.5 FlashGoogle$0.15$0.60$0.751M
YOUGPT-4o-miniOpenAI$0.15$0.60$0.75128K
DeepSeek-V3DeepSeek$0.27$1.10$1.37128K
Claude Haiku 3.5Anthropic$0.80$4.00$4.80200K

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.

☕ Support this tool