Home/OpenAI/GPT-5 mini
OpenAI pricing

GPT-5 mini API Pricing & Cost Calculator

GPT-5 mini is OpenAI's cost-efficient small model — 20x cheaper than GPT-5.5, ideal for high-volume production. Cached input at $0.02/1M tokens enables huge savings on RAG and chat workloads.

OpenAI plans to retire GPT-5 mini on 2026-12-11

Pricing below is still current. Worth factoring the retirement date into anything you are building on it long-term.

Still available from OpenAI: GPT-5.5 Pro, GPT-6 Rosalind, GPT-5.6 Cyber

Input
$0.25
per 1M tokens
Output
$2.00
per 1M tokens
Context window
272K
tokens
Released
2025-08
Cutoff 2025-04
✓ Exact tokenizer·$0.25 in·$2.00 out (per 1M)
Quick start with a use case
Total cost per call$0.001250
Input$0.000250
Output$0.001000
Cost comparison
Standard
$0.001250
With Caching
$0.001138
Save 9% ↓
With Batch
Not supported
Cutting costs? Open models start at $0.28/1M

DeepSeek, Kimi & 200+ open models on Novita AI — often 5–20x cheaper than proprietary APIs for comparable tasks.

Try Novita AI

Affiliate link — we may earn a commission at no extra cost to you.

Detailed pricing

GPT-5 mini pricing breakdown

All pricing dimensions including caching and batch discounts.

TypePrice (per 1M tokens)
Input$0.2500
Output$2.0000
Cached input$0.0250
Cutting costs? Open models start at $0.28/1M

DeepSeek, Kimi & 200+ open models on Novita AI — often 5–20x cheaper than proprietary APIs for comparable tasks.

Try Novita AI

Affiliate link — we may earn a commission at no extra cost to you.

Last verified 2026-10-31 · OpenAI official pricing · ⚠️ Spotted a wrong price? Report in 30s →

How it compares

GPT-5 mini vs alternatives

Single-call cost (1000 input + 500 output tokens) ranked from cheapest.

ModelPer call
GPT-5 mini
OpenAI · this page
$0.001250
GPT-6 Luna
OpenAI
$0.000350
Claude Haiku 5.5
Anthropic
$0.000350
DeepSeek V3.2
DeepSeek
$0.000480
GPT-5.6 Luna
OpenAI
$0.000800
DeepSeek V4-Flash
DeepSeek
$0.000900
Recommended use

When to choose GPT-5 mini

GPT-5 mini shines for general-purpose tasks, image and document understanding, high-throughput, and low-latency tasks. Token counts on this page are exact via the official tokenizer.

✓Context window of 272K tokens handles long conversations and large documents.
✓Prompt caching available — significant savings for repeated system prompts.
✓Tool / function calling supported.
FAQ

Frequently asked questions

GPT-5 mini costs $0.25 per 1M input tokens and $2.00 per 1M output tokens. A typical chat call (1000 input + 500 output tokens) costs approximately $0.0013. Use the calculator above to estimate your specific use case.
GPT-5 mini supports a 272K token context window with a max output of 128,000 tokens. Knowledge cutoff: 2025-04.
Yes. Cached input is priced at $0.03 per 1M tokens — 90% cheaper than uncached input. This is especially valuable for repeated system prompts, long-context retrieval, and chat threads with shared history.
Yes, GPT-5 mini accepts image input. Vision token pricing is generally calculated based on image dimensions and folded into the input token count. Specific image-specific pricing varies — refer to OpenAI's official documentation.
Token counts for GPT-5 mini use the official o200k_base tokenizer (exact). Cost calculations use the prices verified on 2026-10-31. For final billing accuracy, always verify with OpenAI's usage dashboard.
GPT-5 mini does not currently support fine-tuning. Consider another model in the OpenAI family if fine-tuning is required.
Related

Other models you might consider

OpenAI
GPT-6 Luna
The cheapest model on this site — with a 922K context window
$0.10 in$0.50 out
Anthropic
Claude Haiku 5.5
$0.10/$0.50 — but only for prompts up to 100K tokens
$0.10 in$0.50 out
DeepSeek
DeepSeek V3.2
DeepSeek's open-weight MoE — top cost/quality ratio
$0.28 in$0.40 out
OpenAI
GPT-5.6 Luna
The cheapest long-context model OpenAI ships — 20x under the flagship
$0.20 in$1.20 out
DeepSeek
DeepSeek V4-Flash
1M context at budget pricing — $0.30/$1.20
$0.30 in$1.20 out