GPT-5 nano vs GPT-4o mini
Side-by-side comparison of API pricing, specs, benchmarks, and capabilities
| Specification |
by OpenAI
|
by OpenAI
|
|---|---|---|
| Overview | ||
| Status | Current budget | Current budget |
| Released | Aug 7, 2025 | Jul 18, 2024 |
| Pricing per million tokens | ||
| Input | $0.050/Mtok | $0.150/Mtok |
| Output | $0.400/Mtok | $0.600/Mtok |
| Blended avg | $0.138/Mtok | $0.262/Mtok |
| Cached input | $0.005/Mtok | $0.075/Mtok |
| Specifications | ||
| Context window | 400K tokens | 128K tokens |
| Parameters | Proprietary | Proprietary |
| Speed (TPS) | — | — |
| Modalities | ||
| Input |
textimage
|
textimage
|
| Benchmarks source: Artificial Analysis | ||
| Independent composite scores each on its own scale — not part of the average above | ||
| AA Agentic Index | — | 1 |
| AA-Omniscience Index (−100–100) | -28.7 | — |
| Providers | ||
| Available from |
OpenAI — $0.050/$0.400/Mtok
|
OpenAI — $0.150/$0.600/Mtok
|
Cost at scale
1M tokens · 50/50 input/output| Volume | GPT-5 nano | GPT-4o mini | Savings |
|---|---|---|---|
| 1M tokens | $0.14 | $0.26 | $0.12 (45.7%) |
| 10M tokens | $1.38 | $2.62 | $1.25 (47.6%) |
| 100M tokens | $13.75 | $26.25 | $12.5 (47.6%) |
| 1000M tokens | $137.5 | $262.5 | $125 (47.6%) |
When to pick which
distilled from the pricing and spec data above- cost dominates: $0.138/Mtok blended vs $0.262 — 47.6% less on the same 50/50 token mix
- your workload re-reads context (agents, RAG, long chats): cached input costs $0.005/Mtok — 90% off its list input price
- you need the longer context: 400K tokens vs 128K (3.1×)
- this pairing gives GPT-4o mini no edge on price, context, cache discount, or measured performance — pick it only for qualitative fit (ecosystem, compliance, model behavior on your prompts)
The cheaper option here — GPT-5 nano costs $0.138/Mtok blended on OpenAI.
Summary
GPT-5 nano by OpenAI costs $0.050/Mtok input and $0.400/Mtok output, with a 400K-token context window. It supports text, image input.
GPT-4o mini by OpenAI costs $0.150/Mtok input and $0.600/Mtok output, with a 128K-token context window. It supports text, image input.
On a blended cost basis, GPT-5 nano is 47.6% cheaper than GPT-4o mini.It also has a larger context window.
Note: Pricing is per million tokens. Actual costs vary with usage patterns, prompt caching, and batch discounts. Always verify against official provider pricing pages.