gpt-4o-miniGPT-4o mini pricing (September 2026)
OpenAI lists GPT-4o mini at $0.15 per 1M input tokens and $0.60 per 1M output tokens.
On Crazyrouter the same model is $0.0975 / $0.39 — 35% below list price.
GPT-4o mini price by provider
USD per 1M tokens. Cloud prices are the base tier in the default region; the linked source is authoritative.
| Provider | Input | Cached input | Output | Context | Source |
|---|---|---|---|---|---|
| OpenAI | $0.15 | $0.075 | $0.60 | 128K | OpenAI |
| Azure | $0.15 | — | $0.60 | 128K | Azure OpenAI |
| AWS Bedrock | Not offered | ||||
| Google Vertex AI | Not offered | ||||
| OpenRouter | $0.15 | $0.075 | $0.60 | 128K | OpenRouter |
| Crazyrouter | $0.0975 | $0.052 | $0.39 | 128K | crazyrouter.com |
per 1M tokens · Checked Sep 29, 2026
What GPT-4o mini costs per month
Three typical workloads, priced on each provider from the table above.
| Workload | OpenAI | Azure | OpenRouter | Crazyrouter |
|---|---|---|---|---|
| Prototype: 10M in / 2M out | $2.70 | $2.70 | $2.70 | $1.76 |
| Product: 100M in / 20M out | $27.00 | $27.00 | $27.00 | $17.55 |
| Scale: 1B in / 200M out | $270.00 | $270.00 | $270.00 | $175.50 |
Price changes
Tracked daily since Sep 29, 2026; no list-price changes recorded yet.
Alternatives to GPT-4o mini
Same-family models and cheaper options for similar tasks.
GPT-4o mini pricing FAQ
How much does GPT-4o mini cost?
OpenAI charges $0.15 per 1M input tokens and $0.60 per 1M output tokens. Through Crazyrouter the same model is $0.0975 / $0.39.
What is cached input pricing?
Tokens that repeat an earlier prompt prefix are billed at the cached rate ($0.075 per 1M when supported) instead of the full input price.
Is there a batch discount?
Yes. OpenAI offers batch pricing at $0.075 in / $0.30 out per 1M tokens for asynchronous jobs.
Is GPT-4o mini cheaper on Azure, Bedrock or Vertex?
Cloud providers usually match the list price and add regional or provisioned tiers; see the table above for the base rate on each. Crazyrouter applies its discount on top of list.
