Skip to content
Sovyron

GPT-4o mini

gpt-mini128k context16k max outputreleased Jul 18, 2024ReasoningTool calling

As of Nov 22, 2026, the cheapest GPT-4o mini API price is $0.075 per 1M input tokens (Cloudflare AI Gateway) and $0.3 per 1M output tokens (Cloudflare AI Gateway). GPT-4o mini is offered by 25 providers in the gpt-mini family, reasoning enabled. OpenAI's own rate is $0.6 per 1M output tokens.

Cheapest input
$0.075
Cheapest output
$0.3
Official (OpenAI)
$0.6
output per 1M tokens
Providers
25
offering this model
Spread
2.3×
max / min output
Free offers
0
free-tier offers

API pricing by provider

Metered per-token prices. Cheapest input and output are highlighted; † marks a context-tier surcharge. How prices are ranked. Seeing a wide range? Why the same LLM costs different amounts.

GPT-4o mini API prices by provider in USD per 1M tokens, updated Nov 22, 2026
Cloudflare AI Gatewayopenai/gpt-4o-miniCheapest$0.075Cheapest$0.3$0.0375—128k—
Poeopenai/gpt-4o-mini$0.1364$0.5455$0.0682—124k31d ago
Abacusgpt-4o-mini$0.15$0.6——128k—
AI/ML APIopenai/gpt-4o-mini$0.15$0.6$0.075—128k30d agoout −23.1%
CrossModelopenai/gpt-4o-mini$0.15$0.6$0.075$0.15128k—
DigitalOceanopenai-gpt-4o-mini$0.15$0.6$0.075—128k—
Eden AIopenai/gpt-4o-mini$0.15$0.6$0.075—128k—
Heliconegpt-4o-mini$0.15$0.6$0.075—128k—
Impossiblopenai/gpt-4o-mini$0.15$0.6$0.075—128k—
Kilo Gatewayopenai/gpt-4o-mini$0.15$0.6$0.075—128k—
Kilo Gatewayopenai/gpt-4o-mini-2024-07-18$0.15$0.6$0.075—128k—
DevPass (LLM Gateway)gpt-4o-mini$0.15$0.6$0.075—128k—
LLM Gatewayazure/gpt-4o-mini$0.15$0.6$0.075—128k—
LLM Gatewayopenai/gpt-4o-mini$0.15$0.6$0.075—128k—
LowRouterauto/openai/gpt-4o-mini$0.15$0.6$0.075—128k—
Merge Gatewayopenai/gpt-4o-mini$0.15$0.6$0.075—128k—
NanoGPTopenai/gpt-4o-mini$0.15$0.6$0.075—128k—
Ofoxopenai/gpt-4o-mini$0.15$0.6$0.075—128k36d ago
OpenAIgpt-4o-mini$0.15$0.6$0.075—128k—
OpenRouteropenai/gpt-4o-mini$0.15$0.6$0.075—128k—
OpenRouteropenai/gpt-4o-mini-2024-07-18$0.15$0.6$0.075—128k—
OrcaRouteropenai/gpt-4o-mini$0.15$0.6$0.075—128k—
Prime Inferenceopenai/gpt-4o-mini$0.15$0.6——128k—
Venice AIopenai-gpt-4o-mini-2024-07-18$0.15$0.6$0.075—128k37d ago
Vercel AI Gatewayopenai/gpt-4o-mini$0.15$0.6$0.075—128k—
TheRouteropenai/gpt-4o-mini$0.162$0.648——128k—
Requestyeugpt-4o-mini@eu$0.165$0.66$0.0825—128k—
Cortecsgpt-4o-mini$0.17$0.683$0.086—128k3d agoout +7.1%

GPT-4o mini price history

Output price per 1M tokens since tracking began on Sep 10, 2026, for the 5 providers whose rate moved. Each step is a recorded change. All recent price changes.

GPT-4o mini output price per 1M tokens by provider, Sep 10, 2026 to Nov 22, 2026$0$0.25$0.5$0.75$1Sep 10, 2026Oct 17, 2026Nov 22, 2026
Poe$0.5455AI/ML API$0.6Ofox$0.6Venice AI$0.6Cortecs$0.683
GPT-4o mini price changes by provider, newest first, USD per 1M tokens
DateProvider1M input1M outputChange
Cortecs$0.159 → $0.17$0.638 → $0.683+7.1%
AI/ML API$0.195 → $0.15$0.78 → $0.6−23.1%
Poe$0.14 → $0.1364$0.54 → $0.5455+1%
Ofox$0.12 → $0.15$0.48 → $0.6+25%
Venice AI$0.1875 → $0.15$0.75 → $0.6−20%
Ofox$0.15 → $0.12$0.6 → $0.48−20%

GPT-4o mini pricing FAQ

What is the cheapest GPT-4o mini API?

As of Nov 22, 2026, Cloudflare AI Gateway has the lowest GPT-4o mini output price at $0.3 per 1M tokens, and Cloudflare AI Gateway has the lowest input price at $0.075 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

How much does GPT-4o mini cost on OpenAI?

OpenAI charges $0.15 per 1M input tokens and $0.6 per 1M output tokens for GPT-4o mini.

How many providers offer GPT-4o mini?

25 providers list GPT-4o mini on Sovyron; 28 of them sell it at a metered per-token price.

Is GPT-4o mini free?

No provider in the Sovyron catalog lists a free tier for GPT-4o mini.

What is the context window of GPT-4o mini?

GPT-4o mini supports a 128k-token context window and up to 16k output tokens.

Token cost calculator

What a month costs at one provider's published rates. Enter the tokens you expect to send and receive; cached tokens use the cached-input price where the provider lists one, and count as ordinary input where it does not. See how much prompt caching saves and why output tokens cost more than input tokens.

Estimated

—