o3-mini
As of Nov 22, 2026, the cheapest o3-mini API price is $1.045 per 1M input tokens (Jiekou.AI) and $4.18 per 1M output tokens (Jiekou.AI). o3-mini is offered by 10 providers in the o-mini family, reasoning enabled.
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.
| Jiekou.AIo3-mini | Cheapest$1.045 | Cheapest$4.18 | $0.5225 | — | 200k | 31d ago |
| Abacuso3-mini | $1.1 | $4.4 | $0.55 | — | 200k | — |
| Cloudflare AI Gatewayopenai/o3-mini | $1.1 | $4.4 | $0.55 | — | 200k | — |
| DigitalOceanopenai-o3-mini | $1.1 | $4.4 | $0.55 | — | 200k | — |
| Heliconeo3-mini | $1.1 | $4.4 | $0.55 | — | 200k | — |
| Impossiblopenai/o3-mini | $1.1 | $4.4 | $0.55 | — | 200k | — |
| Kilo Gatewayopenai/o3-mini | $1.1 | $4.4 | $0.55 | free | 200k | — |
| Merge Gatewayopenai/o3-mini | $1.1 | $4.4 | $0.55 | — | 200k | — |
| NEAR AI Cloudopenai/o3-mini | $1.1 | $4.4 | $0.55 | — | 200k | — |
o3-mini price history
Output price per 1M tokens since tracking began on Sep 10, 2026, for the one provider whose rate moved. Each step is a recorded change. All recent price changes.
| Date | Provider | 1M input | 1M output | Change |
|---|---|---|---|---|
| Jiekou.AI | $1.1 → $1.045 | $4.4 → $4.18 | −5% |
o3-mini pricing FAQ
What is the cheapest o3-mini API?
As of Nov 22, 2026, Jiekou.AI has the lowest o3-mini output price at $4.18 per 1M tokens, and Jiekou.AI has the lowest input price at $1.045 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.
How many providers offer o3-mini?
10 providers list o3-mini on Sovyron; 9 of them sell it at a metered per-token price.
Is o3-mini free?
No provider in the Sovyron catalog lists a free tier for o3-mini.
What is the context window of o3-mini?
o3-mini supports a 200k-token context window and up to 100k 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
—