# o3 (OpenAI) — API pricing and providers

> Reasoning. Model id `openai/o3`. Text model by OpenAI.

- Page: https://infro.io/models/openai/o3
- Vendor: OpenAI (https://infro.io/models/openai)
- Modality: Text
- Endpoint through INFRO: `POST /v1/chat/completions` at https://api.infro.io/v1
- List rate: $2.00 per 1M input tokens and $8.00 per 1M output tokens, with cached input at $0.50 per 1M tokens
- Rates checked: 2026-10-05

Rates are OpenAI's published list price: what the customer's own provider account bills, not an INFRO charge. INFRO is a BYOK control plane; it charges a software subscription and adds 0% to model spend.

**Retirement:** OpenAI has deprecated o3 and has not dated its shutdown yet. OpenAI recommends GPT-5.6 Sol. Source: https://developers.openai.com/api/docs/deprecations

## Providers that serve it

| Provider | Model id sent |
| --- | --- |
| OpenAI | `o3` |
| Azure OpenAI | `o3` |
| OpenRouter | `openai/o3` |

## Questions

### How much does the o3 API cost?

OpenAI's published list rate for o3 is $2.00 per 1M input tokens and $8.00 per 1M output tokens, with cached input at $0.50 per 1M tokens (checked 2026-10-05). The provider account you connect bills you at the rate on that account, so a negotiated rate replaces the list rate. INFRO adds 0% to model spend.

### Which providers serve o3?

In INFRO's provider registry, o3 can be served by OpenAI, Azure OpenAI and OpenRouter. You connect your own account with any of them, and INFRO routes and fails over between the ones you connect.

### What is the o3 model ID?

Request it from INFRO as "openai/o3". INFRO sends each provider its own id: OpenAI "o3", Azure OpenAI "o3", OpenRouter "openai/o3".

### How do I call o3 through an OpenAI-compatible API?

Point an OpenAI SDK, or any HTTP client, at https://api.infro.io/v1 with an INFRO gateway key and send model "openai/o3" to POST /v1/chat/completions. INFRO runs the request on a provider account you connected and returns the provider's response with an estimated cost.

### Is o3 being retired?

OpenAI has deprecated o3 and has not dated its shutdown yet. OpenAI recommends GPT-5.6 Sol.

### Does INFRO mark up o3 usage?

No. OpenAI or the provider you connect bills model usage to your own account. INFRO charges a software subscription for routing, failover, observability, budgets and policy, and takes 0% of model spend.