o3 (2025-04-16) API

Input / 1M tokens$1.76~~$2.00~~

Output / 1M tokens$7.04~~$8.00~~

LLMOpenAI12% below official128K contextReasoningPrompt caching

Loading playground…

About o3 (2025-04-16)

o3 (2025-04-16) by OpenAI is available on API Many from $1.76 per million input tokens and $7.04 per million output tokens, and you call it with the same API key you use for every other model.

It accepts OpenAI-style chat requests with streaming and tools, has a 128K context window and can return up to 16,000 tokens per response.

Prompt caching is supported: cached input tokens are billed at the lower cached rate shown in the price table.

You pay only for successful results: failed or rejected requests are refunded automatically, and every call is recorded in your console with its exact cost.

Related models

−12%

o1o1

LLMOpenAI128K contextReasoning

$13.20 in · $52.80 outTry it

−12%

o1 (2024-12-17)o1-2024-12-17

LLMOpenAIReasoning

$13.20 in · $52.80 outTry it

−12%

o1 minio1-mini

LLMOpenAIReasoning

$0.968 in · $3.87 outTry it

−12%

o1 Mini (2024-09-12)o1-mini-2024-09-12

LLMOpenAIReasoning

$0.968 in · $3.87 outTry it

−12%

o1 previewo1-preview

LLMOpenAIReasoning

$13.20 in · $52.80 outTry it

−12%

o1 Preview (2024-09-12)o1-preview-2024-09-12

LLMOpenAIReasoning

$13.20 in · $52.80 outTry it

−12%

o1 proo1-pro

LLMOpenAIReasoning

$132.00 in · $528.00 outTry it

−12%

o1 Pro (2025-03-19)o1-pro-2025-03-19

LLMOpenAIReasoning

$132.00 in · $528.00 outTry it

Frequently asked questions

How much does the o3 (2025-04-16) API cost?

o3 (2025-04-16) starts at $1.76 per million input tokens and $7.04 per million output tokens on API Many. The price table on this page lists every tier; you are charged only for successful requests.

How do I call o3 (2025-04-16)?

Create an API key in the console, then send a request to /v1/chat/completions with "model": "o3-2025-04-16". The API tab has copy-ready examples in cURL, Python and Node.js.

Is this the official o3 (2025-04-16) model?

Yes. Requests are forwarded to the model maker or an authorized channel with the same parameters, so the output matches the official API.

What happens if a request fails?

Failed, rejected or timed-out requests are not charged. Reserved balance is released automatically and the reason is shown in the call record.