Back to all models

Pricing and availability as of

o3

Scheduled for Deactivation

Next-generation reasoning model with enhanced problem-solving capabilities.

o3
Context
200,000
tokens
Input from
$2.00
per 1M tokens
Output from
$8.00
per 1M tokens
Providers
1
one route
Released
Jun 1, 2025
No ratings yetSign in to rate

Providers for o3

Compare price, limits and live performance side by side. LLM Gateway routes each request to the best provider that can handle your prompt size and parameters.

1 provider

ProviderActions
200k$2.00$8.00$0.50

Prices are per provider at standard rates; open a row for regions, tiers and cache pricing. Throughput, latency and uptime come from LLM Gateway traffic over the last 24 hours and are hidden under 1,000 requests.

o3 API pricing

o3 API pricing starts at $2.00 per 1M input tokens and $8.00 per 1M output tokens through LLM Gateway. Cached input starts at $0.50 per 1M tokens.

ProviderInput / 1M tokensOutput / 1M tokensCached input / 1M tokensContext window
OpenAI$2.00$8.00$0.50200,000 tokens

What o3 costs at volume

Monthly usageCost on OpenAI
1M input + 250K output tokens$4.00
10M input + 2.5M output tokens$40.00
100M input + 25M output tokens$400.00

o3 cost calculator

Estimated monthly cost
$60.00
Cost per request
$0.006

Frequently asked questions

What is o3?

Next-generation reasoning model with enhanced problem-solving capabilities. You can access it through LLM Gateway's OpenAI-compatible API with automatic provider routing, fallback, and cost analytics.

How much does o3 cost?

Pricing for o3 on LLM Gateway starts at $2.00 per million input tokens and $8.00 per million output tokens, depending on the provider. The pricing table above always reflects the current per-provider rates.

What is the context length of o3?

o3 supports a context window of up to 200,000 tokens on its largest provider deployment.

Which providers serve o3?

o3 is served by OpenAI through LLM Gateway. Requests are automatically routed to the best available provider, with fallback when a provider has issues.

Does o3 support tool calling and structured outputs?

o3 supports strict JSON output schema, but not tool calling.

When was o3 released?

o3 was released on June 1, 2025.