OpenAI's API is the gold standard for frontier LLM access, serving the flagship GPT-5 family alongside the cost-efficient GPT-4.1 and GPT-4.1 nano tiers. With 400K+ context windows, function calling, structured outputs, and a massive developer ecosystem, it powers the majority of production AI applications worldwide.
GPT-5 inference pricing
- Developer
- OpenAI
- Quality rank
- #1
- Elo
- 1410
- Context
- 400K
- Weights
- Closed
- Lowest output
- $15.00
Lowest output
$15.00
Median
$15.00
Highest
$15.00
3 results
| Provider | Plan | Price | Regions | Visit | |||
|---|---|---|---|---|---|---|---|
|
|
Azure OpenAI GPT-5 | $15.00 | $2.50 | 400K |
$15.00
/M tokens
Input $2.50/1M tokens
Blended $5.62
Verified
|
Global | Visit → |
|
|
GPT-5 | $15.00 | $2.50 | 400K |
$15.00
/M tokens
Input $2.50/1M tokens
Blended $5.62
Verified
|
Global | Visit → |
|
|
GPT-5 (routed) | $15.00 | $2.50 | 400K |
$15.00
/M tokens
Input $2.50/1M tokens
Blended $5.62
Verified
|
Global | Visit → |
Providers serving this model
Azure AI Foundry (formerly Azure AI Studio) is Microsoft's enterprise model catalog, hosting GPT-5, GPT-4.1, Mistral Large, and other partner models on Azure's managed infrastructure. With FedRAMP, HIPAA, and SOC 2 compliance, private networking, and seamless Azure RBAC integration, it is the natural choice for regulated enterprises already on Microsoft's cloud.
OpenRouter acts as a unified gateway that routes API requests across dozens of inference providers - OpenAI, Anthropic, Google, Together, Groq, and more - through a single API key. It automatically selects the best available provider for each model, with transparent pricing and the ability to fallback if one endpoint goes down.
Frequently asked questions
How much does GPT-5 cost per million tokens?
The lowest input price we track for GPT-5 is $2.50 per million tokens. Output tokens cost more; the table shows input, output, and blended pricing for every inference provider.
What is the cheapest GPT-5 API provider?
Sort the table by output or blended price to find the cheapest GPT-5 endpoint. Prices for the same model vary widely between providers, so the cheapest provider can be several times less than the most expensive.
Which providers serve the GPT-5 API?
Every provider with a published GPT-5 endpoint appears above, with input and output token pricing, context window, and throughput.
What is GPT-5's context window?
GPT-5 supports a 400K context window. A larger context window lets you pass more tokens (documents, code, history) in a single request.
Is GPT-5 open weight or closed source?
GPT-5 is a closed (proprietary) model available only through hosted APIs. Compare provider pricing above to find the cheapest endpoint.
What is blended LLM cost?
Blended cost weights input and output token prices by a typical 3:1 ratio so you can rank providers by one number instead of comparing two prices separately.