GPT-5

Latest flagship model with reasoning, vision, and enhanced capabilities.

400,000 context
Released August 1, 2025
Starting at $1.13/M (10% off) input tokens
Starting at $9.00/M (10% off) output tokens
Streaming
Vision
Tools
Reasoning
JSON Output
Structured JSON
No ratings yetSign in to rate
10% offthis model via OpenAI

Select Provider

All Providers for GPT-5

OffRail routes requests to the best providers that are able to handle your prompt size and parameters.

OpenAI
Context: 400k10% off
Input
$1.25$1.125
10% off
/M tokens
Cache Read
$0.125$0.1125
10% off
/M tokens
Output
$10$9
10% off
/M tokens
+ $0.010$0.009 per search
Get Started
Azure
Context: 400k
Input
$1.25
/M tokens
Cache Read
$0.125
/M tokens
Output
$10
/M tokens
Get Started

Frequently asked questions

What is GPT-5?

Latest flagship model with reasoning, vision, and enhanced capabilities. You can access it through OffRail's OpenAI-compatible API with automatic provider routing, fallback, and cost analytics.

How much does GPT-5 cost?

Pricing for GPT-5 on OffRail starts at $1.25 per million input tokens and $10.00 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 GPT-5?

GPT-5 supports a context window of up to 400,000 tokens on its largest provider deployment.

Which providers serve GPT-5?

GPT-5 is served by OpenAI, Azure through OffRail. Requests are automatically routed to the best available provider, with fallback when a provider has issues.

Does GPT-5 support tool calling and structured outputs?

Yes. GPT-5 supports both tool (function) calling and strict JSON output schema (upstream-enforced) through OffRail.

When was GPT-5 released?

GPT-5 was released on August 1, 2025.