GPT-5
openai
Highest
⚡ Medium
The best model for coding and agentic tasks across domains. GPT-5 is our flagship model for coding, reasoning, and agentic tasks across domains.
Basic Information
Context Window
400,000
tokens
Max Output
128,000
tokens
Knowledge Cutoff
Last Update
Performance
Highest
Overall Rating
Technical Specifications
Detailed technical information and specifications
- Model ID
- GPT-5
- Provider
- openai
- Status
- active
- Created At
- Last Updated
- Availability
- General Availability
Features
Supported features and capabilities of this model
streaming
function_calling
structured_outputs
fine_tuning
distillation
predicted_outputs
reasoning_tokens
Pricing Details
Cost per 1 million tokens for different API types and usage patterns
Standard API
Text Modality
| Type | Price | Unit | Context Type |
|---|---|---|---|
Input | $1.250000 | per mtokens | Standard |
Output | $10.000000 | per mtokens | Standard |
Cached Input | $0.125000 | per mtokens | Standard Reduced cost for cached input |
Batch API
Text Modality - Batch API
| Type | Price | Unit | Context Type | Savings |
|---|---|---|---|---|
| Cached Input | $0.063000 | per mtokens | Standard | -50% |
| Input |
Rate Limits
Request limits by subscription tier
Standard API Limits
| Tier | RPM | TPM | Additional Limits |
|---|---|---|---|
| tier_1 | 500 | 30,000 | Queue:90,000 Requests |
| tier_2 | 5,000 | 450,000 | Queue:1,350,000 Requests |
| tier_3 | 5,000 | 800,000 | Queue:100,000,000 Requests |
| tier_4 | 10,000 | 2,000,000 | Queue:200,000,000 Requests |
| tier_5 | 15,000 | 40,000,000 | Queue:15,000,000,000 Requests |