GPT-5
Default
Recommended
The best model for coding and agentic tasks across domains.
OpenAI • text • vision • function-calling • json-mode • reasoning
Provider ID
gpt-5Loading...
The best model for coding and agentic tasks across domains.
OpenAI • text • vision • function-calling • json-mode • reasoning
gpt-5GPT-5 is our flagship model for coding, reasoning, and agentic tasks across domains.
Complex agentic tasks requiring configurable reasoning effort
$1.25/1M input tokens, $10.00/1M output tokens
400,000 tokens (Large - suitable for extensive codebases)
Advanced reasoning capabilities
Tools supported by this model when using the Responses API or similar interfaces.
v1/chat/completionsv1/responsesv1/realtimev1/assistantsv1/batchSnapshots let you lock in a specific version of the model so that performance and behavior remain consistent. Below is a list of all available snapshots and aliases for GPT-5.
gpt-5-2025-08-07Rate limits ensure fair and reliable access to the API by placing specific caps on requests or tokens used within a given time period. Your usage tier determines how high these limits are set and automatically increases as you send more requests and spend more on the API.
| Tier | RPM | TPM | Batch Queue Limit |
|---|---|---|---|
| Free | - | - | - |
| Tier 1 | 500 | 500,000 | 1,500,000 |
| Tier 2 | 5,000 | 1,000,000 | 3,000,000 |
| Tier 3 | 5,000 | 2,000,000 | 100,000,000 |
| Tier 4 | 10,000 | 4,000,000 | 200,000,000 |
| Tier 5 | 15,000 | 40,000,000 | 15,000,000,000 |
Pricing is based on the number of tokens used. Input and output tokens are priced separately, with output typically costing more.
v1/fine-tuningv1/embeddingsv1/images/generationsv1/videosv1/images/editsv1/audio/speechv1/audio/transcriptionsv1/audio/translationsv1/moderationsv1/completions