GPT-6 Luna (Fast) API
About
Build advanced reasoning agents with GPT-6 Luna (Fast), a specialized AI model optimized for complex logic and chain-of-thought tasks. This model delivers cost-effective pricing at $0.20/1M input and $1.00/1M output tokens, native tool calling support. Access GPT-6 Luna (Fast) via the Vercel AI Gateway API with up to 128K output tokens.
Capabilities
Input Modalities
textimagepdf
Output Modalities
text
Limits
Context Window
1.1M
Tokens
Input Limit
922K
Tokens
Max Output
128K
Tokens
Pricing
Standard (per 1M tokens)
Input
$0.20
Output
$1.00
Caching (per 1M tokens)
Read
$0.02
Write
$0.25
Frequently Asked Questions
GPT-6 Luna (Fast) by Vercel AI Gateway costs $0.20 per 1M input tokens and $1.00 per 1M output tokens. Cached reads cost $0.02 per 1M tokens. Cache writes cost $0.25 per 1M tokens.
Model Details
ID
openai/gpt-6-luna-fast
Provider
Vercel AI GatewayFamily
gpt-luna
Release Date
Sep 22, 2026
Knowledge Cutoff
May 18, 2026
API Integration