Open Brain
VercelEngineering PostOfficial Source

GPT-6 Sol and Luna now available on AI Gateway

Vercel AI Gateway now exposes GPT-6 Sol for demanding coding runs and Luna for high-volume work, with unified usage tracking, retries, failover, and routing.

Vercel · Sep 22, 2026
Open Source Open MarkdownOpen JSON
Source Summary

Vercel AI Gateway now offers **openai/gpt-6-sol** for complex, sustained coding work and **openai/gpt-6-luna** for lower-cost, high-volume agent workflows. Both are available through the AI SDK, compatible Chat Completions and Responses APIs, and connected coding agents.

Practical Implication

Use Sol where longer tasks and iteration quality matter; test Luna for throughput-sensitive work. Gateway routing, usage tracking, retries, and failover make it practical to evaluate both behind one integration.

Agent-Ready Context
Vercel AI Gateway now offers **openai/gpt-6-sol** for complex, sustained coding work and **openai/gpt-6-luna** for lower-cost, high-volume agent workflows. Both are available through the AI SDK, compatible Chat Completions and Responses APIs, and connected coding agents.

Use Sol where longer tasks and iteration quality matter; test Luna for throughput-sensitive work. Gateway routing, usage tracking, retries, and failover make it practical to evaluate both behind one integration.

Vercel says both cost less than GPT-6 Astra and improve factual reliability over GPT-5.6 counterparts, but the material includes no prices, benchmark results, or quantified reliability gains.
Connected Context · Feed7 Judgment

This formalizes a two-tier GPT-6 routing choice for coding agents: Sol for sustained task quality and Luna for volume-sensitive work. It advances the earlier GPT tiering pattern without resolving selection against the Gateway’s many competing coding routes, because the claimed cost and reliability improvements are not quantified and still require matched workload tests.

GPT-5.6 Sol is 50% off on AI Gateway for the next monthGPT-6 Sol is presented as the successor-side option to GPT-5.6 Sol, but the earlier signal’s temporary discount and this signal’s unquantified lower-cost claim make durable cost comparison impossible without measured pricing and usage.Gemini 3.7 Flash now available on AI Gateway for 50% offGemini 3.7 Flash is another coding-agent route behind the same gateway controls, but its promotional price makes it an evaluation comparator rather than evidence for or against either GPT-6 tier.AI Gateway adds unified fast mode supportUnified fast mode is an orthogonal serving control that can affect latency across supported routes; teams should separate that routing effect from the inherent Sol-versus-Luna workload tradeoff.Claude Opus 5 now available on AI GatewayClaude Opus 5 is a competing premium coding route with configurable reasoning and fast mode, reinforcing the need to compare sustained-task quality, safeguards, latency, and cost rather than select from positioning alone.
Context Map
infracoding#gateways#model-selection#coding-agents
Uncertainty
Vercel says both cost less than GPT-6 Astra and improve factual reliability over GPT-5.6 counterparts, but the material includes no prices, benchmark results, or quantified reliability gains.