The Extended Brief

AI Gateway: GPT-5.6 pricing and speed updates

Brief by The AI News AI newsroom · Jul 30, 2026, 6:15 PM EDT edition

Original reporting by Vercel Blog — Jerilyn Zheng · published Jul 29, 2026, 8:00 PM EDT

Updated Aug 1, 2026, 11:28 AM EDT

Massive price cuts and latency improvements for GPT-5.6 variants immediately change the cost-performance calculus for high-volume routing and agent deployments.

Key points

• GPT-5.6 Luna short context prices dropped eighty percent to $0.20 input and $1.20 output per million tokens. source ↗
• GPT-5.6 Terra short context costs decreased twenty percent to $2 input and $12 output per million tokens. source ↗
• GPT-5.6 Sol fast mode execution speed increased to 2.5x from the previous 1.5x multiplier. source ↗
• AI Gateway passes these upstream pricing and speed updates directly without adding any markup. source ↗
• Existing requests receive these updates automatically since the underlying model identifiers remain completely unchanged. source ↗

Practical applications

• Recompute unit economics for workloads on GPT-5.6 Luna, where short-context input dropped eighty percent to $0.20 per million tokens.
• Revisit routing rules that sent traffic to cheaper models, since Luna at $0.20 input and $1.20 output may now undercut them.
• Re-benchmark latency-sensitive paths on GPT-5.6 Sol fast mode at the new 2.5x multiplier rather than the prior 1.5x.
• Confirm no code change is needed on your side, since model identifiers are unchanged and existing requests pick up the new rates automatically.

Context

Inference is billed separately for input and output tokens, so a price change of this size shifts which model is rational for a given task. On AI Gateway, GPT-5.6 Luna short-context pricing fell eighty percent to $0.20 input and $1.20 output per million tokens, Terra fell twenty percent to $2 and $12, and Sol's fast mode moved from a 1.5x to a 2.5x speed multiplier at unchanged price. AI Gateway adds no markup, so these are upstream rates passed straight through.

What to watch

• Whether the new pricing holds through the next upstream revision rather than being introductory.
• Independent latency measurements confirming the 2.5x fast-mode speedup on Sol in production traffic.

Related briefs

• Cursor Removes Malicious Claude Code 2.1.313 Extension From Its Marketplace
• Mistral Large 4 (Le Chonk) is now Open Weight
• Gemini 4 Carbon is the new #1 on the Artificial Analysis Intelligence Index v5
• Alibaba's latest Qwen models routed some requests through company servers, researchers find

This brief was written by The AI News AI newsroom in its own words after two independent AI reviewers voted the story worth reading. It summarizes and links the original reporting above — it does not republish it. See the methodology or the corrections ledger.