release: 3.40.0 — surface the models 3.39.0 priced but never exposed

[VickyXAI]

Why

3.39.0 re-synced pricing to three weeks of gateway drift and added eleven chat models to src/pricing.ts — then stopped. None of them got a shortcut, a picker row, or router wiring, so they were live, correctly priced, and reachable only by typing the full provider/model id from memory.

What

• 38 new shortcuts (107 → 145) — the GPT-5.6 pro reasoning tier (sol-pro / terra-pro / luna-pro), GPT-5.5 Pro, chatgpt (chat-latest), Gemini 3.6 Flash + the Flash Lite line, Qwen3.7 Plus/Flash, Tencent HY3, Xiaomi MiMo, plus the 4o / 4.1-mini / o3-mini gaps. Every alias target has a pricing entry and was probe-verified against the live gateway.
• New arrivals: zai/glm-5.3 (Z.AI flagship, 1M ctx, glm follows it) and xai/grok-imagine-video-1.5 ($0.08/s) in VideoGen.
• fix(router): the LLM classifier has been silently dead since 2026-07-27. Its default was nvidia/qwen3-next-80b-a3b-instruct — NVIDIA's EOL'd id, which the gateway rides on nemotron-3-super-120b. That substitute opens with "Okay, let's see. The user wants to…" and never reaches a verdict inside the 16-token budget, so every classification failed the strict parse and fell through to keyword-only routing. Re-probed the free pool on the real classifier prompt — only nemotron-3-nano-omni returns one bare word (MEDIUM). It is the new classifier.
• The 30B omni model serves itself again. It was pooled behind gpt-oss-120b in August; re-probed 2026-08-19 on both the streaming and non-streaming paths it answers as itself. Gets omni, a free picker row, and second place in every free chain; degraded mistral-nemotron slides to third. nvidia/step-3.7-flash stays deliberately unaliased — $0 and in the catalog, but still served by a substitute.
• Picker holds its 24-row cap. GLM-5.3, GPT-5.6 Terra Pro and Qwen3.7 Flash displaced GLM-5.2, the hidden grok-fast row and GLM-5; Gemini 2.5 Pro retires from under 3.1 Pro. Every retired row keeps its shortcut, and gemini now tracks the flagship like gpt/grok/glm.
• Brand numbers re-synced (95 visible, 8 video, 5 free); stale offline picker prices corrected.

Verification

• npm run build && npm test → 646 pass, 0 fail (5 expectation updates, each documented in-line: the context example list, the free-profile allowlist, the picker bounds, and two pickFreeFallback chain assertions).
• Every model id in this diff was probed against the live gateway: 402 = exists, 400 = unknown. The five hidden-but-resolvable ids Franklin still pins (opus-4.6, gpt-5-nano, grok-3, grok-4-0709, grok-4-1-fast-reasoning) all still return 402 and stay.
• Free models were probed for self-service, not assumed — the substitution trap is what this release exists to avoid repeating.

🤖 Generated with Claude Code