/** * Pricing data — oauth-subscriptions family (OAuth / IDE subscription aliases (cc, codex, gemini-cli, antigravity, copilot, kiro…)). * Pure data; merged by default-pricing.ts via spread (god-file decomposition; semantic split). */ import { GPT_5_3_CODEX_PRICING, GPT_5_5_PRICING, } from "./shared-tiers"; export const DEFAULT_PRICING_OAUTH = { cc: { "claude-fable-5": { input: 10.0, output: 50.0, cached: 1.0, reasoning: 50.0, cache_creation: 12.5, }, "claude-opus-4-8": { input: 5.0, output: 25.0, cached: 0.5, reasoning: 25.0, cache_creation: 6.25, }, "claude-opus-4-7": { input: 5.0, output: 25.0, cached: 0.5, reasoning: 25.0, cache_creation: 6.25, }, "claude-opus-4-6": { input: 5.0, output: 25.0, cached: 0.5, reasoning: 25.0, cache_creation: 6.25, }, "claude-sonnet-4-6": { input: 3.0, output: 15.0, cached: 0.3, reasoning: 15.0, cache_creation: 3.75, }, "claude-opus-4-5-20251101": { input: 5.0, output: 25.0, cached: 0.5, reasoning: 25.0, cache_creation: 6.25, }, "claude-sonnet-4-5-20250929": { input: 3.0, output: 15.0, cached: 0.3, reasoning: 15.0, cache_creation: 3.75, }, "claude-haiku-4-5-20251001": { input: 1.0, output: 5.0, cached: 0.1, reasoning: 5.0, cache_creation: 1.25, }, }, cx: { "codex-auto-review": GPT_5_5_PRICING, // GPT 5.5 "gpt-5.5": GPT_5_5_PRICING, "gpt5.5": GPT_5_5_PRICING, "gpt-5.5-xhigh": GPT_5_5_PRICING, "gpt-5.5-high": GPT_5_5_PRICING, "gpt-5.5-medium": GPT_5_5_PRICING, "gpt-5.5-low": GPT_5_5_PRICING, "gpt-5.5-none": GPT_5_5_PRICING, // GPT 5.4 "gpt-5.4": { input: 5.0, output: 20.0, cached: 2.5, reasoning: 30.0, cache_creation: 5.0, }, "gpt5.4": { input: 5.0, output: 20.0, cached: 2.5, reasoning: 30.0, cache_creation: 5.0, }, // T12: fallback pricing for gpt-5.4 mini variants "gpt-5.4-mini": { input: 1.5, output: 6.0, cached: 0.75, reasoning: 9.0, cache_creation: 1.5, }, "gpt5.4-mini": { input: 1.5, output: 6.0, cached: 0.75, reasoning: 9.0, cache_creation: 1.5, }, // gpt-5.4 reasoning-effort variants share the gpt-5.4 tier (registry exposes // -xhigh/-high/-medium/-low; without these rows they resolved to $0). "gpt-5.4-xhigh": GPT_5_3_CODEX_PRICING, "gpt-5.4-high": GPT_5_3_CODEX_PRICING, "gpt-5.4-medium": GPT_5_3_CODEX_PRICING, "gpt-5.4-low": GPT_5_3_CODEX_PRICING, // GPT 5.3 Codex family (all same pricing tier) "gpt-5.3-codex-spark": GPT_5_3_CODEX_PRICING, "gpt-5.3-codex": GPT_5_3_CODEX_PRICING, "gpt-5.3-codex-xhigh": GPT_5_3_CODEX_PRICING, "gpt-5.3-codex-high": GPT_5_3_CODEX_PRICING, "gpt-5.3-codex-low": GPT_5_3_CODEX_PRICING, "gpt-5.3-codex-none": GPT_5_3_CODEX_PRICING, "gpt-5.1-codex-mini-high": { input: 1.5, output: 6.0, cached: 0.75, reasoning: 9.0, cache_creation: 1.5, }, "gpt-5.2-codex": { input: 5.0, output: 20.0, cached: 2.5, reasoning: 30.0, cache_creation: 5.0, }, "gpt-5.2": { input: 5.0, output: 20.0, cached: 2.5, reasoning: 30.0, cache_creation: 5.0, }, "gpt-5.1-codex-max": { input: 8.0, output: 32.0, cached: 4.0, reasoning: 48.0, cache_creation: 8.0, }, "gpt-5.1-codex": { input: 4.0, output: 16.0, cached: 2.0, reasoning: 24.0, cache_creation: 4.0, }, "gpt-5.1-codex-mini": { input: 1.5, output: 6.0, cached: 0.75, reasoning: 9.0, cache_creation: 1.5, }, "gpt-5.1": { input: 4.0, output: 16.0, cached: 2.0, reasoning: 24.0, cache_creation: 4.0, }, "gpt-5-codex": { input: 3.0, output: 12.0, cached: 1.5, reasoning: 18.0, cache_creation: 3.0, }, "gpt-5-codex-mini": { input: 1.0, output: 4.0, cached: 0.5, reasoning: 6.0, cache_creation: 1.0, }, }, "gemini-cli": { "gemini-3-flash-preview": { input: 0.5, output: 3.0, cached: 0.03, reasoning: 4.5, cache_creation: 0.5, }, "gemini-3.1-flash-lite-preview": { input: 0.5, output: 3.0, cached: 0.03, reasoning: 4.5, cache_creation: 0.5, }, "gemini-3-pro-preview": { input: 2.0, output: 12.0, cached: 0.25, reasoning: 18.0, cache_creation: 2.0, }, "gemini-3.1-pro-preview": { input: 2.0, output: 12.0, cached: 0.25, reasoning: 18.0, cache_creation: 2.0, }, "gemini-2.5-pro": { input: 2.0, output: 12.0, cached: 0.25, reasoning: 18.0, cache_creation: 2.0, }, "gemini-2.5-flash": { input: 0.3, output: 2.5, cached: 0.03, reasoning: 3.75, cache_creation: 0.3, }, // Gemini 2.5 Flash Lite — preco corrigido via ClawRouter: $0.10/$0.40 (era $0.15/$1.25) "gemini-2.5-flash-lite": { input: 0.1, output: 0.4, cached: 0.025, reasoning: 0.6, cache_creation: 0.1, }, }, qw: { "qwen3-coder-plus": { input: 1.0, output: 4.0, cached: 0.5, reasoning: 6.0, cache_creation: 1.0, }, // Next-generation Qwen Coder tier (added Mar 2026) "qwen3-coder-next": { input: 2.0, output: 8.0, cached: 1.0, reasoning: 12.0, cache_creation: 2.0, }, "qwen3-coder-flash": { input: 0.5, output: 2.0, cached: 0.25, reasoning: 3.0, cache_creation: 0.5, }, "vision-model": { input: 1.5, output: 6.0, cached: 0.75, reasoning: 9.0, cache_creation: 1.5, }, // Qwen3.5/3.6 Coder Model — ported from upstream 9router PR #156 (zx07). // Priced identically to the vision tier per upstream defaults. "coder-model": { input: 1.5, output: 6.0, cached: 0.75, reasoning: 9.0, cache_creation: 1.5, }, }, if: { "qwen3-coder-plus": { input: 1.0, output: 4.0, cached: 0.5, reasoning: 6.0, cache_creation: 1.0, }, "kimi-k2": { input: 1.0, output: 4.0, cached: 0.5, reasoning: 6.0, cache_creation: 1.0, }, "kimi-k2-thinking": { input: 1.5, output: 6.0, cached: 0.75, reasoning: 9.0, cache_creation: 1.5, }, "deepseek-r1": { input: 0.75, output: 3.0, cached: 0.375, reasoning: 4.5, cache_creation: 0.75, }, "deepseek-v3.2-chat": { input: 0.28, output: 0.42, cached: 0.014, reasoning: 0.63, cache_creation: 0.28, }, "deepseek-v3.2": { input: 0.28, output: 0.42, cached: 0.014, reasoning: 0.63, cache_creation: 0.28, }, "deepseek-v3.2-reasoner": { input: 0.55, output: 2.19, cached: 0.14, reasoning: 2.19, cache_creation: 0.55, }, // Short-form aliases (Mar 2026) "deepseek-3.1": { input: 0.27, output: 1.1, cached: 0.07, reasoning: 2.2, cache_creation: 0.27, }, "deepseek-3.2": { input: 0.27, output: 1.1, cached: 0.07, reasoning: 2.2, cache_creation: 0.27, }, "minimax-m2": { input: 0.5, output: 2.0, cached: 0.25, reasoning: 3.0, cache_creation: 0.5, }, "glm-4.6": { input: 0.5, output: 2.0, cached: 0.25, reasoning: 3.0, cache_creation: 0.5, }, "glm-4.7": { input: 0.75, output: 3.0, cached: 0.375, reasoning: 4.5, cache_creation: 0.75, }, }, ag: { "gemini-3.1-pro-low": { input: 2.0, output: 12.0, cached: 0.25, reasoning: 18.0, cache_creation: 2.0, }, "gemini-3.1-pro-high": { input: 4.0, output: 18.0, cached: 0.5, reasoning: 27.0, cache_creation: 4.0, }, "gemini-3-flash": { input: 0.5, output: 3.0, cached: 0.03, reasoning: 4.5, cache_creation: 0.5, }, // Antigravity 2.0.4+ exposes Gemini 3.5 Flash as three public client ids // (see ANTIGRAVITY_PUBLIC_MODELS in open-sse/config/antigravityModelAliases.ts): // gemini-3-flash-agent → "Gemini 3.5 Flash (High)" // gemini-3.5-flash-low → "Gemini 3.5 Flash (Medium)" // Both bill at the same per-MTok rates as legacy `gemini-3-flash` above — // without these rows, getPricingForModel("ag", id) returned null and downstream // cost / quota calculations silently fell back to $0. "gemini-3-flash-agent": { input: 0.5, output: 3.0, cached: 0.03, reasoning: 4.5, cache_creation: 0.5, }, "gemini-3.5-flash-low": { input: 0.5, output: 3.0, cached: 0.03, reasoning: 4.5, cache_creation: 0.5, }, // `gemini-pro-agent` is the Antigravity v1.23+ Agent-mode alias for the // Gemini 3.1 Pro (High) tier — bills at the same rates as `gemini-3.1-pro-high`. "gemini-pro-agent": { input: 4.0, output: 18.0, cached: 0.5, reasoning: 27.0, cache_creation: 4.0, }, "claude-sonnet-4-6": { input: 3.0, output: 15.0, cached: 0.3, reasoning: 22.5, cache_creation: 3.0, }, "claude-opus-4-6-thinking": { input: 5.0, output: 25.0, cached: 0.5, reasoning: 37.5, cache_creation: 5.0, }, "gpt-oss-120b-medium": { input: 0.5, output: 2.0, cached: 0.25, reasoning: 3.0, cache_creation: 0.5, }, }, gh: { "gpt-5": { input: 3.0, output: 12.0, cached: 1.5, reasoning: 18.0, cache_creation: 3.0, }, "gpt-5-mini": { input: 0.75, output: 3.0, cached: 0.375, reasoning: 4.5, cache_creation: 0.75, }, "gpt-5.1-codex": { input: 4.0, output: 16.0, cached: 2.0, reasoning: 24.0, cache_creation: 4.0, }, "gpt-5.1-codex-max": { input: 8.0, output: 32.0, cached: 4.0, reasoning: 48.0, cache_creation: 8.0, }, "gpt-4.1": { input: 2.5, output: 10.0, cached: 1.25, reasoning: 15.0, cache_creation: 2.5, }, "claude-4.5-sonnet": { input: 3.0, output: 15.0, cached: 0.3, reasoning: 22.5, cache_creation: 3.0, }, "claude-4.5-opus": { input: 5.0, output: 25.0, cached: 0.5, reasoning: 37.5, cache_creation: 5.0, }, "claude-4.5-haiku": { input: 0.5, output: 2.5, cached: 0.05, reasoning: 3.75, cache_creation: 0.5, }, "gemini-3-pro": { input: 2.0, output: 12.0, cached: 0.25, reasoning: 18.0, cache_creation: 2.0, }, "gemini-3-flash": { input: 0.5, output: 3.0, cached: 0.03, reasoning: 4.5, cache_creation: 0.5, }, "gemini-2.5-pro": { input: 2.0, output: 12.0, cached: 0.25, reasoning: 18.0, cache_creation: 2.0, }, "grok-code-fast-1": { input: 0.5, output: 2.0, cached: 0.25, reasoning: 3.0, cache_creation: 0.5, }, }, kiro: { "claude-fable-5": { input: 15.0, output: 75.0, cached: 7.5, reasoning: 112.5, cache_creation: 15.0, }, "claude-sonnet-4.5": { input: 3.0, output: 15.0, cached: 1.5, reasoning: 15.0, cache_creation: 3.0, }, "claude-haiku-4.5": { input: 0.5, output: 2.5, cached: 0.25, reasoning: 2.5, cache_creation: 0.5, }, // Models from issue #334 "claude-sonnet-4": { input: 3.0, output: 15.0, cached: 1.5, reasoning: 15.0, cache_creation: 3.0, }, "claude-opus-4.8": { input: 15.0, output: 75.0, cached: 7.5, reasoning: 75.0, cache_creation: 15.0, }, "claude-opus-4.7": { input: 15.0, output: 75.0, cached: 7.5, reasoning: 75.0, cache_creation: 15.0, }, "claude-opus-4.6": { input: 15.0, output: 75.0, cached: 7.5, reasoning: 75.0, cache_creation: 15.0, }, "claude-sonnet-4.6": { input: 3.0, output: 15.0, cached: 1.5, reasoning: 15.0, cache_creation: 3.0, }, "deepseek-v3.2": { input: 0.27, output: 1.1, cached: 0.07, reasoning: 1.1, cache_creation: 0.27, }, // Registry exposes this model as "deepseek-3.2" (no "v") — keep both keys priced. "deepseek-3.2": { input: 0.27, output: 1.1, cached: 0.07, reasoning: 1.1, cache_creation: 0.27, }, "minimax-m2.1": { input: 0.4, output: 1.6, cached: 0.1, reasoning: 1.6, cache_creation: 0.4, }, // MiniMax M2.5 — cheaper than M2.1, reasoning + tools "minimax-m2.5": { input: 0.27, output: 0.95, cached: 0.135, reasoning: 1.425, cache_creation: 0.27, }, "glm-5": { input: 1.0, output: 3.2, cached: 0.2, reasoning: 4.8, cache_creation: 1.0, }, "qwen3-coder-next": { input: 2.0, output: 8.0, cached: 0.5, reasoning: 8.0, cache_creation: 2.0, }, // Kiro "Auto" model — routes to best available auto: { input: 3.0, output: 15.0, cached: 1.5, reasoning: 15.0, cache_creation: 3.0, }, // Registry exposes the Auto model as id "auto-kiro" — keep both keys priced. "auto-kiro": { input: 3.0, output: 15.0, cached: 1.5, reasoning: 15.0, cache_creation: 3.0, }, }, };