@fudrouter/fsrouter 0.6.64 → 0.6.66

package/open-sse/providers/pricing.js

@@ -0,0 +1,308 @@
+// Pricing rates for AI models — all rates in $/1M tokens
+//
+// Fallback order (first match wins):
+//   1. PROVIDER_PRICING[provider][model]  — provider-specific override
+//   2. MODEL_PRICING[model]               — canonical model price (provider-agnostic)
+//   3. PATTERN_PRICING                    — glob pattern match (e.g. "codex-*")
+
+/**
+ * Canonical model pricing — provider-agnostic.
+ * Cover all known models; deduplicated across providers.
+ */
+export const MODEL_PRICING = {
+  // === Anthropic / Claude ===
+  "claude-opus-4-6":              { input: 5.00,  output: 25.00, cached: 0.50,  reasoning: 25.00,  cache_creation: 6.25  },
+  "claude-opus-4-5-20251101":     { input: 5.00,  output: 25.00, cached: 0.50,  reasoning: 25.00,  cache_creation: 6.25  },
+  "claude-sonnet-4-6":            { input: 3.00,  output: 15.00, cached: 0.30,  reasoning: 15.00,  cache_creation: 3.75  },
+  "claude-sonnet-4-5-20250929":   { input: 3.00,  output: 15.00, cached: 0.30,  reasoning: 15.00,  cache_creation: 3.75  },
+  "claude-haiku-4-5-20251001":    { input: 1.00,  output: 5.00,  cached: 0.10,  reasoning: 5.00,   cache_creation: 1.25  },
+  "claude-sonnet-4-20250514":     { input: 3.00,  output: 15.00, cached: 1.50,  reasoning: 15.00,  cache_creation: 3.00  },
+  "claude-opus-4-20250514":       { input: 15.00, output: 25.00, cached: 7.50,  reasoning: 112.50, cache_creation: 15.00 },
+  "claude-3-5-sonnet-20241022":   { input: 3.00,  output: 15.00, cached: 1.50,  reasoning: 15.00,  cache_creation: 3.00  },
+  "claude-haiku-4.5":             { input: 0.50,  output: 2.50,  cached: 0.05,  reasoning: 3.75,   cache_creation: 0.50  },
+  "claude-opus-4.1":              { input: 5.00,  output: 25.00, cached: 0.50,  reasoning: 37.50,  cache_creation: 5.00  },
+  "claude-opus-4.5":              { input: 5.00,  output: 25.00, cached: 0.50,  reasoning: 37.50,  cache_creation: 5.00  },
+  "claude-opus-4.6":              { input: 5.00,  output: 25.00, cached: 0.50,  reasoning: 37.50,  cache_creation: 5.00  },
+  "claude-sonnet-4":              { input: 3.00,  output: 15.00, cached: 0.30,  reasoning: 22.50,  cache_creation: 3.00  },
+  "claude-sonnet-4.5":            { input: 3.00,  output: 15.00, cached: 0.30,  reasoning: 22.50,  cache_creation: 3.00  },
+  "claude-sonnet-4.6":            { input: 3.00,  output: 15.00, cached: 0.30,  reasoning: 22.50,  cache_creation: 3.00  },
+  "claude-opus-4-5-thinking":     { input: 5.00,  output: 25.00, cached: 0.50,  reasoning: 37.50,  cache_creation: 5.00  },
+  "claude-opus-4-6-thinking":     { input: 5.00,  output: 25.00, cached: 0.50,  reasoning: 37.50,  cache_creation: 5.00  },
+  "claude-fable-5":               { input: 10.00, output: 50.00, cached: 1.00,  reasoning: 50.00,  cache_creation: 12.50 },
+
+  // === OpenAI / GPT ===
+  "gpt-3.5-turbo":                { input: 0.50,  output: 1.50,  cached: 0.25,  reasoning: 2.25,   cache_creation: 0.50  },
+  "gpt-4":                        { input: 2.50,  output: 10.00, cached: 1.25,  reasoning: 15.00,  cache_creation: 2.50  },
+  "gpt-4-turbo":                  { input: 10.00, output: 30.00, cached: 5.00,  reasoning: 45.00,  cache_creation: 10.00 },
+  "gpt-4o":                       { input: 2.50,  output: 10.00, cached: 1.25,  reasoning: 15.00,  cache_creation: 2.50  },
+  "gpt-4o-mini":                  { input: 0.15,  output: 0.60,  cached: 0.075, reasoning: 0.90,   cache_creation: 0.15  },
+  "gpt-4.1":                      { input: 2.50,  output: 10.00, cached: 1.25,  reasoning: 15.00,  cache_creation: 2.50  },
+  "gpt-5":                        { input: 1.25,  output: 10.00, cached: 0.625, reasoning: 10.00,  cache_creation: 1.25  },
+  "gpt-5-mini":                   { input: 0.25,  output: 2.00,  cached: 0.125, reasoning: 2.00,   cache_creation: 0.25  },
+  "gpt-5-codex":                  { input: 1.25,  output: 10.00, cached: 0.625, reasoning: 10.00,  cache_creation: 1.25  },
+  "gpt-5.1":                      { input: 1.25,  output: 10.00, cached: 0.625, reasoning: 10.00,  cache_creation: 1.25  },
+  "gpt-5.1-codex":                { input: 1.25,  output: 10.00, cached: 0.625, reasoning: 10.00,  cache_creation: 1.25  },
+  "gpt-5.1-codex-mini":           { input: 1.50,  output: 6.00,  cached: 0.75,  reasoning: 9.00,   cache_creation: 1.50  },
+  "gpt-5.1-codex-mini-high":      { input: 2.00,  output: 8.00,  cached: 1.00,  reasoning: 12.00,  cache_creation: 2.00  },
+  "gpt-5.1-codex-max":            { input: 8.00,  output: 32.00, cached: 4.00,  reasoning: 48.00,  cache_creation: 8.00  },
+  "gpt-5.2":                      { input: 1.75,  output: 14.00, cached: 0.175, reasoning: 14.00,  cache_creation: 1.75  },
+  "gpt-5.2-codex":                { input: 1.75,  output: 14.00, cached: 0.175, reasoning: 14.00,  cache_creation: 1.75  },
+  "gpt-5.3-codex":                { input: 1.75,  output: 14.00, cached: 0.175, reasoning: 14.00,  cache_creation: 1.75  },
+  "gpt-5.3-codex-spark":         { input: 3.00,  output: 12.00, cached: 0.30,  reasoning: 12.00,  cache_creation: 3.00  },
+  "gpt-5.6":                      { input: 2.50,  output: 15.00, cached: 0.25,  reasoning: 15.00,  cache_creation: 2.50  },
+  "gpt-5.6-luna":                 { input: 1.00,  output: 6.00,  cached: 0.10,  reasoning: 6.00,   cache_creation: 1.00  },
+  "gpt-5.6-terra":                { input: 2.50,  output: 15.00, cached: 0.25,  reasoning: 15.00,  cache_creation: 2.50  },
+  "gpt-5.6-sol":                  { input: 5.00,  output: 30.00, cached: 0.50,  reasoning: 30.00,  cache_creation: 5.00  },
+  "o1":                           { input: 15.00, output: 60.00, cached: 7.50,  reasoning: 90.00,  cache_creation: 15.00 },
+  "o1-mini":                      { input: 3.00,  output: 12.00, cached: 1.50,  reasoning: 18.00,  cache_creation: 3.00  },
+
+  // === Gemini ===
+  "gemini-3-flash-preview":       { input: 0.50,  output: 3.00,  cached: 0.03,  reasoning: 4.50,   cache_creation: 0.50  },
+  "gemini-3-pro-preview":         { input: 2.00,  output: 12.00, cached: 0.25,  reasoning: 18.00,  cache_creation: 2.00  },
+  "gemini-3.1-pro-low":           { input: 2.00,  output: 12.00, cached: 0.25,  reasoning: 18.00,  cache_creation: 2.00  },
+  "gemini-3.1-pro-high":          { input: 4.00,  output: 18.00, cached: 0.50,  reasoning: 27.00,  cache_creation: 4.00  },
+  "gemini-pro-agent":             { input: 4.00,  output: 18.00, cached: 0.50,  reasoning: 27.00,  cache_creation: 4.00  },
+  "gemini-3-flash-agent":         { input: 0.50,  output: 3.00,  cached: 0.03,  reasoning: 4.50,   cache_creation: 0.50  },
+  "gemini-3.5-flash-low":         { input: 0.50,  output: 3.00,  cached: 0.03,  reasoning: 4.50,   cache_creation: 0.50  },
+  "gemini-3.5-flash-extra-low":   { input: 0.50,  output: 3.00,  cached: 0.03,  reasoning: 4.50,   cache_creation: 0.50  },
+  "gemini-3-flash":               { input: 0.50,  output: 3.00,  cached: 0.03,  reasoning: 4.50,   cache_creation: 0.50  },
+  "gemini-2.5-pro":               { input: 2.00,  output: 12.00, cached: 0.25,  reasoning: 18.00,  cache_creation: 2.00  },
+  "gemini-2.5-flash":             { input: 0.30,  output: 2.50,  cached: 0.03,  reasoning: 3.75,   cache_creation: 0.30  },
+  "gemini-2.5-flash-lite":        { input: 0.15,  output: 1.25,  cached: 0.015, reasoning: 1.875,  cache_creation: 0.15  },
+
+  // === Qwen ===
+  "qwen3-coder-plus":             { input: 1.00,  output: 4.00,  cached: 0.50,  reasoning: 6.00,   cache_creation: 1.00  },
+  "qwen3-coder-flash":            { input: 0.50,  output: 2.00,  cached: 0.25,  reasoning: 3.00,   cache_creation: 0.50  },
+
+  // === Kimi ===
+  "kimi-k2":                      { input: 1.00,  output: 4.00,  cached: 0.50,  reasoning: 6.00,   cache_creation: 1.00  },
+  "kimi-k2-thinking":             { input: 1.50,  output: 6.00,  cached: 0.75,  reasoning: 9.00,   cache_creation: 1.50  },
+  "kimi-k2.5":                    { input: 1.20,  output: 4.80,  cached: 0.60,  reasoning: 7.20,   cache_creation: 1.20  },
+  "kimi-k2.5-thinking":           { input: 1.80,  output: 7.20,  cached: 0.90,  reasoning: 10.80,  cache_creation: 1.80  },
+  "kimi-latest":                  { input: 1.00,  output: 4.00,  cached: 0.50,  reasoning: 6.00,   cache_creation: 1.00  },
+
+  // === DeepSeek ===
+  "deepseek-chat":                { input: 0.14,  output: 0.28,  cached: 0.0028, reasoning: 0.28,   cache_creation: 0.14  },
+  "deepseek-reasoner":            { input: 0.14,  output: 0.28,  cached: 0.0028, reasoning: 0.28,   cache_creation: 0.14  },
+  "deepseek-r1":                  { input: 0.14,  output: 0.28,  cached: 0.0028, reasoning: 0.28,   cache_creation: 0.14  },
+  "deepseek-v3.2-chat":           { input: 0.14,  output: 0.28,  cached: 0.0028, reasoning: 0.28,   cache_creation: 0.14  },
+  "deepseek-v3.2-reasoner":       { input: 0.14,  output: 0.28,  cached: 0.0028, reasoning: 0.28,   cache_creation: 0.14  },
+  "deepseek-v4-flash":            { input: 0.14,  output: 0.28,  cached: 0.0028, reasoning: 0.28,   cache_creation: 0.14  },
+  "deepseek-v4-pro":              { input: 0.435, output: 0.87,  cached: 0.003625, reasoning: 0.87,  cache_creation: 0.435 },
+
+  // === GLM ===
+  "glm-4.6":                      { input: 0.50,  output: 2.00,  cached: 0.25,  reasoning: 3.00,   cache_creation: 0.50  },
+  "glm-4.6v":                     { input: 0.75,  output: 3.00,  cached: 0.375, reasoning: 4.50,   cache_creation: 0.75  },
+  "glm-4.7":                      { input: 0.75,  output: 3.00,  cached: 0.375, reasoning: 4.50,   cache_creation: 0.75  },
+  "glm-5":                        { input: 1.00,  output: 4.00,  cached: 0.50,  reasoning: 6.00,   cache_creation: 1.00  },
+
+  // === MiniMax ===
+  "MiniMax-M3":                   { input: 0.30,  output: 1.20,  cached: 0.06,  reasoning: 1.80,   cache_creation: 0.30  },
+  "MiniMax-M2.1":                 { input: 0.50,  output: 2.00,  cached: 0.25,  reasoning: 3.00,   cache_creation: 0.50  },
+  "MiniMax-M2.5":                 { input: 0.50,  output: 2.00,  cached: 0.25,  reasoning: 3.00,   cache_creation: 0.50  },
+  "MiniMax-M2.7":                 { input: 0.50,  output: 2.00,  cached: 0.25,  reasoning: 3.00,   cache_creation: 0.50  },
+  "minimax-m2.1":                 { input: 0.50,  output: 2.00,  cached: 0.25,  reasoning: 3.00,   cache_creation: 0.50  },
+  "minimax-m2.5":                 { input: 0.60,  output: 2.40,  cached: 0.30,  reasoning: 3.60,   cache_creation: 0.60  },
+
+  // === Grok ===
+  "grok-code-fast-1":             { input: 0.50,  output: 2.00,  cached: 0.25,  reasoning: 3.00,   cache_creation: 0.50  },
+
+  // === OpenRouter fallback ===
+  "auto":                         { input: 2.00,  output: 8.00,  cached: 1.00,  reasoning: 12.00,  cache_creation: 2.00  },
+
+  // === Misc ===
+  "oswe-vscode-prime":            { input: 1.00,  output: 4.00,  cached: 0.50,  reasoning: 6.00,   cache_creation: 1.00  },
+  "gpt-oss-120b-medium":          { input: 0.50,  output: 2.00,  cached: 0.25,  reasoning: 3.00,   cache_creation: 0.50  },
+  "vision-model":                 { input: 1.50,  output: 6.00,  cached: 0.75,  reasoning: 9.00,   cache_creation: 1.50  },
+  "coder-model":                  { input: 1.50,  output: 6.00,  cached: 0.75,  reasoning: 9.00,   cache_creation: 1.50  },
+};
+
+/**
+ * Provider-specific pricing overrides.
+ * Only include entries where price DIFFERS from MODEL_PRICING.
+ * Keyed by provider alias (cc, cx, gc, gh, ...) or provider id (openai, anthropic, ...).
+ */
+export const PROVIDER_PRICING = {
+  // GitHub Copilot (gh) — explicit override, matches canonical gpt-5.3-codex rate
+  gh: {
+    "gpt-5.3-codex": { input: 1.75, output: 14.00, cached: 0.175, reasoning: 14.00, cache_creation: 1.75 },
+  },
+};
+
+/**
+ * Pattern-based pricing fallback — matched when no exact model entry found.
+ * Patterns use simple glob: "*" matches any substring.
+ * First match wins — order matters.
+ */
+export const PATTERN_PRICING = [
+  // --- Codex variants ---
+  { pattern: "*-codex-xhigh",   pricing: { input: 10.00, output: 40.00, cached: 5.00,  reasoning: 60.00,  cache_creation: 10.00 } },
+  { pattern: "*-codex-high",    pricing: { input: 8.00,  output: 32.00, cached: 4.00,  reasoning: 48.00,  cache_creation: 8.00  } },
+  { pattern: "*-codex-max",     pricing: { input: 8.00,  output: 32.00, cached: 4.00,  reasoning: 48.00,  cache_creation: 8.00  } },
+  { pattern: "*-codex-mini-*",  pricing: { input: 1.50,  output: 6.00,  cached: 0.75,  reasoning: 9.00,   cache_creation: 1.50  } },
+  { pattern: "*-codex-mini",    pricing: { input: 1.50,  output: 6.00,  cached: 0.75,  reasoning: 9.00,   cache_creation: 1.50  } },
+  { pattern: "*-codex-low",     pricing: { input: 1.75,  output: 14.00, cached: 0.175, reasoning: 14.00,  cache_creation: 1.75  } },
+  { pattern: "*-codex-none",    pricing: { input: 1.75,  output: 14.00, cached: 0.175, reasoning: 14.00,  cache_creation: 1.75  } },
+  { pattern: "*-codex-spark",   pricing: { input: 3.00,  output: 12.00, cached: 0.30,  reasoning: 12.00,  cache_creation: 3.00  } },
+  { pattern: "codex-*",         pricing: { input: 1.75,  output: 14.00, cached: 0.175, reasoning: 14.00,  cache_creation: 1.75  } },
+  { pattern: "*-codex",         pricing: { input: 1.75,  output: 14.00, cached: 0.175, reasoning: 14.00,  cache_creation: 1.75  } },
+
+  // --- Claude ---
+  { pattern: "claude-opus-*",   pricing: { input: 5.00,  output: 25.00, cached: 0.50,  reasoning: 25.00,  cache_creation: 6.25  } },
+  { pattern: "claude-sonnet-*", pricing: { input: 3.00,  output: 15.00, cached: 0.30,  reasoning: 15.00,  cache_creation: 3.75  } },
+  { pattern: "claude-haiku-*",  pricing: { input: 1.00,  output: 5.00,  cached: 0.10,  reasoning: 5.00,   cache_creation: 1.25  } },
+  { pattern: "claude-*",        pricing: { input: 3.00,  output: 15.00, cached: 0.30,  reasoning: 15.00,  cache_creation: 3.75  } },
+
+  // --- Gemini (specific first, generic last) ---
+  { pattern: "gemini-*-flash-lite", pricing: { input: 0.15, output: 1.25, cached: 0.015, reasoning: 1.875, cache_creation: 0.15 } },
+  { pattern: "gemini-*-flash",  pricing: { input: 0.30,  output: 2.50,  cached: 0.03,  reasoning: 3.75,   cache_creation: 0.30  } },
+  { pattern: "gemini-*-pro",    pricing: { input: 2.00,  output: 12.00, cached: 0.25,  reasoning: 18.00,  cache_creation: 2.00  } },
+  { pattern: "gemini-3-*",      pricing: { input: 0.50,  output: 3.00,  cached: 0.03,  reasoning: 4.50,   cache_creation: 0.50  } },
+  { pattern: "gemini-2.5-*",    pricing: { input: 0.30,  output: 2.50,  cached: 0.03,  reasoning: 3.75,   cache_creation: 0.30  } },
+  { pattern: "gemini-*",        pricing: { input: 0.50,  output: 3.00,  cached: 0.03,  reasoning: 4.50,   cache_creation: 0.50  } },
+
+  // --- GPT (specific first, generic last) ---
+  { pattern: "gpt-5.6-*",       pricing: { input: 2.50,  output: 15.00, cached: 0.25,  reasoning: 15.00,  cache_creation: 2.50  } },
+  { pattern: "gpt-5.3-*",       pricing: { input: 1.75,  output: 14.00, cached: 0.175, reasoning: 14.00,  cache_creation: 1.75  } },
+  { pattern: "gpt-5.2-*",       pricing: { input: 1.75,  output: 14.00, cached: 0.175, reasoning: 14.00,  cache_creation: 1.75  } },
+  { pattern: "gpt-5.1-*",       pricing: { input: 1.25,  output: 10.00, cached: 0.625, reasoning: 10.00,  cache_creation: 1.25  } },
+  { pattern: "gpt-5-*",         pricing: { input: 1.25,  output: 10.00, cached: 0.625, reasoning: 10.00,  cache_creation: 1.25  } },
+  { pattern: "gpt-5*",          pricing: { input: 1.25,  output: 10.00, cached: 0.625, reasoning: 10.00,  cache_creation: 1.25  } },
+  { pattern: "gpt-4o-*",        pricing: { input: 0.15,  output: 0.60,  cached: 0.075, reasoning: 0.90,   cache_creation: 0.15  } },
+  { pattern: "gpt-4o",          pricing: { input: 2.50,  output: 10.00, cached: 1.25,  reasoning: 15.00,  cache_creation: 2.50  } },
+  { pattern: "gpt-4*",          pricing: { input: 2.50,  output: 10.00, cached: 1.25,  reasoning: 15.00,  cache_creation: 2.50  } },
+
+  // --- o1 / o-series ---
+  { pattern: "o1-*",            pricing: { input: 3.00,  output: 12.00, cached: 1.50,  reasoning: 18.00,  cache_creation: 3.00  } },
+  { pattern: "o1",              pricing: { input: 15.00, output: 60.00, cached: 7.50,  reasoning: 90.00,  cache_creation: 15.00 } },
+  { pattern: "o3-*",            pricing: { input: 10.00, output: 40.00, cached: 5.00,  reasoning: 60.00,  cache_creation: 10.00 } },
+  { pattern: "o4-*",            pricing: { input: 2.00,  output: 8.00,  cached: 1.00,  reasoning: 12.00,  cache_creation: 2.00  } },
+
+  // --- Qwen ---
+  { pattern: "qwen3-coder-*",   pricing: { input: 1.00,  output: 4.00,  cached: 0.50,  reasoning: 6.00,   cache_creation: 1.00  } },
+  { pattern: "qwen*-coder-*",   pricing: { input: 1.00,  output: 4.00,  cached: 0.50,  reasoning: 6.00,   cache_creation: 1.00  } },
+  { pattern: "qwen*",           pricing: { input: 0.50,  output: 2.00,  cached: 0.25,  reasoning: 3.00,   cache_creation: 0.50  } },
+
+  // --- Kimi ---
+  { pattern: "kimi-*-thinking",  pricing: { input: 1.80,  output: 7.20,  cached: 0.90,  reasoning: 10.80,  cache_creation: 1.80  } },
+  { pattern: "kimi-k2*",        pricing: { input: 1.20,  output: 4.80,  cached: 0.60,  reasoning: 7.20,   cache_creation: 1.20  } },
+  { pattern: "kimi-*",          pricing: { input: 1.00,  output: 4.00,  cached: 0.50,  reasoning: 6.00,   cache_creation: 1.00  } },
+
+  // --- DeepSeek ---
+  { pattern: "deepseek-*reasoner*", pricing: { input: 0.14, output: 0.28, cached: 0.0028, reasoning: 0.28, cache_creation: 0.14 } },
+  { pattern: "deepseek-r*",     pricing: { input: 0.14,  output: 0.28,  cached: 0.0028, reasoning: 0.28,   cache_creation: 0.14  } },
+  { pattern: "deepseek-v*",     pricing: { input: 0.14,  output: 0.28,  cached: 0.0028, reasoning: 0.28,   cache_creation: 0.14  } },
+  { pattern: "deepseek-*",      pricing: { input: 0.14,  output: 0.28,  cached: 0.0028, reasoning: 0.28,   cache_creation: 0.14  } },
+
+  // --- GLM ---
+  { pattern: "glm-5*",          pricing: { input: 1.00,  output: 4.00,  cached: 0.50,  reasoning: 6.00,   cache_creation: 1.00  } },
+  { pattern: "glm-4*",          pricing: { input: 0.75,  output: 3.00,  cached: 0.375, reasoning: 4.50,   cache_creation: 0.75  } },
+  { pattern: "glm-*",           pricing: { input: 0.50,  output: 2.00,  cached: 0.25,  reasoning: 3.00,   cache_creation: 0.50  } },
+
+  // --- MiniMax ---
+  { pattern: "MiniMax-*",       pricing: { input: 0.50,  output: 2.00,  cached: 0.25,  reasoning: 3.00,   cache_creation: 0.50  } },
+  { pattern: "minimax-*",       pricing: { input: 0.50,  output: 2.00,  cached: 0.25,  reasoning: 3.00,   cache_creation: 0.50  } },
+
+  // --- Grok ---
+  { pattern: "grok-code-*",     pricing: { input: 0.50,  output: 2.00,  cached: 0.25,  reasoning: 3.00,   cache_creation: 0.50  } },
+  { pattern: "grok-*",          pricing: { input: 0.50,  output: 2.00,  cached: 0.25,  reasoning: 3.00,   cache_creation: 0.50  } },
+];
+
+/**
+ * Match a model ID against a glob pattern (* = wildcard). Case-insensitive:
+ * registry ids mix casing (e.g. "MiniMax-M2.5" vs "minimax-m2.5").
+ */
+export function matchPattern(pattern, model) {
+  const regex = new RegExp("^" + pattern.split("*").map(s => s.replace(/[.*+?^${}()|[\]\\]/g, "\\$&")).join(".*") + "$", "i");
+  return regex.test(model);
+}
+
+/**
+ * Resolve pricing for a model using the 3-step fallback chain:
+ *   1. PROVIDER_PRICING[provider][model]
+ *   2. MODEL_PRICING[model]
+ *   3. PATTERN_PRICING (glob match)
+ *
+ * @param {string} provider
+ * @param {string} model
+ * @returns {object|null}
+ */
+export function getPricingForModel(provider, model) {
+  if (!model) return null;
+
+  // 1. Provider-specific override
+  if (provider && PROVIDER_PRICING[provider]?.[model]) {
+    return PROVIDER_PRICING[provider][model];
+  }
+
+  // 2. Canonical model pricing (strip vendor prefix if needed: "deepseek/deepseek-chat" → "deepseek-chat")
+  const baseModel = model.includes("/") ? model.split("/").pop() : model;
+  if (MODEL_PRICING[baseModel]) return MODEL_PRICING[baseModel];
+  if (MODEL_PRICING[model]) return MODEL_PRICING[model];
+
+  // 3. Pattern match
+  for (const { pattern, pricing } of PATTERN_PRICING) {
+    if (matchPattern(pattern, baseModel) || matchPattern(pattern, model)) {
+      return pricing;
+    }
+  }
+
+  return null;
+}
+
+/**
+ * Get all provider pricing (for UI / API).
+ * Returns PROVIDER_PRICING — consumers should fall back to MODEL_PRICING for unlisted models.
+ */
+export function getDefaultPricing() {
+  return PROVIDER_PRICING;
+}
+
+/**
+ * Format cost for display
+ * @param {number} cost
+ * @returns {string}
+ */
+export function formatCost(cost) {
+  if (cost === null || cost === undefined || isNaN(cost)) return "$0.00";
+  return `$${cost.toFixed(2)}`;
+}
+
+/**
+ * Calculate cost from tokens and pricing
+ * @param {object} tokens
+ * @param {object} pricing
+ * @returns {number} cost in dollars
+ */
+export function calculateCostFromTokens(tokens, pricing) {
+  if (!tokens || !pricing) return 0;
+
+  let cost = 0;
+
+  const inputTokens = tokens.prompt_tokens || tokens.input_tokens || 0;
+  const cachedTokens = tokens.cached_tokens || tokens.cache_read_input_tokens || 0;
+  const cacheCreationTokens = tokens.cache_creation_input_tokens || 0;
+  // prompt_tokens is cache-inclusive (see canonicalizeUsage): cached + cache_creation
+  // are subsets, so subtract both to avoid charging them at the full input rate.
+  const nonCachedInput = Math.max(0, inputTokens - cachedTokens - cacheCreationTokens);
+
+  cost += nonCachedInput * (pricing.input / 1000000);
+
+  if (cachedTokens > 0) {
+    cost += cachedTokens * ((pricing.cached || pricing.input) / 1000000);
+  }
+
+  const outputTokens = tokens.completion_tokens || tokens.output_tokens || 0;
+  cost += outputTokens * (pricing.output / 1000000);
+
+  const reasoningTokens = tokens.reasoning_tokens || 0;
+  if (reasoningTokens > 0) {
+    cost += reasoningTokens * ((pricing.reasoning || pricing.output) / 1000000);
+  }
+
+  if (cacheCreationTokens > 0) {
+    cost += cacheCreationTokens * ((pricing.cache_creation || pricing.input) / 1000000);
+  }
+
+  return cost;
+}

package/open-sse/providers/registry/alicode-intl.js

@@ -0,0 +1,30 @@
+export default {
+  id: "alicode-intl",
+  priority: 10,
+  alias: "alicode-intl",
+  display: {
+    name: "Alibaba Intl",
+    icon: "cloud",
+    color: "#FF6A00",
+    textIcon: "ALi",
+    website: "https://modelstudio.console.alibabacloud.com",
+    notice: {
+      apiKeyUrl: "https://modelstudio.console.alibabacloud.com/?apiKey=1",
+    },
+  },
+  category: "apikey",
+  transport: {
+    baseUrl: "https://coding-intl.dashscope.aliyuncs.com/v1/chat/completions",
+    headers: {},
+    quirks: { preserveCacheControl: true },
+  },
+  models: [
+    { id: "qwen3.5-plus", name: "Qwen3.5 Plus" },
+    { id: "kimi-k2.5", name: "Kimi K2.5" },
+    { id: "glm-5", name: "GLM 5" },
+    { id: "MiniMax-M2.5", name: "MiniMax M2.5" },
+    { id: "qwen3-coder-next", name: "Qwen3 Coder Next" },
+    { id: "qwen3-coder-plus", name: "Qwen3 Coder Plus" },
+    { id: "glm-4.7", name: "GLM 4.7" },
+  ],
+};

package/open-sse/providers/registry/alicode.js

@@ -0,0 +1,31 @@
+export default {
+  id: "alicode",
+  priority: 20,
+  alias: "alicode",
+  display: {
+    name: "Alibaba",
+    icon: "cloud",
+    color: "#FF6A00",
+    textIcon: "ALi",
+    website: "https://bailian.console.aliyun.com",
+    notice: {
+      apiKeyUrl: "https://bailian.console.aliyun.com/?apiKey=1",
+    },
+  },
+  category: "apikey",
+  transport: {
+    baseUrl: "https://coding.dashscope.aliyuncs.com/v1/chat/completions",
+    headers: {},
+    quirks: { preserveCacheControl: true },
+  },
+  models: [
+    { id: "qwen3.5-plus", name: "Qwen3.5 Plus" },
+    { id: "kimi-k2.5", name: "Kimi K2.5" },
+    { id: "glm-5", name: "GLM 5" },
+    { id: "MiniMax-M2.5", name: "MiniMax M2.5" },
+    { id: "qwen3-max-2026-01-23", name: "Qwen3 Max" },
+    { id: "qwen3-coder-next", name: "Qwen3 Coder Next" },
+    { id: "qwen3-coder-plus", name: "Qwen3 Coder Plus" },
+    { id: "glm-4.7", name: "GLM 4.7" },
+  ],
+};

package/open-sse/providers/registry/anthropic.js

@@ -0,0 +1,37 @@
+import { CLAUDE_API_HEADERS } from "../shared.js";
+
+export default {
+  id: "anthropic",
+  priority: 30,
+  alias: "anthropic",
+  display: {
+    name: "Anthropic",
+    icon: "smart_toy",
+    color: "#D97757",
+    textIcon: "AN",
+    website: "https://console.anthropic.com",
+    notice: {
+      apiKeyUrl: "https://console.anthropic.com/settings/keys",
+    },
+  },
+  category: "apikey",
+  transport: {
+    baseUrl: "https://api.anthropic.com/v1/messages",
+    format: "claude",
+    headers: {
+      "Anthropic-Version": "2023-06-01",
+      "Anthropic-Beta": "claude-code-20250219,interleaved-thinking-2025-05-14",
+    },
+  },
+  models: [
+    { id: "claude-sonnet-4-20250514", name: "Claude Sonnet 4" },
+    { id: "claude-opus-4-20250514", name: "Claude Opus 4" },
+    { id: "claude-opus-4-7", name: "Claude Opus 4.7" },
+    { id: "claude-opus-4-8", name: "Claude Opus 4.8" },
+    { id: "claude-sonnet-5", name: "Claude Sonnet 5" },
+    { id: "claude-fable-5", name: "Claude Fable 5" },
+    { id: "claude-haiku-4-5", name: "Claude Haiku 4.5" },
+    { id: "claude-3-5-sonnet-20241022", name: "Claude 3.5 Sonnet" },
+  ],
+  serviceKinds: ["llm","imageToText"],
+};

package/open-sse/providers/registry/antigravity.js

@@ -0,0 +1,81 @@
+import { ANTIGRAVITY_IDE_BASE_URL, ANTIGRAVITY_IDE_USER_AGENT, ANTIGRAVITY_OAUTH_CLIENT } from "../shared.js";
+
+export default {
+  id: "antigravity",
+  priority: 20,
+  alias: "ag",
+  uiAlias: "ag",
+  display: {
+    name: "Antigravity",
+    icon: "rocket_launch",
+    color: "#F59E0B",
+    website: "https://antigravity.google",
+    notice: {
+      signupUrl: "https://antigravity.google",
+    },
+    deprecated: true,
+    deprecationNotice: "RISK_NOTICE",
+  },
+  category: "oauth",
+  serviceKinds: ["llm", "image"],
+  transport: {
+    baseUrls: [ANTIGRAVITY_IDE_BASE_URL],
+    format: "antigravity",
+    headers: {
+      "User-Agent": ANTIGRAVITY_IDE_USER_AGENT,
+    },
+    retry: {
+      "429": {
+        attempts: 3,
+      },
+      "500": {
+        attempts: 3,
+      },
+      "503": {
+        attempts: 3,
+      },
+    },
+    usage: {
+      quotaApiUrl: "https://cloudcode-pa.googleapis.com/v1internal:fetchAvailableModels",
+      loadProjectApiUrl: "https://cloudcode-pa.googleapis.com/v1internal:loadCodeAssist",
+      tokenUrl: "https://oauth2.googleapis.com/token",
+    },
+    clientId: "1071006060591-tmhssin2h21lcre235vtolojh4g403ep.apps.googleusercontent.com",
+    clientSecret: "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",
+  },
+  models: [
+    { id: "gemini-3-flash-agent", name: "Gemini 3.5 Flash (High)" },
+    { id: "gemini-3.5-flash-low", name: "Gemini 3.5 Flash (Medium)" },
+    { id: "gemini-3.5-flash-extra-low", name: "Gemini 3.5 Flash (Low)" },
+    { id: "gemini-pro-agent", name: "Gemini 3.1 Pro (High)" },
+    { id: "gemini-3.1-pro-low", name: "Gemini 3.1 Pro (Low)" },
+    { id: "claude-sonnet-4-6", name: "Claude Sonnet 4.6 (Thinking)" },
+    { id: "claude-opus-4-6-thinking", name: "Claude Opus 4.6 (Thinking)" },
+    { id: "gpt-oss-120b-medium", name: "GPT-OSS 120B (Medium)" },
+    { id: "gemini-3-flash", name: "Gemini 3 Flash", thinking: false },
+    // Image generation models
+    { id: "gemini-3.1-flash-image", name: "Gemini 3.1 Flash (Image)", kind: "image", imageGen: true, capabilities: ["textToImage"] },
+  ],
+  oauth: {
+    authorizeUrl: "https://accounts.google.com/o/oauth2/v2/auth",
+    tokenUrl: "https://oauth2.googleapis.com/token",
+    userInfoUrl: "https://www.googleapis.com/oauth2/v1/userinfo",
+    scopes: [
+      "https://www.googleapis.com/auth/cloud-platform",
+      "https://www.googleapis.com/auth/userinfo.email",
+      "https://www.googleapis.com/auth/userinfo.profile",
+      "https://www.googleapis.com/auth/cclog",
+      "https://www.googleapis.com/auth/experimentsandconfigs",
+    ],
+    apiEndpoint: "https://cloudcode-pa.googleapis.com",
+    apiVersion: "v1internal",
+    loadCodeAssistEndpoint: "https://cloudcode-pa.googleapis.com/v1internal:loadCodeAssist",
+    onboardUserEndpoint: "https://cloudcode-pa.googleapis.com/v1internal:onboardUser",
+    loadCodeAssistUserAgent: "google-api-nodejs-client/9.15.1",
+    loadCodeAssistApiClient: "google-cloud-sdk vscode_cloudshelleditor/0.1",
+    refreshLeadMs: 300000,
+  },
+  features: {
+    usage: true,
+  },
+};

package/open-sse/providers/registry/assemblyai.js

@@ -0,0 +1,38 @@
+export default {
+  id: "assemblyai",
+  priority: 30,
+  alias: "assemblyai",
+  aliases: [
+    "aai",
+  ],
+  uiAlias: "aai",
+  display: {
+    name: "AssemblyAI",
+    icon: "record_voice_over",
+    color: "#0062FF",
+    textIcon: "AA",
+    website: "https://assemblyai.com",
+    notice: {
+      apiKeyUrl: "https://www.assemblyai.com/app/api-keys",
+    },
+  },
+  category: "apikey",
+  authType: "apikey",
+  transport: {
+    baseUrl: "https://api.assemblyai.com/v1/audio/transcriptions",
+    validateUrl: "https://api.assemblyai.com/v1/account",
+  },
+  models: [
+    { id: "universal-3-pro", name: "Universal 3 Pro", params: ["language"], kind: "stt" },
+    { id: "universal-2", name: "Universal 2", params: ["language"], kind: "stt" },
+    { id: "best", name: "Best (Nano + Universal)", kind: "stt" },
+    { id: "nano", name: "Nano (Fast)", kind: "stt" },
+  ],
+  serviceKinds: ["stt"],
+  sttConfig: {
+    baseUrl: "https://api.assemblyai.com/v2/transcript",
+    authType: "apikey",
+    authHeader: "authorization",
+    format: "assemblyai",
+  },
+};

package/open-sse/providers/registry/aws-polly.js

@@ -0,0 +1,45 @@
+export default {
+  id: "aws-polly",
+  alias: "polly",
+  display: {
+    name: "AWS Polly",
+    icon: "record_voice_over",
+    color: "#FF9900",
+    textIcon: "PL",
+    website: "https://aws.amazon.com/polly/",
+    notice: {
+      text: "Use AWS Secret Access Key as API key; set providerSpecificData.accessKeyId and optional region.",
+      apiKeyUrl: "https://console.aws.amazon.com/iam/home#/security_credentials"
+    }
+  },
+  category: "apikey",
+  authType: "apikey",
+  serviceKinds: [
+    "tts"
+  ],
+  ttsConfig: {
+    baseUrl: "https://polly.{region}.amazonaws.com/v1/speech",
+    authType: "apikey",
+    authHeader: "aws-sigv4",
+    format: "aws-polly",
+    models: [
+      {
+        id: "standard",
+        name: "Standard"
+      },
+      {
+        id: "neural",
+        name: "Neural"
+      },
+      {
+        id: "long-form",
+        name: "Long-form"
+      },
+      {
+        id: "generative",
+        name: "Generative"
+      }
+    ]
+  },
+  hasProviderSpecificData: true
+};

package/open-sse/providers/registry/azure.js

@@ -0,0 +1,21 @@
+export default {
+  id: "azure",
+  priority: 40,
+  alias: "azure",
+  display: {
+    name: "Azure OpenAI",
+    icon: "cloud",
+    color: "#0078D4",
+    textIcon: "AZ",
+    website: "https://azure.microsoft.com/en-us/products/ai-services/openai-service",
+    notice: {
+      apiKeyUrl: "https://portal.azure.com/#view/Microsoft_Azure_ProjectOxford/CognitiveServicesHub/~/OpenAI",
+    },
+  },
+  category: "apikey",
+  hasProviderSpecificData: true,
+  transport: {
+    baseUrl: "",
+    headers: {},
+  },
+};

package/open-sse/providers/registry/black-forest-labs.js

@@ -0,0 +1,32 @@
+export default {
+  id: "black-forest-labs",
+  priority: 50,
+  alias: "black-forest-labs",
+  aliases: [
+    "bfl",
+  ],
+  uiAlias: "bfl",
+  display: {
+    name: "Black Forest Labs",
+    icon: "image",
+    color: "#111827",
+    textIcon: "BF",
+    website: "https://blackforestlabs.ai",
+    notice: {
+      apiKeyUrl: "https://api.bfl.ai",
+    },
+  },
+  category: "apikey",
+  authType: "apikey",
+  transport: null,
+  models: [
+    { id: "flux-pro-1.1", name: "FLUX Pro 1.1", params: ["n","size"], kind: "image" },
+    { id: "flux-pro-1.1-ultra", name: "FLUX Pro 1.1 Ultra", params: ["size"], kind: "image" },
+    { id: "flux-pro", name: "FLUX Pro", params: ["n","size"], kind: "image" },
+    { id: "flux-dev", name: "FLUX Dev", params: ["n","size"], kind: "image" },
+    { id: "flux-kontext-pro", name: "FLUX Kontext Pro (Edit)", params: ["size"], capabilities: ["edit"], kind: "image" },
+    { id: "flux-kontext-max", name: "FLUX Kontext Max (Edit)", params: ["size"], capabilities: ["edit"], kind: "image" },
+  ],
+  serviceKinds: ["image"],
+  imageConfig: { baseUrl: "https://api.bfl.ai/v1" },
+};