Merge main into model-registry

2026-06-22 14:00:18 +02:00
parent 019b022068 717a8f958a
commit abbd911693
220 changed files with 10488 additions and 4354 deletions
@@ -16,7 +16,7 @@ export const FIREWORKS_MODELS = {
 		cost: {
 			input: 0.14,
 			output: 0.28,
-			cacheRead: 0.03,
+			cacheRead: 0.028,
 			cacheWrite: 0,
 		},
 		contextWindow: 1000000,
@@ -58,6 +58,25 @@ export const FIREWORKS_MODELS = {
 		contextWindow: 202800,
 		maxTokens: 131072,
 	} satisfies Model<"anthropic-messages">,
+	"accounts/fireworks/models/glm-5p2": {
+		id: "accounts/fireworks/models/glm-5p2",
+		name: "GLM 5.2",
+		api: "openai-completions",
+		provider: "fireworks",
+		baseUrl: "https://api.fireworks.ai/inference/v1",
+		compat: {"supportsStore":false,"supportsDeveloperRole":false},
+		reasoning: true,
+		thinkingLevelMap: {"off":"none","minimal":null,"low":"high","medium":"high","xhigh":"max"},
+		input: ["text"],
+		cost: {
+			input: 1.4,
+			output: 4.4,
+			cacheRead: 0.26,
+			cacheWrite: 0,
+		},
+		contextWindow: 1048576,
+		maxTokens: 131072,
+	} satisfies Model<"openai-completions">,
 	"accounts/fireworks/models/gpt-oss-120b": {
 		id: "accounts/fireworks/models/gpt-oss-120b",
 		name: "GPT OSS 120B",
@@ -94,24 +113,6 @@ export const FIREWORKS_MODELS = {
 		contextWindow: 131072,
 		maxTokens: 32768,
 	} satisfies Model<"anthropic-messages">,
-	"accounts/fireworks/models/kimi-k2p5": {
-		id: "accounts/fireworks/models/kimi-k2p5",
-		name: "Kimi K2.5",
-		api: "anthropic-messages",
-		provider: "fireworks",
-		baseUrl: "https://api.fireworks.ai/inference",
-		compat: {"sendSessionAffinityHeaders":true,"supportsEagerToolInputStreaming":false,"supportsCacheControlOnTools":false,"supportsLongCacheRetention":false},
-		reasoning: true,
-		input: ["text", "image"],
-		cost: {
-			input: 0.6,
-			output: 3,
-			cacheRead: 0.1,
-			cacheWrite: 0,
-		},
-		contextWindow: 256000,
-		maxTokens: 256000,
-	} satisfies Model<"anthropic-messages">,
 	"accounts/fireworks/models/kimi-k2p6": {
 		id: "accounts/fireworks/models/kimi-k2p6",
 		name: "Kimi K2.6",
@@ -130,23 +131,23 @@ export const FIREWORKS_MODELS = {
 		contextWindow: 262000,
 		maxTokens: 262000,
 	} satisfies Model<"anthropic-messages">,
-	"accounts/fireworks/models/minimax-m2p5": {
-		id: "accounts/fireworks/models/minimax-m2p5",
-		name: "MiniMax-M2.5",
+	"accounts/fireworks/models/kimi-k2p7-code": {
+		id: "accounts/fireworks/models/kimi-k2p7-code",
+		name: "Kimi K2.7 Code",
 		api: "anthropic-messages",
 		provider: "fireworks",
 		baseUrl: "https://api.fireworks.ai/inference",
 		compat: {"sendSessionAffinityHeaders":true,"supportsEagerToolInputStreaming":false,"supportsCacheControlOnTools":false,"supportsLongCacheRetention":false},
 		reasoning: true,
-		input: ["text"],
+		input: ["text", "image"],
 		cost: {
-			input: 0.3,
-			output: 1.2,
-			cacheRead: 0.03,
+			input: 0.95,
+			output: 4,
+			cacheRead: 0.19,
 			cacheWrite: 0,
 		},
-		contextWindow: 196608,
-		maxTokens: 196608,
+		contextWindow: 262000,
+		maxTokens: 262000,
 	} satisfies Model<"anthropic-messages">,
 	"accounts/fireworks/models/minimax-m2p7": {
 		id: "accounts/fireworks/models/minimax-m2p7",
@@ -166,9 +167,27 @@ export const FIREWORKS_MODELS = {
 		contextWindow: 196608,
 		maxTokens: 196608,
 	} satisfies Model<"anthropic-messages">,
-	"accounts/fireworks/models/qwen3p6-plus": {
-		id: "accounts/fireworks/models/qwen3p6-plus",
-		name: "Qwen 3.6 Plus",
+	"accounts/fireworks/models/minimax-m3": {
+		id: "accounts/fireworks/models/minimax-m3",
+		name: "MiniMax-M3",
+		api: "anthropic-messages",
+		provider: "fireworks",
+		baseUrl: "https://api.fireworks.ai/inference",
+		compat: {"sendSessionAffinityHeaders":true,"supportsEagerToolInputStreaming":false,"supportsCacheControlOnTools":false,"supportsLongCacheRetention":false},
+		reasoning: true,
+		input: ["text"],
+		cost: {
+			input: 0.3,
+			output: 1.2,
+			cacheRead: 0.06,
+			cacheWrite: 0,
+		},
+		contextWindow: 512000,
+		maxTokens: 512000,
+	} satisfies Model<"anthropic-messages">,
+	"accounts/fireworks/models/qwen3p7-plus": {
+		id: "accounts/fireworks/models/qwen3p7-plus",
+		name: "Qwen 3.7 Plus",
 		api: "anthropic-messages",
 		provider: "fireworks",
 		baseUrl: "https://api.fireworks.ai/inference",
@@ -176,9 +195,9 @@ export const FIREWORKS_MODELS = {
 		reasoning: true,
 		input: ["text", "image"],
 		cost: {
-			input: 0.5,
-			output: 3,
-			cacheRead: 0.1,
+			input: 0.4,
+			output: 1.6,
+			cacheRead: 0.08,
 			cacheWrite: 0,
 		},
 		contextWindow: 262144,
@@ -238,4 +257,22 @@ export const FIREWORKS_MODELS = {
 		contextWindow: 262000,
 		maxTokens: 262000,
 	} satisfies Model<"anthropic-messages">,
+	"accounts/fireworks/routers/kimi-k2p7-code-fast": {
+		id: "accounts/fireworks/routers/kimi-k2p7-code-fast",
+		name: "Kimi K2.7 Code Fast",
+		api: "anthropic-messages",
+		provider: "fireworks",
+		baseUrl: "https://api.fireworks.ai/inference",
+		compat: {"sendSessionAffinityHeaders":true,"supportsEagerToolInputStreaming":false,"supportsCacheControlOnTools":false,"supportsLongCacheRetention":false},
+		reasoning: true,
+		input: ["text", "image"],
+		cost: {
+			input: 1.9,
+			output: 8,
+			cacheRead: 0.38,
+			cacheWrite: 0,
+		},
+		contextWindow: 262000,
+		maxTokens: 262000,
+	} satisfies Model<"anthropic-messages">,
 } as const;