@hyperspaceng/neural-ai 0.67.7 → 0.68.1

package/README.md

@@ -851,11 +851,13 @@ interface OpenAICompletionsCompat {
   supportsReasoningEffort?: boolean; // Whether provider supports `reasoning_effort` (default: true)
   supportsUsageInStreaming?: boolean; // Whether provider supports `stream_options: { include_usage: true }` (default: true)
   supportsStrictMode?: boolean;      // Whether provider supports `strict` in tool definitions (default: true)
+  sendSessionAffinityHeaders?: boolean; // Whether to send `session_id`, `x-client-request-id`, and `x-session-affinity` from `sessionId` when caching is enabled (default: false)
   maxTokensField?: 'max_completion_tokens' | 'max_tokens';  // Which field name to use (default: max_completion_tokens)
   requiresToolResultName?: boolean;  // Whether tool results require the `name` field (default: false)
   requiresAssistantAfterToolResult?: boolean; // Whether tool results must be followed by an assistant message (default: false)
   requiresThinkingAsText?: boolean;  // Whether thinking blocks must be converted to text (default: false)
-  thinkingFormat?: 'openai' | 'zai' | 'qwen'; // Format for reasoning param: 'openai' uses reasoning_effort, 'zai' uses thinking: { type: "enabled" }, 'qwen' uses enable_thinking: boolean (default: openai)
+  thinkingFormat?: 'openai' | 'zai' | 'qwen' | 'qwen-chat-template'; // Format for reasoning param: 'openai' uses reasoning_effort, 'zai' uses thinking: { type: "enabled" }, 'qwen' uses enable_thinking: boolean, 'qwen-chat-template' uses chat_template_kwargs.enable_thinking (default: openai)
+  cacheControlFormat?: 'anthropic';  // Anthropic-style cache_control on system prompt, last tool, and last user/assistant text content
   openRouterRouting?: OpenRouterRouting; // OpenRouter routing preferences (default: {})
   vercelGatewayRouting?: VercelGatewayRouting; // Vercel AI Gateway routing preferences (default: {})
 }

package/dist/models.generated.d.ts

@@ -4877,6 +4877,26 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
+        readonly "moonshotai/Kimi-K2.6": {
+            id: string;
+            name: string;
+            api: "openai-completions";
+            provider: string;
+            baseUrl: string;
+            compat: {
+                supportsDeveloperRole: false;
+            };
+            reasoning: true;
+            input: ("image" | "text")[];
+            cost: {
+                input: number;
+                output: number;
+                cacheRead: number;
+                cacheWrite: number;
+            };
+            contextWindow: number;
+            maxTokens: number;
+        };
         readonly "zai-org/GLM-4.7": {
             id: string;
             name: string;
@@ -4959,6 +4979,23 @@ export declare const MODELS: {
         };
     };
     readonly "kimi-coding": {
+        readonly k2p6: {
+            id: string;
+            name: string;
+            api: "anthropic-messages";
+            provider: string;
+            baseUrl: string;
+            reasoning: true;
+            input: ("image" | "text")[];
+            cost: {
+                input: number;
+                output: number;
+                cacheRead: number;
+                cacheWrite: number;
+            };
+            contextWindow: number;
+            maxTokens: number;
+        };
         readonly "kimi-for-coding": {
             id: string;
             name: string;
@@ -6841,6 +6878,40 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
+        readonly "kimi-k2.6": {
+            id: string;
+            name: string;
+            api: "openai-completions";
+            provider: string;
+            baseUrl: string;
+            reasoning: true;
+            input: ("image" | "text")[];
+            cost: {
+                input: number;
+                output: number;
+                cacheRead: number;
+                cacheWrite: number;
+            };
+            contextWindow: number;
+            maxTokens: number;
+        };
+        readonly "ling-2.6-flash-free": {
+            id: string;
+            name: string;
+            api: "openai-completions";
+            provider: string;
+            baseUrl: string;
+            reasoning: false;
+            input: "text"[];
+            cost: {
+                input: number;
+                output: number;
+                cacheRead: number;
+                cacheWrite: number;
+            };
+            contextWindow: number;
+            maxTokens: number;
+        };
         readonly "minimax-m2.5": {
             id: string;
             name: string;
@@ -6875,6 +6946,23 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
+        readonly "minimax-m2.7": {
+            id: string;
+            name: string;
+            api: "openai-completions";
+            provider: string;
+            baseUrl: string;
+            reasoning: true;
+            input: "text"[];
+            cost: {
+                input: number;
+                output: number;
+                cacheRead: number;
+                cacheWrite: number;
+            };
+            contextWindow: number;
+            maxTokens: number;
+        };
         readonly "nemotron-3-super-free": {
             id: string;
             name: string;
@@ -6895,7 +6983,7 @@ export declare const MODELS: {
         readonly "qwen3.5-plus": {
             id: string;
             name: string;
-            api: "openai-completions";
+            api: "anthropic-messages";
             provider: string;
             baseUrl: string;
             reasoning: true;
@@ -6912,7 +7000,7 @@ export declare const MODELS: {
         readonly "qwen3.6-plus": {
             id: string;
             name: string;
-            api: "openai-completions";
+            api: "anthropic-messages";
             provider: string;
             baseUrl: string;
             reasoning: true;
@@ -6979,6 +7067,23 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
+        readonly "kimi-k2.6": {
+            id: string;
+            name: string;
+            api: "openai-completions";
+            provider: string;
+            baseUrl: string;
+            reasoning: true;
+            input: ("image" | "text")[];
+            cost: {
+                input: number;
+                output: number;
+                cacheRead: number;
+                cacheWrite: number;
+            };
+            contextWindow: number;
+            maxTokens: number;
+        };
         readonly "mimo-v2-omni": {
             id: string;
             name: string;
@@ -7050,7 +7155,7 @@ export declare const MODELS: {
         readonly "qwen3.5-plus": {
             id: string;
             name: string;
-            api: "openai-completions";
+            api: "anthropic-messages";
             provider: string;
             baseUrl: string;
             reasoning: true;
@@ -7067,7 +7172,7 @@ export declare const MODELS: {
         readonly "qwen3.6-plus": {
             id: string;
             name: string;
-            api: "openai-completions";
+            api: "anthropic-messages";
             provider: string;
             baseUrl: string;
             reasoning: true;
@@ -8120,7 +8225,7 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
-        readonly "kwaipilot/kat-coder-pro-v2": {
+        readonly "inclusionai/ling-2.6-flash:free": {
             id: string;
             name: string;
             api: "openai-completions";
@@ -8137,7 +8242,7 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
-        readonly "meta-llama/llama-3-8b-instruct": {
+        readonly "kwaipilot/kat-coder-pro-v2": {
             id: string;
             name: string;
             api: "openai-completions";
@@ -8154,7 +8259,7 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
-        readonly "meta-llama/llama-3.1-70b-instruct": {
+        readonly "meta-llama/llama-3-8b-instruct": {
             id: string;
             name: string;
             api: "openai-completions";
@@ -8171,7 +8276,7 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
-        readonly "meta-llama/llama-3.1-8b-instruct": {
+        readonly "meta-llama/llama-3.1-70b-instruct": {
             id: string;
             name: string;
             api: "openai-completions";
@@ -8188,7 +8293,7 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
-        readonly "meta-llama/llama-3.3-70b-instruct": {
+        readonly "meta-llama/llama-3.1-8b-instruct": {
             id: string;
             name: string;
             api: "openai-completions";
@@ -8205,7 +8310,7 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
-        readonly "meta-llama/llama-3.3-70b-instruct:free": {
+        readonly "meta-llama/llama-3.3-70b-instruct": {
             id: string;
             name: string;
             api: "openai-completions";
@@ -8222,14 +8327,14 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
-        readonly "meta-llama/llama-4-maverick": {
+        readonly "meta-llama/llama-3.3-70b-instruct:free": {
             id: string;
             name: string;
             api: "openai-completions";
             provider: string;
             baseUrl: string;
             reasoning: false;
-            input: ("image" | "text")[];
+            input: "text"[];
             cost: {
                 input: number;
                 output: number;
@@ -8800,6 +8905,23 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
+        readonly "moonshotai/kimi-k2.6": {
+            id: string;
+            name: string;
+            api: "openai-completions";
+            provider: string;
+            baseUrl: string;
+            reasoning: true;
+            input: ("image" | "text")[];
+            cost: {
+                input: number;
+                output: number;
+                cacheRead: number;
+                cacheWrite: number;
+            };
+            contextWindow: number;
+            maxTokens: number;
+        };
         readonly "nex-agi/deepseek-v3.1-nex-n1": {
             id: string;
             name: string;
@@ -9276,23 +9398,6 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
-        readonly "openai/gpt-4o:extended": {
-            id: string;
-            name: string;
-            api: "openai-completions";
-            provider: string;
-            baseUrl: string;
-            reasoning: false;
-            input: ("image" | "text")[];
-            cost: {
-                input: number;
-                output: number;
-                cacheRead: number;
-                cacheWrite: number;
-            };
-            contextWindow: number;
-            maxTokens: number;
-        };
         readonly "openai/gpt-5": {
             id: string;
             name: string;
@@ -9327,40 +9432,6 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
-        readonly "openai/gpt-5-image": {
-            id: string;
-            name: string;
-            api: "openai-completions";
-            provider: string;
-            baseUrl: string;
-            reasoning: true;
-            input: ("image" | "text")[];
-            cost: {
-                input: number;
-                output: number;
-                cacheRead: number;
-                cacheWrite: number;
-            };
-            contextWindow: number;
-            maxTokens: number;
-        };
-        readonly "openai/gpt-5-image-mini": {
-            id: string;
-            name: string;
-            api: "openai-completions";
-            provider: string;
-            baseUrl: string;
-            reasoning: true;
-            input: ("image" | "text")[];
-            cost: {
-                input: number;
-                output: number;
-                cacheRead: number;
-                cacheWrite: number;
-            };
-            contextWindow: number;
-            maxTokens: number;
-        };
         readonly "openai/gpt-5-mini": {
             id: string;
             name: string;
@@ -9956,23 +10027,6 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
-        readonly "openrouter/elephant-alpha": {
-            id: string;
-            name: string;
-            api: "openai-completions";
-            provider: string;
-            baseUrl: string;
-            reasoning: false;
-            input: "text"[];
-            cost: {
-                input: number;
-                output: number;
-                cacheRead: number;
-                cacheWrite: number;
-            };
-            contextWindow: number;
-            maxTokens: number;
-        };
         readonly "openrouter/free": {
             id: string;
             name: string;
@@ -10183,7 +10237,7 @@ export declare const MODELS: {
             api: "openai-completions";
             provider: string;
             baseUrl: string;
-            reasoning: true;
+            reasoning: false;
             input: "text"[];
             cost: {
                 input: number;
@@ -11333,6 +11387,23 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
+        readonly "~anthropic/claude-opus-latest": {
+            id: string;
+            name: string;
+            api: "openai-completions";
+            provider: string;
+            baseUrl: string;
+            reasoning: true;
+            input: ("image" | "text")[];
+            cost: {
+                input: number;
+                output: number;
+                cacheRead: number;
+                cacheWrite: number;
+            };
+            contextWindow: number;
+            maxTokens: number;
+        };
     };
     readonly "vercel-ai-gateway": {
         readonly "alibaba/qwen-3-14b": {
@@ -11403,6 +11474,23 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
+        readonly "alibaba/qwen-3.6-max-preview": {
+            id: string;
+            name: string;
+            api: "anthropic-messages";
+            provider: string;
+            baseUrl: string;
+            reasoning: true;
+            input: ("image" | "text")[];
+            cost: {
+                input: number;
+                output: number;
+                cacheRead: number;
+                cacheWrite: number;
+            };
+            contextWindow: number;
+            maxTokens: number;
+        };
         readonly "alibaba/qwen3-235b-a22b-thinking": {
             id: string;
             name: string;
@@ -12746,6 +12834,23 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
+        readonly "moonshotai/kimi-k2.6": {
+            id: string;
+            name: string;
+            api: "anthropic-messages";
+            provider: string;
+            baseUrl: string;
+            reasoning: true;
+            input: ("image" | "text")[];
+            cost: {
+                input: number;
+                output: number;
+                cacheRead: number;
+                cacheWrite: number;
+            };
+            contextWindow: number;
+            maxTokens: number;
+        };
         readonly "nvidia/nemotron-nano-12b-v2-vl": {
             id: string;
             name: string;