@juspay/neurolink 12.9.6 → 12.11.0

package/dist/providers/catalog/baseten.json

@@ -0,0 +1,263 @@
+{
+    "$schema": "./provider-catalog.schema.json",
+    "id": "baseten",
+    "displayName": "Baseten",
+    "aliases": [],
+    "tier": 2,
+    "wire": {
+        "baseURL": "https://inference.baseten.co/v1"
+    },
+    "models": {
+        "default": "zai-org/GLM-5.3-Flash",
+        "fallbacks": [
+            "zai-org/GLM-5.3-Flash",
+            "zai-org/GLM-5.3",
+            "zai-org/GLM-5.2"
+        ],
+        "defaultContextWindow": 1048576,
+        "defaultMaxOutputTokens": 131072,
+        "catalog": {
+            "openai/gpt-oss-120b": {
+                "contextWindow": 128072,
+                "maxOutputTokens": 128072,
+                "pricingPerMTok": {
+                    "input": 0.1,
+                    "output": 0.5,
+                    "cachedInput": 0.1
+                },
+                "vision": false,
+                "status": "production",
+                "description": "OpenAI GPT-OSS 120B; general-purpose model with controllable reasoning"
+            },
+            "zai-org/GLM-4.7": {
+                "contextWindow": 200000,
+                "maxOutputTokens": 200000,
+                "pricingPerMTok": {
+                    "input": 0.6,
+                    "output": 2.2,
+                    "cachedInput": 0.12
+                },
+                "vision": false,
+                "status": "production",
+                "description": "GLM 4.7; fast general-purpose model with 200K context and enhanced tool use"
+            },
+            "moonshotai/Kimi-K2.6": {
+                "contextWindow": 262000,
+                "maxOutputTokens": 262000,
+                "pricingPerMTok": {
+                    "input": 0.95,
+                    "output": 4,
+                    "cachedInput": 0.16
+                },
+                "vision": false,
+                "status": "production",
+                "description": "Kimi K2.6; agentic and coding model for multi-step reasoning and tool use"
+            },
+            "deepseek-ai/DeepSeek-V4-Pro": {
+                "contextWindow": 1048576,
+                "maxOutputTokens": 262144,
+                "pricingPerMTok": {
+                    "input": 1.74,
+                    "output": 3.48,
+                    "cachedInput": 0.145
+                },
+                "vision": false,
+                "status": "production",
+                "description": "DeepSeek V4 Pro; 1M-context mixture-of-experts model for agentic workflows and coding"
+            },
+            "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B": {
+                "contextWindow": 202800,
+                "maxOutputTokens": 202800,
+                "pricingPerMTok": {
+                    "input": 0.6,
+                    "output": 2.4,
+                    "cachedInput": 0.12
+                },
+                "vision": false,
+                "status": "production",
+                "description": "NVIDIA Nemotron 3 Ultra; flagship reasoning and non-reasoning model for code and agentic execution"
+            },
+            "zai-org/GLM-5.2": {
+                "contextWindow": 1048576,
+                "maxOutputTokens": 262144,
+                "pricingPerMTok": {
+                    "input": 1.4,
+                    "output": 4.4,
+                    "cachedInput": 0.14
+                },
+                "vision": false,
+                "status": "production",
+                "description": "GLM 5.2; 1M-context reasoning model"
+            },
+            "moonshotai/Kimi-K2.7-Code": {
+                "contextWindow": 262000,
+                "maxOutputTokens": 262000,
+                "pricingPerMTok": {
+                    "input": 0.95,
+                    "output": 4,
+                    "cachedInput": 0.16
+                },
+                "vision": false,
+                "status": "production",
+                "description": "Kimi K2.7 Code; model for complex coding, code reasoning and long-horizon development"
+            },
+            "deepseek-ai/DeepSeek-V4-Flash-0731": {
+                "contextWindow": 1048576,
+                "maxOutputTokens": 384000,
+                "pricingPerMTok": {
+                    "input": 0.13,
+                    "output": 0.26,
+                    "cachedInput": 0.028
+                },
+                "vision": false,
+                "status": "production",
+                "description": "DeepSeek V4 Flash 0731; fast, low-cost 1M-context mixture-of-experts model"
+            },
+            "thinkingmachines/inkling": {
+                "contextWindow": 1048576,
+                "maxOutputTokens": 32768,
+                "pricingPerMTok": {
+                    "input": 1,
+                    "output": 4.05,
+                    "cachedInput": 0.17
+                },
+                "vision": false,
+                "status": "production",
+                "description": "Thinking Machines Inkling; 1M-context reasoning model"
+            },
+            "zai-org/GLM-5.2-Fast": {
+                "contextWindow": 1048576,
+                "maxOutputTokens": 262144,
+                "pricingPerMTok": {
+                    "input": 2.1,
+                    "output": 6.6,
+                    "cachedInput": 0.21
+                },
+                "vision": false,
+                "status": "production",
+                "description": "GLM 5.2 Fast; 1M-context model"
+            },
+            "moonshotai/Kimi-K3": {
+                "contextWindow": 1048576,
+                "maxOutputTokens": 262144,
+                "pricingPerMTok": {
+                    "input": 3,
+                    "output": 15,
+                    "cachedInput": 0.3
+                },
+                "vision": false,
+                "status": "production",
+                "description": "Kimi K3; 1M-context model"
+            },
+            "thinkingmachines/inkling-small": {
+                "contextWindow": 1048576,
+                "maxOutputTokens": 32768,
+                "pricingPerMTok": {
+                    "input": 0.5,
+                    "output": 1.2,
+                    "cachedInput": 0.1
+                },
+                "vision": false,
+                "status": "production",
+                "description": "Thinking Machines Inkling Small; 1M-context reasoning model"
+            },
+            "deepseek-ai/DeepSeek-V4-Pro-0813": {
+                "contextWindow": 1048576,
+                "maxOutputTokens": 262144,
+                "pricingPerMTok": {
+                    "input": 1.32,
+                    "output": 3.96,
+                    "cachedInput": 0.132
+                },
+                "vision": false,
+                "status": "production",
+                "description": "DeepSeek V4 Pro 0813; dated 1M-context mixture-of-experts model for agentic workflows and coding"
+            },
+            "zai-org/GLM-5.3-Flash": {
+                "contextWindow": 1048576,
+                "maxOutputTokens": 131072,
+                "pricingPerMTok": {
+                    "input": 0.15,
+                    "output": 0.5,
+                    "cachedInput": 0.03
+                },
+                "vision": true,
+                "status": "production",
+                "description": "Recommended - GLM 5.3 Flash; 1M-context reasoning model with live-verified image input"
+            },
+            "zai-org/GLM-5.3": {
+                "contextWindow": 1048576,
+                "maxOutputTokens": 262144,
+                "pricingPerMTok": {
+                    "input": 1.4,
+                    "output": 4.4,
+                    "cachedInput": 0.14
+                },
+                "vision": false,
+                "status": "production",
+                "description": "GLM 5.3; 1M-context reasoning model"
+            },
+            "zai-org/GLM-5.3-Fast": {
+                "contextWindow": 1048576,
+                "maxOutputTokens": 262144,
+                "pricingPerMTok": {
+                    "input": 2.1,
+                    "output": 6.6,
+                    "cachedInput": 0.21
+                },
+                "vision": true,
+                "status": "production",
+                "description": "GLM 5.3 Fast; 1M-context reasoning model with image input"
+            }
+        },
+        "visionModel": "zai-org/GLM-5.3-Flash",
+        "topModels": [
+            "zai-org/GLM-5.3-Flash",
+            "zai-org/GLM-5.3",
+            "zai-org/GLM-5.2",
+            "openai/gpt-oss-120b",
+            "deepseek-ai/DeepSeek-V4-Flash-0731"
+        ]
+    },
+    "capabilities": {
+        "text": true,
+        "streaming": true,
+        "tools": true,
+        "toolsWithStreaming": true,
+        "structuredOutput": true,
+        "structuredOutputWithTools": true,
+        "embeddings": false,
+        "thinking": false
+    },
+    "errorRules": [
+        {
+            "pattern": "please check the api-key you provided",
+            "class": "authentication",
+            "message": "Invalid Baseten API key. Check {apiKeyEnvVar}. Get one at https://app.baseten.co/"
+        }
+    ],
+    "setup": {
+        "url": "https://app.baseten.co/",
+        "apiKeyFormat": null,
+        "billingPolicy": "free-tier",
+        "instructions": [
+            "1. Visit: https://app.baseten.co/ and sign in or create a workspace",
+            "2. Review the current Baseten billing and credit terms in the console before making requests",
+            "3. Create a personal API key in the Baseten console",
+            "4. Set {apiKeyEnvVar} in your .env file"
+        ]
+    },
+    "evidence": {
+        "rosterVerified": {
+            "date": "2026-09-03",
+            "method": "authenticated GET /v1/models",
+            "status": 200
+        },
+        "authProbe": {
+            "date": "2026-09-03",
+            "status": 403
+        },
+        "liveMatrix": null,
+        "addedInPR": "pending"
+    }
+}

package/dist/providers/catalog/gmicloud.json

@@ -0,0 +1,64 @@
+{
+    "$schema": "./provider-catalog.schema.json",
+    "id": "gmicloud",
+    "displayName": "GMI Cloud",
+    "aliases": ["gmi-cloud"],
+    "tier": 2,
+    "wire": {
+        "baseURL": "https://api.gmi-serving.com/v1"
+    },
+    "models": {
+        "default": "MiniMaxAI/MiniMax-M3",
+        "fallbacks": ["MiniMaxAI/MiniMax-M3"],
+        "defaultContextWindow": 1048576,
+        "defaultMaxOutputTokens": 524288,
+        "catalog": {
+            "MiniMaxAI/MiniMax-M3": {
+                "contextWindow": 1048576,
+                "maxOutputTokens": 524288,
+                "vision": false,
+                "status": "production",
+                "description": "MiniMaxAI/MiniMax-M3 — live GMI Cloud-probed model"
+            }
+        },
+        "topModels": ["MiniMaxAI/MiniMax-M3"]
+    },
+    "capabilities": {
+        "text": true,
+        "streaming": true,
+        "tools": true,
+        "toolsWithStreaming": true,
+        "structuredOutput": true,
+        "structuredOutputWithTools": true,
+        "embeddings": false,
+        "thinking": false
+    },
+    "errorRules": [],
+    "setup": {
+        "url": "https://console.gmicloud.ai",
+        "apiKeyFormat": "^eyJ[A-Za-z0-9_-]+\\.[A-Za-z0-9_-]+\\.[A-Za-z0-9_-]+$",
+        "billingPolicy": "free-tier",
+        "instructions": [
+            "1. Visit: https://console.gmicloud.ai",
+            "2. Sign in and select the Inference service",
+            "3. Create an API key; check Console → Inference → Model Hub for current model pricing",
+            "4. Set {apiKeyEnvVar} in your .env file"
+        ]
+    },
+    "evidence": {
+        "rosterVerified": {
+            "date": "2026-09-03",
+            "method": "authenticated GET /v1/models",
+            "status": 200
+        },
+        "authProbe": {
+            "date": "2026-09-03",
+            "status": 401
+        },
+        "liveMatrix": {
+            "date": "2026-09-03",
+            "result": "MiniMax-M3 accepted max_completion_tokens=524288 and rejected 1048576 with an explicit 524288 limit. Structured output: the endpoint ignores response_format (json_schema and json_object both return prose with no prompt hint; raw fetch, 2026-09-03), so the SDK's structured-output fallback re-asks with the schema spelled out in the system prompt and coerces the reply — generate({ schema }) returned a schema-valid structuredData 3/3 in the prompt-fallback experiment and again in the final live proof through dist/index.js. structuredOutput and structuredOutputWithTools are declared true on that basis."
+        },
+        "addedInPR": "pending"
+    }
+}

package/dist/providers/catalog/inception-labs.json

@@ -0,0 +1,75 @@
+{
+    "$schema": "./provider-catalog.schema.json",
+    "id": "inception-labs",
+    "displayName": "Inception Labs",
+    "aliases": ["inception", "mercury"],
+    "tier": 2,
+    "wire": {
+        "baseURL": "https://api.inceptionlabs.ai/v1"
+    },
+    "models": {
+        "default": "mercury-2",
+        "fallbacks": ["mercury-2"],
+        "defaultContextWindow": 128000,
+        "defaultMaxOutputTokens": 50000,
+        "catalog": {
+            "mercury-2": {
+                "contextWindow": 128000,
+                "maxOutputTokens": 50000,
+                "pricingPerMTok": {
+                    "input": 0.25,
+                    "output": 0.75,
+                    "cachedInput": 0.025
+                },
+                "vision": false,
+                "status": "production",
+                "description": "Recommended - Mercury 2, Inception's enterprise diffusion LLM (dLLM); reasoning, tool use, structured output; 128K context, 1000+ tok/s"
+            }
+        }
+    },
+    "capabilities": {
+        "text": true,
+        "streaming": true,
+        "tools": true,
+        "toolsWithStreaming": true,
+        "structuredOutput": true,
+        "structuredOutputWithTools": true,
+        "embeddings": false,
+        "thinking": false
+    },
+    "errorRules": [
+        {
+            "pattern": "Model must be one of the following",
+            "class": "invalid-model",
+            "message": "Inception Labs model '{model}' is not valid. Pick a current model \u2014 see https://docs.inceptionlabs.ai/get-started/models."
+        }
+    ],
+    "setup": {
+        "url": "https://platform.inceptionlabs.ai/dashboard/api-keys",
+        "apiKeyFormat": "^sk_[A-Za-z0-9_-]+$",
+        "billingPolicy": "free-tier",
+        "instructions": [
+            "1. Visit: https://platform.inceptionlabs.ai and sign in (Google OAuth works)",
+            "2. New accounts get 100M free tokens with no card required",
+            "3. Create an API key under Dashboard -> API Keys",
+            "4. Set {apiKeyEnvVar} in your .env file"
+        ]
+    },
+    "evidence": {
+        "rosterVerified": {
+            "date": "2026-09-03",
+            "method": "authenticated GET /v1/models",
+            "status": 200
+        },
+        "authProbe": {
+            "date": "2026-09-03",
+            "status": 401,
+            "code": "invalid_api_key"
+        },
+        "liveMatrix": {
+            "date": "2026-09-03",
+            "result": "Full capability sweep on mercury-2: chat, stream, system_role, content_text_parts, sampling_params, tools, tools_stream, tools_roundtrip_null, tool_choice_without_tools, json_object, json_schema and tools_plus_schema all 200. The smoke-test json_schema probe (max_tokens:60) came back truncated (finish_reason=length, null content) because this diffusion model spends part of the budget on reasoning tokens before content; re-probed live with max_tokens:300 and got a clean schema-conformant reply ({\"name\":\"Lila Whitaker\",\"age\":34}, finish_reason=stop), confirming structuredOutput:true is correct. vision is 400 (text-only; rejects image_url on mercury-2, matching the vendor docs' 'Supported Formats: Text'). bad_key is 401 'Incorrect API key provided'. bad_model is 400 with an array-shaped pydantic error.message; the shared OpenAI-compat wire-error builder coerces a non-string Error message via toString, so that array becomes the literal string \"[object Object]\" and no regex pattern can match the real text \u2014 errorRules is intentionally left empty rather than shipping a rule that can never fire (see notes)."
+        },
+        "addedInPR": "pending"
+    }
+}

package/dist/providers/catalog/index.generated.d.ts

@@ -1,3 +1,3 @@
 import type { ProviderCatalogJson } from "../../types/index.js";
 export declare const CATALOG_JSON_ENTRIES: ProviderCatalogJson[];
-export declare const CATALOG_PROVIDER_IDS: readonly ["cerebras", "cloudflare", "fireworks", "groq", "mistral", "perplexity", "sambanova", "together-ai", "xai"];
+export declare const CATALOG_PROVIDER_IDS: readonly ["baseten", "cerebras", "cloudflare", "fireworks", "gmicloud", "groq", "inception-labs", "io-intelligence", "mistral", "perplexity", "sambanova", "together-ai", "upstage", "xai"];

package/dist/providers/catalog/index.generated.js

@@ -1,33 +1,48 @@
 // GENERATED FILE — do not edit. Regenerate with `pnpm run codegen:catalog`.
 // Source of truth: the per-provider JSON files in this directory.
+import basetenJson from "./baseten.json" with { type: "json" };
 import cerebrasJson from "./cerebras.json" with { type: "json" };
 import cloudflareJson from "./cloudflare.json" with { type: "json" };
 import fireworksJson from "./fireworks.json" with { type: "json" };
+import gmicloudJson from "./gmicloud.json" with { type: "json" };
 import groqJson from "./groq.json" with { type: "json" };
+import inceptionLabsJson from "./inception-labs.json" with { type: "json" };
+import ioIntelligenceJson from "./io-intelligence.json" with { type: "json" };
 import mistralJson from "./mistral.json" with { type: "json" };
 import perplexityJson from "./perplexity.json" with { type: "json" };
 import sambanovaJson from "./sambanova.json" with { type: "json" };
 import togetherAiJson from "./together-ai.json" with { type: "json" };
+import upstageJson from "./upstage.json" with { type: "json" };
 import xaiJson from "./xai.json" with { type: "json" };
 export const CATALOG_JSON_ENTRIES = [
+    basetenJson,
     cerebrasJson,
     cloudflareJson,
     fireworksJson,
+    gmicloudJson,
     groqJson,
+    inceptionLabsJson,
+    ioIntelligenceJson,
     mistralJson,
     perplexityJson,
     sambanovaJson,
     togetherAiJson,
+    upstageJson,
     xaiJson,
 ];
 export const CATALOG_PROVIDER_IDS = [
+    "baseten",
     "cerebras",
     "cloudflare",
     "fireworks",
+    "gmicloud",
     "groq",
+    "inception-labs",
+    "io-intelligence",
     "mistral",
     "perplexity",
     "sambanova",
     "together-ai",
+    "upstage",
     "xai",
 ];