{
    "$schema": "./provider-catalog.schema.json",
    "id": "vultr-inference",
    "displayName": "Vultr Inference",
    "aliases": [],
    "tier": 2,
    "wire": {
        "baseURL": "https://api.vultrinference.com/v1"
    },
    "models": {
        "default": "glm-5.2",
        "fallbacks": [
            "deepseek-v4.1-flash",
            "qwen3.8-flash-next",
            "mimo-v2.6-flash-rl"
        ],
        "defaultContextWindow": 131072,
        "defaultMaxOutputTokens": 32768,
        "catalog": {
            "glm-5.2": {
                "contextWindow": 1048576,
                "maxOutputTokens": 1048576,
                "pricingPerMTok": {
                    "input": 0.75,
                    "output": 3
                },
                "vision": true,
                "status": "production",
                "description": "NeuroLink default. Roster entry named \"GLM 5.2\" on the unauthenticated GET https://api.vultrinference.com/v1/models (2026-09-29, 24 entries). Roster description: \"GLM-5.2 is Z.ai's flagship model for long-horizon tasks, sustaining agentic work across a solid 1M-token context.\" Roster fields: text input max_context_length 1,048,576 tokens; output max_length 1,048,576 tokens; prompt price $0.75 and completion price $3 per MTok (cost_usd 0.00000075 and 0.000003 per token); streaming true; tools listed among the supported parameters; input modalities text, image. Vision is true because the roster lists an image input modality (sources url and base64; formats image/png, image/jpeg, image/webp, image/gif); no image request was sent."
            },
            "deepseek-v4.1-flash": {
                "contextWindow": 1048576,
                "maxOutputTokens": 1048576,
                "pricingPerMTok": {
                    "input": 0.15,
                    "output": 0.6
                },
                "vision": true,
                "status": "production",
                "description": "Fallback. Roster entry named \"DeepSeek V4.1 Flash\" on the unauthenticated GET https://api.vultrinference.com/v1/models (2026-09-29, 24 entries). Roster description: \"DeepSeek V4.1 Flash is a mixture-of-experts model with 552B backbone parameters, a one-million-token context window, and support for reasoning and tool calling.\" Roster fields: text input max_context_length 1,048,576 tokens; output max_length 1,048,576 tokens; prompt price $0.15 and completion price $0.6 per MTok (cost_usd 0.00000015 and 0.0000006 per token); streaming true; tools listed among the supported parameters; input modalities text, image. Vision is true because the roster lists an image input modality (sources url and base64; formats image/png, image/jpeg, image/webp, image/gif); no image request was sent."
            },
            "qwen3.8-flash-next": {
                "contextWindow": 262144,
                "maxOutputTokens": 262144,
                "pricingPerMTok": {
                    "input": 0.1,
                    "output": 0.2
                },
                "vision": true,
                "status": "production",
                "description": "Fallback. Roster entry named \"Qwen 3.8 Flash Next\" on the unauthenticated GET https://api.vultrinference.com/v1/models (2026-09-29, 24 entries). Roster description: \"Qwen3.8 Flash Next with NVFP4 weights, a 262,144-token context window, reasoning, and tool calling.\" Roster fields: text input max_context_length 262,144 tokens; output max_length 262,144 tokens; prompt price $0.1 and completion price $0.2 per MTok (cost_usd 0.0000001 and 0.0000002 per token); streaming true; tools listed among the supported parameters; input modalities text, image, video. Vision is true because the roster lists an image input modality (sources url and base64; formats image/png, image/jpeg, image/webp, image/gif); no image request was sent."
            },
            "mimo-v2.6-flash-rl": {
                "contextWindow": 1048576,
                "maxOutputTokens": 1048576,
                "pricingPerMTok": {
                    "input": 0.1,
                    "output": 0.25
                },
                "vision": true,
                "status": "production",
                "description": "Fallback. Roster entry named \"MiMo V2.6 Flash RL\" on the unauthenticated GET https://api.vultrinference.com/v1/models (2026-09-29, 24 entries). Roster description: \"MiMo V2.6 Flash RL is Xiaomi's efficiency-balanced mixture-of-experts model with 309B total and 15B active parameters, hybrid sliding-window attention, and a 1M-token context.\" \"Supports reasoning and tool calling, served at FP8.\" Roster fields: text input max_context_length 1,048,576 tokens; output max_length 1,048,576 tokens; prompt price $0.1 and completion price $0.25 per MTok (cost_usd 0.0000001 and 0.00000025 per token); streaming true; tools listed among the supported parameters; input modalities text, image, audio, video. Vision is true because the roster lists an image input modality (sources url and base64; formats image/png, image/jpeg, image/webp, image/gif); no image request was sent."
            },
            "deepseek-v4-flash-0731": {
                "contextWindow": 1048576,
                "maxOutputTokens": 1048576,
                "pricingPerMTok": {
                    "input": 0.1,
                    "output": 0.25
                },
                "vision": true,
                "status": "production",
                "description": "Roster-listed. Roster entry named \"DeepSeek V4 Flash 0731\" on the unauthenticated GET https://api.vultrinference.com/v1/models (2026-09-29, 24 entries). Roster description: \"DeepSeek's official V4 Flash release with substantially enhanced agentic capabilities and a built-in speculative decoding module.\" Roster fields: text input max_context_length 1,048,576 tokens; output max_length 1,048,576 tokens; prompt price $0.1 and completion price $0.25 per MTok (cost_usd 0.0000001 and 0.00000025 per token); streaming true; tools listed among the supported parameters; input modalities text, image. Vision is true because the roster lists an image input modality (sources url and base64; formats image/png, image/jpeg, image/webp, image/gif); no image request was sent."
            },
            "glm-5.3": {
                "contextWindow": 1048576,
                "maxOutputTokens": 1048576,
                "pricingPerMTok": {
                    "input": 0.75,
                    "output": 3
                },
                "vision": true,
                "status": "production",
                "description": "Roster-listed. Roster entry named \"GLM 5.3\" on the unauthenticated GET https://api.vultrinference.com/v1/models (2026-09-29, 24 entries). Roster description: \"Served at NVFP4 across a 1M-token context.\" Roster fields: text input max_context_length 1,048,576 tokens; output max_length 1,048,576 tokens; prompt price $0.75 and completion price $3 per MTok (cost_usd 0.00000075 and 0.000003 per token); streaming true; tools listed among the supported parameters; input modalities text, image. Vision is true because the roster lists an image input modality (sources url and base64; formats image/png, image/jpeg, image/webp, image/gif); no image request was sent."
            },
            "glm-5.3-flash": {
                "contextWindow": 1048576,
                "maxOutputTokens": 1048576,
                "pricingPerMTok": {
                    "input": 0.1,
                    "output": 0.35
                },
                "vision": true,
                "status": "production",
                "description": "Roster-listed. Roster entry named \"GLM 5.3 Flash\" on the unauthenticated GET https://api.vultrinference.com/v1/models (2026-09-29, 24 entries). Roster description: \"Z.ai's first natively multimodal GLM-5 model: a 320B-parameter MoE with ~18B active per token, combining sparse and linear attention for cheap long-context serving across a 1M-token window.\" Roster fields: text input max_context_length 1,048,576 tokens; output max_length 1,048,576 tokens; prompt price $0.1 and completion price $0.35 per MTok (cost_usd 0.0000001 and 0.00000035 per token); streaming true; tools listed among the supported parameters; input modalities text, image, video. Vision is true because the roster lists an image input modality (sources url and base64; formats image/png, image/jpeg, image/webp, image/gif); no image request was sent."
            },
            "glm-5.x-menthol": {
                "contextWindow": 202752,
                "maxOutputTokens": 202752,
                "pricingPerMTok": {
                    "input": 0.4,
                    "output": 1.75
                },
                "vision": true,
                "status": "production",
                "description": "Roster-listed. Roster entry named \"GLM 5\" on the unauthenticated GET https://api.vultrinference.com/v1/models (2026-09-29, 24 entries). Roster description: \"Z.ai's GLM-5, a 744B-parameter MoE flagship for agentic reasoning and coding, served in FP8.\" Roster fields: text input max_context_length 202,752 tokens; output max_length 202,752 tokens; prompt price $0.4 and completion price $1.75 per MTok (cost_usd 0.0000004 and 0.00000175 per token); streaming true; tools listed among the supported parameters; input modalities text, image. Vision is true because the roster lists an image input modality (sources url and base64; formats image/png, image/jpeg, image/webp, image/gif); no image request was sent."
            },
            "laguna-s-2.1": {
                "contextWindow": 1048576,
                "maxOutputTokens": 1048576,
                "pricingPerMTok": {
                    "input": 0.09,
                    "output": 0.18
                },
                "vision": true,
                "status": "production",
                "description": "Roster-listed. Roster entry named \"Laguna S 2.1\" on the unauthenticated GET https://api.vultrinference.com/v1/models (2026-09-29, 24 entries). Roster description: \"Laguna S 2.1 is a 118B total parameter Mixture-of-Experts model with 8B activated parameters per token, designed for agentic coding and long-horizon work.\" Roster fields: text input max_context_length 1,048,576 tokens; output max_length 1,048,576 tokens; prompt price $0.09 and completion price $0.18 per MTok (cost_usd 0.00000009 and 0.00000018 per token); streaming true; tools listed among the supported parameters; input modalities text, image. Vision is true because the roster lists an image input modality (sources url and base64; formats image/png, image/jpeg, image/webp, image/gif); no image request was sent."
            },
            "mimo-v2.6-pro-rl": {
                "contextWindow": 1048576,
                "maxOutputTokens": 1048576,
                "pricingPerMTok": {
                    "input": 0.4,
                    "output": 0.8
                },
                "vision": true,
                "status": "production",
                "description": "Roster-listed. Roster entry named \"MiMo V2.6 Pro RL\" on the unauthenticated GET https://api.vultrinference.com/v1/models (2026-09-29, 24 entries). Roster description: \"MiMo V2.6 Pro RL is Xiaomi's mixture-of-experts model with 1.02T total and 42B active parameters, hybrid sliding-window attention, and a 1M-token context.\" \"Supports reasoning and tool calling, served at FP8.\" Roster fields: text input max_context_length 1,048,576 tokens; output max_length 1,048,576 tokens; prompt price $0.4 and completion price $0.8 per MTok (cost_usd 0.0000004 and 0.0000008 per token); streaming true; tools listed among the supported parameters; input modalities text, image, audio, video. Vision is true because the roster lists an image input modality (sources url and base64; formats image/png, image/jpeg, image/webp, image/gif); no image request was sent."
            },
            "minimax-m3": {
                "contextWindow": 524288,
                "maxOutputTokens": 524288,
                "pricingPerMTok": {
                    "input": 0.2,
                    "output": 0.9
                },
                "vision": true,
                "status": "production",
                "description": "Roster-listed. Roster entry named \"MiniMax M3\" on the unauthenticated GET https://api.vultrinference.com/v1/models (2026-09-29, 24 entries). Roster description: \"MiniMax M3 is a natively multimodal MoE model (~428B parameters, ~23B active) with a 1M-token context.\" Roster fields: text input max_context_length 524,288 tokens; output max_length 524,288 tokens; prompt price $0.2 and completion price $0.9 per MTok (cost_usd 0.0000002 and 0.0000009 per token); streaming true; tools listed among the supported parameters; input modalities text, image, video. Vision is true because the roster lists an image input modality (sources url and base64; formats image/png, image/jpeg, image/webp, image/gif); no image request was sent. The roster description text says a 1M-token context while the max_context_length field says 524,288; contextWindow uses the field."
            },
            "muse-glimmer-30b": {
                "contextWindow": 131072,
                "maxOutputTokens": 131072,
                "pricingPerMTok": {
                    "input": 0.25,
                    "output": 1
                },
                "vision": true,
                "status": "production",
                "description": "Roster-listed. Roster entry named \"Muse Glimmer 30B\" on the unauthenticated GET https://api.vultrinference.com/v1/models (2026-09-29, 24 entries). Roster description: \"Muse Glimmer 30B is a dense multimodal model for reasoning, coding, and tool use, with a 131072-token context.\" Roster fields: text input max_context_length 131,072 tokens; output max_length 131,072 tokens; prompt price $0.25 and completion price $1 per MTok (cost_usd 0.00000025 and 0.000001 per token); streaming true; tools listed among the supported parameters; input modalities text, image, video. Vision is true because the roster lists an image input modality (sources url and base64; formats image/png, image/jpeg, image/webp, image/gif); no image request was sent."
            }
        },
        "topModels": [
            "glm-5.2",
            "deepseek-v4.1-flash",
            "qwen3.8-flash-next",
            "mimo-v2.6-flash-rl",
            "deepseek-v4-flash-0731",
            "glm-5.3",
            "glm-5.3-flash",
            "glm-5.x-menthol",
            "laguna-s-2.1",
            "mimo-v2.6-pro-rl",
            "minimax-m3",
            "muse-glimmer-30b"
        ]
    },
    "capabilities": {
        "text": true,
        "streaming": true,
        "tools": "model-dependent",
        "toolsWithStreaming": true,
        "structuredOutput": false,
        "structuredOutputWithTools": false,
        "embeddings": false,
        "thinking": false
    },
    "errorRules": [
        {
            "status": 401,
            "class": "authentication",
            "message": "Vultr Inference rejected the request with HTTP 401 (Unauthorized). Check {apiKeyEnvVar}; the steps to retrieve a key are at {setupUrl}"
        },
        {
            "status": 429,
            "class": "rate-limit",
            "message": "Vultr Inference reports HTTP 429 (Rate limit exceeded)."
        }
    ],
    "setup": {
        "url": "https://docs.vultr.com/products/compute/serverless-inference/provisioning",
        "apiKeyFormat": null,
        "billingPolicy": "no-free-tier",
        "instructions": [
            "1. Visit: https://docs.vultr.com/products/compute/serverless-inference/provisioning and follow the Vultr Console steps: Products, Serverless, Inference, Add Serverless Inference, then provide a Label, \"acknowledge the list of supported models and the charges note\", and click Add Serverless Inference",
            "2. Open the new subscription's management page and copy the API key from its overview page (https://docs.vultr.com/products/compute/serverless-inference/management/connection: \"API key is necessary to send any request to the inference endpoints\")",
            "3. Charges: the provisioning page above lists the charges note among the items to acknowledge, and the FAQ (https://docs.vultr.com/products/compute/serverless-inference/faq) says the subscription's Usage tab shows \"details on your current token usage, overage, and any associated costs\"",
            "4. Set {apiKeyEnvVar} in your .env file (the authentication example on https://api.vultrinference.com/ writes ${VULTR_API_KEY}, which NeuroLink does not read)"
        ],
        "description": "Chat completions endpoint at https://api.vultrinference.com/v1 (https://api.vultrinference.com/ documents POST /chat/completions with bearer-token authentication and says \"Responses follow OpenRouter's chat completion shape whichever engine serves the model\"; the FAQ at https://docs.vultr.com/products/compute/serverless-inference/faq says to \"replace your current inference API URL (such as OpenAI's base API URL) with Vultr’s API URL\"). The chat-completions request message schema at https://api.vultrinference.com/ lists role (system, assistant, user, tool, developer) and content (type string, \"The contents of the message.\"); the tool call id description says \"Send it back unchanged as the `tool_call_id` of the tool result.\" The roster route is public (\"Most API routes require a bearer token. The public `/v1/models` route does not.\") and lists 24 entries, 15 with a text output; the catalog holds 12 chat models. billingPolicy no-free-tier is the schema's closest value (the schema has no unknown value) and is not a Vultr statement. Each model's status production is a value the schema requires and is not a Vultr statement. models.defaultContextWindow (131,072) and models.defaultMaxOutputTokens (32,768) are placeholders for ids outside the catalog that the vendor does not publish: 131,072 is the context the roster lists for muse-glimmer-30b and 32,768 is the default the chat-completions page shows for max_completion_tokens. errorRules match the documented statuses 401 and 429; the 401 body was observed on unauthenticated GETs of /v1/models/all, /v1/usage and /v1/models/glm-5.2 ({\"message\":\"No API key provided\"}); no POST to /chat/completions was sent."
    },
    "evidence": {
        "rosterVerified": {
            "date": "2026-09-29",
            "status": 200,
            "method": "unauthenticated GET https://api.vultrinference.com/v1/models — 24 models; credential-free, no key used"
        },
        "authProbe": {
            "date": "2026-09-29",
            "status": 401,
            "method": "unauthenticated GET https://api.vultrinference.com/v1/models/all with no credentials — 401 {\"message\":\"No API key provided\"} (the same body on GET /v1/usage and GET /v1/models/glm-5.2); the body carries no error code; GET https://api.vultrinference.com/v1/chat/completions answered 404 (the documented method is POST and none was sent); credential-free, no key used"
        },
        "billingProbe": {
            "date": "2026-09-29",
            "method": "public pages https://docs.vultr.com/products/compute/serverless-inference/provisioning (Console steps: \"acknowledge the list of supported models and the charges note\") and https://docs.vultr.com/products/compute/serverless-inference/faq (Usage tab: \"details on your current token usage, overage, and any associated costs\"); no free-tier statement read; credential-free"
        },
        "liveMatrix": null,
        "addedInPR": "https://github.com/juspay/neurolink/pull/1860"
    }
}