{
    "$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"
    }
}