{
    "$schema": "./provider-catalog.schema.json",
    "id": "wafer",
    "displayName": "Wafer",
    "aliases": [],
    "tier": 2,
    "wire": {
        "baseURL": "https://pass.wafer.ai/v1"
    },
    "models": {
        "default": "GLM-5.3",
        "fallbacks": ["DeepSeek-V4-Pro", "Kimi-K3", "GLM-5.2"],
        "defaultContextWindow": 128000,
        "defaultMaxOutputTokens": 16384,
        "catalog": {
            "GLM-5.3": {
                "contextWindow": 1048576,
                "pricingPerMTok": {
                    "input": 0.29,
                    "output": 4.4,
                    "cachedInput": 0.2359
                },
                "vision": false,
                "status": "production",
                "description": "NeuroLink default. The model named in the curl request example on https://docs.wafer.ai/serverless and on https://docs.wafer.ai/serverless/zero-data-retention. Unauthenticated GET https://pass.wafer.ai/v1/models roster (2026-09-29, 8 models), wafer.description: \"GLM-5.3 — Z.ai's flagship GLM-5.3 MoE (391B, NVFP4), self-hosted on the Wafer fleet with a 1M-token context window and frontier coding/agentic performance. Available serverless.\" Roster values: context_length 1,048,576; input_cents_per_million 29, output_cents_per_million 440 ($0.29 / $4.40 per MTok input/output); cache_read_microcents_per_million 23,590,000 ($0.2359 per MTok cache-read); capabilities.vision false; chat_completions supported, tools, streaming, json_object and json_schema true."
            },
            "DeepSeek-V4-Pro": {
                "contextWindow": 1048576,
                "pricingPerMTok": {
                    "input": 0.4,
                    "output": 4.2,
                    "cachedInput": 0.32
                },
                "vision": false,
                "status": "production",
                "description": "Fallback. Unauthenticated GET https://pass.wafer.ai/v1/models roster (2026-09-29, 8 models), wafer.description: \"DeepSeek-V4-Pro -- DeepSeek's V4 Pro MoE, self-hosted on the Wafer fleet with a 1M-token context window, reasoning-effort control and tool calling. Available serverless.\" Roster values: context_length 1,048,576; input_cents_per_million 40, output_cents_per_million 420 ($0.40 / $4.20 per MTok input/output); cache_read_microcents_per_million 32,000,000 ($0.32 per MTok cache-read); capabilities.vision false; chat_completions supported, tools, streaming, json_object and json_schema true."
            },
            "Kimi-K3": {
                "contextWindow": 1048576,
                "maxOutputTokens": 131072,
                "pricingPerMTok": {
                    "input": 1.44,
                    "output": 9,
                    "cachedInput": 0.3
                },
                "vision": true,
                "status": "production",
                "description": "Fallback. Unauthenticated GET https://pass.wafer.ai/v1/models roster (2026-09-29, 8 models), wafer.description: \"Kimi K3 sparse MoE model, self-hosted on the Wafer fleet. Available serverless with a 1M-token context window and strong coding/agentic performance.\" Roster values: context_length 1,048,576; max_output_tokens 131,072; input_cents_per_million 144, output_cents_per_million 900 ($1.44 / $9.00 per MTok input/output); cache_read_microcents_per_million 30,000,000 ($0.3 per MTok cache-read); capabilities.vision true and supports_vision true; not probed with an image request; chat_completions supported, tools, streaming, json_object and json_schema true."
            },
            "GLM-5.2": {
                "contextWindow": 1048576,
                "pricingPerMTok": {
                    "input": 0.32,
                    "output": 4.4,
                    "cachedInput": 0.2599
                },
                "vision": false,
                "status": "production",
                "description": "Fallback. Unauthenticated GET https://pass.wafer.ai/v1/models roster (2026-09-29, 8 models), wafer.description: \"GLM-5.2 — Z.ai's GLM-5.2 MoE (NVFP4), self-hosted on the Wafer fleet with a 1M-token context window, strong coding and reasoning, and tool calling. Available serverless.\" Roster values: context_length 1,048,576; input_cents_per_million 32, output_cents_per_million 440 ($0.32 / $4.40 per MTok input/output); cache_read_microcents_per_million 25,990,000 ($0.2599 per MTok cache-read); capabilities.vision false; chat_completions supported, tools, streaming, json_object and json_schema true."
            },
            "Qwen3.8-27B": {
                "contextWindow": 262144,
                "pricingPerMTok": {
                    "input": 0.04,
                    "output": 4.4,
                    "cachedInput": 0.0342
                },
                "vision": true,
                "status": "production",
                "description": "Roster-listed. Unauthenticated GET https://pass.wafer.ai/v1/models roster (2026-09-29, 8 models), wafer.description: \"Qwen3.8-27B -- Alibaba's dense 27B vision-language model, self-hosted on the Wafer fleet with a 262K-token context window, image and video input, reasoning-effort control and tool calling. Available serverless.\" Roster values: context_length 262,144; input_cents_per_million 4, output_cents_per_million 440 ($0.04 / $4.40 per MTok input/output); cache_read_microcents_per_million 3,420,000 ($0.0342 per MTok cache-read); capabilities.vision true and supports_vision true; not probed with an image request; chat_completions supported, tools, streaming, json_object and json_schema true."
            },
            "GLM-5.3-Flash": {
                "contextWindow": 1048576,
                "pricingPerMTok": {
                    "input": 0.75,
                    "output": 0.5,
                    "cachedInput": 0.03
                },
                "vision": true,
                "status": "production",
                "description": "Roster-listed. Unauthenticated GET https://pass.wafer.ai/v1/models roster (2026-09-29, 8 models), wafer.description: \"GLM-5.3-Flash — Z.ai's fast GLM-5.3 MoE variant, self-hosted on the Wafer fleet with a 1M-token context window and strong coding/agentic performance. Available serverless to gateway partners.\" Roster values: context_length 1,048,576; input_cents_per_million 75, output_cents_per_million 50 ($0.75 / $0.50 per MTok input/output); cache_read_microcents_per_million 3,000,000 ($0.03 per MTok cache-read); capabilities.vision true and supports_vision true; not probed with an image request; chat_completions supported, tools, streaming, json_object and json_schema true."
            },
            "DeepSeek-V4.1-Flash": {
                "contextWindow": 1048576,
                "pricingPerMTok": {
                    "input": 0.02,
                    "output": 0.7,
                    "cachedInput": 0.016
                },
                "vision": true,
                "status": "production",
                "description": "Roster-listed. Unauthenticated GET https://pass.wafer.ai/v1/models roster (2026-09-29, 8 models), wafer.description: \"DeepSeek-V4.1-Flash — DeepSeek's V4.1 Flash MoE (552B total, 8B active for prefill / 16B for decode, 1M-token context), self-hosted on the Wafer fleet with reasoning-effort control and tool calling. Available serverless.\" Roster values: context_length 1,048,576; input_cents_per_million 2, output_cents_per_million 70 ($0.02 / $0.70 per MTok input/output); cache_read_microcents_per_million 1,600,000 ($0.016 per MTok cache-read); capabilities.vision true and supports_vision true; not probed with an image request; chat_completions supported, tools, streaming, json_object and json_schema true."
            },
            "DeepSeek-V4-Flash-0731-Fast": {
                "contextWindow": 1048576,
                "pricingPerMTok": {
                    "input": 0.07,
                    "output": 0.35,
                    "cachedInput": 0.0531
                },
                "vision": false,
                "status": "production",
                "description": "Roster-listed. Unauthenticated GET https://pass.wafer.ai/v1/models roster (2026-09-29, 8 models), wafer.description: \"The same model served for high TPS.\" Roster values: context_length 1,048,576; input_cents_per_million 7, output_cents_per_million 35 ($0.07 / $0.35 per MTok input/output); cache_read_microcents_per_million 5,310,000 ($0.0531 per MTok cache-read); capabilities.vision false; chat_completions supported, tools, streaming, json_object and json_schema true."
            }
        },
        "topModels": [
            "GLM-5.3",
            "DeepSeek-V4-Pro",
            "Kimi-K3",
            "GLM-5.2",
            "Qwen3.8-27B",
            "GLM-5.3-Flash",
            "DeepSeek-V4.1-Flash",
            "DeepSeek-V4-Flash-0731-Fast"
        ],
        "visionModel": "Qwen3.8-27B"
    },
    "capabilities": {
        "text": true,
        "streaming": true,
        "tools": true,
        "toolsWithStreaming": true,
        "structuredOutput": true,
        "structuredOutputWithTools": false,
        "embeddings": false,
        "thinking": false
    },
    "errorRules": [
        {
            "status": 401,
            "class": "authentication",
            "message": "Wafer returned HTTP 401 authentication_error. Check {apiKeyEnvVar}. Get one at {setupUrl}"
        }
    ],
    "setup": {
        "url": "https://app.wafer.ai",
        "apiKeyFormat": null,
        "billingPolicy": "no-free-tier",
        "instructions": [
            "1. Visit: https://app.wafer.ai and sign in — the docs say \"Sign in at app.wafer.ai to add credits and create an API key. Store your key securely.\" (https://docs.wafer.ai/serverless)",
            "2. Add credits and create an API key — the docs say \"Add credits, create an API key, and pay per token.\" (https://docs.wafer.ai/serverless)",
            "3. Set {apiKeyEnvVar} in your .env file (the docs' Authentication row shows the Authorization: Bearer header)"
        ],
        "description": "OpenAI-compatible endpoint at https://pass.wafer.ai/v1 (https://docs.wafer.ai/serverless: \"Access Wafer models through an OpenAI-compatible API.\"), with the 8 models the unauthenticated GET /models roster listed on 2026-09-29 in models.catalog. An unauthenticated GET of https://pass.wafer.ai/v1/chat/completions returned HTTP 401 with error.type authentication_error and error.code missing_api_key (2026-09-29), so errorRules match status 401. models.defaultContextWindow (128000) and models.defaultMaxOutputTokens (16384) are placeholders the vendor does not publish. billingPolicy is recorded as no-free-tier because the schema has no unknown value; the vendor's stated flow is \"Add credits, create an API key, and pay per token.\""
    },
    "evidence": {
        "rosterVerified": {
            "date": "2026-09-29",
            "status": 200,
            "method": "unauthenticated GET https://pass.wafer.ai/v1/models — 8 models; credential-free, no key used"
        },
        "authProbe": {
            "date": "2026-09-29",
            "status": 401,
            "code": "missing_api_key",
            "method": "unauthenticated GET https://pass.wafer.ai/v1/chat/completions — error.type authentication_error; credential-free, no key used"
        },
        "billingProbe": {
            "date": "2026-09-29",
            "method": "public page https://docs.wafer.ai/serverless — \"Add credits, create an API key, and pay per token.\"; credential-free"
        },
        "liveMatrix": null,
        "addedInPR": "https://github.com/juspay/neurolink/pull/1860"
    }
}