{
    "$schema": "./provider-catalog.schema.json",
    "id": "fireworks",
    "displayName": "Fireworks AI",
    "aliases": [],
    "tier": 2,
    "wire": {
        "baseURL": "https://api.fireworks.ai/inference/v1"
    },
    "models": {
        "default": "accounts/fireworks/models/kimi-k3",
        "fallbackModelName": "accounts/fireworks/models/gpt-oss-120b",
        "fallbacks": [
            "accounts/fireworks/models/kimi-k3",
            "accounts/fireworks/models/gpt-oss-120b",
            "accounts/fireworks/models/qwen3p8-max",
            "accounts/fireworks/models/glm-5p3"
        ],
        "defaultContextWindow": 128000,
        "defaultMaxOutputTokens": 4096,
        "catalog": {
            "accounts/fireworks/models/kimi-k2p6": {
                "enumMember": "KIMI_K2P6",
                "vision": false,
                "status": "retired",
                "description": "Retired 2026-09 — still listed on the Fireworks /models roster, but the chat endpoint 404s 'Model not found, inaccessible, and/or not deployed' (since the 2026-09-26 nightly); superseded by kimi-k3, same Moonshot family"
            },
            "accounts/fireworks/models/gpt-oss-120b": {
                "enumMember": "GPT_OSS_120B",
                "vision": false,
                "status": "production",
                "description": "GPT-OSS 120B — Apache-2.0 OpenAI weights"
            },
            "accounts/fireworks/models/kimi-k3": {
                "enumMember": "KIMI_K3",
                "vision": true,
                "status": "production",
                "description": "Recommended - Kimi K3, newest Moonshot generation; vision-capable"
            },
            "accounts/fireworks/models/qwen3p8-max": {
                "enumMember": "QWEN3P8_MAX",
                "vision": true,
                "status": "production",
                "description": "Qwen 3.8 Max — vision-capable"
            },
            "accounts/fireworks/models/glm-5p3": {
                "enumMember": "GLM_5P3",
                "vision": false,
                "status": "production",
                "description": "GLM 5.3 — Zhipu flagship"
            },
            "accounts/fireworks/models/minimax-m3": {
                "enumMember": "MINIMAX_M3",
                "vision": false,
                "status": "production",
                "description": "MiniMax M3"
            },
            "accounts/fireworks/models/deepseek-v4-flash-0731": {
                "enumMember": "DEEPSEEK_V4_FLASH_0731",
                "vision": false,
                "status": "production",
                "description": "DeepSeek V4 Flash — low-latency DeepSeek"
            },
            "accounts/fireworks/models/deepseek-v4-pro": {
                "enumMember": "DEEPSEEK_V4_PRO",
                "vision": false,
                "status": "retired",
                "description": "Retired 2026-08 as a usable id — still on the Fireworks roster but never answers: a real chat call hangs past 120s on this account"
            },
            "accounts/fireworks/models/glm-5p1": {
                "enumMember": "GLM_5P1",
                "vision": false,
                "status": "retired",
                "description": "Retired 2026-08 — Fireworks returns 404 'not deployed'"
            },
            "accounts/fireworks/models/glm-5": {
                "enumMember": "GLM_5",
                "vision": false,
                "status": "retired",
                "description": "Retired 2026-08 — Fireworks returns 404 'not deployed'"
            },
            "accounts/fireworks/models/kimi-k2p5": {
                "enumMember": "KIMI_K2P5",
                "vision": false,
                "status": "retired",
                "description": "Retired 2026-08 — Fireworks returns 404 'not deployed'"
            },
            "accounts/fireworks/models/llama-v3p2-90b-vision-instruct": {
                "enumMember": "LLAMA_V3P2_90B_VISION_INSTRUCT",
                "vision": false,
                "status": "retired",
                "description": "Retired 2026-08 — Fireworks returns 404 'not deployed'"
            },
            "accounts/fireworks/models/llama-v3p2-11b-vision-instruct": {
                "enumMember": "LLAMA_V3P2_11B_VISION_INSTRUCT",
                "vision": false,
                "status": "retired",
                "description": "Retired 2026-08 — Fireworks returns 404 'not deployed'"
            },
            "accounts/fireworks/models/phi-3-vision-128k-instruct": {
                "enumMember": "PHI_3_VISION_128K_INSTRUCT",
                "vision": false,
                "status": "retired",
                "description": "Retired 2026-08 — Fireworks returns 404 'not deployed'"
            }
        },
        "topModels": [
            "accounts/fireworks/models/kimi-k3",
            "accounts/fireworks/models/gpt-oss-120b",
            "accounts/fireworks/models/qwen3p8-max",
            "accounts/fireworks/models/glm-5p3"
        ]
    },
    "capabilities": {
        "text": true,
        "streaming": true,
        "tools": true,
        "toolsWithStreaming": true,
        "structuredOutput": true,
        "structuredOutputWithTools": true,
        "embeddings": false,
        "thinking": false
    },
    "errorRules": [
        {
            "status": 401,
            "pattern": "Invalid API key|Authentication",
            "class": "authentication",
            "message": "Invalid Fireworks API key. Get one at https://fireworks.ai/account/api-keys"
        }
    ],
    "setup": {
        "url": "https://fireworks.ai/account/api-keys",
        "apiKeyFormat": null,
        "billingPolicy": "free-with-card",
        "instructions": [
            "1. Visit: https://fireworks.ai/account/api-keys",
            "2. Sign in to your Fireworks AI account",
            "3. Create a new API key",
            "4. Set {apiKeyEnvVar} in your .env file"
        ]
    },
    "evidence": {
        "rosterVerified": {
            "date": "2026-09-28",
            "method": "GET /models against the live account, cross-checked with a real chat call per id"
        },
        "liveMatrix": {
            "date": "2026-09-28",
            "result": "Issue #1796: the 2026-09-26 nightly model-liveness gate reported the default, kimi-k2p6, as dead, sending the matrix vision test down the text-only fallback. Confirmed live — GET /models still lists kimi-k2p6, but POST /chat/completions 404s 'Model not found, inaccessible, and/or not deployed', the same still-listed-but-unservable pattern deepseek-v4-pro hit in 2026-08 (hung past 120s rather than 404ing). Moved the default to kimi-k3, the same Moonshot family's newest generation: 200 OK on both a text-only call and a call carrying a PNG, and a full-length call returns a proper OpenAI-shaped tool_calls entry with finish_reason=tool_calls, confirming vision and tool support both survive the swap. kimi-k2p6 marked retired rather than deleted, per the frozen-enum rule. gpt-oss-120b, qwen3p8-max and glm-5p3 (the rest of fallbacks/topModels) were re-probed alive at the same time; glm-5p3 still only answers text calls, not image ones, as found 2026-08-30."
        },
        "addedInPR": "https://github.com/juspay/neurolink/pull/1587"
    }
}