@juspay/neurolink
Version:
The pipe layer of an AI nervous system: one interface connecting provider neurons to your application, across three inference types — generate, stream and decide. `decide` returns typed, calibrated judgements from a non-generative model (~400ms, ~$0.00002
155 lines (154 loc) • 7.31 kB
JSON
{
"$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roster, but the chat endpoint 404s 'Model not found, inaccessible, and/or not deployed' (since the 2026-09-26 nightly); superseded by kimi-k3, same Moonshot family"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"
}
}