@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, ~$0.00002
173 lines (172 loc) • 6.78 kB
JSON
{
"$schema": "./provider-catalog.schema.json",
"id": "together-ai",
"displayName": "Together AI",
"enumTypeName": "TogetherAIModels",
"credentialsKey": "together",
"aliases": ["together"],
"tier": 2,
"wire": {
"baseURL": "https://api.together.xyz/v1",
"envOverrides": {
"apiKey": "TOGETHER_API_KEY",
"baseURL": "TOGETHER_BASE_URL",
"model": "TOGETHER_MODEL"
}
},
"models": {
"default": "meta-llama/Llama-3.3-70B-Instruct-Turbo",
"fallbackModelName": "meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo",
"fallbacks": [
"meta-llama/Llama-3.3-70B-Instruct-Turbo",
"meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo",
"meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo",
"meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo",
"mistralai/Mixtral-8x22B-Instruct-v0.1",
"Qwen/Qwen2.5-72B-Instruct-Turbo",
"deepseek-ai/DeepSeek-R1",
"deepseek-ai/DeepSeek-V3"
],
"defaultContextWindow": 128000,
"defaultMaxOutputTokens": 4096,
"catalog": {
"meta-llama/Llama-3.3-70B-Instruct-Turbo": {
"enumMember": "LLAMA_3_3_70B_INSTRUCT_TURBO",
"contextWindow": 128000,
"pricingPerMTok": { "input": 0.88, "output": 0.88 },
"vision": false,
"status": "production",
"description": "Recommended - Llama 3.3 70B Turbo"
},
"meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo": {
"enumMember": "LLAMA_3_1_405B_INSTRUCT_TURBO",
"contextWindow": 128000,
"pricingPerMTok": { "input": 3.5, "output": 3.5 },
"vision": false,
"status": "production",
"description": "Flagship 405B"
},
"meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo": {
"enumMember": "LLAMA_3_1_70B_INSTRUCT_TURBO",
"contextWindow": 128000,
"pricingPerMTok": { "input": 0.88, "output": 0.88 },
"vision": false,
"status": "production",
"description": "Llama 3.1 70B Instruct Turbo"
},
"meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo": {
"enumMember": "LLAMA_3_1_8B_INSTRUCT_TURBO",
"contextWindow": 128000,
"pricingPerMTok": { "input": 0.18, "output": 0.18 },
"vision": false,
"status": "production",
"description": "Llama 3.1 8B Instruct Turbo — fastest"
},
"mistralai/Mixtral-8x22B-Instruct-v0.1": {
"enumMember": "MIXTRAL_8X22B_INSTRUCT",
"contextWindow": 65536,
"pricingPerMTok": { "input": 1.2, "output": 1.2 },
"vision": false,
"status": "production",
"description": "Mistral 8x22B MoE"
},
"mistralai/Mixtral-8x7B-Instruct-v0.1": {
"enumMember": "MIXTRAL_8X7B_INSTRUCT",
"contextWindow": 32768,
"pricingPerMTok": { "input": 0.6, "output": 0.6 },
"vision": false,
"status": "production",
"description": "Mixtral 8x7B Instruct"
},
"Qwen/Qwen2.5-72B-Instruct-Turbo": {
"enumMember": "QWEN_2_5_72B_INSTRUCT_TURBO",
"contextWindow": 32768,
"pricingPerMTok": { "input": 1.2, "output": 1.2 },
"vision": false,
"status": "production",
"description": "Qwen 2.5 72B Turbo"
},
"Qwen/Qwen2.5-Coder-32B-Instruct": {
"enumMember": "QWEN_2_5_CODER_32B",
"contextWindow": 32768,
"vision": false,
"status": "production",
"description": "Qwen 2.5 Coder 32B Instruct"
},
"deepseek-ai/DeepSeek-R1": {
"enumMember": "DEEPSEEK_R1",
"contextWindow": 64000,
"pricingPerMTok": { "input": 7.0, "output": 7.0 },
"vision": false,
"status": "production",
"description": "DeepSeek R1 reasoning"
},
"deepseek-ai/DeepSeek-V3": {
"enumMember": "DEEPSEEK_V3",
"contextWindow": 64000,
"pricingPerMTok": { "input": 1.25, "output": 1.25 },
"vision": false,
"status": "production",
"description": "DeepSeek V3"
},
"google/gemma-2-27b-it": {
"enumMember": "GEMMA_2_27B_IT",
"contextWindow": 8192,
"vision": false,
"status": "production",
"description": "Google Gemma 2 27B IT"
},
"microsoft/WizardLM-2-8x22B": {
"enumMember": "WIZARDLM_2_8X22B",
"contextWindow": 65536,
"vision": false,
"status": "production",
"description": "WizardLM 2 8x22B"
}
},
"topModels": [
"meta-llama/Llama-3.3-70B-Instruct-Turbo",
"meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo",
"Qwen/Qwen2.5-72B-Instruct-Turbo",
"deepseek-ai/DeepSeek-R1",
"mistralai/Mixtral-8x22B-Instruct-v0.1"
]
},
"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 Together AI API key. Get one at https://api.together.xyz/settings/api-keys"
}
],
"setup": {
"url": "https://api.together.xyz/settings/api-keys",
"apiKeyFormat": null,
"billingPolicy": "free-with-card",
"instructions": [
"1. Visit: https://api.together.xyz/settings/api-keys",
"2. Sign in to your Together AI account",
"3. Create a new API key",
"4. Set {apiKeyEnvVar} in your .env file"
]
},
"evidence": {
"rosterVerified": {
"date": "2026-08-28",
"method": "transcribed from pre-migration TS catalog"
},
"liveMatrix": null,
"addedInPR": "https://github.com/juspay/neurolink/pull/1587"
}
}