II.
Provider JSON
Structured · liveprovider:together-ai
Together AI json
Inspect the normalized record payload exactly as the atlas UI reads it.
{
"id": "provider:together-ai",
"_kind": "Provider",
"_file": "compute/providers/together-ai.yaml",
"_cluster": "compute",
"attributes": {
"versionRange": ">=2024-01-01",
"displayName": "Together AI",
"vendor": "Together AI",
"authMethods": [
"api-key"
],
"authMethodNotes": "Standard `Authorization: Bearer <api-key>`. OpenAI-compatible surface\nplus a native fine-tuning API.\n",
"endpoints": {
"base": "https://api.together.xyz/v1",
"chat_completions": "https://api.together.xyz/v1/chat/completions",
"completions": "https://api.together.xyz/v1/completions",
"embeddings": "https://api.together.xyz/v1/embeddings",
"models": "https://api.together.xyz/v1/models"
},
"pricing": "See https://www.together.ai/pricing — pricing varies per open-weights\nmodel and tier.\n",
"pricingTiers": [
{
"name": "serverless",
"rateLimit": "Tiered per-account RPM caps",
"priceMultiplier": 1,
"description": "Pay-per-token serverless inference (default)."
},
{
"name": "dedicated",
"rateLimit": "GPU-hour billed; per-deployment throughput",
"priceMultiplier": 1,
"description": "Dedicated endpoints — reserved GPU capacity."
},
{
"name": "batch",
"rateLimit": "Async; processed within 24h SLA",
"priceMultiplier": 0.5,
"description": "Together Batch Inference — discounted async."
}
],
"rateLimitSignalingProtocol": "OpenAI-compatible. 429 with `retry-after`; `x-ratelimit-*` headers\nsurfaced where applicable.\n",
"dataResidencyOptions": [
"us",
"us-east-1"
],
"vendorFeatures": [
"capability:supports-batch-api"
],
"slaTier": "together-no-public-sla",
"regions": [
"global",
"us-east-1"
]
},
"outgoingEdges": [
{
"from": "provider:together-ai",
"to": "layer:2-provider",
"kind": "realizes",
"attributes": {}
},
{
"from": "provider:together-ai",
"to": "model:llama-4-405b-instruct@current",
"kind": "serves"
}
],
"incomingEdges": [
{
"from": "model:codestral-22b@current",
"to": "provider:together-ai",
"kind": "served_by"
},
{
"from": "model:deepseek-r1-distill-qwen-32b@current",
"to": "provider:together-ai",
"kind": "served_by"
},
{
"from": "model:deepseek-r1@current",
"to": "provider:together-ai",
"kind": "served_by"
},
{
"from": "model:deepseek-v3@current",
"to": "provider:together-ai",
"kind": "served_by"
},
{
"from": "model:gemma-2-27b@current",
"to": "provider:together-ai",
"kind": "served_by"
},
{
"from": "model:llama-3-1-405b-instruct@current",
"to": "provider:together-ai",
"kind": "served_by"
},
{
"from": "model:llama-3-1-70b-instruct@current",
"to": "provider:together-ai",
"kind": "served_by"
},
{
"from": "model:llama-3-3-70b-instruct@current",
"to": "provider:together-ai",
"kind": "served_by"
},
{
"from": "model:llama-4-405b-instruct@current",
"to": "provider:together-ai",
"kind": "served_by"
},
{
"from": "model:llama-4-maverick@current",
"to": "provider:together-ai",
"kind": "served_by"
},
{
"from": "model:llama-4-scout@current",
"to": "provider:together-ai",
"kind": "served_by"
},
{
"from": "model:mistral-large-2@current",
"to": "provider:together-ai",
"kind": "served_by"
},
{
"from": "model:phi-3-medium@current",
"to": "provider:together-ai",
"kind": "served_by"
},
{
"from": "model:qwen-2-5-72b-instruct@current",
"to": "provider:together-ai",
"kind": "served_by"
},
{
"from": "model:qwen-2-5-coder-32b@current",
"to": "provider:together-ai",
"kind": "served_by"
},
{
"from": "model:qwq-32b-preview@current",
"to": "provider:together-ai",
"kind": "served_by"
}
]
}