II.
Provider overview
Reference · liveprovider:together-ai
Together AI overview
Inspect the raw attributes, linked wiki pages, and inbound or outbound graph edges for provider:together-ai.
Attributes
versionRange
>=2024-01-01
displayName
Together AI
vendor
Together AI
authMethods
- api-key
authMethodNotes
Standard `Authorization: Bearer <api-key>`. OpenAI-compatible surface
plus a native fine-tuning API.
endpoints
base
chat_completions
completions
embeddings
models
pricing
See https://www.together.ai/pricing — pricing varies per open-weights
model and tier.
pricingTiers
- nameserverlessrateLimitTiered per-account RPM capspriceMultiplier1descriptionPay-per-token serverless inference (default).
- namededicatedrateLimitGPU-hour billed; per-deployment throughputpriceMultiplier1descriptionDedicated endpoints — reserved GPU capacity.
- namebatchrateLimitAsync; processed within 24h SLApriceMultiplier0.5descriptionTogether Batch Inference — discounted async.
rateLimitSignalingProtocol
OpenAI-compatible. 429 with `retry-after`; `x-ratelimit-*` headers
surfaced where applicable.
dataResidencyOptions
- us
- us-east-1
vendorFeatures
slaTier
together-no-public-sla
regions
- global
- us-east-1
Outgoing edges
realizes1
- layer:2-provider·LayerProvider
serves1
- model:llama-4-405b-instruct@current·ModelVersionLlama 4 405B Instruct
Incoming edges
served_by16
- model:codestral-22b@current·ModelVersionCodestral 22B
- model:deepseek-r1-distill-qwen-32b@current·ModelVersionDeepSeek R1 Distill Qwen 32B
- model:deepseek-r1@current·ModelVersionDeepSeek R1
- model:deepseek-v3@current·ModelVersionDeepSeek V3
- model:gemma-2-27b@current·ModelVersionGemma 2 27B
- model:llama-3-1-405b-instruct@current·ModelVersionLlama 3.1 405B Instruct
- model:llama-3-1-70b-instruct@current·ModelVersionLlama 3.1 70B Instruct
- model:llama-3-3-70b-instruct@current·ModelVersionLlama 3.3 70B Instruct
- model:llama-4-405b-instruct@current·ModelVersionLlama 4 405B Instruct
- model:llama-4-maverick@current·ModelVersionLlama 4 Maverick
- model:llama-4-scout@current·ModelVersionLlama 4 Scout
- model:mistral-large-2@current·ModelVersionMistral Large 2
- model:phi-3-medium@current·ModelVersionPhi-3 Medium
- model:qwen-2-5-72b-instruct@current·ModelVersionQwen 2.5 72B Instruct
- model:qwen-2-5-coder-32b@current·ModelVersionQwen 2.5 Coder 32B
- model:qwq-32b-preview@current·ModelVersionQwQ 32B Preview