Registry / Tools / Together AI

Together AI facts

tool_together_ai
Platform

Together AI

AI cloud platform for model APIs, inference, fine-tuning, evaluations, GPU clusters, and sandboxes.

last verified: 2026-05-10pricing checked: 2026-05-10
01

Fact summary

Name
Together AI
Company / maker
Together AI
Entity type
Platform
Availability
Public
Pricing model
Usage Based
Pricing unit
month
Primary pricing route
Model Api
Delivery modes
APISDKWeb AppCLI
Supported platforms
Web
Data state
source backed
02

Official links

Formal source rows with URL, source type, and freshness.
LinkURLsource typechecked
Official websitewww.together.ai official-site2026-05-10
Pricing pagewww.together.ai/pricing official-pricing-page2026-05-10
Documentationdocs.together.ai official-documentation2026-05-10
API docsdocs.together.ai official-documentation2026-05-10
03

Access and delivery

Supported platforms and delivery modes are intentionally separate.

Supported platforms

Web

Delivery modes

APISDKWeb AppCLI
04

Capabilities

Capability tags

Model ApisModel HostingEvaluation MonitoringData Etl
Input types
TextImageAudioVideoStructured DataFunction CallSpreadsheetUrl
Output types
TextImageAudioVideoStructured JsonEmbeddingsDocument
06

Pricing summary

Pricing summary

Derived from official pricing routes where available
pricingModel
Usage Based
pricingUnit
month
startingPrice
$0.03 / month
currency
USD
pricingLastChecked
2026-05-10
07

Pricing routes

Each route is a first-class record with source URL and checked date.
GPU clusters
routeType: api-usage

Official pricing lists on-demand and reserved GPU cluster hourly pricing for H100, H200, and B200 hardware.

Dedicated inference
routeType: api-usage

Official pricing lists dedicated inference GPU instance prices such as H100, H200, and B200 hourly pricing.

Serverless inference API
routeType: model-api
primary route

Official pricing lists serverless inference prices per 1M tokens and model-specific prices across chat, vision, image, audio, video, embeddings, rerank, and moderation.

08

Pricing plans

plantrackmonthlyusage limitfeaturessourcechecked
Code Interpreterapi0.03per 60-minute sessionExecute LLM-generated code securely using the API2026-05-10
Managed Storageapi0.16per GiB/month for Shared FilesystemHigh-bandwidth, parallel filesystem colocated with compute2026-05-10
Fine-Tuning Standardapi-Usage-based per 1M tokens processed; rates vary by model size and methodSupervised Fine-Tuning, Direct Preference Optimization, LoRA and full fine-tuning options2026-05-10
Code Sandboxapi-Per vCPU $0.0446/hour; per GiB RAM $0.0149/hourCustomize a deployment of VM sandboxes for large development environments2026-05-10
Dedicated Inference 1x B200 180GBapi-$9.95 per hourGuaranteed performance with no sharing, Support for custom models, Autoscaling and traffic spike handling2026-05-10
Dedicated Inference 1x H200 141GBapi-$5.49 per hourGuaranteed performance with no sharing, Support for custom models, Autoscaling and traffic spike handling2026-05-10
Dedicated Inference 1x H100 80GBapi-$3.99 per hourGuaranteed performance with no sharing, Support for custom models, Autoscaling and traffic spike handling2026-05-10
Serverless Inferenceapi-Usage-based model pricing per 1M tokens, per image, per audio minute, per video, or related unit depending on modalityChat, Vision, Image, Audio, Video, Transcribe, Embeddings, Rerank, Moderation2026-05-10
09

Evidence and sources

source URLsource typeused forchecked
www.together.ai/supportofficial-documentationsupport2026-05-10
docs.together.aiofficial-documentationdocumentation, api-access, capabilities2026-05-10
www.together.ai/pricingofficial-pricing-pagepricing, pricing-routes2026-05-10
www.together.aiofficial-siteidentity, capabilities, access2026-05-10
10

Freshness and recent changes

Facts verified
2026-05-10
Identity and core facts
Pricing checked
2026-05-10
Pricing routes and plans
Record updated
2026-05-10
Public record freshness
11

Related pages

One-hop registry pages derived from this record's modeled facts. This section does not infer peer tools.