ToolPicker
Together AI

Together AI

36/100

Serverless embeddings (Multilingual E5, etc.), per-token.

together.ai

// scorecard · 36/100

verified 1mo ago
methodology →
Agent-readiness14/35
Agent registration (api_key)6/9
Public API5/5
OpenAPI spec0/9
MCP server0/9
llms.txt3/3
Reliability & performance0/15
Actively maintained
Production-ready0/4
Updated recently
Pricing6/13
Itemized public pricing6/6
Free tier / trial0/4
Free-tier generosity0/3
Docs & DX2/12
Docs quality
Public API2/2
Quickstart / examples0/2
Security & compliance10/12
SOC 26/6
ISO 270012/2
GDPR0/2
Security / trust page2/2
Openness4/10
Open source0/6
Open / un-gated API4/4
Company maturity0/3
Company size
Years operating

// rankings · cost per standard workload

#5 in Embeddings$2/ 100M tokens

Multilingual E5 large $0.02/1M x100 = $2/mo

together.ai/pricing

// overview

Together AI provides a full-stack AI native cloud platform for high-performance inference, accelerated compute via GPU clusters, and model shaping/fine-tuning of open-source models. It offers serverless inference APIs, batch inference, dedicated endpoints, and research-optimized infrastructure including storage and evaluations. Key offerings include access to models like MiniMax-M3, Gemma 4 31B, DeepSeek V4 Pro and hardware such as B200/H100 clusters.

Best for: AI teams and developers running open-source models for inference, fine-tuning and pre-training at scale

// pricing

Serverless Inferenceper 1M tokens
  • Chat, Vision, Embeddings and other modalities for listed models

// security & compliance

SOC 2 ISO 27001 GDPR HIPAA

// features

  • Serverless Inference APIs
  • Batch Inference
  • Dedicated Model Inference
  • GPU Clusters (B200, H100, GB200)
  • Fine-Tuning & Evaluations
  • Managed Storage

sources