Icon for Together AI

Together AI

The fastest cloud platform for building and running generative AI.

Together.ai Inference provides fast, scalable, and cost-efficient serverless API endpoints for deploying and fine-tuning leading open-source models like Llama-2 and Mistral. It emphasizes speed and efficiency, claiming up to 3x faster performance and 6x lower costs than competitors, alongside automatic scaling to meet growing API request volumes. The platform supports over 100 models.

Pricing: Per token usage

Hosting Cloud + Self-hosted
Pricing Usage Based, Pay-per-token
HQ 🇺🇸 United States
Founded 2022
License PROPRIETARY
Compliance SOC 2 · HIPAA · GDPR · SSO

Data and privacy

Checked 17 November 2026
Data processed
Not stated for the default endpoints; some models are also sold as 'US geo-pinned' at a higher price source
DPA
Not public
Sub-processors
View the list ↗
US parent company
Yes

Read from Together AI's own legal pages. "Not public" means it is not on their site; some providers share it on request.

Screenshot of Together AI webpage

Together AI prices by model

Per 1M tokens, read off Together AI's own pricing page on the date shown.

Model Input / 1M Cached / 1M Output / 1M Checked Notes
DeepSeek V4 Pro $1.32 $0.13 $3.96 14 Nov 2026 Listed as DeepSeek V4 Pro 0813
DeepSeek V4.1 Flash $0.30 $0.006 $1.20 14 Nov 2026
DeepSeek V4.1 Flash 1017 $0.30 $0.006 $1.20 17 Nov 2026 US geo-pinned $0.375 / $1.50.
GLM 5.3 $1.40 $0.26 $4.40 14 Nov 2026
GLM 5.3 Flash $0.15 $0.03 $0.50 14 Nov 2026
Kimi K3 $3.00 $0.30 $15.00 14 Nov 2026
Kimi K3.1 Pro $2.00 $0.20 $10.00 17 Nov 2026
MiniMax M3.1 Flash $0.15 $0.015 $0.60 17 Nov 2026 US geo-pinned $0.1875 / $0.75.
Tev1 4B Experimental $0.042 – $0.00 17 Nov 2026 Listed as Tev1 4B Experimental. Output tokens are free.
gpt-oss-120b $0.15 – $0.60 14 Nov 2026

Together AI runs open-weight models as a hosted service behind an OpenAI-compatible API, alongside fine-tuning, dedicated endpoints, batch jobs, an evaluations API, a code-execution sandbox and custom model hosting. For teams that want the same models on reserved hardware, it also rents GPU clusters directly.

Serverless pricing is per model and per million tokens. Read on 14 November 2026 from Together's own pricing page: DeepSeek V4.1 Flash at $0.30 in and $1.20 out ($0.006 cached); GLM-5.3 at $1.40 and $4.40 ($0.26 cached); Kimi K3 at $3.00 and $15.00; gpt-oss-120B at $0.15 and $0.60. US geo-pinned versions of several models cost 25% more. Dedicated inference is listed at $5.49 per H100 GPU-hour and $9.29 for B200; GPU clusters start at $3.99 per H100-hour on demand, $3.45 reserved for 31 to 90 days and $1.99 preemptible. The model catalogue changes quickly: Llama 3.3 70B and MiniMax M3 left the serverless list this autumn. Treat any of these figures as needing a re-check rather than as settled.

The company was founded in 2022, is led by Vipul Ved Prakash, holds ISO 27001:2022 certification and announced an $800 million Series C on 1 July 2026 with investors including NVIDIA, Aramco Ventures, Vista Equity and General Catalyst.

Also listed in

Work on Together AI? Feature it at the top of Inference APIs.

Is your product missing?

Add it here →