Together AI
Together Computer, Inc. (Together AI) · together.ai · Last checked:
- Serverless per-token API
- Dedicated endpoints
- Bring-your-own-model containers
Company status
Active, privately held.
Sources 1, 2, 3, 4, 5 · checked 2026-11-08
Capabilities
- Serverless inference for open-weight chat, vision, image, audio, embedding, and rerank models priced per 1M tokens or per unit
- OpenAI-compatible API (drop-in client setup); also supports OpenAI Responses and Anthropic Messages APIs
- Dedicated model inference on single-tenant GPUs billed per GPU-hour; provisioned throughput with SLAs
- Dedicated container inference for custom models, including serving an OpenAI-compatible endpoint
- Batch inference API; fine-tuning and post-training
- Privacy policy: no training on customer data without explicit opt-in
Sources 1, 2, 3, 4, 5 · checked 2026-11-08
Who it tends to fit
- Teams that want serverless open-weight models and a path to dedicated or custom containers
- Buyers needing SOC 2 Type 2 and ISO 27001 documents in a trust center
Sources 1, 2, 3, 4, 5 · checked 2026-11-08
Pricing
Published per-token pricing on https://www.together.ai/pricing (serverless price per 1M tokens by model); dedicated inference billed per GPU-hour (for example, NVIDIA HGX H100 listed at $5.49 per GPU-hour on demand).
Sources 1, 2, 3, 4, 5 · checked 2026-11-08
Published certifications
- SOC 2 Type 2
- ISO 27001:2022
Listed as stated by the vendor. Scope can differ by product or subsidiary; request current reports.
Sources 1, 2, 3, 4, 5 · checked 2026-11-08
Limitations to check
- HIPAA not listed in the Trust Center; ask for BAA terms if needed
- Data retention options for inference are not stated on the pages checked; confirm in the DPA
- Region choice is not documented on the pages checked
Sources 1, 2, 3, 4, 5 · checked 2026-11-08
Sources
- Pricing: serverless price per 1M tokens; provisioned throughput; dedicated inference per GPU per hour (HGX H100 $5.49)www.together.ai/pricingChecked 2026-11-08
- Trust Center compliance: SOC 2, ISO 27001:2022; SOC 2 Type 2 report updated June 17, 2026; ISO 27001:2022 certification announced May 29, 2026trust.together.aiChecked 2026-11-08
- Drop-in OpenAI client setup; supports OpenAI Responses API and Anthropic Messages APIdocs.together.ai/docs/openai-api-compatibilityChecked 2026-11-08
- Dedicated containers: serve an OpenAI-compatible endpoint for custom modelsdocs.together.ai/docs/dedicated-containers-openaiChecked 2026-11-08
- Privacy policy: data not used to train models without explicit opt-in and consentwww.together.ai/privacyChecked 2026-11-08
Report a correction: [email protected]. Facts are re-checked at least every 90 days.