Together AI
Cloud platform for OSS LLM inference and fine-tuning — serverless inference, dedicated endpoints, fine-tuning API, training cluster.
Active · Verified 2026-10-27 · fresh as of 2026-10-27 · 20 cited facts, 0 with a third-party source · 1 recorded change · Suggest a correction
At a glance
- Type
- Inference + fine-tuning cloud vendor fix
- Tier
- T1
- Section
- Inference platforms & gateways
- Latest release
- v3.0.0 (2026-10-22) — together (Python SDK) registry fix
- License
- proprietary; Python SDK Apache-2.0 registry fix
- GitHub
- searched not found vendor fix
- Pricing
- Serverless pay-per-token (e.g. $0.15–$3.00 per 1M input tokens); dedicated endpoints per GPU-hour (H100 $5.49/hr); fine-tuning per 1M training tokens; GPU clusters from $3.19–$3.99 per H100-hour vendor fix
- Funding
- $800M Series C 2026-07-01 (Aramco Ventures, NVIDIA, Vista Equity, General Catalyst, Salesforce Ventures and others); earlier rounds: $20M seed, $102.5M Series A, $305M Series B at $3.3B valuation vendor fix
- Freshness
- 2026-10-27 fix
- Layer
- model-infra repo fix
- Licensing
- commercial registry fix
- SDK languages
- python, rest, typescript vendor fix
- Protocols
- openai-compatible vendor fix
- Compliance
- gdpr, iso27001, soc2-type2 vendor fix
When to use
Optimised for: searched not found
Anti-fit: searched not found
Pros & cons
Pros
searched not found
Cons
searched not found
Claims & capabilities
$305M Series B (Feb 2025) at ~$3.3B; Salesforce, Snowflake among early customers.
Technical surface
- API surface
- searched not found
- Backend storage
- not applicable — not a memory product
- Deployment
- Managed-only — serverless and dedicated inference, fine-tuning, GPU clusters
- Embedding model
- not applicable — not a memory product
- Multi-tenancy
- searched not found
- MCP
- searched not found
- A2A
- searched not found
- OpenTelemetry
- searched not found
Compare Together AI with…
Similar systems
Other inference platforms & gateways in the catalog, ranked by inbound references.
- LiteLLM T1
BerriAI's open-source LLM gateway — unified OpenAI-format API for 100+ providers; LiteLLM Proxy adds budgets, fallbacks, observability, rate-limiting.
- OpenRouter T1
Unified API + marketplace for 300+ models — pay-as-you-go credits, automatic fallback, model arena. Used as default LLM router by many JS/TS agents.
- Fireworks AI T1
Fast inference platform for OSS LLMs — custom Cuda kernels, speculative decoding, multi-LoRA serving. Targets latency-sensitive production use cases.
- vLLM T1
Open-source LLM inference engine with PagedAttention — high-throughput batching, paged KV-cache. UC Berkeley origin; de-facto OSS inference stack.
- Portkey AI T2
AI gateway + observability — load balancing across 200+ LLMs, retries, caching, eval, prompts. Open-source Gateway + commercial Portkey Cloud. Acquired by Palo Alto Networks (closed about 2026-06); now sold as Prisma AIRS AI Gateway (GA 2026-07-16).
- Baseten T1
Inference platform for ML models — Truss package format, Chains for multi-model workflows, autoscaling GPU/CPU serving. Targeted at production teams shipping LLM/diffusion endpoints.
Sources (19 cited facts, 0 third-party)
Each fact links to the page it came from; the badge says who published it (how to read sources).
- What it is Inference + fine-tuning cloud vendor
- What it does & what's distinct Cloud platform for OSS LLM inference and fine-tuning — serverless inference, dedicated e… vendor
- Claims / benefits $305M Series B (Feb 2025) at ~$3.3B; Salesforce, Snowflake among early customers. vendor
- Created 2022 vendor
- Latest release v3.0.0 (2026-10-22) — together (Python SDK) registry
- License proprietary; Python SDK Apache-2.0 registry
- Funding $800M Series C 2026-07-01 (Aramco Ventures, NVIDIA, Vista Equity, General Catalyst, Sale… vendor
- Customers / scale Salesforce, Zoom, The Washington Post, Cognition Labs, Pika Labs; serving Llama / Mixtra… vendor
- Pricing Serverless pay-per-token (e.g. $0.15–$3.00 per 1M input tokens); dedicated endpoints per… vendor
- Deployment Managed-only — serverless and dedicated inference, fine-tuning, GPU clusters vendor
- HQ San Francisco, CA, USA. vendor
- Founders / pedigree Vipul Ved Prakash (CEO; ex-Topsy), Ce Zhang (CTO; ETH Zurich), Chris Re, Percy Liang; fo… vendor
- architecture-deployment-locus cloud vendor
- licensing-bucket commercial registry
- positioning-platform-vs-product platform vendor
- taxonomy-three-layer-rollup model-infra repo
- compliance-certifications gdpr,iso27001,soc2-type2 vendor
- sdk-languages python,rest,typescript vendor
- protocol-support openai-compatible vendor
What changed
Changes to this record's lifecycle, licence, release, pricing and hosting facts, from the catalog's git history. Subscribe (Atom)
- 2026-10-27
- License first recorded as “proprietary; Python SDK Apache-2.0” source
- Latest release first recorded as “v3.0.0 (2026-10-22) — together (Python SDK)” source
- Pricing “Pay-per-token / dedicated GPU” → “Serverless pay-per-token (e.g. $0.15–$3.00 per 1M input tokens); dedicated endpoints per GPU-hour (H100 $5.49/hr); fine-tuning per 1M training tokens; GPU clusters from $3.19–$3.99 per H100-hour” source
- Funding / ownership “$228.5M total raised through Series A 2024-03 ($106M, Salesforce Ventures led; $1.25B valuation); Series B 2024-11 reportedly $200M+ at $3.3B.” → “$800M Series C 2026-07-01 (Aramco Ventures, NVIDIA, Vista Equity, General Catalyst, Salesforce Ventures and others); earlier rounds: $20M seed, $102.5M Series A, $305M Series B at $3.3B valuation” source
- Deployment first recorded as “Managed-only — serverless and dedicated inference, fine-tuning, GPU clusters” source
Related systems
References (14)
- AutoGen / AG2 integrates with — Together AI docs third-party/agent integrations: AutoGen (AG2). (verified 2026-10-29)
- Composio integrates with — Together AI docs third-party/agent integrations: Composio. (verified 2026-10-29)
- CrewAI integrates with — Together AI docs third-party/agent integrations: CrewAI. (verified 2026-10-29)
- DSPy integrates with — Together AI docs third-party/agent integrations: DSPy. (verified 2026-10-29)
- Helicone integrates with — Together AI docs third-party/agent integrations: Helicone gateway/observability. (verified 2026-10-29)
- Hugging Face Inference API (Embeddings) integrates with — Together AI docs third-party/agent integrations: Hugging Face Inference integration guide. (verified 2026-10-29)
- LangChain (framework) integrates with — Together AI docs third-party/agent integrations: LangChain (langchain-together package). (verified 2026-10-29)
- LangGraph (orchestration) integrates with — Together AI docs third-party/agent integrations: LangGraph. (verified 2026-10-29)
- LiteLLM integrates with — Together AI docs third-party/agent integrations: LiteLLM (incl. Claude Code on Together via LiteLLM proxy). (verified 2026-10-29)
- LlamaIndex (framework) integrates with — Together AI docs third-party/agent integrations: LlamaIndex. (verified 2026-10-29)
- Mastra integrates with — Together AI docs third-party/agent integrations: Mastra quickstart. (verified 2026-10-29)
- Phidata (now Agno) integrates with — Together AI docs third-party/agent integrations: Agno. (verified 2026-10-29)
- Pydantic-AI integrates with — Together AI docs third-party/agent integrations: PydanticAI. (verified 2026-10-29)
- Vercel AI SDK integrates with — Together AI docs third-party/agent integrations: Vercel AI SDK quickstart. (verified 2026-10-29)
Referenced by (27)
- Agent Router (formerly Envoy AI Gateway) integrates with — Agent Router supported-providers page lists Together AI. (verified 2026-10-29)
- agentgateway integrates with — agentgateway integrations docs have a Together AI provider page. (verified 2026-10-29)
- Arize Phoenix integrates with — Arize Phoenix docs have a Together AI integration page. (verified 2026-10-29)
- Braintrust integrates with — Braintrust docs have a Together AI integration page. (verified 2026-10-29)
- Chroma integrates with — Chroma's docs have a Together AI integration page. (verified 2026-10-29)
- Comet ML integrates with — Comet's Opik docs have a Together AI integration page. (verified 2026-10-29)
- Haystack (framework) integrates with — Haystack integrations directory has a TogetherAI integration page ("Use the Together API for text generation models"). (verified 2026-10-29)
- Inspect AI integrates with — Inspect AI model-providers page documents a Together AI provider. (verified 2026-10-29)
- LangChain (framework) integrates with — LangChain docs have a Together integration provider page (Fast inference for open-source models). (verified 2026-10-29)
- Langfuse integrates with — Langfuse's integrations directory has a Together AI integration page. (verified 2026-10-29)
- Letta / MemGPT integrates with — Letta models docs list Together AI in the supported model provider table. (verified 2026-10-29)
- LiteLLM integrates with — LiteLLM docs have a Together AI provider page. (verified 2026-10-29)
- LiveKit Agents integrates with — LiveKit Agents docs have a Together AI model plugin page. (verified 2026-10-29)
- LlamaIndex (framework) integrates with — LlamaIndex has an official LLM integration package llama-index-llms-together in its repo. (verified 2026-10-29)
- Mem0 integrates with — Mem0 docs have a Together AI as LLM Provider LLM provider page for Mem0 open source. (verified 2026-10-29)
- OpenInference integrates with — The OpenInference repo README lists an OpenInference instrumentation package for Together AI. (verified 2026-10-29)
- OpenLLMetry (Traceloop) integrates with — OpenLLMetry's What's Supported page lists Together AI as instrumented out of the box. (verified 2026-10-29)
- OpenRouter integrates with — OpenRouter lists Together as an inference provider (providers API slug "together"). (verified 2026-10-29)
- Phidata (now Agno) integrates with — Agno ships a together model provider module (agno.models.together). (verified 2026-10-29)
- Pipecat (Daily) integrates with — Pipecat docs have a Together AI service page. (verified 2026-10-29)
- Portkey AI integrates with — Portkey docs have a Together AI LLM provider integration page. (verified 2026-10-29)
- Pydantic-AI integrates with — Pydantic AI "Other compatible APIs" docs have a Together AI section. (verified 2026-10-29)
- Temporal integrates with — Temporal integrations catalog lists Together AI model-provider integration. (verified 2026-10-29)
- TrueFoundry AI Gateway integrates with — TrueFoundry AI Gateway docs have a Together AI model-provider page. (verified 2026-10-29)
- Vapi integrates with — Vapi docs list Together AI as a provider/integration. (verified 2026-10-29)
- Vercel AI SDK integrates with — AI SDK docs have a Together.ai official AI SDK provider page. (verified 2026-10-29)
- Weights & Biases integrates with — W&B Weave docs have a Together AI integration page. (verified 2026-10-29)