---
title: Together AI
slug: together-ai
url: "https://toolweight.com/tools/together-ai"
homepage: "https://www.together.ai"
categories: llm-apis
last_verified: 2026-11-07
dataset_version: 0738be72
license: CC-BY-4.0
---

# Together AI

> Serverless and dedicated hosting for open-weight models

- Runs open-weight models at scale: serverless endpoints for 200+ models, dedicated GPU instances, plus fine-tuning
- Value is a Western contract and a US region in front of models whose origin API you may not want to call
- Per-model price list rather than a single flagship rate

## Identity

|  |  |
| --- | --- |
| Name | Together AI |
| Company | Together AI |
| One-liner | Serverless and dedicated hosting for open-weight models |
| Site | https://www.together.ai |
| Docs | https://docs.together.ai |
| Founded | 2022 |
| Funding | Late-stage private |
| Open source | No |
| Compared in | 1 |

## Where it is compared

### [LLM APIs](https://toolweight.com/compare/llm-apis)
Ranked **#11 of 18** on default weights.
| Field | Value | Confidence | Verified | Source | Note | Permalink |
| --- | --- | --- | --- | --- | --- | --- |
| Flagship model | Open-weight catalogue, DeepSeek-V3.x, Kimi K2, Qwen3, Llama 4 | Vendor-claimed | 2026-01-15 | https://docs.together.ai/docs/serverless-models | Priced per model by size class rather than as a single flagship rate. | https://toolweight.com/compare/llm-apis#together-ai--flagship_model |
| Context window | - | Unknown | - | - | Per-model. | https://toolweight.com/compare/llm-apis#together-ai--context_window |
| Max output | - | Unknown | - | - | Per-model. | https://toolweight.com/compare/llm-apis#together-ai--max_output |
| Image input | ◐ | Inferred | 2026-01-15 | - | - | https://toolweight.com/compare/llm-apis#together-ai--vision |
| Audio in/out | ◐ | Inferred | 2026-01-15 | - | - | https://toolweight.com/compare/llm-apis#together-ai--audio_io |
| Open weights | ● | Inferred | 2026-01-15 | - | Serves only open-weight models, so anything you build on here can be lifted onto your own hardware. | https://toolweight.com/compare/llm-apis#together-ai--open_weights |
| OpenAI-compat API | ● | Vendor-claimed | 2026-01-15 | https://docs.together.ai/docs/openai-api-compatibility | - | https://toolweight.com/compare/llm-apis#together-ai--openai_compatible |
| TTFT p50 | - | Unknown | - | - | - | https://toolweight.com/compare/llm-apis#together-ai--ttft_p50 |
| Output tok/s | - | Unknown | - | - | - | https://toolweight.com/compare/llm-apis#together-ai--throughput_tps |
| $/M input | - | Unknown | - | - | Per-model tiers roughly tracking parameter count; sub-$1/M for 70B-class models, low single digits for the largest MoE models. | https://toolweight.com/compare/llm-apis#together-ai--price_in |
| $/M output | - | Unknown | - | - | - | https://toolweight.com/compare/llm-apis#together-ai--price_out |
| $/M cache read | - | Unknown | - | - | - | https://toolweight.com/compare/llm-apis#together-ai--cached_input |
| Batch discount | 50% | Inferred | 2026-01-15 | - | A discounted batch endpoint is offered for supported models. | https://toolweight.com/compare/llm-apis#together-ai--batch_discount |
| Tool use | ◐ | Inferred | 2026-01-15 | - | - | https://toolweight.com/compare/llm-apis#together-ai--tool_use |
| Schema output | ● | Inferred | 2026-01-15 | - | JSON-schema constrained decoding is supported on most served models. | https://toolweight.com/compare/llm-apis#together-ai--structured_output |
| Effort control | ○ | Inferred | 2026-01-15 | - | - | https://toolweight.com/compare/llm-apis#together-ai--reasoning_effort |
| Computer use | ○ | Inferred | 2026-01-15 | - | - | https://toolweight.com/compare/llm-apis#together-ai--computer_use |
| MCP support | ○ | Inferred | 2026-01-15 | - | - | https://toolweight.com/compare/llm-apis#together-ai--mcp_support |
| Cache TTL | - | Unknown | - | - | - | https://toolweight.com/compare/llm-apis#together-ai--prompt_cache_ttl |
| Continuity policy | Serverless models are rotated off when demand drops, typically with a deprecations page and short notice measured in weeks. Because everything served is open-weight, the mitigation is always available: move to a dedicated endpoint on the same platform, to another host, or onto your own GPUs with the same checkpoint. | Inferred | 2026-01-15 | - | - | https://toolweight.com/compare/llm-apis#together-ai--continuity_policy |
| Notice period | 14 days | Vendor-claimed | 2026-11-07 | https://docs.together.ai/docs/deprecations | - | https://toolweight.com/compare/llm-apis#together-ai--deprecation_notice |
| Pinnable versions | ● | Inferred | 2026-01-15 | - | - | https://toolweight.com/compare/llm-apis#together-ai--pinned_snapshots |
| Zero retention | ● | Vendor-claimed | 2026-11-07 | https://docs.together.ai/docs/zero-data-retention | Opt-in org setting, applies to requests after enabling. Uploaded fine-tuning/batch files remain stored until deleted. | https://toolweight.com/compare/llm-apis#together-ai--zero_retention |
| Trains on your data | ○ | Inferred | 2026-01-15 | - | - | https://toolweight.com/compare/llm-apis#together-ai--trains_on_data |
| AU region | ○ | Inferred | 2026-01-15 | - | - | https://toolweight.com/compare/llm-apis#together-ai--au_region |
| API since | 2023 | Inferred | - | - | - | https://toolweight.com/compare/llm-apis#together-ai--launch_year |
| Positioning | Open-weight models with a Western contract and dedicated capacity | Inferred | - | - | - | https://toolweight.com/compare/llm-apis#together-ai--positioning |

**Verdict.** The pragmatic way to run Chinese open weights on US infrastructure under a recognisable contract; dedicated endpoints shine at steady load.

## Alternatives

- [Qwen](https://toolweight.com/tools/alibaba-qwen), Alibaba's model family, huge open-weight range, closed flagship
- [Amazon Bedrock](https://toolweight.com/tools/amazon-bedrock), Multi-vendor model access inside your existing AWS account
- [Anthropic](https://toolweight.com/tools/anthropic), Claude models, built around long agentic runs and tool use
- [Cerebras](https://toolweight.com/tools/cerebras), Wafer-scale inference, the fastest tokens per second available
- [Cohere](https://toolweight.com/tools/cohere), Enterprise-focused models built for RAG and private deployment
- [DeepSeek](https://toolweight.com/tools/deepseek), Frontier-adjacent models at a small fraction of Western prices
- [Fireworks AI](https://toolweight.com/tools/fireworks-ai), Fast open-weight inference with strong structured-output support
- [Google Gemini](https://toolweight.com/tools/google-gemini), Gemini via AI Studio for prototyping or Vertex AI for production
- [Groq](https://toolweight.com/tools/groq), Custom LPU silicon serving open-weight models at extreme speed
- [Meta Llama](https://toolweight.com/tools/meta-llama), Open-weight Llama models, hosted almost everywhere but Meta
- [Mistral AI](https://toolweight.com/tools/mistral-ai), European lab with an open-weight lineage and EU-resident hosting
- [Moonshot AI](https://toolweight.com/tools/moonshot-ai), Kimi models, open-weight agentic performance at low cost

## Logo & brand colours

SVG files: https://toolweight.com/teams/together-ai/logo.svg and https://toolweight.com/teams/together-ai/mono.svg. JSON: https://toolweight.com/api/v1/brands/together-ai.

| Hex | oklch |
| --- | --- |
| #13171b | oklch(20.2% 0.010 248.3) |

## Licence and attribution

Data from Toolweight (https://toolweight.com), licensed CC-BY-4.0.

- Licence: [CC-BY-4.0](https://creativecommons.org/licenses/by/4.0/)
- Canonical HTML: https://toolweight.com/tools/together-ai
- Machine-readable: https://toolweight.com/tools/together-ai.md · https://toolweight.com/api/v1 · https://toolweight.com/mcp
- Toolweight takes no affiliate revenue and sells no placements.