spb/tools-spboucher-ai

1{2  "slug": "together-ai",3  "name": "Together AI",4  "aliases": ["Together", "Together Cloud", "together.ai"],5  "vendor": { "name": "Together AI", "slug": "together-ai-inc", "website": "https://www.together.ai" },6  "homepage_url": "https://www.together.ai/",7  "docs_url": "https://docs.together.ai/intro",8  "repo_url": "https://github.com/togethercomputer/together-python",9  "pricing_url": "https://www.together.ai/pricing",10  "privacy_url": "https://www.together.ai/privacy",11  "product_type": "platform",12  "product_status": "active",13  "summary": "Cloud platform for open-source models: serverless and dedicated inference, fine-tuning, GPU clusters, batch jobs and code sandboxes behind an OpenAI-compatible API",14  "description": "Together AI is a cloud platform for running, training and serving open-weight models. Serverless inference exposes a large catalog of language, reasoning, speech, image and video models through an OpenAI-compatible API, billed per token or per media unit; dedicated endpoints give single-tenant GPU instances billed per GPU-hour; and fine-tuning jobs (supervised and preference-based) train on your data before deployment. Further services include provisioned throughput, batch inference, evaluations, code sandboxes and a code interpreter, and reserved or on-demand GPU clusters with attached storage for training at scale. Official Python and TypeScript SDKs mirror the API.\n\nThe catalog spans families such as Llama, Qwen, DeepSeek, Kimi, GLM, Mixtral, gpt-oss and Gemma for text, Whisper for speech and FLUX among image models, which makes Together a common choice for teams who want open models without operating vLLM themselves or who need burst GPU capacity. Pricing is usage-based throughout, with enterprise terms for reserved capacity. Limits are those of a hosted provider: data is processed off-premises, the catalog changes as models are added or retired, and heavy sustained use may be cheaper on owned hardware.",15  "capabilities": ["Serverless inference on open-weight text, speech, image and video models", "Dedicated single-tenant endpoints billed per GPU-hour", "Supervised and preference fine-tuning with deployment", "Batch inference, provisioned throughput and evaluations", "Code sandboxes and code interpreter", "On-demand and reserved GPU clusters", "OpenAI-compatible API with Python and TypeScript SDKs"],16  "workflows": ["Serve a Qwen or Llama model to an application without managing GPUs", "Fine-tune an open model on domain data and deploy it to an endpoint", "Rent a GPU cluster for a short training run"],17  "advantages": ["Wide open-model catalog under one API", "Path from serverless to dedicated to clusters", "OpenAI compatibility eases migration"],18  "limitations": ["Hosted only", "Catalog and prices change frequently", "Sustained high volume may favor self-hosting"],19  "prerequisites": ["Together AI account and API key"],20  "audiences": ["Developers using open models without infrastructure", "Teams fine-tuning open models", "Researchers needing short-term GPU capacity"],21  "alternatives": ["groq", "openrouter", "vllm", "hugging-face-hub", "mistral-ai"],22  "categories": [{ "slug": "model-providers", "primary": true }, { "slug": "model-training", "label": "Fine-tuning and GPU clusters" }],23  "tags": ["llm", "api", "open-weights", "gpu", "fine-tuning", "python", "typescript"],24  "use_cases": ["serve-models", "fine-tune-models", "build-agents"],25  "operating_systems": ["any"],26  "execution_modes": ["cloud"],27  "interfaces": ["api", "sdk", "web"],28  "deployment_models": ["saas", "managed-cloud"],29  "integrations": ["OpenAI SDK compatibility", "LangChain", "LlamaIndex", "LiteLLM", "Hugging Face Hub"],30  "data_formats": ["JSON", "JSONL (fine-tuning)", "Audio", "Images", "Video"],31  "languages": ["Python", "TypeScript"],32  "source_model": "proprietary",33  "pricing_model": ["usage-based", "enterprise"],34  "pricing_checked_at": "2026-11-02",35  "self_hostable": false,36  "sources": [37    { "url": "https://www.together.ai/", "type": "official_site", "title": "Together AI", "supports": ["name", "summary"], "checked_at": "2026-11-02" },38    { "url": "https://docs.together.ai/intro", "type": "official_docs", "title": "Together AI documentation", "supports": ["capabilities", "interfaces", "languages"], "checked_at": "2026-11-02" },39    { "url": "https://www.together.ai/pricing", "type": "pricing_page", "supports": ["pricing_model", "capabilities"], "checked_at": "2026-11-02" },40    { "url": "https://github.com/togethercomputer/together-python", "type": "repository", "title": "together-python (Apache-2.0)", "supports": ["languages"], "checked_at": "2026-11-02" }41  ],42  "confidence": "high",43  "discovery_method": "editorial-research",44  "depth": "standard",45  "editorial_status": "reviewed",46  "visibility": "public",47  "featured": false,48  "author": "batch-A"49}50