MCP server

Together AI MCP by usefulapi

io.usefulapi/together-ai

Checked 26 Oct 2026, 08:29 UTC · Connected to it and listed its tools

Run Together AI chat, embeddings and images; manage fine-tunes, batches and endpoints.

Website Source

At a glance

Type

MCP server

Publisher

usefulapi.io (verified by the MCP Registry)

Status

Working at last check

Tools

23

Token cost

About 4,594 tokens per request

Sets up in

Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, VS Code, Antigravity, ChatGPT, OpenAI API, Grok

Last checked

26 Oct 2026, 08:29 UTC

Connect it to your agent

Add to CursorAdd to VS CodeVS Code Insiders

Opens the app, which shows the server and asks you to confirm. For other apps, copy the setup below.

Claude Code

claude mcp add --transport http together-ai https://together-ai.usefulapi.io/mcp

Claude Desktop

Settings → Connectors → Add custom connector, and paste the URL.

Codex (config.toml)

[mcp_servers.together-ai]
url = "https://together-ai.usefulapi.io/mcp"

Gemini CLI

{"mcpServers":{"together-ai":{"httpUrl":"https://together-ai.usefulapi.io/mcp"}}}

Cursor

{"mcpServers":{"together-ai":{"url":"https://together-ai.usefulapi.io/mcp"}}}

VS Code

{"servers":{"together-ai":{"type":"http","url":"https://together-ai.usefulapi.io/mcp"}}}

Antigravity

agy mcp add together-ai https://together-ai.usefulapi.io/mcp

ChatGPT

Settings → Apps & Connectors → Advanced settings: turn on Developer mode, then Create a connector and paste the URL. Which plans can do this varies.

OpenAI API (Responses tools)

{"type":"mcp","server_label":"together-ai","server_url":"https://together-ai.usefulapi.io/mcp","require_approval":"always"}

Grok (xAI API tools)

{"type":"mcp","server_label":"together-ai","server_url":"https://together-ai.usefulapi.io/mcp"}

Tools

• together_cancel_batch ~96 tokens
  Cancel a batch job that has not finished. Together: POST /batches/{id}/cancel.
• together_cancel_fine_tune ~127 tokens
  Cancel a running fine-tuning job. Cannot be resumed, but a new job can continue from its last checkpoint via from_checkpoint. Together: POST /fine-tunes/{id}/cancel.
• together_chat_completion ~406 tokens
  Run a chat completion on a Together model (billed per token). Non-streaming. For a dedicated endpoint pass its `<project_slug>/<endpoint_slug>` as the model. Together: POST /chat/completions.
• together_create_batch ~264 tokens
  Start an asynchronous batch job over an uploaded JSONL input file (purpose batch-api), at a discount to real-time inference. Together: POST /batches.
• together_create_embeddings ~153 tokens
  Generate vector embeddings for one or more texts (billed per token). Together: POST /embeddings.
• together_create_endpoint ~437 tokens
  Deploy a model on dedicated GPUs. The endpoint STARTS AUTOMATICALLY and bills per minute of uptime until stopped — set inactive_timeout to auto-stop it, and use together_list_hardware for valid hardware ids. Together: POST /endpoints.
• together_create_fine_tune ~880 tokens
  Start a fine-tuning job on an uploaded training file (billed per token processed). Stop it with together_cancel_fine_tune. Together: POST /fine-tunes.
• together_generate_image ~418 tokens
  Generate images from a prompt (billed per image/megapixel). Returns image URLs by default rather than base64, to keep responses small. Together: POST /images/generations.
• together_get_batch ~124 tokens
  Fetch one batch job: status (VALIDATING, IN_PROGRESS, COMPLETED, FAILED, EXPIRED, CANCELLED), progress, and the output_file_id / error_file_id once done. Together: GET /batches/{id}.
• together_get_endpoint ~120 tokens
  Fetch one dedicated endpoint: state, model, hardware, autoscaling bounds and display name. Together: GET /endpoints/{endpointId}.
• together_get_file ~119 tokens
  Fetch one file's metadata, including its processing_status and validation_report (why a fine-tune training file was rejected). Together: GET /files/{id}.
• together_get_fine_tune ~118 tokens
  Fetch one fine-tuning job: status, progress, hyperparameters, token counts, cost and the output model name. Together: GET /fine-tunes/{id}.
• together_list_batches ~76 tokens
  List batch inference jobs with status, progress, model and input/output/error file ids. Together: GET /batches.
• together_list_endpoints ~188 tokens
  List endpoints with model, owner and state (PENDING, STARTING, STARTED, STOPPING, STOPPED, ERROR). Use mine=true and type=dedicated to see what is running on your account and billing by the minute. Together: GET /endpoints.
• together_list_evaluations ~149 tokens
  List LLM-as-a-judge evaluation jobs (classify, score, compare) with status, parameters and results once completed. Together: GET /evaluation.
• together_list_files ~87 tokens
  List uploaded data files (fine-tune, eval and batch-api inputs, plus job outputs) with size, type, purpose and validation status. Together: GET /files.
• together_list_fine_tune_events ~134 tokens
  List the event log of one fine-tuning job (queued, started, checkpoint saved, epoch completed, errors). The first place to look when a job failed. Together: GET /fine-tunes/{id}/events.
• together_list_fine_tunes ~78 tokens
  List fine-tuning jobs with status, base model, output model name and training settings. Together: GET /fine-tunes.
• together_list_hardware ~134 tokens
  List hardware configurations for dedicated endpoints with GPU type/count/memory and price in cents per minute. Pass a model to get only compatible configurations with live availability. Together: GET /hardware.
• together_list_models ~124 tokens
  List Together's models with type (chat, language, code, image, embedding, moderation, rerank), context length, organization, license and per-token pricing. Together: GET /models.
• together_start_endpoint ~127 tokens
  Start a stopped dedicated endpoint. It bills per minute of uptime until stopped. Reversible with together_stop_endpoint. Together: PATCH /endpoints/{endpointId} with state=STARTED.
• together_stop_endpoint ~126 tokens
  Stop a running dedicated endpoint, which stops its per-minute billing. Requests to it fail until it is started again. Together: PATCH /endpoints/{endpointId} with state=STOPPED.
• together_whoami ~109 tokens
  Identify the API key: its organization, project and project slug. The project slug forms the `<project_slug>/<endpoint_slug>` model name for dedicated-endpoint inference. A cheap way to confirm the key works. Together: GET /whoami.

Browse

• Website monitoring
• Image generation
• Searching your documents (RAG)
• Calling other AI models

Related MCP servers

• Mistral MCP by usefulapi
  Manage your Mistral platform — models, files, batch jobs, agents and RAG document libraries.
• HL-AI-4.6 Chat
  Chat demo for HL-AI-4.6 (Qwen3-8B LoRA fine-tune)
• Kromoss
  Text-to-image fine-tune of MOSS-Image-Base with 8-step turbo
• ACE-Step 1.5 jpdenpa full fine-tune
  Full fine-tune of ACE-Step 1.5 turbo on Japanese songs
• betterimage.io
  Social cards and OG images from designed templates: card from a URL, presets, meta tags, link checks
• Model Ruler — AI Cost Calculators
  Read-only AI/LLM cost tools with current MCP discovery and attributable Registry transport.
• HeatPulse
  AI-news gateway for agents: curated events, digests, live LLM leaderboards, intent router.
• WELANDA Engraving Designer
  Design a laser engraving for a WELANDA snus case, preview it and hand the user a checkout link.

Badge for your README

[![AptLynx](https://aptlynx.net/badge/io.usefulapi/together-ai.svg)](https://aptlynx.net/servers/io.usefulapi/together-ai)

Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents