io.usefulapi/together-ai

up checked 2026-11-11T08:37:49.342Z

Unclaimed · Unverified

Agent searches it appeared in, last 30 days: 0. Run this server? Claim the listing: verified label, uptime alerts and analytics.

Publisher-provided title

Together AI MCP by usefulapi

Publisher-provided description

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

Summary by lookupd

Runs chat, embeddings and image models, and manages fine-tunes, batch jobs and dedicated GPU endpoints on Together AI.

Install

Claude Code, remote (streamable-http)

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

Codex, remote (streamable-http)

codex mcp add together-ai --url https://together-ai.usefulapi.io/mcp

Cursor, remote (streamable-http) → .cursor/mcp.json

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

Other clients: docs. Or tell your agent: Set up lookupd for me: read https://lookupd.com/agent.md and follow it.

Tools (23 tools)

Publisher-provided text

• together_whoami Identify the API key: its organization, project and project slug. The project slug forms the `<project_slug>/<endpoint_slug>` model name for dedicated-endpoint
• together_list_models List Together's models with type (chat, language, code, image, embedding, moderation, rerank), context length, organization, license and per-token pricing. Toge
• together_list_files 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_get_file 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_list_fine_tunes List fine-tuning jobs with status, base model, output model name and training settings. Together: GET /fine-tunes.
• together_get_fine_tune Fetch one fine-tuning job: status, progress, hyperparameters, token counts, cost and the output model name. Together: GET /fine-tunes/{id}.
• together_list_fine_tune_events 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
• together_list_batches List batch inference jobs with status, progress, model and input/output/error file ids. Together: GET /batches.
• together_get_batch Fetch one batch job: status (VALIDATING, IN_PROGRESS, COMPLETED, FAILED, EXPIRED, CANCELLED), progress, and the output_file_id / error_file_id once done. Togeth
• together_list_endpoints 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 yo
• together_get_endpoint Fetch one dedicated endpoint: state, model, hardware, autoscaling bounds and display name. Together: GET /endpoints/{endpointId}.
• together_list_hardware List hardware configurations for dedicated endpoints with GPU type/count/memory and price in cents per minute. Pass a model to get only compatible configuration
• together_list_evaluations List LLM-as-a-judge evaluation jobs (classify, score, compare) with status, parameters and results once completed. Together: GET /evaluation.
• together_chat_completion 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. To
• together_create_embeddings Generate vector embeddings for one or more texts (billed per token). Together: POST /embeddings.
• together_generate_image Generate images from a prompt (billed per image/megapixel). Returns image URLs by default rather than base64, to keep responses small. Together: POST /images/ge
• together_create_fine_tune 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_cancel_fine_tune 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}/ca
• together_create_batch 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_cancel_batch Cancel a batch job that has not finished. Together: POST /batches/{id}/cancel.
• together_create_endpoint 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_start_endpoint Start a stopped dedicated endpoint. It bills per minute of uptime until stopped. Reversible with together_stop_endpoint. Together: PATCH /endpoints/{endpointId}
• together_stop_endpoint Stop a running dedicated endpoint, which stops its per-minute billing. Requests to it fail until it is started again. Together: PATCH /endpoints/{endpointId} wi

Details

• Version: 1.37.3
• Transports: streamable-http
• Uptime (7 days): 100%
• Median latency: 739 ms
• First indexed: 2026-11-01T10:06:35.764Z
• Last seen in registry: 2026-11-11T00:17:36.017Z
• Repository: https://github.com/m190/usefulapi-mcp
• Website: https://usefulapi.io/together-ai/

Badge for your README

Shows this live status and links here; updates hourly.

[![lookupd status](https://lookupd.com/badge/io.usefulapi/together-ai.svg)](https://lookupd.com/servers/io.usefulapi/together-ai)

• 62071 servers
• Last crawl: 2026-11-11T16:17:25.167Z
• API base: https://api.lookupd.com
• MCP URL: https://api.lookupd.com/mcp