Integration

Together AI integration

Together AI inference and training platform. Run chat and text completions, embeddings and reranking against 100+ open-source models, generate images and video, synthesise and transcribe speech, execute code in a sandboxed interpreter session, submit batch inference jobs, upload training files and drive supervised fine-tuning and evaluation jobs. The inference surface is OpenAI-compatible, so a model id is the only thing most calls change. Authentication is a bearer API key that scopes every call to one account.

Connect Together AI How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Together AI.Built from the 31 Together AI tools below, on the connection you add once.

Common Together AI use cases

Build semantic search systems
Debug fine-tuning failures
Build voice assistants
Monitor training progress
Generate marketing visuals
Generate text continuations
Clean up old fine-tuning jobs
Improve RAG pipeline accuracy
Download uploaded training data
Stop incorrectly configured jobs

What you can do with Together AI

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Fine tuning, 6 operations

cancel_fine_tuning_jobCancel fine tuning jobPOSTStops an in-progress fine-tuning job and releases associated compute resources.
create_fine_tuning_jobCreate fine tuning jobPOSTInitiates a fine-tuning job to customize models on specific datasets and use cases.
delete_fine_tuning_jobDelete fine tuning jobDELETEPermanently deletes a fine-tuning job record.
download_fine_tuned_modelDownload fine tuned modelGETDownloads ZSTD-compressed weights of a fine-tuned model.
get_fine_tuning_jobGet fine tuning jobGETRetrieves detailed status and metrics for a specific fine-tuning job.
list_fine_tuning_jobsList fine tuning jobsGETRetrieves all fine-tuning jobs with their current status and progress information.

File, 5 operations

delete_fileDelete fileDELETEPermanently removes an uploaded file from storage.
get_fileGet fileGETRetrieve file metadata.
get_file_contentGet file contentGETRetrieves the raw contents of a single uploaded data file.
list_filesList filesGETRetrieves all uploaded files with metadata including size, purpose, and upload timestamps.
upload_fileUpload filePOSTUploads training or validation datasets for use in fine-tuning and evaluation.

Batche, 3 operations

create_batchCreate batchPOSTCreate a batch job.
get_batchGet batchGETGet a batch job.
list_batchesList batchesGETList batch jobs.

Evaluation, 3 operations

create_evaluation_jobCreate evaluation jobPOSTCreate an evaluation job.
get_evaluation_jobGet evaluation jobGETGet evaluation job details.
list_evaluation_jobsList evaluation jobsGETGet all evaluation jobs.

Audio, 1 operation

audio_speechAudio speechPOSTConverts text to speech audio using TTS models.

Cancel, 1 operation

cancel_batchCancel batchPOSTCancel a batch job.

Chat, 1 operation

chat_completionsChat completionsPOSTGenerates conversational responses using open-source chat models with OpenAI-compatible API format.

Completion, 1 operation

completionsCompletionsPOSTGenerates text completions from a prompt using open-source language models.

Embedding, 1 operation

embeddingsEmbeddingsPOSTGenerates vector embeddings from text for semantic search and similarity analysis.

Event, 1 operation

list_fine_tuning_eventsList fine tuning eventsGETRetrieves chronological event logs and training metrics for a fine-tuning job.

Execute, 1 operation

execute_codeExecute codePOSTExecute code.

Image, 1 operation

image_generationsImage generationsPOSTCreates images from text descriptions using state-of-the-art open-source diffusion models.

Model, 1 operation

list_modelsList modelsGETRetrieves all available models across different modalities including chat, completion, embedding, image, and audio.

Rerank, 1 operation

rerankRerankPOSTReranks documents by relevance to a query for improved search quality.

Session, 1 operation

list_code_sessionsList code sessionsGETList active sessions.

Statu, 1 operation

get_evaluation_job_statusGet evaluation job statusGETGet evaluation job status and results.

Transcription, 1 operation

audio_transcriptionsAudio transcriptionsPOSTTranscribes audio files to text using speech recognition models.

Translation, 1 operation

audio_translationsAudio translationsPOSTTranslates audio from any language to English text.

Use Together AI from Claude Code, Cursor or Codex

Connect Together AI in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Together AI operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Together AI

Create your workspace
Sign up free. Nothing to install.
Connect Together AI once
Add your Together AI connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.

Together AI integration FAQ

What can you do with the Together AI integration?

LiveContext exposes 31 operations on Together AI, covering fine tuning, file, batche and evaluation. Common uses include Build semantic search systems, Debug fine-tuning failures and Build voice assistants.