Use Together AI with your AI.
Connect your account once and let the AI you already use work with it, without building another integration. Access 100+ open-source models for chat, image generation, and fine-tuning. Power your AI agents with Llama 3.3, Flux, and more.
Developed, maintained, and hosted by Vinkius.
MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED
Waiting for input…
Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.
Complete set · 27 capabilities
The complete Together AI capability set.
These are the exact actions your AI can choose when you ask it to work with Together AI.
01-04
4 capabilities in this set.
Part of 27 available through Together AI.
- 01
Cancel batch
Cancel a running batch job
- 02
Create batch
Create a new asynchronous batch job
- 03
Create chat completion
3-70B-Instruct-Turbo. Generate a model response for a given chat conversation
- 04
Create embeddings
Turn text into vector embeddings
05-08
4 capabilities in this set.
Part of 27 available through Together AI.
- 05
Create image generation
Generate images from text prompts
- 06
Create text completion
Generate text completions for a given prompt
- 07
Delete endpoint
Delete a dedicated endpoint
- 08
Get fine tune
Get details of a specific fine-tuning job
09-12
4 capabilities in this set.
Part of 27 available through Together AI.
- 09
List batches
List all batch jobs
- 10
List fine tunes
List all fine-tuning jobs
- 11
Create audio speech
Text-to-Speech (TTS) generation
- 12
Create audio transcription
Transcriptions (STT) from audio file
13-16
4 capabilities in this set.
Part of 27 available through Together AI.
- 13
Create endpoint
Create a dedicated endpoint for predictable performance
- 14
Create fine tune
Create a fine-tuning job
- 15
Delete file
Delete an uploaded file
- 16
Delete fine tune
Delete a fine-tuning job
17-20
4 capabilities in this set.
Part of 27 available through Together AI.
- 17
Create rerank
Reorder documents by relevance to a query
- 18
Get batch
Get details of a specific batch job
- 19
Get endpoint
Get details of a specific dedicated endpoint
- 20
Get file
Retrieve metadata for a specific file
21-24
4 capabilities in this set.
Part of 27 available through Together AI.
- 21
List endpoints
List all dedicated endpoints
- 22
List files
List all uploaded files
- 23
List fine tune checkpoints
List checkpoints for a fine-tuning job
- 24
List models
List all available models on Together AI
25-27
3 capabilities in this set.
Part of 27 available through Together AI.
- 25
Create video generation
Create videos from text or image prompts
- 26
Update endpoint
Update a dedicated endpoint (Start/Stop/Scale)
- 27
Upload file
Upload a file for fine-tuning, evals, or batch inference
Observed, not estimated
1006ms average. Fast in production.
Together AI is checked daily against the live service.
- Fastest day
- 883ms
- Slowest day
- 1306ms
- 14-day trend
- Slowing+10%
Connect your client
One URL. Every client.
Activate the Connector, copy your link, and paste it into the client you already use. 27 capabilities arrive ready to run.
Preview access · not provider authentication
The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Together AI, so you can see the experience inside your AI.
It does not authenticate your account with Together AI. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.
Together AI Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_3DCNpnHYF8hhWcXn2SCKuEfpGwWZe18MoQz7sb18/mcpClaude Desktop
Follow the steps below to connect in seconds.
- 1In Claude Desktop, open Settings → Connectors.
- 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
- 3Click Add and start a new chat — Together AI capabilities are ready to use.
{
"mcpServers": {
"together-ai-alternative-mcp": {
"url": "https://edge.vinkius.com/vk_preview_3DCNpnHYF8hhWcXn2SCKuEfpGwWZe18MoQz7sb18/mcp"
}
}
}
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Step-by-step instructions for each client are in the guide. How to connect
FAQ
Questions Together AI owners ask.
- 01
How do I generate a chat response using a specific model like Llama 3.3?
Use the create_chat_completion capability. Specify the model name (e.g., 'meta-llama/Llama-3.3-70B-Instruct-Turbo') and provide an array of messages. The agent will return the generated response from the model.
- 02
Can I create images from text prompts with this server?
Yes! Use the create_image_generation capability. You can specify the model, the prompt description, and optional parameters like width, height, and steps to get high-quality visual outputs.
- 03
How can I check the status of my asynchronous batch jobs?
You can use list_batches to see all your current batch jobs or get_batch with a specific Job ID to retrieve detailed status and results for a particular task.
Explore
More in AI Frontier
OpenAI AI Connector
Use GPT-4o, DALL-E 3, embeddings, fine-tuning, and moderation as tools inside your AI agent workflows.
ViewWriter (AI Enterprise LLM) AI Connector
Access Writer's enterprise-grade LLMs and Knowledge Graph capabilities to generate content, manage files, and
ViewVoyage AI (AI Embeddings API) AI Connector
Generate high-quality text, multimodal, and contextualized embeddings, plus high-precision reranking for RAG w
ViewEden AI AI Connector
Access 100+ AI models through a single API — route LLMs, generate embeddings, and execute specialized AI tasks
View
Suggestions
IBM watsonx AI Connector
Connect IBM watsonx to any AI agent via MCP.
ViewAssemblyAI AI Connector
Transcribe audio and video files with industry-leading accuracy, detect speakers, and extract insights from sp
ViewNVIDIA AI AI Connector
Access LLMs, embeddings, code generation, and reasoning via NVIDIA API Catalog.
ViewKling AI (Generative Video & Image) AI Connector
Generate cinematic videos and images via Kling AI — use text-to-video, image-to-video, and AI virtual try-on.
View
