Be the first to get access to new connectors. Get early access →
ConnectorBay Early access

Together AI dedicated endpoints, deployments, analytics and instance types (your key) — connector documentation

  • MCP endpoint: https://byok-together-dedicated-inference.connectorbay.com/mcp
  • REST API: POST https://byok-together-dedicated-inference.connectorbay.com/v1/tools/{tool_name}, described by the OpenAPI 3.1 spec at https://byok-together-dedicated-inference.connectorbay.com/openapi.json
  • Transport: Streamable HTTP, stateless, MCP specification 2025-06-18 or later
  • Authentication: your own Together AI Dedicated Inference API key, sent in the X-Upstream-Key header of every request (never stored, logged or cached)
  • Health: https://byok-together-dedicated-inference.connectorbay.com/health · Tool schemas: https://byok-together-dedicated-inference.connectorbay.com/tools.json
  • Publisher: Unify Dynamics LLC · connectorbay.com/byok-together-dedicated-inference · agent@connectorbay.com

What Together AI dedicated endpoints, deployments, analytics and instance types (your key) is for

Together AI dedicated endpoints, deployments, analytics and instance types (your key) lets an AI assistant read your own Together AI Dedicated Inference data through the Together AI Dedicated Inference API with a key you supply (API key). Read-only: 12 tools (list_endpoints, get_endpoint, list_endpoint_events, get_endpoint_analytics, list_deployments, get_deployment, list_deployment_adapters, list_organization_endpoints, list_placement_profiles, list_instance_types, list_ab_experiments, list_shadow_experiments). The BYOK key travels with each request, is used for that one call only and is never stored, logged or cached; it is only ever sent to api.together.ai. Unofficial connector by Unify Dynamics LLC: not affiliated with, endorsed by or sponsored by Together AI Dedicated Inference. Together AI Dedicated Inference and its logos are trademarks of their owners and are used only to say which service the connector works with.

Ask your assistant things like:

  • "Which dedicated endpoints do I have on Together AI and are they ready?"
  • "Show the traffic split of one of my Together AI dedicated endpoints."
  • "Why did my Together AI dedicated endpoint scale or fail recently?"
  • "What is the latency and error rate of my Together AI dedicated endpoint this week?"
  • "Which deployments run behind my Together AI dedicated endpoint?"
  • "What autoscaling settings does one of my Together AI deployments have?"

What it does

  • list_endpoints: List the dedicated inference endpoints of a project with type, visibility, traffic split and a summary of each deployment (model, hardware, state, replicas).
  • get_endpoint: Get one dedicated endpoint with its traffic split and deployment summaries.
  • list_endpoint_events: List an endpoint's audit and lifecycle events (scaling, provisioning, errors), newest first.
  • get_endpoint_analytics: Get aggregated request counts, latency percentiles, throughput, error rate, GPU utilization and token totals for an endpoint over a time range. Reads metrics only; no inference is run.
  • list_deployments: List the deployments of an endpoint with model, hardware, state, replica counts, autoscaling bounds, runtime engine and placement.
  • get_deployment: Get one deployment's configuration, autoscaling policy, placement, runtime information and provisioning status.
  • list_deployment_adapters: List the LoRA adapters attached to a deployment with their load state per cluster.
  • list_organization_endpoints: List endpoints shared with every project of an organization.
  • list_placement_profiles: List the reusable placement profiles of a project: ordered region preferences that decide where deployments may run.
  • list_instance_types: List the GPU instance types available for dedicated inference with GPU type, count, memory, price per hour in cents and regional availability.
  • list_ab_experiments: List the A/B traffic experiments of an endpoint with control and variant deployments and their traffic percentages.
  • list_shadow_experiments: List the shadow experiments of an endpoint, which mirror sampled traffic to target deployments, with state and targets.

BYOK key

You bring your own Together AI Dedicated Inference API key (https://api.together.ai/settings/projects/~current/api-keys). Your assistant sends it in the X-Upstream-Key header with each request. ConnectorBay uses it for that one call only: it is never stored, logged or cached, never shown in an answer, and it is only sent to api.together.ai over https, with no redirects followed. Create a key with the fewest permissions the tools need (read-only if the provider offers it), and revoke it at the provider whenever you like.

Data sources

Live from the Together AI Dedicated Inference API (api.together.ai) with a BYOK key; documentation: https://docs.together.ai/reference/dmi/endpoints-list. Endpoints checked against that documentation on 2026-10-16.

What it is not

Unofficial connector by Unify Dynamics LLC: not affiliated with, endorsed by or sponsored by Together AI Dedicated Inference. Together AI Dedicated Inference and its logos are trademarks of their owners and are used only to say which service the connector works with. It is read-only: it never creates, changes, sends or deletes anything in your Together AI Dedicated Inference account.

Built for: Worldwide. Languages: English.