--- title: "Together AI MCP server for AI agents - actionlake" description: "Give Claude 183 Together AI actions through one MCP server: projects endpoints rollouts. Your agent never holds the credential. 100,000 calls a month free." canonical: https://actionlake.com/connectors/together-ai updated: 2026-10-23 --- Connectors · AI # Together AI MCP server for AI agents. actionlake is an MCP gateway: one remote MCP server that connects Claude and other MCP clients to Together AI and the rest of your systems. It gives your agent 183 Together AI actions (101 reads, 57 writes and 25 that wait for a confirmation) and holds the Together AI credential itself, so the agent never does. It paces Together AI's limits and records every call. [Connect Together AI free](https://actionlake.com/console?start=sandbox) [See pricing](https://actionlake.com/pricing) 100,000 free calls a month. No card, no email, no password: press Start a free sandbox on the next screen and keep the key it shows you. `claude mcp add --transport http actionlake https://connect.actionlake.com/mcp` the first call ``` do { action: "together_ai.deployments.list", intent: "check which Together AI account is connected" } # Get the list of deployments · read · 1 upstream call ``` - 183 actions in one signed file - 101 read look, never change - 57 write create and update - 25 wait for a yes destructive, confirmed first Set up ## Connect Together AI in three steps. 1. 01 ### Add actionlake to Claude. Run the command once in Claude Code; its consent page can create a free sandbox: 100,000 calls a month, no card. In the Claude app, add a custom connector with the URL below and paste your key on the consent page. Creating a new sandbox from the Claude app is not yet tested by us. `https://connect.actionlake.com/mcp` 2. 02 ### Connect Together AI. API key. No consent screen: your agent can connect it for you, but the key then passes through your chat. To keep it out of the model's context, paste it in the console instead. actionlake stores what you paste write-only, sealed under your tenant's key. - `api_key` Together AI API key (api.together.ai > Settings > API Keys) ``` account { op: "connections.requirements", service: "together_ai" } # free: exactly what to paste, and what is found for you ``` 3. 03 ### Make the first call. Check before a write. Ask in plain words; Claude picks the action. Before anything changes, `check` validates the call and prices it, for free. ``` do { action: "together_ai.deployments.list" } # get the list of deployments · read · 1 upstream call check { action: "together_ai.deployments.create", input: { … } } # free: inputs, permissions, cost and confirmations, nothing sent ``` Together AI at a glance **Sign-in** API key. No consent screen: your agent can connect it for you, but the key then passes through your chat. To keep it out of the model's context, paste it in the console instead. **You provide** `api_key` **Limits we pace to** 60 calls a minute, per connection **API covered** Together AI API 2.0.0`api.together.ai` **Built from** Together AI's documentation, read 23 October 2026[docs.together.ai](https://docs.together.ai/openapi.yaml) [docs.together.ai](https://docs.together.ai/reference/chat-completions-1) **Service file** Version 1.0.0, signed (Ed25519) **Cached reads** 87 of 101 reads, for up to 5 minutes; a write clears what it affects **Shared entities** 2, so ask can line Together AI up with your other systems **Data** Processed and stored in Sydney, Australia. No US region yet Capabilities ## What an AI agent can do in Together AI. 183 actions in 74 areas. Every one carries its effect, so a key can allow the reads and hold the rest. - **101** read look, never change - **57** write create and update - **25** destructive wait for a confirmation 1. ### Projects endpoints rollouts 10 3 read · 5 write · 2 destructive Create a rollout · List endpoint rollouts · Get a rollout · Delete a rollout 2. ### Fine tunes 7 4 read · 1 write · 2 destructive Create job · List all jobs · List job · Delete a fine-tune job 3. ### RL training sessions operations 7 0 read · 7 write · 0 destructive Custom forward-backward pass · Forward-backward pass · Create inference checkpoint · Optimizer step 4. ### Compute clusters instances remediations 6 2 read · 3 write · 1 destructive compute_clusters_instances_remediations.create · List remediations · compute_clusters_instances_remediations.get · compute_clusters_instances_remediations.approve 5. ### Deployments 6 2 read · 3 write · 1 destructive Get the list of deployments · Create a new deployment · Get a deployment by ID or name · Update a deployment 6. ### Compute clusters 5 2 read · 2 write · 1 destructive Create a GPU cluster · List all GPU clusters · Get GPU cluster by cluster ID · Update a GPU cluster 7. ### Compute clusters addons 5 2 read · 2 write · 1 destructive compute_clusters_addons.create · compute_clusters_addons.list · compute_clusters_addons.get · compute_clusters_addons.update 8. ### Compute clusters storage volumes 5 2 read · 2 write · 1 destructive Create a shared volume · List all shared volumes · Get a shared volume by ID · Update a shared volume **66 more areas · 132 actions** - Deployments secrets **5** - Deployments storage volumes **5** - Projects endpoints **5** - Projects endpoints ab experiments **5** - Projects endpoints deployments **5** - Projects endpoints deployments adapters **5** - Projects endpoints shadow experiments **5** - Projects endpoints shadow experiments targets **5** - Projects models **5** - RL model resources **5** - RL training sessions **5** - Batches **4** - Evaluation **3** - Files **3** - Projects models uploads **3** - Queue jobs **3** - Shaping **3** - Deployments revisions **2** - Projects configs **2** - Projects models revisions **2** - Projects placement profiles **2** - Public inference instance types **2** - RL checkpoints **2** - Shaping FP4 jobs **2** - Supported models **2** - Videos **2** - Billing usage **1** - Chat completions **1** - Completions **1** - Compute passive health check alerts **1** - Compute regions **1** - Deployments logs **1** - Deployments storage files **1** - Embeddings **1** - Evaluation models **1** - Evaluation status **1** - Fine tunes checkpoints **1** - Fine tunes download tokenized dataset **1** - Fine tunes events **1** - Fine tunes metrics **1** - Fine tunes models limits **1** - Fine tunes models supported **1** - Image generations **1** - Organizations endpoints **1** - Organizations models **1** - Projects **1** - Projects endpoints analytics **1** - Projects endpoints events **1** - Projects models files **1** - Projects models uploads events **1** - Public endpoints **1** - Queue **1** - Queue metrics **1** - Rerank **1** - RL checkpoints download urls **1** - RL supported models **1** - RL training sessions operations custom forward backward **1** - RL training sessions operations forward backward **1** - RL training sessions operations inference checkpoint **1** - RL training sessions operations optim step **1** - RL training sessions operations sample **1** - RL training sessions operations training checkpoint **1** - RL training sessions operations weights sync **1** - Shaping events **1** - Voices **1** - Whoami **1** Top actions ## The Together AI API, shaped for agents. The ids your agent types, what each does, and the one name it shares with other systems. 32 of Together AI's 32 action names are shared with at least one other connector, so an agent learns them once. | Action | What it does | Effect | Same name in | | --- | --- | --- | --- | | `together_ai.deployments.list` Get the list of deployments | Get the list of deployments | read | `infra.deployment.list` 8 connectors | | `together_ai.files.list` List all files | List all files | read | `content.file.list` 77 connectors | | `together_ai.deployments.create` Create a new deployment | Create a new deployment | write | `infra.deployment.create` 7 connectors | | `together_ai.files.get` Retrieve file metadata | Retrieve file metadata | read | `content.file.get` 74 connectors | | `together_ai.deployments.delete` Delete a deployment | Delete a deployment | destructive | `infra.deployment.delete` 7 connectors | | `together_ai.compute_regions.list` List regions and corresponding supported driver versions | List regions and corresponding supported driver versions | read | `infra.region.list` 16 connectors | | `together_ai.deployments_storage_volumes.list` Get the list of project volumes | Get the list of project volumes | read | `infra.volume.list` 10 connectors | | `together_ai.batches.list` List batch jobs | List batch jobs | read | `automation.background_job.list` 34 connectors | | `together_ai.deployments_storage_volumes.create` Create a new volume | Create a new volume | write | `infra.volume.create` 8 connectors | | `together_ai.whoami.get` Identify the caller | Identify the caller | read | `identity.current_user.get` 307 connectors | | `together_ai.batches.create` Create a batch job | Create a batch job | write | `automation.background_job.create` 29 connectors | | `together_ai.compute_clusters.create` Create a GPU cluster | Create a GPU cluster | write | `infra.container_cluster.create` 6 connectors | Try it ## Prompts to paste into Claude. Each one names the Together AI actions it will call, so you know what it reads and what it changes before you send it. 1. Read read Which Together AI files changed this week, and who changed them? calls `together_ai.files.list` 2. Write write Create a new deployment in Together AI. Show me exactly what you will send before you save it. calls `together_ai.deployments.create` Governance for Together AI ## Destructive actions wait for a yes. 25 Together AI actions are destructive. These are all of them: - Delete a deployment `together_ai.deployments.delete` - Delete a file `together_ai.files.delete` - Delete a volume `together_ai.deployments_storage_volumes.delete` - Delete a model `together_ai.projects_models.delete` - Delete GPU cluster by cluster ID `together_ai.compute_clusters.delete` - Cancel a batch job `together_ai.batches.cancel` - Delete a fine-tune job `together_ai.fine_tunes.delete` - Delete an endpoint `together_ai.projects_endpoints.delete` - Delete a secret `together_ai.deployments_secrets.delete` - compute_clusters_addons.delete `together_ai.compute_clusters_addons.delete` - Delete a rollout `together_ai.projects_endpoints_rollouts.delete` - Delete a deployment `together_ai.projects_endpoints_deployments.delete` - Delete a shared volume by ID `together_ai.compute_clusters_storage_volumes.delete` - Delete an A/B experiment `together_ai.projects_endpoints_ab_experiments.delete` - Delete a shadow experiment `together_ai.projects_endpoints_shadow_experiments.delete` - Remove a deployment adapter `together_ai.projects_endpoints_deployments_adapters.delete` - Delete a shadow experiment target `together_ai.projects_endpoints_shadow_experiments_targets.delete` - Clear a model's pending jobs `together_ai.queue.clear` - Cancel shaping job `together_ai.shaping.cancel` - Cancel job `together_ai.fine_tunes.cancel` - Cancel a queued job `together_ai.queue_jobs.cancel` - Stop model resources `together_ai.rl_model_resources.stop` - Stop training session `together_ai.rl_training_sessions.stop` - Cancel a rollout `together_ai.projects_endpoints_rollouts.cancel` - compute_clusters_instances_remediations.cancel `together_ai.compute_clusters_instances_remediations.cancel` A destructive action runs only with `confirm: true`. Under the `human` policy the agent cannot confirm for itself: the run stops until a named person approves, in the console or from a signed link in an email. The cap on a key is refused before the call is sent, never after. do together_ai.deployments.delete confirm_policy: **human** Delete a deployment? **intent:** the user asked me to delete a deployment run suspended · waiting for a named person · key _together-ai-agent_ cannot confirm itself In the console, or from an emailed signed link. a key for this connector ``` account { op: "keys.create", name: "together-ai-agent", allowed_actions: ["together_ai.*"], cap_calls: 2000, confirm_policy: "human_for_writes", approval_rules: [ { match: "together_ai.deployments.delete", approver: "lead@example.com" }, { match: "together_ai.files.delete", approver: "lead@example.com" }, { match: "together_ai.deployments_storage_volumes.delete", approver: "lead@example.com" } ] } ``` Illustrative. Scoped to Together AI only, capped at 2,000 upstream calls, every write confirmed, and the destructive ones approved by a named person. Cost ## What Together AI costs on actionlake. Every Together AI action is one upstream call, the only thing actionlake bills. Searching, `check`, `cost`, `account` and any call Together AI refused with 401, 403, 429 or a 5xx are free. Paid plans start at US$49 a month for 250,000 calls, with overage from US$0.30 down to US$0.18 per 1,000. - 1 upstream call per action all 183 Together AI actions - 49 actions page each page of a long list is one call - 87 reads can be cached a cache hit costs nothing - 100,000 calls a month, free paid plans from US$49 a month for 250,000 [See pricing](https://actionlake.com/pricing) Action index ## Every Together AI action. 183 actions by area: the id your agent calls, what it does, and its effect. **Projects endpoints rollouts 10** - `together_ai.projects_endpoints_rollouts.cancel` Cancel a rollout destructive - `together_ai.projects_endpoints_rollouts.create` Create a rollout write - `together_ai.projects_endpoints_rollouts.delete` Delete a rollout destructive - `together_ai.projects_endpoints_rollouts.get` Get a rollout read - `together_ai.projects_endpoints_rollouts.list` List endpoint rollouts read - `together_ai.projects_endpoints_rollouts.pause` Pause a rollout write - `together_ai.projects_endpoints_rollouts.preview_defaults` Preview rollout defaults read - `together_ai.projects_endpoints_rollouts.promote` Promote a rollout write - `together_ai.projects_endpoints_rollouts.resume` Resume a rollout write - `together_ai.projects_endpoints_rollouts.start` Start a rollout write **Fine tunes 7** - `together_ai.fine_tunes.cancel` Cancel job destructive - `together_ai.fine_tunes.create` Create job write - `together_ai.fine_tunes.delete` Delete a fine-tune job destructive - `together_ai.fine_tunes.estimate_price` Estimate price read - `together_ai.fine_tunes.get` List job read - `together_ai.fine_tunes.list` List all jobs read - `together_ai.fine_tunes.preview` Preview tokenized data read **RL training sessions operations 7** - `together_ai.rl_training_sessions_operations.custom_forward_backward` Custom forward-backward pass write - `together_ai.rl_training_sessions_operations.forward_backward` Forward-backward pass write - `together_ai.rl_training_sessions_operations.inference_checkpoint` Create inference checkpoint write - `together_ai.rl_training_sessions_operations.optim_step` Optimizer step write - `together_ai.rl_training_sessions_operations.sample` Sample write - `together_ai.rl_training_sessions_operations.training_checkpoint` Save training checkpoint write - `together_ai.rl_training_sessions_operations.weights_sync` Weights sync write **Compute clusters instances remediations 6** - `together_ai.compute_clusters_instances_remediations.approve` compute_clusters_instances_remediations.approve write - `together_ai.compute_clusters_instances_remediations.cancel` compute_clusters_instances_remediations.cancel destructive - `together_ai.compute_clusters_instances_remediations.create` compute_clusters_instances_remediations.create write - `together_ai.compute_clusters_instances_remediations.get` compute_clusters_instances_remediations.get read - `together_ai.compute_clusters_instances_remediations.list` List remediations read - `together_ai.compute_clusters_instances_remediations.reject` compute_clusters_instances_remediations.reject write **Deployments 6** - `together_ai.deployments.create` Create a new deployment write - `together_ai.deployments.delete` Delete a deployment destructive - `together_ai.deployments.get` Get a deployment by ID or name read - `together_ai.deployments.list` Get the list of deployments read - `together_ai.deployments.rollback` Roll back a deployment to a previous revision write - `together_ai.deployments.update` Update a deployment write **Compute clusters 5** - `together_ai.compute_clusters.create` Create a GPU cluster write - `together_ai.compute_clusters.delete` Delete GPU cluster by cluster ID destructive - `together_ai.compute_clusters.get` Get GPU cluster by cluster ID read - `together_ai.compute_clusters.list` List all GPU clusters read - `together_ai.compute_clusters.update` Update a GPU cluster write **Compute clusters addons 5** - `together_ai.compute_clusters_addons.create` compute_clusters_addons.create write - `together_ai.compute_clusters_addons.delete` compute_clusters_addons.delete destructive - `together_ai.compute_clusters_addons.get` compute_clusters_addons.get read - `together_ai.compute_clusters_addons.list` compute_clusters_addons.list read - `together_ai.compute_clusters_addons.update` compute_clusters_addons.update write **Compute clusters storage volumes 5** - `together_ai.compute_clusters_storage_volumes.create` Create a shared volume write - `together_ai.compute_clusters_storage_volumes.delete` Delete a shared volume by ID destructive - `together_ai.compute_clusters_storage_volumes.get` Get a shared volume by ID read - `together_ai.compute_clusters_storage_volumes.list` List all shared volumes read - `together_ai.compute_clusters_storage_volumes.update` Update a shared volume write **Deployments secrets 5** - `together_ai.deployments_secrets.create` Create a new secret write - `together_ai.deployments_secrets.delete` Delete a secret destructive - `together_ai.deployments_secrets.get` Get a secret by ID or name read - `together_ai.deployments_secrets.list` Get the list of project secrets read - `together_ai.deployments_secrets.update` Update a secret write **Deployments storage volumes 5** - `together_ai.deployments_storage_volumes.create` Create a new volume write - `together_ai.deployments_storage_volumes.delete` Delete a volume destructive - `together_ai.deployments_storage_volumes.get` Get a volume by ID or name read - `together_ai.deployments_storage_volumes.list` Get the list of project volumes read - `together_ai.deployments_storage_volumes.update` Update a volume write **Projects endpoints 5** - `together_ai.projects_endpoints.create` Create an endpoint write - `together_ai.projects_endpoints.delete` Delete an endpoint destructive - `together_ai.projects_endpoints.get` Get an endpoint read - `together_ai.projects_endpoints.list` List endpoints read - `together_ai.projects_endpoints.update` Update an endpoint write **Projects endpoints ab experiments 5** - `together_ai.projects_endpoints_ab_experiments.create` Create an A/B experiment write - `together_ai.projects_endpoints_ab_experiments.delete` Delete an A/B experiment destructive - `together_ai.projects_endpoints_ab_experiments.get` Get an A/B experiment read - `together_ai.projects_endpoints_ab_experiments.list` List A/B experiments read - `together_ai.projects_endpoints_ab_experiments.update` Update an A/B experiment write **Projects endpoints deployments 5** - `together_ai.projects_endpoints_deployments.create` Create a deployment write - `together_ai.projects_endpoints_deployments.delete` Delete a deployment destructive - `together_ai.projects_endpoints_deployments.get` Get a deployment read - `together_ai.projects_endpoints_deployments.list` List deployments read - `together_ai.projects_endpoints_deployments.update` Update a deployment write **Projects endpoints deployments adapters 5** - `together_ai.projects_endpoints_deployments_adapters.create` Add a deployment adapter write - `together_ai.projects_endpoints_deployments_adapters.delete` Remove a deployment adapter destructive - `together_ai.projects_endpoints_deployments_adapters.get` Get a deployment adapter read - `together_ai.projects_endpoints_deployments_adapters.list` List deployment adapters read - `together_ai.projects_endpoints_deployments_adapters.update` Update a deployment adapter write **Projects endpoints shadow experiments 5** - `together_ai.projects_endpoints_shadow_experiments.create` Create a shadow experiment write - `together_ai.projects_endpoints_shadow_experiments.delete` Delete a shadow experiment destructive - `together_ai.projects_endpoints_shadow_experiments.get` Get a shadow experiment read - `together_ai.projects_endpoints_shadow_experiments.list` List shadow experiments read - `together_ai.projects_endpoints_shadow_experiments.update` Update a shadow experiment write **Projects endpoints shadow experiments targets 5** - `together_ai.projects_endpoints_shadow_experiments_targets.create` Create a shadow experiment target write - `together_ai.projects_endpoints_shadow_experiments_targets.delete` Delete a shadow experiment target destructive - `together_ai.projects_endpoints_shadow_experiments_targets.get` Get a shadow experiment target read - `together_ai.projects_endpoints_shadow_experiments_targets.list` List shadow experiment targets read - `together_ai.projects_endpoints_shadow_experiments_targets.update` Update a shadow experiment target write **Projects models 5** - `together_ai.projects_models.create` Create a model write - `together_ai.projects_models.delete` Delete a model destructive - `together_ai.projects_models.get` Get a model read - `together_ai.projects_models.list` List project models read - `together_ai.projects_models.update` Update a model write **RL model resources 5** - `together_ai.rl_model_resources.create` Create model resources write - `together_ai.rl_model_resources.estimate_cost` Estimate on-demand model resource cost read - `together_ai.rl_model_resources.get` Get model resources read - `together_ai.rl_model_resources.list` List model resources read - `together_ai.rl_model_resources.stop` Stop model resources destructive **RL training sessions 5** - `together_ai.rl_training_sessions.create` Create training session write - `together_ai.rl_training_sessions.get` Get training session read - `together_ai.rl_training_sessions.list` List training sessions read - `together_ai.rl_training_sessions.stop` Stop training session destructive - `together_ai.rl_training_sessions.update` Update a training session write **Batches 4** - `together_ai.batches.cancel` Cancel a batch job destructive - `together_ai.batches.create` Create a batch job write - `together_ai.batches.get` Get a batch job read - `together_ai.batches.list` List batch jobs read **Evaluation 3** - `together_ai.evaluation.create` Create an evaluation job write - `together_ai.evaluation.get` Get evaluation job details read - `together_ai.evaluation.list` Get all evaluation jobs read **Files 3** - `together_ai.files.delete` Delete a file destructive - `together_ai.files.get` Retrieve file metadata read - `together_ai.files.list` List all files read **Projects models uploads 3** - `together_ai.projects_models_uploads.create` Create a remote model upload write - `together_ai.projects_models_uploads.get` Get a remote model upload read - `together_ai.projects_models_uploads.list` List remote model uploads read **Queue jobs 3** - `together_ai.queue_jobs.cancel` Cancel a queued job destructive - `together_ai.queue_jobs.get` Get job status read - `together_ai.queue_jobs.submit` Submit a queued job write **Shaping 3** - `together_ai.shaping.cancel` Cancel shaping job destructive - `together_ai.shaping.get` Get shaping job read - `together_ai.shaping.list` List shaping jobs read **Deployments revisions 2** - `together_ai.deployments_revisions.get` Get the full configuration of a specific revision read - `together_ai.deployments_revisions.list` List revision history events of a deployment read **Projects configs 2** - `together_ai.projects_configs.get` Get a model configuration read - `together_ai.projects_configs.list` List model configurations read **Projects models revisions 2** - `together_ai.projects_models_revisions.get` Get a model volume revision read - `together_ai.projects_models_revisions.list` List model revisions read **Projects placement profiles 2** - `together_ai.projects_placement_profiles.get` Get a placement profile read - `together_ai.projects_placement_profiles.list` List placement profiles read **Public inference instance types 2** - `together_ai.public_inference_instance_types.get` Get an inference instance type read - `together_ai.public_inference_instance_types.list` List inference instance types read **RL checkpoints 2** - `together_ai.rl_checkpoints.get` Get checkpoint read - `together_ai.rl_checkpoints.list` List checkpoints read **Shaping FP4 jobs 2** - `together_ai.shaping_fp4_jobs.create` Prepare a fine-tuned model for FP4 inference write - `together_ai.shaping_fp4_jobs.estimate` Estimate FP4 preparation cost read **Supported models 2** - `together_ai.supported_models.get` Get a supported model read - `together_ai.supported_models.list` List supported models read **Videos 2** - `together_ai.videos.create` Create video write - `together_ai.videos.get` Fetch video metadata read **Billing usage 1** - `together_ai.billing_usage.list` Get billing usage read **Chat completions 1** - `together_ai.chat_completions.create` Create chat completion write **Completions 1** - `together_ai.completions.create` Create completion write **Compute passive health check alerts 1** - `together_ai.compute_passive_health_check_alerts.list` List passive health check alerts read **Compute regions 1** - `together_ai.compute_regions.list` List regions and corresponding supported driver versions read **Deployments logs 1** - `together_ai.deployments_logs.list` Get logs for a deployment read **Deployments storage files 1** - `together_ai.deployments_storage_files.get_url` Get a file download URL read **Embeddings 1** - `together_ai.embeddings.create` Create embedding write **Evaluation models 1** - `together_ai.evaluation_models.list` Get model list read **Evaluation status 1** - `together_ai.evaluation_status.get` Get evaluation job status and results read **Fine tunes checkpoints 1** - `together_ai.fine_tunes_checkpoints.list` List checkpoints read **Fine tunes download tokenized dataset 1** - `together_ai.fine_tunes_download_tokenized_dataset.get` Download tokenized dataset read **Fine tunes events 1** - `together_ai.fine_tunes_events.list` List job events read **Fine tunes metrics 1** - `together_ai.fine_tunes_metrics.list` Get metrics read **Fine tunes models limits 1** - `together_ai.fine_tunes_models_limits.get` Get model limits read **Fine tunes models supported 1** - `together_ai.fine_tunes_models_supported.get` List supported models read **Image generations 1** - `together_ai.image_generations.create` Create image write **Organizations endpoints 1** - `together_ai.organizations_endpoints.list` List organization endpoints read **Organizations models 1** - `together_ai.organizations_models.list` List organization models read **Projects 1** - `together_ai.projects.list` List available projects read **Projects endpoints analytics 1** - `together_ai.projects_endpoints_analytics.get` Get endpoint analytics read **Projects endpoints events 1** - `together_ai.projects_endpoints_events.list` List endpoint events read **Projects models files 1** - `together_ai.projects_models_files.list` List model files read **Projects models uploads events 1** - `together_ai.projects_models_uploads_events.list` List remote model upload events read **Public endpoints 1** - `together_ai.public_endpoints.list` List public endpoints read **Queue 1** - `together_ai.queue.clear` Clear a model's pending jobs destructive **Queue metrics 1** - `together_ai.queue_metrics.get` Get queue metrics read **Rerank 1** - `together_ai.rerank.create` Create a rerank request write **RL checkpoints download urls 1** - `together_ai.rl_checkpoints_download_urls.list` Download checkpoint read **RL supported models 1** - `together_ai.rl_supported_models.list` List supported models read **RL training sessions operations custom forward backward 1** - `together_ai.rl_training_sessions_operations_custom_forward_backward.get` Get custom forward-backward operation read **RL training sessions operations forward backward 1** - `together_ai.rl_training_sessions_operations_forward_backward.get` Get forward-backward operation read **RL training sessions operations inference checkpoint 1** - `together_ai.rl_training_sessions_operations_inference_checkpoint.get` Get inference checkpoint operation read **RL training sessions operations optim step 1** - `together_ai.rl_training_sessions_operations_optim_step.get` Get optim-step operation read **RL training sessions operations sample 1** - `together_ai.rl_training_sessions_operations_sample.get` Get sample operation read **RL training sessions operations training checkpoint 1** - `together_ai.rl_training_sessions_operations_training_checkpoint.get` Get save training checkpoint operation read **RL training sessions operations weights sync 1** - `together_ai.rl_training_sessions_operations_weights_sync.get` Get weights-sync operation read **Shaping events 1** - `together_ai.shaping_events.list` List shaping job events read **Voices 1** - `together_ai.voices.list` Fetch available voices for each model read **Whoami 1** - `together_ai.whoami.get` Identify the caller read Questions ## The Together AI MCP server, answered. **Is there a Together AI MCP server for Claude?** Yes. actionlake is an MCP gateway: a remote MCP server that gives Claude, or another MCP client, 183 Together AI actions across projects endpoints rollouts, fine tunes, RL training sessions operations and compute clusters instances remediations, through the same eight tools it uses for every other connector. actionlake is independent; it is not made or endorsed by Together AI. **What do I need to connect Together AI?** Together AI API key (api.together.ai > Settings > API Keys). The free call account { op: "connections.requirements", service: "together_ai" } lists exactly what to paste. **Can an AI agent delete or change things in Together AI?** Only if its key allows it, and only with an explicit confirmation. 25 Together AI actions are destructive, including delete a deployment, delete a file and delete a volume. Each runs only with confirm: true. Under the human confirm policy, or an approval rule on the key, the run waits until a named person approves it. **Will an AI agent use up my Together AI API limit?** actionlake paces every call to the limits in the Together AI service file: 60 calls a minute per connection. Repeated reads are answered from cache (87 Together AI actions can be), which never reaches Together AI. **What does a Together AI action cost?** One upstream call, the only unit actionlake bills. A list that pages bills one call per page (49 Together AI actions page). Cache hits, searches, dry runs and calls Together AI refused with 401, 403, 429 or a 5xx are free. The Free plan includes 100,000 calls a month with no card. Paid plans start at US$49 a month for 250,000 calls, with overage from US$0.30 down to US$0.18 per 1,000. **Which Together AI API does it cover?** The Together AI API 2.0.0 at api.together.ai. It is built from Together AI's documentation as read on 23 October 2026. 183 actions in 74 areas, each one in the signed service file (version 1.0.0). **Does actionlake keep my Together AI data, and where?** actionlake processes and stores data in Sydney, Australia; there is no US region yet. Reads may be cached for up to 5 minutes, and a write clears the reads it affects. Each run's request and response is kept, sealed, for your plan's trace window: 1 day on Free, 3 days on Starter, 7 days on Pro, 14 days on Team, 30 days on Business and 30 days on Enterprise. Your Together AI credential is sealed under your tenant's key, never logged and never returned. Your traffic is not used to train models. **Which AI clients can use it?** Claude Code, tested by us end to end, and the Claude app as a custom connector, tested by us with an existing key. Other MCP clients that support remote servers over Streamable HTTP (MCP revisions 2025-06-18 and 2025-11-25) and OAuth dynamic client registration, or a bearer header, should connect the same way; we have not tested them. Or plain REST, under the same action names. ## More connectors like Together AI Shares the most action names with - [Fireworks AI 14](https://actionlake.com/connectors/fireworks-ai) - [Google Gemini API (AI Studio) 12](https://actionlake.com/connectors/google-gemini-api-ai-studio) - [Groq 10](https://actionlake.com/connectors/groq) - [xAI Grok API 10](https://actionlake.com/connectors/xai-grok-api) - [Perplexity 8](https://actionlake.com/connectors/perplexity) - [Google Vertex AI 6](https://actionlake.com/connectors/google-vertex-ai) Joins with, on shared entities - [Slack 1](https://actionlake.com/connectors/slack) - [Canvas LMS 1](https://actionlake.com/connectors/canvas-lms) - [Unified.to 1](https://actionlake.com/connectors/unified-to) - [Appwrite Cloud 1](https://actionlake.com/connectors/appwrite-cloud) - [Teamwork 1](https://actionlake.com/connectors/teamwork) - [ERPNext (Frappe) 1](https://actionlake.com/connectors/erpnext-frappe) Browse - [All AI connectors](https://actionlake.com/connectors/category/ai) - [All connectors](https://actionlake.com/connectors) - [How actionlake compares](https://actionlake.com/compare) actionlake is independent. It is not made or endorsed by Together AI; the name is the vendor's own. Counts are from the Together AI service file, version 1.0.0. ## Give your agent Together AI today. [Connect Together AI free](https://actionlake.com/console?start=sandbox) [See pricing](https://actionlake.com/pricing) Start free - 100,000 calls/month, no card. No signup. Hard caps on every key. Cached answers are free. --- Source: https://actionlake.com/connectors/together-ai More: https://actionlake.com/llms.txt