Together APIs
The Together REST API. See https://docs.together.ai for more details.
AI & machine learning#machine-learning
Fork copies the collection into your workspace, without the publisher's secrets, so you can add your own key and send requests. Star saves it to your starred APIs (Account › Marketplace) and helps others find it.
Overview
The Together REST API. See https://docs.together.ai for more details.
Endpoints 195
EndpointService
- GETList organization endpoints
/v2/organizations/:organizationId/endpointsLists endpoints shared with every project in the specified organization. Project-private and public endpoints are not included. - GETList endpoints
/v2/projects/:projectId/endpointsLists the dedicated inference endpoints owned by the specified project. - POSTCreate an endpoint
/v2/projects/:projectId/endpointsCreates a stable, inference-addressable endpoint. Add one or more deployments and configure its traffic split before sending inference requests to the… - GETGet an endpoint
/v2/projects/:projectId/endpoints/:idRetrieves an endpoint and lightweight summaries of the deployments attached to it. - DELETEDelete an endpoint
/v2/projects/:projectId/endpoints/:idPermanently deletes an endpoint. Delete its deployments first; use etag to reject the request if the endpoint changed after it was read. - PATCHUpdate an endpoint
/v2/projects/:projectId/endpoints/:idUpdates mutable endpoint fields such as its endpoint string, visibility, or deployment traffic split. Use updateMask to select fields explicitly and etag in… - GETGet endpoint analytics
/v2/projects/:projectId/endpoints/:id/analyticsReturns aggregated request, token, latency, throughput, error, and resource-utilization metrics for an endpoint over a time range. Optionally includes… - GETList endpoint events
/v2/projects/:projectId/endpoints/:id/eventsLists an endpoint's audit and lifecycle events newest first. The feed combines endpoint changes with provisioning, scaling, readiness, rollout, and other… - GETList public endpoints
/v2/public/endpointsLists endpoints that are publicly visible across Together projects.
VolumeService
- GETList organization models
/v2/organizations/:organizationId/modelsLists custom models shared with every project in the specified organization. Project-private and public models are not included. - GETGet organization model
/v2/organizations/:organizationId/models/:modelIdRetrieves a custom model shared with every project in the specified organization, regardless of which project owns it. Returns not found if the model belongs… - GETList project models
/v2/projects/:projectId/modelsLists custom model resources owned by the specified project. Use the organization endpoint to list models shared across projects or the supported-model… - POSTCreate a model
/v2/projects/:projectId/modelsRegisters a custom model resource in the project. Registration creates the model's metadata; upload or import model files separately before deploying it. - GETGet a model
/v2/projects/:projectId/models/:idRetrieves a custom model's metadata, visibility, weight information, and base-model relationship. - DELETEDelete a model
/v2/projects/:projectId/models/:idPermanently deletes a custom model resource. The model must not be in use by an active deployment. - PATCHUpdate a model
/v2/projects/:projectId/models/:idUpdates mutable model metadata such as its inference name, description, base model, or visibility. - GETList model files
/v2/projects/:projectId/models/:id/filesLists files in the latest or specified revision of a model, including paths, sizes, and content hashes. - GETList model revisions
/v2/projects/:projectId/models/:id/revisionsLists the immutable file revisions available for a custom model, newest first. - GETGet a model volume revision
/v2/projects/:projectId/models/:id/revisions/:revisionIdRetrieves metadata for one immutable revision of a custom model's files. - GETList remote model uploads
/v2/projects/:projectId/models/uploadsLists asynchronous jobs that import model files from Hugging Face or a presigned remote URL. - POSTCreate a remote model upload
/v2/projects/:projectId/models/uploadsStarts an asynchronous job that imports model files from Hugging Face or a presigned URL into a registered model and creates a model revision when the import… - GETGet a remote model upload
/v2/projects/:projectId/models/uploads/:idRetrieves the status, progress details, retry counts, and timestamps for a remote model import job. - GETList remote model upload events
/v2/projects/:projectId/models/uploads/:id/eventsLists progress and diagnostic events for a remote model import job.
ConfigService
- GETList model configurations
/v2/projects/:projectId/configsLists production-ready configuration revisions compatible with a reference model. Specify the model with referenceModel or the deprecated referenceModelId; if… - GETGet a model configuration
/v2/projects/:projectId/configs/:idRetrieves a model configuration revision by ID, including its runtime selectors and certifications.
DeploymentService
- GETList deployments
/v2/projects/:projectId/endpoints/:endpointId/deploymentsLists the deployments attached to an endpoint, including their model, configuration, scaling settings, placement, and current status. - POSTCreate a deployment
/v2/projects/:projectId/endpoints/:endpointId/deploymentsCreates a model deployment under an endpoint. The deployment provisions asynchronously; monitor its status before routing live traffic to it. - GETGet a deployment
/v2/projects/:projectId/endpoints/:endpointId/deployments/:idRetrieves a deployment's desired configuration, placement, runtime information, and current provisioning status. - DELETEDelete a deployment
/v2/projects/:projectId/endpoints/:endpointId/deployments/:idPermanently deletes a deployment from its endpoint. Remove the deployment from live traffic first; use etag to reject the request if it changed after it was… - PATCHUpdate a deployment
/v2/projects/:projectId/endpoints/:endpointId/deployments/:idUpdates mutable deployment fields such as its model, configuration, autoscaling bounds, or LoRA support. Changes that affect serving may trigger asynchronous… - GETList deployment adapters
/v2/projects/:projectId/endpoints/:endpointId/deployments/:deploymentId/adaptersLists LoRA adapters attached to a deployment with per-cluster load state. - POSTAdd a deployment adapter
/v2/projects/:projectId/endpoints/:endpointId/deployments/:deploymentId/adaptersAttaches a LoRA adapter to a deployment. If the deployment is at adapter capacity, force can evict the oldest adapter. - GETGet a deployment adapter
/v2/projects/:projectId/endpoints/:endpointId/deployments/:deploymentId/adapters/:idGets an adapter attachment by its dad_ id and returns its per-cluster load state. - DELETERemove a deployment adapter
/v2/projects/:projectId/endpoints/:endpointId/deployments/:deploymentId/adapters/:id?etag=stringDetaches an adapter attachment by its dad_ id using its row-level etag for optimistic concurrency. - PATCHUpdate a deployment adapter
/v2/projects/:projectId/endpoints/:endpointId/deployments/:deploymentId/adapters/:idUpdates the pinned revision of an adapter attachment by its dad_ id using its row-level etag for optimistic concurrency.
RolloutService
- GETList endpoint rollouts
/v2/projects/:projectId/endpoints/:endpointId/rolloutsLists rollout histories for an endpoint. Use filter=ROLLOUT_FILTER_ACTIVE to return only the active rollout, if one exists. - POSTCreate a rollout
/v2/projects/:projectId/endpoints/:endpointId/rolloutsCreates a rollout in the pending state without shifting traffic. Start the rollout in a separate request after reviewing its strategy and metric gates. - POSTPreview rollout defaults
/v2/projects/:projectId/endpoints/:endpointId/rollouts/preview-defaultsReturns the values a create request would pick for any field left unset, plus the capacity context needed to display them, without creating a rollout.… - GETGet a rollout
/v2/projects/:projectId/endpoints/:endpointId/rollouts/:idRetrieves a rollout's strategy, lifecycle state, current traffic percentage, step history, and metric-gate results. - DELETEDelete a rollout
/v2/projects/:projectId/endpoints/:endpointId/rollouts/:idDeletes a rollout record. An active rollout must be aborted or completed before it can be deleted. - POSTStart a rollout
/v2/projects/:projectId/endpoints/:endpointId/rollouts/:id/startStarts a pending rollout and begins its configured traffic-shifting workflow. - POSTPause a rollout
/v2/projects/:projectId/endpoints/:endpointId/rollouts/:id/pauseRequests a running or stabilizing rollout to pause and records an optional reason. The response returns the PAUSING snapshot; poll GetRollout until state is… - POSTResume a rollout
/v2/projects/:projectId/endpoints/:endpointId/rollouts/:id/resumeResumes a pausing, paused, or system-paused rollout from its current step and traffic split. - POSTCancel a rollout
/v2/projects/:projectId/endpoints/:endpointId/rollouts/:id/cancelCancels a running, pausing, paused, system-paused, or stabilizing rollout by freezing the current traffic split into standing weights. Revert is removed and… - POSTPromote a rollout
/v2/projects/:projectId/endpoints/:endpointId/rollouts/:id/promoteCompletes a running or paused rollout immediately by sending all live traffic to the target deployment.
ABExperimentService
- GETList A/B experiments
/v2/projects/:projectId/endpoints/:endpointId/abExperimentsLists the managed live-traffic experiments configured for an endpoint. - POSTCreate an A/B experiment
/v2/projects/:projectId/endpoints/:endpointId/abExperimentsCreates a managed control/variant split across two to 20 deployments under the same endpoint. Exactly one member is the control, member percentages must add… - GETGet an A/B experiment
/v2/projects/:projectId/endpoints/:endpointId/abExperiments/:idRetrieves an A/B experiment and its participating deployments, roles, and traffic percentages. - DELETEDelete an A/B experiment
/v2/projects/:projectId/endpoints/:endpointId/abExperiments/:idDeletes an A/B experiment and removes its managed traffic split. The deployments themselves are not deleted. - PATCHUpdate an A/B experiment
/v2/projects/:projectId/endpoints/:endpointId/abExperiments/:idUpdates an experiment's description or member traffic percentages. Use the experiment etag for optimistic concurrency.
ShadowExperimentService
- GETList shadow experiments
/v2/projects/:projectId/endpoints/:endpointId/shadowExperimentsLists experiments that mirror sampled endpoint traffic to target deployments without affecting client responses. Set includeTargets=true to include target… - POSTCreate a shadow experiment
/v2/projects/:projectId/endpoints/:endpointId/shadowExperimentsCreates an experiment that mirrors a sampled portion of endpoint traffic to one or more target deployments without returning their responses to clients. Add a… - GETGet a shadow experiment
/v2/projects/:projectId/endpoints/:endpointId/shadowExperiments/:idRetrieves a shadow experiment, including its sampling strategy and target deployments. - DELETEDelete a shadow experiment
/v2/projects/:projectId/endpoints/:endpointId/shadowExperiments/:idDeletes a shadow experiment and its target records. The underlying deployments are not deleted. - PATCHUpdate a shadow experiment
/v2/projects/:projectId/endpoints/:endpointId/shadowExperiments/:id?updateMask=stringUpdates a shadow experiment's description or source sampling strategy. updateMask is required; source changes also require the current etag in the request body. - GETList shadow experiment targets
/v2/projects/:projectId/endpoints/:endpointId/shadowExperiments/:experimentId/targetsLists the deployments that receive mirrored requests from a shadow experiment. - POSTCreate a shadow experiment target
/v2/projects/:projectId/endpoints/:endpointId/shadowExperiments/:experimentId/targetsAdds a deployment under the same endpoint as a target for mirrored requests. - GETGet a shadow experiment target
/v2/projects/:projectId/endpoints/:endpointId/shadowExperiments/:experimentId/targets/:idRetrieves one target configured to receive mirrored requests from a shadow experiment. - DELETEDelete a shadow experiment target
/v2/projects/:projectId/endpoints/:endpointId/shadowExperiments/:experimentId/targets/:idRemoves a target from a shadow experiment without deleting the underlying deployment. - PATCHUpdate a shadow experiment target
/v2/projects/:projectId/endpoints/:endpointId/shadowExperiments/:experimentId/targets/:id?updateMask=stringUpdates a shadow target's name, deployment, or description. updateMask is required and must select at least one mutable field.
PlacementProfileService
- GETList placement profiles
/v2/projects/:projectId/placement-profilesLists reusable, project-visible placement policies that control the regions where deployments may be scheduled. - GETGet a placement profile
/v2/projects/:projectId/placement-profiles/:idRetrieves a reusable placement profile and its ordered region preferences.
InstanceTypeService
- GETList inference instance types
/v2/public/inference-instance-typesLists hardware instance types currently available to inference deployments, including GPU resources, pricing, regions, and best-effort capacity headroom. - GETGet an inference instance type
/v2/public/inference-instance-types/:idRetrieves the GPU resources, pricing, regional availability, and best-effort capacity headroom for one inference instance type.
SupportedModelsService
- GETList supported models
/v2/supported-modelsLists Together-hosted base models that can be deployed for dedicated inference, together with their capabilities and certified deployment profiles. - GETGet a supported model
/v2/supported-models/:idRetrieves a Together-hosted base model and the certified model, configuration, hardware, and performance profiles available for deployment.
Deployments
- GETGet the list of deployments
/v1/deploymentsGet a list of all deployments in your project - POSTCreate a new deployment
/v1/deploymentsCreate a new deployment with specified configuration - GETGet a deployment by ID or name
/v1/deployments/:idRetrieve details of a specific deployment by its ID or name - DELETEDelete a deployment
/v1/deployments/:idDelete an existing deployment - PATCHUpdate a deployment
/v1/deployments/:idUpdate an existing deployment configuration - GETGet logs for a deployment
/v1/deployments/:id/logsRetrieve logs from a deployment, optionally filtered by replica ID. - GETList revision history events of a deployment
/v1/deployments/:id/revisionsReturns the revision history of the deployment, in descending order. Defaults to the most recent events. Only the 200 most recent events are retained per… - GETGet the full configuration of a specific revision
/v1/deployments/:id/revisions/:revisionIdentifierReturns the deployment configuration defined by the specified revision. Only the 50 most recent revisions per deployment retain their configuration; older… - POSTRoll back a deployment to a previous revision
/v1/deployments/:id/rollbackRe-applies the spec of a previous revision. Pods running the target revision will be retained. Other pods will be drained and restarted with the target…
Secrets
- GETGet the list of project secrets
/v1/deployments/secretsRetrieve all secrets in your project - POSTCreate a new secret
/v1/deployments/secretsCreate a new secret to store sensitive configuration values - GETGet a secret by ID or name
/v1/deployments/secrets/:idRetrieve details of a specific secret by its ID or name - DELETEDelete a secret
/v1/deployments/secrets/:idDelete an existing secret - PATCHUpdate a secret
/v1/deployments/secrets/:idUpdate an existing secret's value or metadata
DeploymentsStorage
- GETDownload a file
/v1/deployments/storage/:filenameDownload a file by redirecting to a signed URL - GETGet a file download URL
/v1/deployments/storage/:filename/urlCreate a signed URL for downloading a deployment storage file
DeploymentsVolumes
- GETGet the list of project volumes
/v1/deployments/storage/volumesRetrieve all volumes in your project - POSTCreate a new volume
/v1/deployments/storage/volumesCreate a new volume to preload files in deployments
Volumes
- GETGet a volume by ID or name
/v1/deployments/storage/volumes/:idRetrieve details of a specific volume by its ID or name - DELETEDelete a volume
/v1/deployments/storage/volumes/:idDelete an existing volume - PATCHUpdate a volume
/v1/deployments/storage/volumes/:idUpdate an existing volume's configuration or contents
Voices
- GETFetch available voices for each model
/v1/voicesFetch available voices for each model
Video
- GETFetch video metadata
/v2/videos/:idFetch video metadata - POSTCreate video
/v2/videosCreate a video
Chat
- POSTCreate chat completion
https://api-inference.together.ai/v1/chat/completionsGenerate a model response for a given chat conversation. Supports single queries and multi-turn conversations with system, user, and assistant messages.
Completion
- POSTCreate completion
/v1/completionsGenerate text completions for a given prompt using a language, code, or image model.
Embeddings
- POSTCreate embedding
/v1/embeddingsGenerate vector embeddings for one or more text inputs. Returns numerical arrays representing semantic meaning, useful for search, classification, and…
Images
- POSTCreate image
/v1/images/generationsUse an image model to generate an image for a given prompt.
Files
- GETList all files
/v1/filesList the metadata for all uploaded data files. - GETRetrieve file metadata
/v1/files/:idRetrieve the metadata for a single uploaded data file. - DELETEDelete a file
/v1/files/:idDelete a previously uploaded data file. - GETGet file contents
/v1/files/:id/contentGet the contents of a single uploaded data file. - POSTUpload a file
/v1/files/uploadUpload a file with specified purpose, file name, and file type.
Fine-tuning
- GETList all jobs
/v1/fine-tunesList the metadata for all fine-tuning jobs. Returns a list of FinetuneResponseTruncated objects. - POSTCreate job
/v1/fine-tunesCreate a fine-tuning job with the provided model and training data. - POSTEstimate price
/v1/fine-tunes/estimate-priceEstimate the price of a fine-tuning job. - POSTPreview tokenized data
/v1/fine-tunes/previewPreview how sampled rows from a fine-tuning training file will be tokenized before packing. - GETList job
/v1/fine-tunes/:idList the metadata for a single fine-tuning job. - DELETEDelete a fine-tune job
/v1/fine-tunes/:idDelete a fine-tuning job. - GETList job events
/v1/fine-tunes/:id/eventsList the events for a single fine-tuning job. - GETList checkpoints
/v1/fine-tunes/:id/checkpointsList the checkpoints for a single fine-tuning job. - GETDownload tokenized dataset
/v1/fine-tunes/:id/download-tokenized-datasetGet a presigned URL for the tokenized dataset archive generated for a fine-tune job. - GETDownload model
/v1/finetune/download?ft_id=stringReceive a compressed fine-tuned model or checkpoint. - POSTCancel job
/v1/fine-tunes/:id/cancelCancel a currently running fine-tuning job. Returns a FinetuneResponseTruncated object. - GETGet metrics
/v1/fine-tunes/:id/metricsRetrieves recorded training metrics for a fine-tuning job in chronological order. All query parameters are optional: omit them to retrieve all metrics. - GETList supported models
/v1/fine-tunes/models/supportedList models supported for fine-tuning. - GETGet model limits
/v1/fine-tunes/models/limits?model_name=stringGet model limits for a specific fine-tuning model.
Shaping
- GETList shaping jobs
/v1/shapingList shaping jobs owned by the caller's project. - POSTPrepare a fine-tuned model for FP4 inference
/v1/shaping/prepare-for-fp4-inferencePrepares a fine-tuned model for FP4 inference: an adapter is merged into its base model and the result quantized to FP4; a full model is quantized as it is.… - POSTEstimate FP4 preparation cost
/v1/shaping/prepare-for-fp4-inference/estimateReports the price and expected wall-clock time for preparing the model named by model_object_id or the deprecated adapter_object_id without creating a job.… - GETGet shaping job
/v1/shaping/:idRetrieve a shaping job owned by the caller's project. - POSTCancel shaping job
/v1/shaping/:id/cancelRequest cancellation of a shaping job owned by the caller's project. - GETList shaping job events
/v1/shaping/:id/eventsList events for a shaping job owned by the caller's project.
Rerank
- POSTCreate a rerank request
/v1/rerankRerank a list of documents by relevance to a query. Returns a relevance score and ordering index for each document.
Audio
- POSTCreate audio generation request
/v1/audio/speechGenerate audio from input text - GETReal-time text-to-speech via WebSocket
/v1/audio/speech/websocketEstablishes a WebSocket connection for real-time text-to-speech generation. This endpoint uses WebSocket protocol… - POSTCreate audio transcription request
/v1/audio/transcriptionsTranscribes audio into text - POSTCreate audio translation request
/v1/audio/translationsTranslates audio into English - GETReal-time audio transcription via WebSocket
/v1/realtime?model=string&input_audio_format=pcm_s16le_16000Establishes a WebSocket connection for real-time audio transcription. This endpoint uses WebSocket protocol (wss://api.together.ai/v1/realtime) for…
GPUClusterService
- GETList all GPU clusters
/v1/compute/clustersList all GPU clusters. - POSTCreate a GPU cluster
/v1/compute/clustersCreate an Instant Cluster on Together's high-performance GPU clusters. With features like on-demand scaling, long-lived resizable high-bandwidth shared… - GETGet GPU cluster by cluster ID
/v1/compute/clusters/:cluster_idRetrieve information about a specific GPU cluster. - PUTUpdate a GPU cluster
/v1/compute/clusters/:cluster_idUpdate the configuration of an existing GPU cluster. - DELETEDelete GPU cluster by cluster ID
/v1/compute/clusters/:cluster_idDelete a GPU cluster by cluster ID.
RegionService
- GETList regions and corresponding supported driver versions
/v1/compute/regions
SharedVolumeService
- GETList all shared volumes
/v1/compute/clusters/storage/volumesList all shared volumes. - PUTUpdate a shared volume
/v1/compute/clusters/storage/volumesUpdate the configuration of an existing shared volume. - POSTCreate a shared volume
/v1/compute/clusters/storage/volumesInstant Clusters supports long-lived, resizable in-DC shared storage with user data persistence. You can dynamically create and attach volumes to your cluster… - GETGet a shared volume by ID
/v1/compute/clusters/storage/volumes/:volume_idRetrieve information about a specific shared volume. - DELETEDelete a shared volume by ID
/v1/compute/clusters/storage/volumes/:volume_idDelete a shared volume. Note that if this volume is attached to a cluster, deleting will fail.
Batches
- GETList batch jobs
/v1/batchesList all batch jobs for the authenticated user - POSTCreate a batch job
/v1/batchesCreate a new batch job with the given input file and endpoint - GETGet a batch job
/v1/batches/:idGet details of a batch job by ID - POSTCancel a batch job
/v1/batches/:id/cancelCancel a batch job by ID
evaluation
- GETGet all evaluation jobs
/v1/evaluation - POSTCreate an evaluation job
/v1/evaluation - GETGet model list
/v1/evaluation/model-list - GETGet evaluation job details
/v1/evaluation/:id - GETGet evaluation job status and results
/v1/evaluation/:id/status
Queue
- POSTCancel a queued job
/v1/queue/cancelCancel a pending job. Only jobs in pending status can be canceled. Running jobs cannot be stopped. Returns the job status after the attempt. If the job is not… - POSTClear a model's pending jobs
/v1/queue/clearCancel all pending jobs for the given model. Running jobs are left untouched. Returns the number of jobs that were canceled. - GETGet queue metrics
/v1/queue/metrics?model=stringGet the current queue statistics for a model, including pending and running job counts. - GETGet job status
/v1/queue/status?request_id=string&model=stringPoll the current status of a previously submitted job. Provide the request_id and model as query parameters. - POSTSubmit a queued job
/v1/queue/submitSubmit a new job to the queue for asynchronous processing. Jobs are processed in strict priority order (higher priority first, FIFO within the same priority).…
RL
- GETList model resources
/v1/rl/model-resourcesLists the caller's model resources. - POSTCreate model resources
/v1/rl/model-resourcesProvisions a standalone model resource that training sessions can attach to. - POSTEstimate on-demand model resource cost
/v1/rl/model-resources/estimate-costEstimates a model resource's on-demand hourly price without creating it. - GETGet model resources
/v1/rl/model-resources/:model_resources_idGets a model resource by its ID and returns its details. - POSTStop model resources
/v1/rl/model-resources/:model_resources_id/stopStops the model resource and releases its allocated compute. If active training sessions are attached, the request fails unless force=true. A forced stop also… - POSTExtend model resources expiry
/v1/rl/model-resources/:model_resources_id/extend-expiryKeeps a ready model resource from stopping for inactivity for at least the given number of seconds from now. It moves the resource's expires_at to at least… - POSTEstimate rollout time and price
/v1/rl/rollouts/estimateEstimates rollout-only time, generator GPU-hours, billed GPU-hours of the whole model resource, and price for a supported model and GPU type. Each generator… - GETList training sessions
/v1/rl/training-sessionsLists all training sessions. - POSTCreate training session
/v1/rl/training-sessionsCreates a training session and returns its details. - GETList supported models
/v1/rl/supported-modelsReturns the models supported by the RL service and their limits for training/sampling operations. - GETGet training session
/v1/rl/training-sessions/:session_idGets a training session by its ID and returns its details. - PATCHUpdate a training session
/v1/rl/training-sessions/:session_idUpdates the display name or metadata associated with a training session. Omitted fields remain unchanged, and empty strings clear existing values. - POSTStop training session
/v1/rl/training-sessions/:session_id/stopStops a training session. - GETGet forward-backward operation
/v1/rl/training-sessions/:session_id/operations/forward-backward/:operation_idRetrieves the current status and result of a forward-backward operation. - GETGet optim-step operation
/v1/rl/training-sessions/:session_id/operations/optim-step/:operation_idRetrieves the current status and result of an optim-step operation. - GETGet weights-sync operation
/v1/rl/training-sessions/:session_id/operations/weights-sync/:operation_idRetrieves the current status and result of a weights-sync operation. - GETGet sample operation
/v1/rl/training-sessions/:session_id/operations/sample/:operation_idRetrieves the current status and result of a sample operation. - POSTForward-backward pass
/v1/rl/training-sessions/:session_id/operations/forward-backwardSubmits a forward-backward pass operation that will asynchronously compute gradients via backpropagation. - POSTCustom forward-backward pass
/v1/rl/training-sessions/:session_id/operations/custom-forward-backwardSubmits a forward-backward pass driven by externally computed gradients of the loss with respect to per-token log-probabilities. - GETGet custom forward-backward operation
/v1/rl/training-sessions/:session_id/operations/custom-forward-backward/:operation_idRetrieves the current status and result of a custom forward-backward operation. - POSTOptimizer step
/v1/rl/training-sessions/:session_id/operations/optim-stepSubmits an optimizer step operation that will asynchronously apply accumulated gradients to update model parameters. Does not make the updated parameters… - POSTWeights sync
/v1/rl/training-sessions/:session_id/operations/weights-syncSubmits a weights-sync operation that makes the session's current trained parameters available for sampling. Call this after optim-step when you want… - POSTSample
/v1/rl/training-sessions/:session_id/operations/sampleSubmits a sample operation that will asynchronously generate text completions with logprobs. - POSTCreate inference checkpoint
/v1/rl/training-sessions/:session_id/operations/inference-checkpointSubmits an operation that will asynchronously save the current LoRA adapter as an inference checkpoint and upload it to object storage. - GETGet inference checkpoint operation
/v1/rl/training-sessions/:session_id/operations/inference-checkpoint/:operation_idRetrieves the current status and result of an inference checkpoint operation. - POSTSave training checkpoint
/v1/rl/training-sessions/:session_id/operations/training-checkpointSubmits an operation that will asynchronously save the full training state (adapter + optimizer + step). - GETGet save training checkpoint operation
/v1/rl/training-sessions/:session_id/operations/training-checkpoint/:operation_idRetrieves the current status and result of a save training checkpoint operation. - GETList checkpoints
/v1/rl/checkpointsLists training and inference checkpoints owned by the caller, newest first. Filter by type, session, or base model, for example to recover a checkpoint ID for… - GETGet checkpoint
/v1/rl/checkpoints/:idReturns metadata for a checkpoint: type, base model, LoRA rank, step, and owning session. - GETDownload checkpoint
/v1/rl/checkpoints/:id/download?variant=CHECKPOINT_VARIANT_UNSPECIFIEDReturns presigned URLs for downloading a checkpoint's model files. Only inference checkpoints support downloading.
InstanceClusterAddOnService
- GETInstanceClusterAddOnService_List
/v1/compute/clusters/:cluster_id/addons - POSTInstanceClusterAddOnService_Create
/v1/compute/clusters/:cluster_id/addons - GETInstanceClusterAddOnService_Get
/v1/compute/clusters/:cluster_id/addons/:addon_id - PUTInstanceClusterAddOnService_Update
/v1/compute/clusters/:cluster_id/addons/:addon_id - DELETEInstanceClusterAddOnService_Delete
/v1/compute/clusters/:cluster_id/addons/:addon_id
RemediationService
- GETList remediations
/v1/compute/clusters/:cluster_id/instances/:instance_id/remediationsLists remediations for an instance or cluster. - POSTRemediationService_CreateRemediation
/v1/compute/clusters/:cluster_id/instances/:instance_id/remediationsCreates a new remediation for an instance. Remediations created via the API goes directly to PENDING state. Our system may trigger automated remediations that… - GETRemediationService_GetRemediation
/v1/compute/clusters/:cluster_id/instances/:instance_id/remediations/:remediation_idRetrieve the status of a specific remdiation on a specific instance in a specific cluster. - POSTRemediationService_ApproveRemediation
/v1/compute/clusters/:cluster_id/instances/:instance_id/remediations/:remediation_id/approveApproves a pending remediation. Only remediations with state PENDING_APPROVAL can be approved. On APPROVE: state changes to PENDING and the remediation… - POSTRemediationService_CancelRemediation
/v1/compute/clusters/:cluster_id/instances/:instance_id/remediations/:remediation_id/cancelCancels a pending remediation. Only remediations in PENDING_APPROVAL or PENDING state can be cancelled. - POSTRemediationService_RejectRemediation
/v1/compute/clusters/:cluster_id/instances/:instance_id/remediations/:remediation_id/rejectRejects a pending remediation. Only remediations with state PENDING_APPROVAL can be rejected. On REJECT: state changes to CANCELLED. The reviewed_by,…
HealthCheckService
- GETList passive health check alerts
/v1/compute/passive_health_check_alertsLists passive health check alerts. Filters combine across axes; empty values skip that axis.
Projects
- GETList available projects
/v1/projectsRetrieve a list of accessible projects.
Account
- GETIdentify the caller
/v3/whoamiReturns identity information for the authenticated caller. Accepts project API keys and user session JWTs. The response type indicates which fields are…
Billing
- GETGet billing usage
/v1/billing/usageReturns an organization's billing usage for a month as cost-annotated line items grouped into time windows. Finalized windows are returned through the end of…
API details
- Base URL
https://api.together.ai- Authentication
- A bearer token in the Authorization header
- Operations
- 195 operations on 144 pathsGET 102POST 63DELETE 16PATCH 11PUT 3
- Main resources
- RL 30Fine-tuning 14VolumeService 14DeploymentService 10RolloutService 10ShadowExperimentService 10Deployments 9EndpointService 9RemediationService 6Shaping 6
- Response formats
application/jsonapplication/octet-streamtext/event-streamaudio/mpeg- Description format
- OpenAPI 3.1.0, API version
2.0.0 - Links
- OpenAPI document · Terms of service · Support
- Listed from
- Together's published OpenAPI description
How to test the Together APIs in Swastik Codes
- Open the APISelect “Fork & run in Swastik Codes” on this page. Sign in or create a free account if asked.
- Fork it into your workspaceChoose a workspace. You get your own copy of the Together APIs collection, without the publisher's secrets.
- Add your credentialsThis API uses A bearer token in the Authorization header. Add yours in the collection's variables or an environment; the requests already reference it.
- Send a requestPick an endpoint, for example “List organization endpoints” (GET /v2/organizations/:organizationId/endpoints), and press Send. Check the response, add tests and run the whole collection with the runner.
Frequently asked questions
What is the Together APIs?
The Together REST API. See https://docs.together.ai for more details. It is listed under AI & machine learning and has 195 endpoints.
Who publishes the Together APIs?
It is listed from Together's public API description (an OpenAPI document), not published by Together on Swastik Codes. Anyone who controls together.ai can claim the profile by adding a DNS TXT record.
What is the base URL of the Together APIs?
Requests go to https://api.together.ai. Endpoint paths are added to this base URL.
How do I authenticate with the Together APIs?
With A bearer token in the Authorization header.
How many endpoints does the Together APIs have?
195 operations on 144 paths (102 GET, 63 POST, 16 DELETE, 11 PATCH, 3 PUT). The largest groups are RL, Fine-tuning, VolumeService, DeploymentService.
Is forking the Together APIs free?
Yes. Forking copies the collection into your workspace for free. It has been starred 0 times and forked 0 times.