Server definition
- Hash
- sha256:4f4549810ec9ca23b8300435ad702dfaec4a9a4e6c3c486af015757cd0c51171
- What it is
- What a remote MCP server returned when asked what it offers: 23 tools
The blob, as servednamed by its sha256
{
"instructions": null,
"tools": [
{
"description": "Cancel a batch job that has not finished. Together: POST /batches/{id}/cancel.",
"inputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"batch_id": {
"description": "The batch job id.",
"minLength": 1,
"type": "string"
}
},
"required": [
"batch_id"
],
"type": "object"
},
"name": "together_cancel_batch",
"outputSchema": null
},
{
"description": "Cancel a running fine-tuning job. Cannot be resumed, but a new job can continue from its last checkpoint via from_checkpoint. Together: POST /fine-tunes/{id}/cancel.",
"inputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"fine_tune_id": {
"description": "The job id, e.g. ft-abc123.",
"minLength": 1,
"type": "string"
}
},
"required": [
"fine_tune_id"
],
"type": "object"
},
"name": "together_cancel_fine_tune",
"outputSchema": null
},
{
"description": "Run a chat completion on a Together model (billed per token). Non-streaming. For a dedicated endpoint pass its `<project_slug>/<endpoint_slug>` as the model. Together: POST /chat/completions.",
"inputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"max_tokens": {
"description": "Maximum tokens to generate.",
"maximum": 9007199254740991,
"minimum": 1,
"type": "integer"
},
"messages": {
"description": "The conversation so far.",
"items": {
"properties": {
"content": {
"type": "string"
},
"role": {
"enum": [
"system",
"user",
"assistant",
"tool"
],
"type": "string"
}
},
"required": [
"role",
"content"
],
"type": "object"
},
"minItems": 1,
"type": "array"
},
"model": {
"description": "Model name, e.g. meta-llama/Llama-3.3-70B-Instruct-Turbo.",
"minLength": 1,
"type": "string"
},
"reasoning_effort": {
"description": "Reasoning effort for reasoning models that support it.",
"enum": [
"low",
"medium",
"high"
],
"type": "string"
},
"repetition_penalty": {
"type": "number"
},
"seed": {
"description": "Seed for reproducible sampling.",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"type": "integer"
},
"stop": {
"description": "Stop sequences.",
"items": {
"type": "string"
},
"type": "array"
},
"temperature": {
"maximum": 2,
"minimum": 0,
"type": "number"
},
"top_k": {
"maximum": 9007199254740991,
"minimum": 0,
"type": "integer"
},
"top_p": {
"maximum": 1,
"minimum": 0,
"type": "number"
}
},
"required": [
"model",
"messages"
],
"type": "object"
},
"name": "together_chat_completion",
"outputSchema": null
},
{
"description": "Start an asynchronous batch job over an uploaded JSONL input file (purpose batch-api), at a discount to real-time inference. Together: POST /batches.",
"inputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"completion_window": {
"description": "Time window for completion, e.g. 24h.",
"type": "string"
},
"endpoint": {
"description": "The API each line of the input file is sent to.",
"enum": [
"/v1/chat/completions",
"/v1/audio/transcriptions",
"/v1/audio/translations"
],
"type": "string"
},
"input_file_id": {
"description": "File id of the uploaded JSONL request file.",
"minLength": 1,
"type": "string"
},
"model_id": {
"description": "Model to process the requests with.",
"type": "string"
},
"priority": {
"description": "Processing priority.",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"type": "integer"
}
},
"required": [
"input_file_id",
"endpoint"
],
"type": "object"
},
"name": "together_create_batch",
"outputSchema": null
},
{
"description": "Generate vector embeddings for one or more texts (billed per token). Together: POST /embeddings.",
"inputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"input": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"type": "string"
},
"minItems": 1,
"type": "array"
}
],
"description": "A text, or a list of texts, to embed."
},
"model": {
"description": "Embedding model, e.g. BAAI/bge-large-en-v1.5.",
"minLength": 1,
"type": "string"
}
},
"required": [
"model",
"input"
],
"type": "object"
},
"name": "together_create_embeddings",
"outputSchema": null
},
{
"description": "Deploy a model on dedicated GPUs. The endpoint STARTS AUTOMATICALLY and bills per minute of uptime until stopped — set inactive_timeout to auto-stop it, and use together_list_hardware for valid hardware ids. Together: POST /endpoints.",
"inputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"autoscaling": {
"description": "Replica bounds for autoscaling.",
"properties": {
"max_replicas": {
"description": "Maximum replicas to scale up to under load.",
"maximum": 9007199254740991,
"minimum": 1,
"type": "integer"
},
"min_replicas": {
"description": "Replicas kept running even with no load.",
"maximum": 9007199254740991,
"minimum": 0,
"type": "integer"
}
},
"required": [
"min_replicas",
"max_replicas"
],
"type": "object"
},
"availability_zone": {
"description": "Availability zone, e.g. us-central-4b.",
"type": "string"
},
"disable_speculative_decoding": {
"type": "boolean"
},
"display_name": {
"description": "Human-readable name.",
"type": "string"
},
"hardware": {
"description": "Hardware id, e.g. 1x_nvidia_a100_80gb_sxm.",
"minLength": 1,
"type": "string"
},
"inactive_timeout": {
"description": "Minutes of inactivity before auto-stop; 0 disables it.",
"maximum": 9007199254740991,
"minimum": 0,
"type": "integer"
},
"model": {
"description": "The model to deploy.",
"minLength": 1,
"type": "string"
},
"state": {
"description": "Initial state. Pass STOPPED to create without starting (and without billing).",
"enum": [
"STARTED",
"STOPPED"
],
"type": "string"
}
},
"required": [
"model",
"hardware",
"autoscaling"
],
"type": "object"
},
"name": "together_create_endpoint",
"outputSchema": null
},
{
"description": "Start a fine-tuning job on an uploaded training file (billed per token processed). Stop it with together_cancel_fine_tune. Together: POST /fine-tunes.",
"inputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"batch_size": {
"anyOf": [
{
"maximum": 9007199254740991,
"minimum": 1,
"type": "integer"
},
{
"const": "max",
"type": "string"
}
],
"description": "Batch size, or 'max' (the default)."
},
"from_checkpoint": {
"description": "Continue from a previous job: <job_id>, <output_model_name>, optionally with :<step>.",
"type": "string"
},
"learning_rate": {
"exclusiveMinimum": 0,
"type": "number"
},
"max_seq_length": {
"maximum": 9007199254740991,
"minimum": 1,
"type": "integer"
},
"model": {
"description": "Base model to fine-tune.",
"minLength": 1,
"type": "string"
},
"n_checkpoints": {
"description": "Intermediate checkpoints to save.",
"maximum": 9007199254740991,
"minimum": 1,
"type": "integer"
},
"n_epochs": {
"description": "Passes over the training data.",
"maximum": 9007199254740991,
"minimum": 1,
"type": "integer"
},
"n_evals": {
"description": "Evaluations on the validation set during training.",
"maximum": 9007199254740991,
"minimum": 0,
"type": "integer"
},
"suffix": {
"description": "Suffix for the fine-tuned model's name (max 64 chars).",
"maxLength": 64,
"type": "string"
},
"training_file": {
"description": "File id of an uploaded training file (purpose fine-tune).",
"minLength": 1,
"type": "string"
},
"training_method": {
"description": "Supervised fine-tuning (sft, the default) or preference tuning (dpo).",
"oneOf": [
{
"properties": {
"method": {
"const": "sft",
"type": "string"
},
"train_on_inputs": {
"anyOf": [
{
"type": "boolean"
},
{
"const": "auto",
"type": "string"
}
],
"description": "Whether prompt/user tokens contribute to the loss; 'auto' lets Together decide."
}
},
"required": [
"method",
"train_on_inputs"
],
"type": "object"
},
{
"properties": {
"dpo_beta": {
"type": "number"
},
"dpo_normalize_logratios_by_length": {
"type": "boolean"
},
"dpo_reference_free": {
"type": "boolean"
},
"method": {
"const": "dpo",
"type": "string"
},
"rpo_alpha": {
"type": "number"
},
"simpo_gamma": {
"type": "number"
}
},
"required": [
"method"
],
"type": "object"
}
]
},
"training_type": {
"description": "Full fine-tune or LoRA. Together defaults to LoRA when omitted.",
"oneOf": [
{
"properties": {
"type": {
"const": "Full",
"type": "string"
}
},
"required": [
"type"
],
"type": "object"
},
{
"properties": {
"lora_alpha": {
"description": "Scaling factor applied to the LoRA adapter weights.",
"type": "number"
},
"lora_dropout": {
"description": "Dropout on LoRA adapter inputs.",
"maximum": 1,
"minimum": 0,
"type": "number"
},
"lora_r": {
"description": "Rank of the LoRA adapter matrices.",
"maximum": 9007199254740991,
"minimum": 1,
"type": "integer"
},
"lora_trainable_modules": {
"description": "Comma-separated target modules, or all-linear for the model defaults.",
"type": "string"
},
"type": {
"const": "Lora",
"type": "string"
}
},
"required": [
"type",
"lora_r",
"lora_alpha"
],
"type": "object"
}
]
},
"validation_file": {
"description": "File id of an uploaded validation file.",
"type": "string"
},
"warmup_ratio": {
"maximum": 1,
"minimum": 0,
"type": "number"
}
},
"required": [
"model",
"training_file"
],
"type": "object"
},
"name": "together_create_fine_tune",
"outputSchema": null
},
{
"description": "Generate images from a prompt (billed per image/megapixel). Returns image URLs by default rather than base64, to keep responses small. Together: POST /images/generations.",
"inputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"guidance_scale": {
"description": "Prompt adherence; higher is more literal.",
"type": "number"
},
"height": {
"description": "Height in pixels.",
"maximum": 9007199254740991,
"minimum": 64,
"type": "integer"
},
"image_url": {
"description": "Input image URL, for models that support editing.",
"type": "string"
},
"model": {
"description": "Image model, e.g. black-forest-labs/FLUX.1-schnell.",
"minLength": 1,
"type": "string"
},
"n": {
"description": "Number of images.",
"maximum": 4,
"minimum": 1,
"type": "integer"
},
"negative_prompt": {
"description": "What to steer away from.",
"type": "string"
},
"output_format": {
"enum": [
"jpeg",
"png"
],
"type": "string"
},
"prompt": {
"description": "What to draw.",
"minLength": 1,
"type": "string"
},
"response_format": {
"description": "url (default here) or base64. base64 can be very large.",
"enum": [
"url",
"base64"
],
"type": "string"
},
"seed": {
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"type": "integer"
},
"steps": {
"description": "Number of generation steps.",
"maximum": 9007199254740991,
"minimum": 1,
"type": "integer"
},
"width": {
"description": "Width in pixels.",
"maximum": 9007199254740991,
"minimum": 64,
"type": "integer"
}
},
"required": [
"model",
"prompt"
],
"type": "object"
},
"name": "together_generate_image",
"outputSchema": null
},
{
"description": "Fetch one batch job: status (VALIDATING, IN_PROGRESS, COMPLETED, FAILED, EXPIRED, CANCELLED), progress, and the output_file_id / error_file_id once done. Together: GET /batches/{id}.",
"inputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"batch_id": {
"description": "The batch job id.",
"minLength": 1,
"type": "string"
}
},
"required": [
"batch_id"
],
"type": "object"
},
"name": "together_get_batch",
"outputSchema": null
},
{
"description": "Fetch one dedicated endpoint: state, model, hardware, autoscaling bounds and display name. Together: GET /endpoints/{endpointId}.",
"inputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"endpoint_id": {
"description": "The endpoint id, e.g. endpoint-d23901de-....",
"minLength": 1,
"type": "string"
}
},
"required": [
"endpoint_id"
],
"type": "object"
},
"name": "together_get_endpoint",
"outputSchema": null
},
{
"description": "Fetch one file's metadata, including its processing_status and validation_report (why a fine-tune training file was rejected). Together: GET /files/{id}.",
"inputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"file_id": {
"description": "The file id, e.g. file-abc123.",
"minLength": 1,
"type": "string"
}
},
"required": [
"file_id"
],
"type": "object"
},
"name": "together_get_file",
"outputSchema": null
},
{
"description": "Fetch one fine-tuning job: status, progress, hyperparameters, token counts, cost and the output model name. Together: GET /fine-tunes/{id}.",
"inputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"fine_tune_id": {
"description": "The job id, e.g. ft-abc123.",
"minLength": 1,
"type": "string"
}
},
"required": [
"fine_tune_id"
],
"type": "object"
},
"name": "together_get_fine_tune",
"outputSchema": null
},
{
"description": "List batch inference jobs with status, progress, model and input/output/error file ids. Together: GET /batches.",
"inputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {},
"type": "object"
},
"name": "together_list_batches",
"outputSchema": null
},
{
"description": "List endpoints with model, owner and state (PENDING, STARTING, STARTED, STOPPING, STOPPED, ERROR). Use mine=true and type=dedicated to see what is running on your account and billing by the minute. Together: GET /endpoints.",
"inputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"mine": {
"description": "Only endpoints owned by the caller.",
"type": "boolean"
},
"type": {
"description": "Filter by endpoint type.",
"enum": [
"dedicated",
"serverless"
],
"type": "string"
},
"usage_type": {
"description": "Filter by usage type.",
"enum": [
"on-demand",
"reserved"
],
"type": "string"
}
},
"type": "object"
},
"name": "together_list_endpoints",
"outputSchema": null
},
{
"description": "List LLM-as-a-judge evaluation jobs (classify, score, compare) with status, parameters and results once completed. Together: GET /evaluation.",
"inputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"limit": {
"description": "Maximum number of jobs to return.",
"maximum": 1000,
"minimum": 1,
"type": "integer"
},
"status": {
"description": "Filter by status: pending, queued, running, completed, error, user_error.",
"type": "string"
}
},
"type": "object"
},
"name": "together_list_evaluations",
"outputSchema": null
},
{
"description": "List uploaded data files (fine-tune, eval and batch-api inputs, plus job outputs) with size, type, purpose and validation status. Together: GET /files.",
"inputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {},
"type": "object"
},
"name": "together_list_files",
"outputSchema": null
},
{
"description": "List the event log of one fine-tuning job (queued, started, checkpoint saved, epoch completed, errors). The first place to look when a job failed. Together: GET /fine-tunes/{id}/events.",
"inputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"fine_tune_id": {
"description": "The job id, e.g. ft-abc123.",
"minLength": 1,
"type": "string"
}
},
"required": [
"fine_tune_id"
],
"type": "object"
},
"name": "together_list_fine_tune_events",
"outputSchema": null
},
{
"description": "List fine-tuning jobs with status, base model, output model name and training settings. Together: GET /fine-tunes.",
"inputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {},
"type": "object"
},
"name": "together_list_fine_tunes",
"outputSchema": null
},
{
"description": "List hardware configurations for dedicated endpoints with GPU type/count/memory and price in cents per minute. Pass a model to get only compatible configurations with live availability. Together: GET /hardware.",
"inputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"model": {
"description": "Only hardware compatible with this model, with availability.",
"type": "string"
}
},
"type": "object"
},
"name": "together_list_hardware",
"outputSchema": null
},
{
"description": "List Together's models with type (chat, language, code, image, embedding, moderation, rerank), context length, organization, license and per-token pricing. Together: GET /models.",
"inputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"dedicated": {
"description": "Only return models that can run on dedicated endpoints.",
"type": "boolean"
}
},
"type": "object"
},
"name": "together_list_models",
"outputSchema": null
},
{
"description": "Start a stopped dedicated endpoint. It bills per minute of uptime until stopped. Reversible with together_stop_endpoint. Together: PATCH /endpoints/{endpointId} with state=STARTED.",
"inputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"endpoint_id": {
"description": "The endpoint id.",
"minLength": 1,
"type": "string"
}
},
"required": [
"endpoint_id"
],
"type": "object"
},
"name": "together_start_endpoint",
"outputSchema": null
},
{
"description": "Stop a running dedicated endpoint, which stops its per-minute billing. Requests to it fail until it is started again. Together: PATCH /endpoints/{endpointId} with state=STOPPED.",
"inputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"endpoint_id": {
"description": "The endpoint id.",
"minLength": 1,
"type": "string"
}
},
"required": [
"endpoint_id"
],
"type": "object"
},
"name": "together_stop_endpoint",
"outputSchema": null
},
{
"description": "Identify the API key: its organization, project and project slug. The project slug forms the `<project_slug>/<endpoint_slug>` model name for dedicated-endpoint inference. A cheap way to confirm the key works. Together: GET /whoami.",
"inputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {},
"type": "object"
},
"name": "together_whoami",
"outputSchema": null
}
]
}Verify it yourself
curl -s https://api.teppi.xyz/v1/evidence/sha256:4f4549810ec9ca23b8300435ad702dfaec4a9a4e6c3c486af015757cd0c51171 | sha256sum