Getting Started
Features
- Request Logs
- Datasets
- Fine Tuning
- Direct Preference Optimization (DPO)
- Evaluations
- Criteria
- Chat Completions
- Caching
- Updating Metadata Tags
- Pruning Rules
- Fallback
- Deployments
- External Models
API Reference
- Logs
- Chat Completions
- Datasets
- Models
- Criteria
Pricing
Create Model
Train a new model.
curl --request POST \
--url https://api.openpipe.ai/api/v1/models \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '{
"datasetId": "<string>",
"slug": "<string>",
"pruningRuleIds": [],
"trainingConfig": {
"provider": "openpipe",
"baseModel": "<string>",
"enable_sft": true,
"enable_preference_tuning": false,
"sft_hyperparameters": {},
"preference_hyperparameters": {},
"hyperparameters": {
"is_sft_enabled": true,
"batch_size": "auto",
"learning_rate_multiplier": 123,
"num_epochs": 123,
"is_preference_tuning_enabled": true,
"preference_tuning_variant": "DPO",
"preference_tuning_learning_rate_multiplier": 123,
"preference_tuning_num_epochs": 123,
"preference_tuning_training_beta": 123,
"preference_tuning_adapter_weight": 123
}
},
"defaultTemperature": 123
}'{
"id": "<string>",
"name": "<string>",
"object": "model",
"description": "<string>",
"created": "<string>",
"updated": "<string>",
"openpipe": {
"baseModel": "<string>",
"hyperparameters": {},
"status": "PENDING",
"datasetId": "<string>",
"errorMessage": "<string>"
},
"contextWindow": 123,
"maxCompletionTokens": 123,
"capabilities": [
"chat"
],
"pricing": {
"chatIn": 123,
"chatOut": 123
},
"owned_by": "<string>"
}Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Body
openpipe The base model to train from. This could be a base model name or the slug of a previously trained model. Supported base models include: meta-llama/Meta-Llama-3.1-8B-Instruct, meta-llama/Meta-Llama-3.1-70B-Instruct, meta-llama/Llama-3.3-70B-Instruct, meta-llama/Llama-3.1-8B, meta-llama/Llama-3.1-70B, Qwen/Qwen2.5-72B-Instruct, Qwen/Qwen2.5-Coder-7B-Instruct, Qwen/Qwen2.5-Coder-32B-Instruct, Qwen/Qwen2.5-1.5B-Instruct, Qwen/Qwen2.5-7B-Instruct, Qwen/Qwen2-VL-7B-Instruct, Qwen/Qwen2.5-14B-Instruct, mistralai/Mistral-Nemo-Base-2407, mistralai/Mistral-Small-24B-Base-2501, meta-llama/Llama-3.2-1B-Instruct, meta-llama/Llama-3.2-3B-Instruct, google/gemma-3-1b-it, google/gemma-3-4b-it, google/gemma-3-12b-it, google/gemma-3-27b-it
Whether to enable SFT training. If true, the model will be trained using SFT. Can be used in conjunction with DPO training.
Whether to enable DPO training. If true, the model will be trained using DPO. Can be used in conjunction with SFT training.
Hyperparameters for SFT training job. Ensure enable_sft is true. If no SFT hyperparameters are provided, default values will be used.
Hyperparameters for DPO training job. Ensure enable_preference_tuning is true. If no preference hyperparameters are provided, default values will be used.
DPO DEPRECATED: Use the sft_hyperparameters and preference_hyperparameters fields instead.
auto DPO Response
model PENDING, TRAINING, DEPLOYED, ERROR, DEPRECATED, PENDING_DEPRECATION, QUEUED, PROVISIONING chat, tools, json curl --request POST \
--url https://api.openpipe.ai/api/v1/models \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '{
"datasetId": "<string>",
"slug": "<string>",
"pruningRuleIds": [],
"trainingConfig": {
"provider": "openpipe",
"baseModel": "<string>",
"enable_sft": true,
"enable_preference_tuning": false,
"sft_hyperparameters": {},
"preference_hyperparameters": {},
"hyperparameters": {
"is_sft_enabled": true,
"batch_size": "auto",
"learning_rate_multiplier": 123,
"num_epochs": 123,
"is_preference_tuning_enabled": true,
"preference_tuning_variant": "DPO",
"preference_tuning_learning_rate_multiplier": 123,
"preference_tuning_num_epochs": 123,
"preference_tuning_training_beta": 123,
"preference_tuning_adapter_weight": 123
}
},
"defaultTemperature": 123
}'{
"id": "<string>",
"name": "<string>",
"object": "model",
"description": "<string>",
"created": "<string>",
"updated": "<string>",
"openpipe": {
"baseModel": "<string>",
"hyperparameters": {},
"status": "PENDING",
"datasetId": "<string>",
"errorMessage": "<string>"
},
"contextWindow": 123,
"maxCompletionTokens": 123,
"capabilities": [
"chat"
],
"pricing": {
"chatIn": 123,
"chatOut": 123
},
"owned_by": "<string>"
}