projectstring uuid required
inference_contract'chat' | 'decision' required
- chat - Chat
- decision - Decision
status'queued' | 'quantizing' | 'deploying' | 'warming' | 'ready' | 'failed' | 'deleting' | 'deleted' required
- queued - Queued
- quantizing - Quantizing
- deploying - Deploying
- warming - Warming
- ready - Ready
- failed - Failed
- deleting - Deleting
- deleted - Deleted
quantization'fp8' | 'bf16' required
base_model_idstring required
Base model ID used for the fine-tuning job.
gpu_typestring required
Modal GPU type: 'L4' or 'L40S'.
lora_rankinteger required
LoRA rank; 0 for full models.
weights_pathstring required
Path inside the Modal overmind-weights Volume.
checkpoint_hashstring required
Content hash of the quantized weights directory.
max_model_leninteger required
Maximum context length passed to vLLM --max-model-len.
num_parametersinteger required
sla_tierstring required
'hot' keeps a warm container alive; 'standard' scales to zero.
inference_urlstring required
Modal web endpoint URL for the model's vLLM container pool.
error_messagestring required
created_atstring date-time required
deployed_atstring date-time nullable required
finetuning_job_idstring uuid required
finetuning_job_namestring nullable required
capability_idstring nullable required
capability_namestring nullable required
request_countinteger required
last_active_atstring date-time nullable required
total_tokensinteger nullable required
avg_tokens_per_secondnumber double nullable required
avg_latency_msnumber double nullable required
cost_totalnumber double nullable required
cost_this_monthnumber double nullable required