Python SDK for LoRA fine-tuning with supervised fine-tuning and reinforcement learning
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Not given
Not given
Pricing
Free: $0 with 60 requests/minute and 1,000 requests/day for first 7 days, then standard limits. Team: $70 per organization per month for up to 10 members with 600 requests/min. Enterprise: Custom annual pricing. Personal plan for IQ Code: $6 per month with 2,000 routing decisions.
Not given
Key features
Multi-provider support (OpenAI, Anthropic, Google, Mistral, xAI, DeepSeek)
Built-in model routing for cost optimization
Per-person usage tracking without prompt visibility
Zero Data Retention (ZDR) option
forward_backward() operation for computing loss and accumulating gradients
optim_step() for updating the adapter
sample() for generating from current or saved policy
save_state() to save and resume training state
Tinker API compatibility
Separate trainer and sampler resources
Synchronous and asynchronous RL patterns
Frozen base model weights with LoRA adapter updates
Support for open models from Qwen, Google, DeepSeek, Moonshot AI, NVIDIA, and Z.ai
What makes it different
Privacy-first monitoring: usage analytics without storing prompt or completion text by default
Support for any OpenAI- or Anthropic-shaped endpoint through single gateway URL
Managed training and sampling infrastructure, no setup required
Tinker-compatible API for easy migration
Ready-made SFT and RL recipes through Loops cookbook
IQ Routing
Loops