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
NG
Not given
Pricing model
Freemium
Not given
Pricing
Developer plan with free usage tier and pay-as-you-go pricing; Growth plan with higher rate limits and access to all 6 models; Enterprise plan with custom contracts. New accounts receive $50 in starter credits. Pricing available in NGN, KES, GHS, ZAR, UGX, TZS, and EGP with no conversion fees.
Not given
Key features
Wakanda agentic developer workspace with code generation and command execution
REST API with chat completions and streaming support
Tera intelligent routing layer that matches requests to specialist models
Rantera Kasi stratospheric AI infrastructure at 20km altitude
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
Models trained on African context and languages, not adapted from elsewhere
Pricing denominated in local African currencies with no conversion fees
Managed training and sampling infrastructure, no setup required
Tinker-compatible API for easy migration
Ready-made SFT and RL recipes through Loops cookbook
Rantera
Loops