Auriko
Route and monitor model inference with provider and budget controls
Refuseless
Hosted open-weight language models for coding and security workflows
Meet Refuseless
Refuseless provides hosted access to open-weight language models through an OpenAI-compatible API. Its catalog includes abliterated models, which have been modified at the weight level to reduce refusal behavior, alongside unmodified alternatives. Developers can connect existing applications and coding agents without running their own model infrastructure, using chat completions, streaming responses, tool calls, and reasoning output where supported.
The service is aimed at coding and security workflows, with documentation for agents such as OpenCode and Pi. Usage is charged against prepaid credits according to each model’s input, cached-input, and output token rates, and balances can be funded by card or supported cryptocurrencies. Refuseless states that it does not retain prompts or outputs on its own systems; requests routed to external model providers remain subject to those providers’ data policies.
Discussion
Tried it? Share a useful thought or ask a question.
Good conversations start with a hello.
Sign in to commentProduct details
- Website
- refuseless.com
- Status
- Launched
- Category
- Artificial intelligence
- Listed
Explore related topics
Similar products
Zro
Hosted inference endpoints for coding agents and compatible API clients
Ramp Router
Route model requests through one endpoint with fallbacks and usage visibility.
Poolside
Build coding agents with the Laguna family of open-weight models
Relace
Access hosted inference for open-weight language models
Mouse-1
Add a fast decision layer to an AI agent’s execution workflow.