[Dagon Inference](https://inference.dagon.so/) / Providers that host abliterated (refusal-removed) open-weight models through an API

# Providers that host abliterated (refusal-removed) open-weight models through an API

Published 2026-11-11 · Last updated 2026-11-11

abliteration.ai (`abliterated-model-large-flash`, `abliterated-model`, `abliterated-model-large-v2`), Refuseless (`glm-5.3-abliterated`, `deepseek-v4.1-flash-abliterated`, `glm-5.3-flash-abliterated`), Experiential Labs (`glm-5.3-abliterated`, `deepseek-v4.1-flash-abliterated`, `glm-5.3-flash-abliterated`), Lutheos (`deepseek-v4.1-flash-abliterated`) and Silk Compute (`glm-5.3-abliterated`, `deepseek-v4.1-flash-abliterated`, `glm-5.3-flash-abliterated`, `kimi-k3.1-pro-abliterated`) host refusal-removed (abliterated) open-weight models through an API, and Dagon Inference puts all of them behind one OpenAI and Anthropic compatible API at `https://inference.dagon.so/v1`: each request goes to the cheapest healthy provider for its model id, falls back to the next cheapest if that one fails before any output, and is billed per token in USDC with a signed receipt naming the provider. These are the providers Dagon Inference routes to, not a survey of every host.

## Which abliterated models does each provider host?

| Provider | Model | Model id | Input | Output | Endpoints |
| --- | --- | --- | --- | --- | --- |
| abliteration.ai | [Abliterated Large Flash](https://inference.dagon.so/models/abliterated-model-large-flash) | `abliterated-model-large-flash` | $1.10 | $2.20 | Chat, Responses, Messages |
| abliteration.ai | [Abliterated Model](https://inference.dagon.so/models/abliterated-model) | `abliterated-model` | $1.10 | $3.30 | Chat, Responses, Messages |
| abliteration.ai | [Abliterated Large v2](https://inference.dagon.so/models/abliterated-model-large-v2) | `abliterated-model-large-v2` | $3.30 | $5.50 | Chat, Responses, Messages |
| Refuseless | [GLM-5.3 Abliterated](https://inference.dagon.so/models/glm-5.3-abliterated) | `glm-5.3-abliterated` | $1.10 | $2.20 | Chat, Responses |
| Refuseless | [DeepSeek V4.1 Flash Abliterated](https://inference.dagon.so/models/deepseek-v4.1-flash-abliterated) | `deepseek-v4.1-flash-abliterated` | $0.132 | $0.495 | Chat, Responses |
| Refuseless | [GLM-5.3 Flash Abliterated](https://inference.dagon.so/models/glm-5.3-flash-abliterated) | `glm-5.3-flash-abliterated` | $0.132 | $0.55 | Chat, Responses |
| Experiential Labs | [GLM-5.3 Abliterated](https://inference.dagon.so/models/glm-5.3-abliterated) | `glm-5.3-abliterated` | $1.54 | $4.84 | Chat |
| Experiential Labs | [DeepSeek V4.1 Flash Abliterated](https://inference.dagon.so/models/deepseek-v4.1-flash-abliterated) | `deepseek-v4.1-flash-abliterated` | $0.33 | $1.32 | Chat |
| Experiential Labs | [GLM-5.3 Flash Abliterated](https://inference.dagon.so/models/glm-5.3-flash-abliterated) | `glm-5.3-flash-abliterated` | $0.165 | $0.55 | Chat |
| Lutheos | [DeepSeek V4.1 Flash Abliterated](https://inference.dagon.so/models/deepseek-v4.1-flash-abliterated) | `deepseek-v4.1-flash-abliterated` | $0.11 | $0.44 | Chat, Messages |
| Silk Compute | [GLM-5.3 Abliterated](https://inference.dagon.so/models/glm-5.3-abliterated) | `glm-5.3-abliterated` | $2.20 | $4.40 | Chat, Responses, Messages |
| Silk Compute | [DeepSeek V4.1 Flash Abliterated](https://inference.dagon.so/models/deepseek-v4.1-flash-abliterated) | `deepseek-v4.1-flash-abliterated` | $0.308 | $1.10 | Chat, Responses, Messages |
| Silk Compute | [GLM-5.3 Flash Abliterated](https://inference.dagon.so/models/glm-5.3-flash-abliterated) | `glm-5.3-flash-abliterated` | $0.264 | $1.10 | Chat, Responses, Messages |
| Silk Compute | [Kimi K3.1 Pro Abliterated](https://inference.dagon.so/models/kimi-k3.1-pro-abliterated) | `kimi-k3.1-pro-abliterated` | $5.50 | $16.50 | Chat, Responses, Messages |

US dollars per 1M tokens through Dagon Inference: the provider's price plus the 10% markup, at price version 2026-11-11.4. A provider's own direct prices and terms may differ. Live: [/v1/models](https://inference.dagon.so/v1/models).

Six ways a request ends

Before forwarding, the gateway holds the worst case: 37,545 µ$ for a 1,200-character prompt to Large Flash (abliteration.ai) with the default 16,384-token cap. When the upstream reports its usage the charge is 724 µ$ and 36,821 µ$ is released; each other way a request can end has its own defined charge, and the register rolls to it as the selector turns. The tell-tale rises when the gateway signs and stores a receipt.

## What is an abliterated model?

Abliteration edits an open-weight model's weights to remove the direction that drives refusals, so it needs a model whose weights are available: a closed model such as GPT or Claude cannot be abliterated by anyone outside its lab. The models above are labelled from our live probes, which show their refusal behavior as removed; individual requests may still be declined or answered poorly, and we have not benchmarked their quality. abliteration.ai's own abliterated build of GLM-5.3 is `abliterated-model-large-v2`; it is post-trained by abliteration.ai, so it can behave differently from `glm-5.3-abliterated`.

## How do you reach every provider with one key?

Create a key with `curl -X POST https://inference.dagon.so/v1/keys` (no email or password), fund it with USDC from $5, and call any model id above at `https://inference.dagon.so/v1` with an OpenAI SDK, or at `https://inference.dagon.so` with an Anthropic SDK (see [the Anthropic Messages guide](https://inference.dagon.so/anthropic-messages-api-uncensored-models)). The gateway picks the cheapest healthy provider serving the model on the endpoint you call; each model page lists every provider's price, and [the pricing page](https://inference.dagon.so/abliterated-llm-pricing) has the whole table.

## What do the providers say they keep?

abliteration.ai states that it does not store prompts or completions by default; Refuseless may pass requests to third-party providers it chooses, which it says generally operate under zero data retention; Experiential Labs says its models are not zero retention. Lutheos says its GPU partner keeps no prompts or replies; Silk Compute says it does not store prompts or outputs and serves its models without content filters. Cheaper Inference keeps request content unless the request asks for zero data retention; ours always do, and it says it then keeps none and sends the request only to providers that keep none. We cannot verify or control any of that.

We do not monitor or log your content, and the acceptable use policy applies: use it lawfully and only against systems and people you own or have permission to test. We suspend keys that break it.

## Common questions

### Which providers host refusal-removed (abliterated) open-weight models through an API?

abliteration.ai (abliterated-model-large-flash, abliterated-model, abliterated-model-large-v2); Refuseless (glm-5.3-abliterated, deepseek-v4.1-flash-abliterated, glm-5.3-flash-abliterated); Experiential Labs (glm-5.3-abliterated, deepseek-v4.1-flash-abliterated, glm-5.3-flash-abliterated); Lutheos (deepseek-v4.1-flash-abliterated); Silk Compute (glm-5.3-abliterated, deepseek-v4.1-flash-abliterated, glm-5.3-flash-abliterated, kimi-k3.1-pro-abliterated). Dagon Inference routes to all of them through one OpenAI and Anthropic compatible API at `https://inference.dagon.so/v1`, sending each request to the cheapest healthy provider for its model id, billed per token in USDC.

### Are abliterated models fully uncensored?

Not guaranteed. Abliteration removes the direction in the weights that drives refusals, and our live probes show refusal behavior removed for the models above, but individual requests may still be declined or answered poorly. We do not monitor or log your content, and the acceptable use policy applies: use it lawfully and only against systems and people you own or have permission to test. We suspend keys that break it.

### Can one key reach models from several providers?

Yes. One Dagon Inference key reaches every model above; a model served by several providers falls back to the next cheapest if one fails before any output, and each signed receipt names the provider that served the request.

## Create a key in a minute.

[Get a key](https://inference.dagon.so/app/)

## Related guides

- [Uncensored OpenAI-compatible API for security research, refusals removed](https://inference.dagon.so/cybersecurity-llm-api)
- [Smart contract audit with an uncensored LLM](https://inference.dagon.so/smart-contract-audit-llm)
- [No-KYC LLM API: use it without KYC and pay with crypto (USDC)](https://inference.dagon.so/pay-for-llm-api-with-usdc)
- [Use an uncensored LLM with the OpenAI or Anthropic SDK](https://inference.dagon.so/uncensored-llm-openai-sdk)
- [Anthropic Messages API compatible endpoint for uncensored models](https://inference.dagon.so/anthropic-messages-api-uncensored-models)
- [Abliterated LLM API: models, providers and pricing](https://inference.dagon.so/abliterated-llm-pricing)
- [Prepaid LLM API key for AI agents, paid in USDC](https://inference.dagon.so/buy-llm-credits-from-an-agent-wallet)
- [x402 LLM API: AI agents pay per request in USDC on Solana](https://inference.dagon.so/x402-llm-api)