Leaving Silk Compute? Uncensored AI models instead
Silk Compute advertises abliterated Kimi K3 at a million tokens of context, but its uncensored inference was offline when we checked. These are the uncensored and abliterated APIs serving today, including Wild West API.
What Silk Compute is, and where it stops
Silk Compute advertises abliterated Kimi K3, GLM 5.2 and DeepSeek V4 Flash, with Kimi K3 at $7 in and $35 out per million tokens. On 6 October 2026 its own homepage said uncensored inference was offline while it moves to a new GPU cluster.
Other options people compare with Silk Compute
| Option | What it is |
|---|---|
| Apixo | Discounted LLM API with a small uncensored line from $0.10 per million tokens; its GLM 5.3 Flash Uncensored adds a ~14,000 token built-in prompt to every call. |
| MuAPI | About 20 abliterated models through OpenAI and Anthropic endpoints, priced below most gateways. |
| Shannon AI | Uncensored gateway serving 21 open models from its own GPUs with no filters, including a 3-bit compressed Kimi K3. |
| Crowbot | Cheap OpenAI-format API with no-email accounts and a couple of uncensored models; abliterated Kimi K3 coming soon. |
| Audn AI | Red-team company selling its own abliterated models per token or on flat monthly plans, with a published refusal benchmark. |
| abliteration.ai | Hosted API for its own three abliterated models, including an abliterated GLM-5.3 with 1M context, plus web search and a policy gateway. |
| Featherless | Flat monthly subscription over tens of thousands of open Hugging Face models, hundreds of them abliterated or uncensored, hosted by Featherless itself. |
Weighing the two directly? Wild West API vs Silk Compute puts pricing, endpoints, spend caps and model policy side by side, checked against Silk Compute's own site.
What Wild West API carries instead
Wild West API sells 5 uncensored models on one OpenAI-compatible endpoint, every one able to call tools. Ordered for this particular job rather than by a single ranking: Outlaw 1 Xploded leads because it is the cheapest of the set on output at $1.00 per million tokens.
| Model | Context | In | Out | Tools |
|---|---|---|---|---|
| Outlaw 1 Xploded outlaw-1-xploded |
1.05M | $0.300 | $1.00 | Yes |
| GLM 5.3 Flash Xploded glm-5.3-flash-xploded |
1.05M | $0.400 | $1.60 | Yes |
| Qwen3.8 27B Xploded qwen3.8-27b-xploded |
524k | $0.300 | $2.40 | Yes |
| MiMo V2.6 Flash Xploded mimo-v2.6-flash-xploded |
1.05M | $1.00 | $3.00 | Yes |
Switching takes one base URL
Anything that speaks the OpenAI chat completions format works unchanged. Point it here, use a Wild West API key, and name the model from the table.
curl https://wildwestapi.com/v1/chat/completions \ -H "Authorization: Bearer sk-ww-..." \ -H "Content-Type: application/json" \ -d '{ "model": "outlaw-1-xploded", "messages": [{"role": "user", "content": "Hello"}] }'
FAQ
Is Wild West API actually uncensored, or does it just say so?
Wild West API does not moderate requests. It prices the call, holds the money against your key cap and passes the request to the model. What comes back is whatever that model does: an uncensored build refuses far less than a frontier model but can still decline, and only an abliterated build has the refusal direction removed outright. Neither tag is a promise that any given answer will arrive.
What does it cost compared with Silk Compute?
You pay per token at the rates in the table above, with no subscription. $0.300 in and $1.00 out per million tokens for Outlaw 1 Xploded.
Can I cap what a key is allowed to spend?
Yes, and the cap is enforced before the request goes upstream rather than reconciled afterwards. The reply cannot physically cost more than the hold placed before it was sent.
Will it work with my existing client?
If the client takes an OpenAI-compatible base URL, yes: point it at https://wildwestapi.com/v1 with a Wild West API key. Claude Code and the Anthropic SDKs use the Anthropic format, which is served too.