DeepSeek R1 Distill Llama 70B Abliterated
This is an uncensored version of deepseek-ai/DeepSeek-R1-Distill-Llama-70B created with abliteration (see remove-refusals-with-transformers to know more about it). This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens.
- Input / output price
- $2.88 / $2.88 per 1M
- Context
- 33K tokens
- Released
- Jan 30, 2025
Paste into Claude Code, Cursor, or Codex
Help me set up the Respan gateway: fetch and follow https:/
Providers
One provider serves this model, priced per 1M tokens after gateway discounts.
| Provider | Input | Output |
|---|---|---|
Featherless featherless/deepseek-r1-distill-llama-70b-abliterated | $2.88/M | $2.88/M |
Pricing
USD per 1M tokens on Featherless, after gateway discounts.
- Input
- $2.88 per 1M
- Output
- $2.88 per 1M
- Cache read
- $4.00 per 1M
Cost by volume
Total cost from 0 to 1T tokens.
Throughput and latency
30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.
Output speed
Higher is better18tokens/sacross providers
Time to first token
Lower is better13sacross providers
Response latency
Lower is better15sacross providers
Apps
Use DeepSeek R1 Distill Llama 70B Abliterated in the tools you already run. Each guide points the app at the Respan gateway.
Setup guides for more apps are in the integration docs.
DeepSeek R1 Distill Llama 70B Abliterated FAQ
Short answers, built from the data on this page.
DeepSeek R1 Distill Llama 70B Abliterated is a model from Deepseek, released on Jan 30, 2025. This is an uncensored version of deepseek-ai/DeepSeek-R1-Distill-Llama-70B created with abliteration (see remove-refusals-with-transformers to know more about it). This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens.
On the Respan gateway, DeepSeek R1 Distill Llama 70B Abliterated costs $2.88 per 1M input tokens and $2.88 per 1M output tokens on Featherless, after gateway discounts.
DeepSeek R1 Distill Llama 70B Abliterated is served by Featherless.
DeepSeek R1 Distill Llama 70B Abliterated accepts up to 33K tokens of context.
Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "deepseek-r1-distill-llama-70b-abliterated". To set it up with a coding agent, copy the agent setup prompt at the top of this page.
Certified where it counts.
Built to meet the security and privacy standards that enterprise and healthcare teams require.
ISO 27001
The internationally recognized standard for information security management.
SOC 2
Secure, compliant management of your data across all of our systems.
GDPR
Operated under GDPR, the world's strictest standard for data privacy.
HIPAA
HIPAA compliant, with a BAA available for healthcare teams.