UltraGPT
DeepSeek: R1 Distill Llama 70B
DeepSeek R1 Distill Llama 70B is a distilled large language model based on [Llama-3.3-70B-Instruct](/meta-llama/llama-3.3-70b-instruct), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). The model combines advanced distillation techniques to achieve high performance across...
Intelligence overview
8.2K tok
Context window
7.4K tok
Max output
What DeepSeek: R1 Distill Llama 70B can do.
Reasoning
Extended reasoning
Works through problems step by step before answering, trading latency for accuracy on harder tasks.
Development
Streaming
Streams tokens as they're generated instead of waiting on the full response.
Pay for what you use.
Every model in UltraGPT runs behind one flat subscription — this is the underlying per-token cost the catalog tracks.
$0.8 / 1M tok
$0.8 / 1M tok
Built for serious work.
Think
Works through multi-step problems with extended reasoning before it answers.
Ask DeepSeek: R1 Distill Llama 70B anything.
A preview of the real UltraGPT composer — the model you see here is the model you get.
Continues in the UltraGPT app — one login, every model.
How DeepSeek: R1 Distill Llama 70B stacks up.
The closest models in the catalog by provider, capability and score — real entries, pulled from the same directory.
Technical details.
Specification
- Context window
- 8.2K tokens
- Max output
- 7.4K tokens
- Input modalities
- Text
- Output modalities
- Text
- Knowledge cutoff
- Jul 31, 2024
- Release date
- Jan 23, 2025
- Streaming
- Supported
- Tool calling
- Not supported
- JSON mode
- Not supported
More from DeepSeek, and everything else.
This model is one entry in the full UltraGPT catalog — browse the rest, compare pricing and context windows, or filter by capability.