DeepSeek R1 Distill Llama 70B
DeepSeek R1 Distill Llama 70B is a text-based AI model by DeepSeek. It features a 131K token context window, 51 tok/s output speed, $0.70/1M input tokens pricing. It scores 16.0 on the intelligence index.
Strengths
- +Very affordable pricing ($0.70/1M tokens)
Benchmarks
Intelligence16.0Coding11.4Math53.7
MMLU-Pro
0.8
GPQA
0.4
LiveCodeBench
0.3
Intelligence
16.0
Coding
11.4
Math
53.7
Output Speed
51 tok/s
Latency (TTFT)
0.77s
Blended Price
$0.88/M
Pricing per 1M Tokens
| Input (Prompt) | $0.70 |
| Output (Completion) | $1.05 |
| Cache Read | Free |
| Cache Write | Free |
Specifications
| Context Length | 131K |
| Max Output Tokens | N/A |
| Input Modalities | Text |
| Output Modalities | Text |
| Tokenizer | N/A |
Compare DeepSeek R1 Distill Llama 70B with:
Alternatives to DeepSeek R1 Distill Llama 70B
More from DeepSeek
Frequently Asked Questions
How much does DeepSeek R1 Distill Llama 70B cost?
DeepSeek R1 Distill Llama 70B costs $0.70/1M input tokens and $1.05/1M output tokens.
What is DeepSeek R1 Distill Llama 70B's context window?
DeepSeek R1 Distill Llama 70B supports a context window of 131K tokens, which is approximately 66 pages of text.
Is DeepSeek R1 Distill Llama 70B good for coding?
DeepSeek R1 Distill Llama 70B has a lower coding score of 11.4. For demanding coding tasks, consider a model with a higher coding benchmark.
How fast is DeepSeek R1 Distill Llama 70B?
DeepSeek R1 Distill Llama 70B generates output at 51 tok/s. Time to first token is 0.77s.
Is there a free version of DeepSeek R1 Distill Llama 70B?
Last updated: