Skip to content

Model Library

DeepSeekReleased January 20, 2025

DeepSeek R1 Distill Llama 70B

DeepSeek · Released January 20, 2025

View public research Browse the library

Intelligence score

10

At a glance

Intelligence
10
Speed
29.9tokens/sec
Latency
710mstime to first token
Input price
$0.70per 1M tokens
Output price
$1.05per 1M tokens
Context window
130Ktokens
Parameters
70billions

Summary

Comparison summary

DeepSeek R1 Distill Llama 70B scores 10 (estimated) on the Artificial Analysis Intelligence Index, placing it above average among other open weight models of similar size (median: 9). DeepSeek R1 Distill Llama 70B generates output at 29.9 tokens per second (based on the median across providers serving the model), which is at the lower end compared to other open weight models of similar size (median: 88.2 t/s). DeepSeek R1 Distill Llama 70B costs $0.70 per 1M input tokens (somewhat higher than average, median: $0.40) and $1.05 per 1M output tokens (somewhat higher than average, median: $0.84), based on the median across providers serving the model.

Specifications

Technical specifications

Model nameDeepSeek R1 Distill Llama 70B
ProviderDeepSeek
Release dateJanuary 20, 2025
Intelligence score10
Speed29.9 tokens/sec
Latency (TTFT)0.71s
Input price$0.70 / 1M tokens
Output price$1.05 / 1M tokens
Context window130,000 tokens
Parameters70B
ReasoningYes
Input modalitiestext
Output modalities—
Open weightsYes
LicenseLLAMA 3
API availability—
SourceModel Intelligence legacy profile: deepseek-r1-distill-llama-70b

Pricing

Token prices

Price per 1M tokens

DeepSeek R1 Distill Llama 70B, as listed in the catalog record

Input $0.70 and output $1.05 per 1M tokens. Missing prices are hatched and marked "Not published".
  1. Input$0.70
  2. Output$1.05

Model Intelligence legacy profile: deepseek-r1-distill-llama-70b

FAQ · 19

Frequently asked questions

DeepSeek R1 Distill Llama 70B was released on January 20, 2025.

DeepSeek R1 Distill Llama 70B was created by DeepSeek.

DeepSeek R1 Distill Llama 70B scores 10 (estimated) on the Artificial Analysis Intelligence Index, placing it above average among other open weight models of similar size (median: 9).

DeepSeek R1 Distill Llama 70B generates output at 29.9 tokens per second (based on the median across providers serving the model), which is at the lower end compared to other open weight models of similar size (median: 88.2 t/s).

DeepSeek R1 Distill Llama 70B has a time to first token (TTFT) of 0.71s (based on the median across providers serving the model), which is very competitive compared to other open weight models of similar size (median: 1.52s).

DeepSeek R1 Distill Llama 70B costs $0.70 per 1M input tokens (somewhat higher than average, median: $0.40) and $1.05 per 1M output tokens (somewhat higher than average, median: $0.84), based on the median across providers serving the model.

DeepSeek R1 Distill Llama 70B costs $0.70 per 1M input tokens and $1.05 per 1M output tokens (based on the median across providers serving the model). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.73 per 1M tokens. Pricing may vary by provider.

Yes, DeepSeek R1 Distill Llama 70B is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.

DeepSeek R1 Distill Llama 70B supports text input.

DeepSeek R1 Distill Llama 70B supports text output.

No, DeepSeek R1 Distill Llama 70B does not support image input. It can only process text.

No, DeepSeek R1 Distill Llama 70B is not multimodal. It only supports text input.

DeepSeek R1 Distill Llama 70B has a context window of 130k tokens. This determines how much text and conversation history the model can process in a single request.

Yes, DeepSeek R1 Distill Llama 70B is open weights. The model weights are publicly available and can be downloaded for self-hosting.

DeepSeek R1 Distill Llama 70B has 70 billion parameters.

DeepSeek R1 Distill Llama 70B is released under the LLAMA 3.3 COMMUNITY LICENSE AGREEMENT license. This license allows commercial use.

DeepSeek R1 Distill Llama 70B achieves a score of 10 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.

Yes, DeepSeek R1 Distill Llama 70B is available via API through 3 providers.

DeepSeek R1 Distill Llama 70B is available through 3 API providers.