DeepSeek: R1 Distill Llama 70B
This model is no longer available.Add AI to your application with Puter.js.
Explore Other Models
Model Card
DeepSeek R1 Distill Llama 70B is a 70 billion parameter dense model fine-tuned from Llama 3.3-70B-Instruct using 800K reasoning samples generated by DeepSeek R1. It brings R1's reasoning capabilities to a more accessible size while maintaining strong performance on math and coding benchmarks.
Context Window 131K
tokens
Max Output 16K
tokens
Input Cost $0.7
per million tokens
Output Cost $0.8
per million tokens
Release Date Jan 23, 2025
Code Example
Add AI to your app with the Puter.js AI API — no API keys or setup required.
// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';
puter.ai.chat("Explain quantum computing in simple terms").then(response => {
document.body.innerHTML = response.message.content;
});
<html>
<body>
<script src="https://js.puter.com/v2/"></script>
<script>
puter.ai.chat("Explain quantum computing in simple terms").then(response => {
document.body.innerHTML = response.message.content;
});
</script>
</body>
</html>
More AI Models From DeepSeek
DeepSeek V4 Flash Vision Experimental
DeepSeek V4 Flash Vision Experimental is an experimental multimodal version of DeepSeek's V4 Flash model, released by DeepSeek in August 2026. It is a sparse Mixture-of-Experts model with 284B total parameters and 13B activated per token, and it accepts images (JPEG, PNG, GIF, WebP) alongside text through the same API used for V4 Flash, at the same per-token pricing. DeepSeek reports that it matches V4 Flash on text tasks including agentic reasoning and world knowledge, while adding image understanding for document and chart parsing, visual question answering, and agent workflows that interleave text and images. On multimodal agent benchmarks, DeepSeek's own numbers show gains over the text-only V4 Flash, with Terminal Bench 2.1 rising from 82.7 to 83.9, ApexBench from 26.2 to 36.5, and Agents' Last Exam from 25.2 to 27.3, approaching Anthropic's Opus 4.8 (85.0 on Terminal Bench 2.1). On NL2Repo it trails Opus 4.8, 57.7 versus 69.7.
ChatDeepSeek V4 Pro 0813
DeepSeek V4 Pro 0813 is the production release of DeepSeek's V4 Pro flagship model, a 1.6-trillion-parameter Mixture-of-Experts model with 49B parameters active per token, marking the end of a four-month preview. It keeps the preview's 1,048,576-token context window, 384,000-token max output, and three reasoning modes (non-thinking, high, and max effort). DeepSeek reports large gains over the preview build: Terminal Bench 2.1 rose from 72.1 to 87.9 and DeepSWE from 12.8 to 62.7. At max reasoning effort it scores 80.6% on SWE-bench Verified, matching Gemini 3.1 Pro, along with 90.1% on GPQA Diamond, 87.5% on MMLU-Pro, and a Codeforces rating of 3,206, ahead of GPT-5.4's 3,168. Priced at $0.38 per million input tokens and $1.14 per million output tokens. Pinning the 0813 route locks an application to this exact checkpoint rather than the rolling deepseek-v4-pro alias, useful for agentic coding and long-context reasoning tasks.
ChatDeepSeek V4 Flash (0731)
DeepSeek V4 Flash 0731 is DeepSeek's July 31, 2026 dated checkpoint of V4 Flash, a sparse Mixture-of-Experts chat model with 284B total parameters and 13B active per token. This route runs on Alibaba's infrastructure with a 1,000,000-token context window and adjustable reasoning effort (low, high, max). It was re-post-trained for coding agents and tool use, and DeepSeek reports it scoring 82.7 on Terminal Bench 2.1 (up from 61.8 for the April preview), 76.7 on Cybergym, 70.3 on Toolathlon, and 54.4 on DeepSWE, outscoring the larger V4 Pro preview on these agentic tasks despite far fewer activated parameters. At max reasoning effort it also reaches 89.0% on ARC-AGI-1 and 61.4% on ARC-AGI-2, at $0.02 and $0.04 per task. These figures are vendor-reported and weren't independently reproduced at release. Pinning the dated route locks an application to this exact checkpoint, suited to coding agents, tool-calling workflows, and long-context codebase or document analysis.
Frequently Asked Questions
You can access R1 Distill Llama 70B by DeepSeek through Puter.js AI API. Include the library in your web app or Node.js project and start making calls with just a few lines of JavaScript — no backend and no configuration required. You can also use it with Python or cURL via Puter's OpenAI-compatible API.
Yes, it is free if you're using it through Puter.js. With the User-Pays Model, you can add R1 Distill Llama 70B to your app at no cost — your users pay for their own AI usage directly, making it completely free for you as a developer.
| Price per 1M tokens | |
|---|---|
| Input | $0.7 |
| Output | $0.8 |
R1 Distill Llama 70B was created by DeepSeek and released on Jan 23, 2025.
R1 Distill Llama 70B supports a context window of 131K tokens. For reference, that is roughly equivalent to 262 pages of text.
R1 Distill Llama 70B can generate up to 16K tokens in a single response.
R1 Distill Llama 70B scores 9.8 on the Artificial Analysis Intelligence Index, outperforming 32% of tracked models. On math, it scores 53.7 (outperforms 50% of models).
Yes — the R1 Distill Llama 70B API works with any JavaScript framework, Node.js, or plain HTML through Puter.js. Just include the library and start building. See the documentation for more details.
Get started with Puter.js
Add AI to your application without worrying about API keys or setup.
Explore Models View Tutorials