R1 Distill Qwen 1.5B Check detailed information and pricing for AI models

Context Length 131,072 tokens, deepseek from provided

131,072
Context Tokens
$0.18
Prompt Price
$0.18
Output Price
8/16
Feature Support
Reasoning #4

Model Overview

DeepSeek R1 Distill Qwen 1.5B is a distilled large language model based on [Qwen 2.5 Math 1.5B](https://huggingface.co/Qwen/Qwen2.5-Math-1.5B), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). It's a very small and efficient model which outperforms [GPT 4o 0513](/openai/gpt-4o-2024-05-13) on Math Benchmarks. Other benchmark results include: - AIME 2024 pass@1: 28.9 - AIME 2024 cons@64: 52.7 - MATH-500 pass@1: 83.9 The model leverages fine-tuning from DeepSeek R1's outputs, enabling competitive performance comparable to larger frontier models.

Basic Information

Developer
deepseek
Model Series
Other
Release Date
2025-01-31
Context Length
131,072 tokens
Max Completion Tokens
32,768 tokens
Variant
standard

Pricing Information

Prompt Tokens
$0.18 / 1M tokens
Completion Tokens
$0.18 / 1M tokens

Supported Features

Supported (8)

Top K
Frequency Penalty
Presence Penalty
Repetition Penalty
Response Format
Min P
Logit Bias
Reasoning

Unsupported (8)

Image Input
Seed
Tool Usage
Logprobs
Top Logprobs
Structured Outputs
Web Search Options
Top A

Actual Usage Statistics

#205
Out of 345 total models
268.25M
Total Tokens Last 30 Days
8.94M
Daily Average Usage
37%
Weekly Usage Change

Usage Trend for the Last 30 Days

Models by Same Author (deepseek)

R1 Distill Qwen 7B
131,072 tokens
$0.10 / $0.20
Deepseek R1 0528 Qwen3 8B (free)
131,072 tokens
Free
Deepseek R1 0528 Qwen3 8B
131,072 tokens
$0.05 / $0.10
R1 0528 (free)
163,840 tokens
Free
R1 0528
128,000 tokens
$0.50 / $2.15

Similar Price Range Models

Spotlight
arcee-ai
131,072 tokens
$0.18 / $0.18
Llama 3.1 Sonar 8B Online
perplexity
127,072 tokens
$0.20 / $0.20
Gemma 2 9B
google
8,192 tokens
$0.20 / $0.20
LlamaGuard 2 8B
meta-llama
8,192 tokens
$0.20 / $0.20
Mistral 7B Instruct v0.2
mistralai
32,768 tokens
$0.20 / $0.20