DeepSeek R1 Distill Qwen3 8B 0528

Name: DeepSeek R1 Distill Qwen3 8B 0528
Author: Novita AI

DeepSeek-R1-0528-Qwen3-8B is a high-performance reasoning model based on the Qwen3 8B Base model, enhanced through the integration of DeepSeek-R1-0528's Chain-of-Thought (CoT) optimization.

Context

128K

Max output

32K

Input price

$0.06/1M tokens

Output price

$0.09/1M tokens

Capabilities

Show unsupported (6)

Reasoning & Interaction

Reasoning

Infrastructure

Streaming

Details

Model IDdeepseek/deepseek-r1-0528-qwen3-8b

ProviderNovita AI

CreatorDeepSeek

Familydeepseek-r1

License—

Statusactive

Typechat

Input modalitiestext

Output modalitiestext

Open weight—

Parameters8B

Architecture—

Context window128K tokens

Max input—

Max output32K tokens

Reasoning tokens—

Knowledge cutoff—

Release date2025-05-29

Sourceofficial

Endpoints

Chat CompletionsPOST

Generate chat responses with messageshttps://api.novita.ai/v3/openai/v1/chat/completions

Pricing

Input

$0.06

Output

$0.09

Cache write

—

Cache read

—

Batch in

—

Batch out

—

Family Comparison: deepseek-r1

Model	Caps	Perf	Speed	Context	Max out	Pricing
DeepSeek R1 Distill Qwen3 8B 0528	RS	—	—	128K	32K	$0.06$0.09
DeepSeek R1 Distill Qwen 14B	S	—	—	33K	16K	$0.15$0.15
DeepSeek R1 Distill Qwen 32B	S	—	—	64K	32K	$0.3$0.3
DeepSeek R1 0528	RTJJMS	—	—	164K	33K	$0.7$2.5
DeepSeek R1 Turbo	RTJJMS	—	—	64K	16K	$0.7$2.5
DeepSeek R1 Distill Llama 70B	RS	—	—	8K	8K	$0.8$0.8
DeepSeek R1	RTS	—	—	64K	8K	$4$4
DeepSeek R1	RTS	—	—	64K	16K	$4$4

API

GET/v1/models/novita/deepseek/deepseek-r1-0528-qwen3-8b