DeepSeek logo

DeepSeek R1 528 Qwen3 8B


DeepSeek R1 528 Qwen3 8B is DeepSeek logoDeepSeek's language model with a 128K context window and up to 32K output tokens. A compact 8B reasoning model distilled from DeepSeek R1 0528's chain-of-thought into the Qwen3 8B base, targeting efficient open-source reasoning.
Spec
Canonical IDdeepseek-r1-528-qwen3-8b
TypeLanguage
StatusActive
CreatorDeepSeekDeepSeek
Providers
Context Window128K tokens
Max Output32K tokens
Input ModalitiesText
Output ModalitiesText
Reasoning Effortsdefault
Parameters8B

Capabilities

Input1/5
Text
Image·
Audio·
Video·
PDF·
Output1/5
Text
Image·
Audio·
Video·
Embedding·
Capabilities1/13
Reasoning
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Pricing by Provider

ProviderStandard
Input
$ / 1M
Output
$ / 1M
Novita logo
Novita
$0.060$0.090

Cost Calculator

Preset:
Compares every provider & tier in USD

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
DeepSeek R1 0528164K$0.200$0.600Available
DeepSeek R1 528B164KAvailable
DeepSeek R1 Distill Qwen 32B131K$0.270$0.270Available
DeepSeek R1 Distill Llama 70B131K$0.200$0.600Available
DeepSeek R1164K$0.280$0.400Available
DeepSeek R1 528 Qwen3 8B128KCurrent
DeepSeek R1Available
DeepSeek R1 0528 Distill Qwen3 8B131K$0.200$0.200Available
DeepSeek R1 528B Turbo33KAvailable
DeepSeek R1 671B131K$0.800$0.800Available
DeepSeek R1 Basic128K$0.550$2.19Available

Model IDs