DeepSeek R1 0528 Distill Qwen3 8B

DeepSeek R1 0528 Distill Qwen3 8B is a text model from Fireworks AI with a context window of 131K tokens and max output of 131K tokens. Pricing starts at 0.20 per million input tokens and 0.20 per million output tokens.

Capabilities

Vision Function Calling Reasoning JSON Schema System Messages Web Search Prompt Caching Audio Input Audio Output

Specifications

Model Keyfireworks_ai/accounts/fireworks/models/deepseek-r1-0528-distill-qwen3-8b
ProviderFireworks AI
Provider IDfireworks_ai
ModeText
Canonical Namedeepseek-r1-distill-qwen-3-8b-0528
Context Window131K tokens
Max Output131K tokens

Pricing

TypePer 1K TokensPer 1M Tokens
Input Tokens0.0002000.200
Output Tokens0.0002000.200

Benchmarks

Intelligence Index16.4#116
Coding Index7.8#141
Math Index63.7#38
MMLU-Pro0.7#90
GPQA0.6#96
HLE0.1#86
LiveCodeBench0.5#60
AIME0.7#26
IFBench0.2#170
Time to First Token0.00s#1
SciCode0.2#160
MATH-5000.9#29
AIME 20250.6#38
LCR0.1#123
TerminalBench Hard0.0#133
TAU20.0#154