Qwen3 30B A3b Instruct 2507

Qwen3 30B A3b Instruct 2507 is a text model from Fireworks AI with a context window of 262K tokens and max output of 262K tokens. Pricing starts at 0.50 per million input tokens and 0.50 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/qwen3-30b-a3b-instruct-2507
ProviderFireworks AI
Provider IDfireworks_ai
ModeText
Canonical Nameqwen-3-30b-a3b-2507
Context Window262K tokens
Max Output262K tokens

Pricing

TypePer 1K TokensPer 1M Tokens
Input Tokens0.0005000.500
Output Tokens0.0005000.500

Benchmarks

Intelligence Index15.0#130
Coding Index14.2#103
Math Index66.3#36
MMLU-Pro0.8#62
GPQA0.7#81
HLE0.1#70
LiveCodeBench0.5#57
AIME0.7#16
IFBench0.3#119
Time to First Token1.12s#183
SciCode0.3#98
MATH-5001.0#12
AIME 20250.7#36
LCR0.2#98
TerminalBench Hard0.1#98
TAU20.1#151