Qwen3 30B A3b Thinking 2507

Qwen3 30B A3b Thinking 2507 is a text model from Fireworks AI with a context window of 262K tokens and max output of 262K tokens. Pricing starts at 0.90 per million input tokens and 0.90 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-thinking-2507
ProviderFireworks AI
Provider IDfireworks_ai
ModeText
Canonical Nameqwen-3-30b-a3b-thinking-2507
Context Window262K tokens
Max Output262K tokens

Pricing

TypePer 1K TokensPer 1M Tokens
Input Tokens0.0009000.900
Output Tokens0.0009000.900

Benchmarks

Intelligence Index22.4#81
Coding Index14.7#99
Math Index56.3#48
MMLU-Pro0.8#48
GPQA0.7#64
HLE0.1#47
LiveCodeBench0.7#31
AIME0.9#6
IFBench0.5#44
Time to First Token1.04s#171
SciCode0.3#79
MATH-5001.0#11
AIME 20250.6#48
LCR0.6#36
TerminalBench Hard0.1#106
TAU20.3#90