Qwen: Qwen3 30B A3B Thinking 2507
microqwen/qwen3-30b-a3b-thinking-2507
Qwen3-30B-A3B-Thinking-2507 is a 30B parameter Mixture-of-Experts reasoning model optimized for complex tasks requiring extended multi-step thinking. The model is designed specifically for “thinking mode,” where internal reasoning traces are separated...
AA INDEX7.6
CONTEXT82K
MODALITYtext->text
OPENNESSProprietary
ADDEDAug 2026
LAST PRICED12 days ago
Input
$0.20 /M
Output
$2.40 /M
Blended (40/60)
$1.52 /M
Cost / IQ
$7.9726 /M
Cost / IQ = Blended Price ÷ (AA Intelligence Score ÷ 40). Normalises price by model intelligence so you can compare value across tiers. Lower = better value per unit of intelligence. Not a transactional price.
24h0%
7d0%
Price History
30-day view, daily close
Low: $1.52/M
High: $1.52/M
Average: $1.52/M
Provider
Model by Qwen. Priced at blended $1.52/M. Provider endpoint records are not available yet, so no serving providers are listed for this model.
Cost / IQ Comparison
Cost / IQ (quality-adjusted $/M)$7.9726/M
Cost per GPT-4-equivalent token. Lower = better value. Comparable across all models.
33.9% above SIT TPI
Value Ranking (by Cost / IQ)
Rank #400 of 522 micro models
← YOU ARE HERE | Qwen: Qwen3 30B A3B Thinking 2507
Data Sources
Source
Aggregator
1 source · updated recently
API Access
# Get this model's current price
curl https://api.inferenceindexer.ai/v1/models/qwen/qwen3-30b-a3b-thinking-2507
# Response (truncated)
{ "model_id": "qwen/qwen3-30b-a3b-thinking-2507", "name": "Qwen: Qwen3 30B A3B Thinking 2507", "blended_price_per_m": 1.52, "sit_adjusted_price": 7.972575 }