Qwen: Qwen3 235B A22B Thinking 2507
microqwen/qwen3-235b-a22b-thinking-2507
Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144...
AA INDEX12.7
CONTEXT128K
MODALITYtext->text
OPENNESSProprietary
ADDEDAug 2026
LAST PRICED10 min ago
Input
$0.45 /M
Output
$3.50 /M
Blended (40/60)
$2.28 /M
Cost / IQ
$7.1811 /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: $1.88/M
High: $2.28/M
Average: $2.06/M
Provider Comparison
1 providers · click a column to sort
| Provider | Input $/M | Output $/M | Blended $/M ↑ | vs Median |
|---|---|---|---|---|
| ↓Venice | $0.45 | $3.50 | $2.28 | median |
Blended price = 40% input + 60% output. Median price shown in header is the reference price for this model.
Cost / IQ Comparison
Cost / IQ (quality-adjusted $/M)$7.1811/M
Cost per GPT-4-equivalent token. Lower = better value. Comparable across all models.
98.6% above SIT TPI
Value Ranking (by Cost / IQ)
Rank #439 of 521 micro models
← YOU ARE HERE | Qwen: Qwen3 235B A22B Thinking 2507
Data Sources
Source
Direct provider data
1 source · updated recently
API Access
# Get this model's current price
curl https://api.inferenceindexer.ai/v1/models/qwen/qwen3-235b-a22b-thinking-2507
# Response (truncated)
{ "model_id": "qwen/qwen3-235b-a22b-thinking-2507", "name": "Qwen: Qwen3 235B A22B Thinking 2507", "blended_price_per_m": 2.28, "sit_adjusted_price": 7.181102 }