Qwen3.6 35B A3B (Reasoning) API Pricing

Alibaba · released 2026-04-16 · merges 2 reasoning-effort tiers

Benchmarks shown for the highest-scoring reasoning tier. Merged tiers: Qwen3.6 35B A3B (Reasoning), Qwen3.6 35B A3B (Non-reasoning).

Pricing

$0.375
input / 1M tokens
0.037¢ / 1K
$2.25
output / 1M tokens
0.225¢ / 1K
$0.844
blended / 1M tokens
0.084¢ / 1K

What it actually costs

WorkloadTokensCost
Short chat reply500 in / 300 out0.0862¢
RAG query4,000 in / 500 out0.263¢
Long document summary50,000 in / 1,000 out$0.0210
Code review of a 2k-line file30,000 in / 2,000 out$0.0158
1,000 chat replies/day for 30 days30,000 × (500 in / 300 out)$25.88

Cost = (input tokens ÷ 1,000,000 × $0.375) + (output tokens ÷ 1,000,000 × $2.25).

Benchmarks

18.2
Intelligence
#143 of 533
41.9
Coding
#89 of 197
Math
127
Tokens/sec
1.15s
Time to first token

Similar intelligence, lower price

ModelIntelligenceBlended $/1M
MiMo-V2-Flash (Reasoning)20.8$0.15
Step 3.5 Flash 260317.0$0.15
Step 3.5 Flash16.6$0.15
Gemma 4 26B A4B (Reasoning)16.7$0.179
Grok 4 Fast (Reasoning)17.9$0.275

Leaderboard neighbours

ModelIntelligenceBlended $/1M
KAT-Coder-Pro V118.6
MiniMax-M218.6$0.525
GLM-4.6 (Reasoning)18.5$0.963
Qwen3.6 35B A3B (Reasoning)18.2$0.844
Gemini 3 Flash Preview (Non-reasoning)17.9$1.125
Grok 4 Fast (Reasoning)17.9$0.275
Claude 3.7 Sonnet (Reasoning)17.7

More from Alibaba

ModelIntelligenceBlended $/1M
Qwen3.8 Max (0902)45.4$3.00
Qwen3.8 Max40.2$3.00
Qwen3.8 2.4T A95B39.9$3.00
Qwen3.8-Flash-Next39.8$0.23
Qwen3.8 27B (xhigh)33.7$1.125
Qwen3.7 Max29.5$3.75
Qwen3.6 Max Preview28.4$2.925
Qwen3.6 Plus27.0$1.125

Count tokens & estimate cost for Qwen3.6 35B A3B (Reasoning) See Qwen3.6 35B A3B (Reasoning) on the leaderboard

Source: Artificial Analysis · last synced 2026-09-22

FAQ

Who develops Qwen3.6 35B A3B (Reasoning)?

Qwen3.6 35B A3B (Reasoning) is developed by Alibaba, released 2026-04-16.

How much does Qwen3.6 35B A3B (Reasoning) cost per million tokens?

Qwen3.6 35B A3B (Reasoning) costs $0.375 per 1M input tokens and $2.25 per 1M output tokens ($0.844 blended), per Artificial Analysis's official pricing data.

How does Qwen3.6 35B A3B (Reasoning) rank on benchmarks?

Qwen3.6 35B A3B (Reasoning) scores 18.2 on the Artificial Analysis Intelligence Index, ranking #143 of 533 models we track.

Is there a cheaper model with similar intelligence to Qwen3.6 35B A3B (Reasoning)?

Yes — MiMo-V2-Flash (Reasoning) scores similar intelligence (20.8) at $0.15/1M blended, versus $0.844/1M for Qwen3.6 35B A3B (Reasoning).

Where does this data come from?

Pricing and benchmark data for Qwen3.6 35B A3B (Reasoning) comes from Artificial Analysis (artificialanalysis.ai), synced daily. Last synced 2026-09-22.