QwenOpen weightsReleased Apr 14, 2026Qwen3.6 35B A3B pricing, benchmarks and cost analysis
Epoch Capabilities Index (ECI)range 141.1 to 145.8
Throughput not measured for this model
In $0.100Out $0.950 per 1MCache discount 50%
Context window, tokens
Ranks are among the 101 models we track (intelligence = Epoch Capabilities Index by Epoch AI, CC BY 4.0; intelligence and speed: among those with data; cost: #1 is cheapest). Monthly cost uses the default workload of 2,000 input and 500 output tokens, 10,000 requests a day, 40% cached.
Comparison summary
On the default workload (2,000 input and 500 output tokens, 10,000 requests a day, 40% cached), Qwen3.6 35B A3B comes to $191 a month, 78% below the $873 median of the 101 models we track. It ranks #18 of 101 on cost, where #1 is the cheapest.
It scores 143.7 on the Epoch Capabilities Index (#60 of 66). Among the 8 other models within 2 points, 3 cost less, and it costs 16% less than their median ($227). The cheapest stable-priced model that scores at least as high is Qwen3.7 Flash (144.1) at $31.74 a month, 83% less.
Cached input is 50% cheaper than fresh input, a smaller discount than the 90% median. The weights are open, so other hosts can serve it and prices may differ from the provider's own.
Technical specifications
- Context window
- 262K tokens
- Input price
- $0.100 / 1M
- Cached input price
- $0.050 / 1M
- Output price
- $0.950 / 1M
- Cache discount
- 50%
- Batch API
- Not listed
- Open weights
- Yes
- Release date
- Apr 14, 2026
- Price volatility
- Stable
Benchmarks
Best score for this model on each leaderboard, ranked against the other models listed there.
Your monthly bill
Standard
$191 / month- Input
- $36.00
- Cached input
- $12.00
- Output
- $142.50
Batch
No batch rates are listed for this model.
Price history
- Oct 20, 2026Input $0.150 → $0.100▼ 33%
- Oct 20, 2026Output $1.00 → $0.950▼ 5%
- Oct 15, 2026Input $0.100 → $0.150▲ 50%
- Oct 15, 2026Output $0.950 → $1.00▲ 5%
- Oct 15, 2026Cached input $0.100 → $0.050▼ 50%
- Oct 11, 2026Input $0.150 → $0.100▼ 33%
- Oct 11, 2026Output $1.00 → $0.950▼ 5%
- Oct 11, 2026Cached input $0.050 → $0.100▲ 100%
- Sep 21, 2026Input $0.100 → $0.150▲ 50%
- Sep 21, 2026Output $0.900 → $1.00▲ 11%
Cheaper alternatives
Models with stable pricing and a Epoch Capabilities Index within 2 points of Qwen3.6 35B A3B (or higher) that cost less for the default workload.
