Context
262K
Max output
262K
Serving providers
9
Cheapest input
$0.05 /1M
On-demand listed rates, OpenRouter routed quotes and Vercel reseller quotes. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.
Benchmarks
independent evaluations · source: Artificial Analysis and Hugging Face leaderboardsSpeed & latency
Output speed
133 t/s
tokens / second
Time to first token
2.06s
latency
Headline indices
Individual benchmarks · click a row for effort variants
| Benchmark | Best score | Effort | Cost / task | |||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| AIME 2026 | 93% | default | — | |||||||||||||||||||||||||||||
| Automation Bench | 0.1 | default | — | |||||||||||||||||||||||||||||
| CritPt | 0% | default | — | |||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||
| EvalComputeProxyFrozen Aug 18, 2026 | 336.1 | reasoning: false | — | |||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||
| GDPval v2Frozen Aug 18, 2026 | 1055.3 | default | — | |||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||
| GPQA Diamond | 84% | default | — | |||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||
| Humanity's Last Exam | 22% | default | — | |||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||
| IFBench | 64% | default | — | |||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||
| Long-Context Reasoning | 72% | default | — | |||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||
| MMMU-Pro | 75% | default | — | |||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||
| Omniscience | -22.2 | default | — | |||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||
| Omniscience Accuracy | 0.2 | default | — | |||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||
| Omniscience Non Hallucination | 0.5 | default | — | |||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||
| SciCode | 37% | default | — | |||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||
| SWE-bench Pro | 50% | default | — | |||||||||||||||||||||||||||||
| SWE-bench Verified | 73% | default | — | |||||||||||||||||||||||||||||
| Terminal Bench40 | 0 | default | — | |||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||
| TerminalBench Hard | 35% | default | — | |||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||
| TerminalBench v2.1 | 45% | default | — | |||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||
| τ-bench Banking | 9% | default | — | |||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||
| τ²-bench | 95% | default | — | |||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||
Artificial Analysis last published scores for this benchmark on Sep 9, 2026. Scores here are frozen at that date, and models released since are not on it.
Artificial Analysis last published scores for this benchmark on Aug 18, 2026. Scores here are frozen at that date, and models released since are not on it.
Pricing by serving provider
standard tier · per 1M tokens · click a provider to expandInput pricing runs from $0.05 to $0.254 per 1M tokens across 9 providers, so the dearest route costs 408% more than the cheapest for the same model.
| Serving provider | Input /1M | Output /1M | Endpoints | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| SailCheapest | $0.05 | $0.40 | 1 | |||||||||||||
Standardsail/Qwen/Qwen3.6-35B-A3B
| ||||||||||||||||
| DeepInfra | $0.10 | $0.95 | 1 | |||||||||||||
Standarddeepinfra/Qwen/Qwen3.6-35B-A3B
| ||||||||||||||||
| OpenRouter | $0.10 | $0.95 | 1 | |||||||||||||
Standardqwen/qwen3.6-35b-a3b
| ||||||||||||||||
| Pinstripes | $0.14 | $0.45 | 1 | |||||||||||||
Standardpinstripes/ps/qwen3.6-35b-a3b
| ||||||||||||||||
| Libertai | $0.15 | $0.50 | 1 | |||||||||||||
Standardlibertai/qwen3.6-35b-a3b
| ||||||||||||||||
| Novita | $0.248 | $1.49 | 1 | |||||||||||||
Standardnovita/qwen/qwen3.6-35b-a3b
| ||||||||||||||||
| Scaleway | $0.25 | $1.50 | 1 | |||||||||||||
Standardscaleway/qwen/qwen3.6-35b-a3b
| ||||||||||||||||
| Wandb | $0.25 | $1.25 | 1 | |||||||||||||
Standardwandb/Qwen/Qwen3.6-35B-A3B
| ||||||||||||||||
| Aihubmix is dearest at $0.254 / $1.52 | ||||||||||||||||
Price history
listed seller prices, input and output per 1M tokens Input Output
Input down 80% since first tracked
Cost calculator
estimate your monthly spend on this model$42
estimated / month
Model IDs
copy the exact identifier for your platformsail/Qwen/Qwen3.6-35B-A3Bdeepinfra/Qwen/Qwen3.6-35B-A3Bqwen/qwen3.6-35b-a3bpinstripes/ps/qwen3.6-35b-a3blibertai/qwen3.6-35b-a3bnovita/qwen/qwen3.6-35b-a3bscaleway/qwen/qwen3.6-35b-a3bwandb/Qwen/Qwen3.6-35B-A3Baihubmix/qwen3.6-35b-a3b
Frequently asked questions
Qwen3.6 35B A3B pricing, context and availabilityHow much does Qwen3.6 35B A3B cost?
Qwen3.6 35B A3B costs $0.05 per 1M input tokens from Sail, and $0.40 per 1M output tokens from Sail. Across 9 serving providers, input prices range from $0.05 to $0.254 per 1M tokens.
What is the context window of Qwen3.6 35B A3B?
Qwen3.6 35B A3B accepts up to 262K tokens of context and can return up to 262K output tokens.
Which providers serve Qwen3.6 35B A3B?
Qwen3.6 35B A3B is available from 9 serving providers, each with its own pricing and model ID. Sail is currently the cheapest.
What can Qwen3.6 35B A3B do?
Qwen3.6 35B A3B supports image input (vision), tool use, reasoning, prompt caching, structured output and web search.
Other Alibaba models
compare pricing across the Alibaba lineupQwen3 Next 80B A3B Instruct$0.09/1M · 11 providersQwen3 32B$0.08/1M · 10 providersQwen3 Next 80B A3B Thinking$0.14/1M · 10 providersQwen3.8 Max$1.65/1M · 10 providersQwen3 VL 235B A22B Instruct$0.20/1M · 9 providersQwen2.5 Coder 32B Instruct$0.05/1M · 8 providersQwen3 235B A22b Instruct 2507$0.09/1M · 8 providersQwen3.6 27B$0.15/1M · 8 providers
Listed prices from LiteLLM, OpenRouter and Vercel · last checked Oct 14, 2026
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI