Context
262K
Max output
66K
Serving providers
1
Cheapest input
$0.25 /1M
Prices are on-demand list rates. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.

Benchmarks

independent evaluations · source: Artificial Analysis
Speed & latency
Output speed
150 t/s
tokens / second
Time to first token
15.14s
latency
Headline indices
Individual benchmarks · click a row for effort variants
BenchmarkBest scoreEffortCost / task
CritPt1%default
EvalComputeProxy106.3reasoning: false
GDPval805.2reasoning: false
GPQA Diamond85%default
Humanity's Last Exam20%default
IFBench73%default
IT-Bench SRE22%default
Long-Context Reasoning63%default
MMMU-Pro73%default
Omniscience-46.4default
SciCode38%default
TerminalBench Hard27%default
τ²-bench89%default

Pricing by serving provider

standard tier · per 1M tokens · click a provider to expand
Serving providerInput /1MOutput /1MEndpoints
OpenRouterCheapest$0.25$2.001
ComponentUnitStandardBatchCached
Text input/1M tok$0.2500
Text output/1M tok$2.00

Price history

input + output $/1M since we started tracking
Input Output
$0.000$0.500$1.00$1.50$2.00Mar 9Jun 22$2.00$0.250

Cost calculator

estimate your monthly spend on this model
$210
estimated / month

Model IDs

copy the exact identifier for your platform
openrouter/qwen/qwen3.5-35b-a3b

Frequently asked questions

Qwen3.5-35B-A3B pricing, context and availability

How much does Qwen3.5-35B-A3B cost?

Qwen3.5-35B-A3B costs $0.25 per 1M input tokens and $2.00 per 1M output tokens at its cheapest provider via OpenRouter.

What is the context window of Qwen3.5-35B-A3B?

Qwen3.5-35B-A3B accepts up to 262K tokens of context and can return up to 66K output tokens.

What can Qwen3.5-35B-A3B do?

Qwen3.5-35B-A3B supports image input (vision), tool use and reasoning.

Other Alibaba models

compare pricing across the Alibaba lineup
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI