Alibaba (Qwen)

Qwen3.6 35B-A3B

Type
language model
Context
262K tokens
Max output
33K
Released
17 April 2026
API string
qwen3.6-35b-a3b
Weights
open

Prices by provider

Provider Input, $ per 1M Output, $ per 1M In our data since
EmpirioLabs AI $0.07 $0.42 31 Jul 2026
DeepInfra $0.1 $0.95 31 Jul 2026
Venice AI $0.1 $1 31 Jul 2026
NanoGPT $0.112 $0.8 31 Jul 2026
pinstripes $0.14 $0.45 31 Jul 2026
OpenRouter $0.14 $1 31 Jul 2026
Pioneer $0.14 $1 31 Jul 2026
libertai $0.15 $0.5 31 Jul 2026
Hugging Face $0.15 $0.95 31 Jul 2026
Kilo Code $0.161 $0.965 31 Jul 2026
NEAR AI $0.17 $1.1 31 Jul 2026
zenifra $0.19 $0.48 31 Jul 2026
SiliconFlow $0.2 $1.6 31 Jul 2026
siliconflow-cn $0.23 $1.86 31 Jul 2026
Alibaba (Qwen) $0.248 $1.485 31 Jul 2026
LLM Gateway $0.248 $1.485 31 Jul 2026
Merge Gateway $0.248 $1.485 31 Jul 2026
OrcaRouter $0.248 $1.485 31 Jul 2026
Scaleway $0.25 $1.5 31 Jul 2026
Weights & Biases $0.25 $1.25 31 Jul 2026
neuralwatt $0.29 $1.15 31 Jul 2026
greenpt $0.342 $2.052 31 Jul 2026
evroc $0.345 $1.38 31 Jul 2026

Only the base tier and only per-token prices are shown. Batch, discounted and cached rates, as well as prices per image or per second of video, do not go into this table: they cannot stand in the same column as a price per million tokens.

The date in the last column is the day this price first entered our collection. The price may well be older: before that day we simply were not recording it. It has not changed since — otherwise a new row with a new date would stand in its place.

Measurement results

Task set Result Run conditions Measured by
WeirdML — unusual machine learning tasks 34.49 % https://htihle.github.io/weirdml.html
Terminal-Bench — working in the command line 24.6 % · with a tuned harness https://www.tbench.ai/leaderboard/terminal-bench/2.0
CritPt — physics problems 0.29 %