Start free trial

Qwen: Qwen3.6 35B A3B

qwen/qwen3-6-35b-a3b
CompareAPITry this model

Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token.

Modalities
In / out per 1M$0.10 / $0.90
Context256K
ReleasedApr 27, 2026

Providers

11 providers serve this model upstream.

Providers serving this model
ProviderInput /MOutput /MCache read /MLatency P50Throughput P50Uptime
Parasailfp8$0.10$0.90$0.030.56s99 tps100%
CoreWeavefp8$0.10$0.95$0.050.60s127 tps100%
AkashMLfp8$0.10$0.90$0.050.84s56 tps100%
Prime Intellectfp8$0.03$0.26$0.031.11s73 tps100%
DekaLLM$0.10$1.00$0.050.71s129 tps99.97%
Phala$0.20$1.27$0.060.68s156 tps99.82%
Darkbloomfp4$0.05$0.70$0.030.80s62 tps98.63%
DeepInfraus · fp8$0.10$0.95$0.100.67s116 tps98.06%
SiliconFlowfp8$0.24$1.80$0.151.29s33 tps93.48%
Venicefp8$0.10$1.00Variable0.70s77 tps91%
AtlasCloudfp8$0.25$1.25$0.250.41s115 tps85.89%

Market-wide measurements, refreshed every 15 minutes. They describe who serves Qwen3.6 35B A3B in general, not how ProjectCOZY routes your requests.

Pricing

List rates per 1M tokens — what Qwen3.6 35B A3B costs pay-as-you-go elsewhere, not what you pay here.

Input
$0.10
per 1M tokens
Output
$0.90
per 1M tokens
Cache read
$0.03
per 1M cached tokens
Included in every pass
Qwen3.6 35B A3B is included in every ProjectCOZY pass at no extra cost — one flat rate, no per-token metering. The rates above are there for comparison.

Performance

Time to first token and output speed across every provider, over the last 3 days.

0.0s5.0s10.0s15.0s20.0s
Oct 29, 12 AMOct 29, 8 AMOct 29, 4 PMOct 30, 12 AMOct 30, 8 AMOct 30, 4 PMOct 31, 12 AMOct 31, 8 AMOct 31, 4 PMNov 1, 12 AMNov 1, 8 AMNov 1, 4 PM
Darkbloom DeepInfra (us) Parasail Phala CoreWeave DekaLLM SiliconFlow AkashML Venice AtlasCloud Prime Intellect
0 tok/s250 tok/s500 tok/s750 tok/s1000 tok/s
Oct 29, 12 AMOct 29, 8 AMOct 29, 4 PMOct 30, 12 AMOct 30, 8 AMOct 30, 4 PMOct 31, 12 AMOct 31, 8 AMOct 31, 4 PMNov 1, 12 AMNov 1, 8 AMNov 1, 4 PM
Darkbloom DeepInfra (us) Parasail Phala CoreWeave DekaLLM SiliconFlow AkashML Venice AtlasCloud

Uptime

100% of requests were served successfully over the last 3 days, across all providers.

Last 3 daysAvailability 99.9%
Oct 29, 6:00 PMNow
Availability over the last 24 hoursAvailability 99.85%
100% 98% 97% 95%
Oct 31, 6:10 PMNow

Apps

Tools that most often run Qwen3.6 35B A3B, by tokens this week.

Portkey AIProgramming App · 33.8% of tokens32.5BSekai Agent33.2% of tokens31.9BSekai14.8% of tokens14.2BClaude CodeCli Agent · 9.2% of tokens8.8Bmarl commit0 rollouts8.9% of tokens8.5B

Activity

1348.9B tokens processed market-wide in the last month.

0100.0B200.0B300.0B400.0B
Oct 2Oct 7Oct 12Oct 17Oct 22Oct 27Nov 1
Tokens

FAQ

Which model id do I use for Qwen3.6 35B A3B?
qwen/qwen3.6-35b-a3b. Send it as the model field from any OpenAI-compatible client, against https://minuykh.app/v1.
How much context does Qwen3.6 35B A3B hold?
262,144 tokens per request, of which up to 235,929 can be the response.
What can it accept and return?
Input: text, image, video. Output: text.
What does Qwen3.6 35B A3B cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $0.10 per 1M input tokens and $0.90 per 1M output tokens.
Who built Qwen3.6 35B A3B?
Qwen, in the Qwen3.6 family.

Explore

Other models your pass can call.

Aion 3.5aion-labs/aion-3.5256KAionAion 3.5 Miniaion-labs/aion-3.5-mini256KAionAion-2.0aion-labs/aion-2.0128KAionAion-3.0aion-labs/aion-3.0128KAionAion-3.0-Miniaion-labs/aion-3.0-mini128KAionAion-RP 1.0 (8B)aion-labs/aion-rp-llama-3.1-8b32KAion