Start free trial

Qwen: Qwen3.5-122B-A10B

qwen/qwen3-5-122b-a10b
CompareAPITry this model

The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency.

Modalities
In / out per 1M$0.26 / $2.08
Context256K
ReleasedFeb 25, 2026

Providers

4 providers serve this model upstream.

Providers serving this model
ProviderInput /MOutput /MCache read /MLatency P50Throughput P50Uptime
Alibaba Cloud Int.$0.26$2.08Variable0.55s108 tps99.67%
NovitaAIbf16$0.40$3.20Variable1.20s102 tps95.48%
SiliconFlowfp8$0.26$2.08Variable1.23s62 tps87.02%
AtlasCloudfp8$0.30$2.40$0.301.15s96 tps80.65%

Market-wide measurements, refreshed every 15 minutes. They describe who serves Qwen3.5-122B-A10B in general, not how ProjectCOZY routes your requests.

Pricing

List rates per 1M tokens — what Qwen3.5-122B-A10B costs pay-as-you-go elsewhere, not what you pay here.

Input
$0.26
per 1M tokens
Output
$2.08
per 1M tokens
Cache read
—
not published
Included in every pass
Qwen3.5-122B-A10B 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 AM
Alibaba Cloud Int. NovitaAI SiliconFlow AtlasCloud
0 tok/s200 tok/s400 tok/s600 tok/s800 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 AM
Alibaba Cloud Int. NovitaAI SiliconFlow AtlasCloud

Uptime

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

Last 3 daysAvailability 98.4%
Oct 29, 6:00 PMNow
Availability over the last 24 hoursAvailability 95.86%
100% 78% 56% 35%
Oct 31, 6:10 PMNow

Apps

Tools that most often run Qwen3.5-122B-A10B, by tokens this week.

Hermes AgentPersonal Agent · 35.6% of tokens965.8MpiCli Agent · 25.1% of tokens680.0MDeepSeek Harness17.9% of tokens484.6MMaterials Design Agents12.2% of tokens332.2MCodexCli Agent · 9.2% of tokens249.4M

Activity

40.0B tokens processed market-wide in the last month.

01.0B2.0B3.0B4.0B
Oct 2Oct 7Oct 12Oct 17Oct 22Oct 27Nov 1
Tokens

FAQ

Which model id do I use for Qwen3.5-122B-A10B?
qwen/qwen3.5-122b-a10b. Send it as the model field from any OpenAI-compatible client, against https://minuykh.app/v1.
How much context does Qwen3.5-122B-A10B hold?
262,144 tokens per request, of which up to 65,536 can be the response.
What can it accept and return?
Input: text, image, video. Output: text.
What does Qwen3.5-122B-A10B cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $0.26 per 1M input tokens and $2.08 per 1M output tokens.
Who built Qwen3.5-122B-A10B?
Qwen, in the Qwen3.5 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