Costs less than most peers
Maker's price: $1.10 blended / 1M, cheaper than 6 of 9 priced peers.
Alibaba · Chat
Qwen3.5 122B-A10B is a multimodal reasoning model with 256K context, efficient sparse MoE inference, and text, image, and video input.
Evidence and sources
International storefront (alibabacloud.com) is Singapore-incorporated; mainland operating entity 杭州阿里云智能科技有限公司 (Hangzhou).
Maker's price: $1.10 blended / 1M, cheaper than 6 of 9 priced peers.
The weights are public. 2 of the 9 peers that say either way have open weights.
Supported operations and provider-stated features
| 262K | $0.40 | $3.20 | |
| 262K | $0.1126 | $0.9008 | |
| 258K | $0.115>128k $0.287 | $0.917>128k $2.294 | |
| 131K | $0.115cache read $0.023 | $0.917 | |
| 262K | $0.115 | $0.917 | |
| —Not published by the provider | |||
| 262K | |||
| 262K | $0.1196 | $0.9565 | |
| 992K | $0.12 | $0.92 | |
| 262K | $0.22 | $2.20 |
Showing 10 of 50: the maker's own listing first, then the cheapest per 1M input tokens from each provider.
Also sold by Atlascloud, Databricks, DeepInfra, Eurouter, Flowdot, Gmicloud, Hugging Face, Infomaniak, Jalapeno, Kilo, Libertai, Llmgateway, Llmgateway Providers, Mixlayer, NanoGPT, Nous Portal, Novita AI, Ofox, OpenRouter, SiliconFlow, Tensorx, Thalam, Watt.
5 listings without a price are hidden.
These providers advertise this model. Researchers have found some resellers serving a different, cheaper model, so see how to check whether a provider meets your needs.
Named effort levels run from lowest to highest. Select a result to see its source details.
| Benchmark | Score |
|---|---|
| Arena ELO | |
| Chinese | |
| Creative Writing | |
| English |
| Benchmark | w. sub @ 64, instruct | wo sub @ 64, instruct |
|---|---|---|
| Video-MME-v2 | ||
| Avg Acc | ||
| Capability Consistency | ||
| Level 1 |
| Benchmark | w. sub @ 64, instruct | wo sub @ 64, instruct |
|---|---|---|
| Level 2 | ||
| Level 3 | ||
| Reasoning Coherence |
| Benchmark | Score |
|---|---|
| AISG SEA-HELM | |
| (Burmese) | |
| (English) | |
| (Filipino) |
| Benchmark | Score |
|---|---|
| (Indonesian) | |
| (Malay) | |
| (Tamil) | |
| (Thai) | |
| (Vietnamese) |
| Benchmark | qwen3.5-122b-a10b |
|---|---|
| 4: ALT_환각방지 | |
| 4 subset: haerae_bench_v1_rc | |
| 4 subset: haerae_bench_v1_wo_rc | |
| 4 subset: hrm8k |
Data credits: Data by LLM Stats · SEA-HELM leaderboard, AI Singapore (AI Products team), National University of Singapore. Published aggregate scores; results licence not stated (SEA-HELM code is MIT). · LMArena, CC BY 4.0 (licence) · Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · OpenEvals/leaderboard-data, MIT (licence) · OpenRouter public benchmark leaderboard and search-lane exports, CC BY 4.0. Fractional source scores converted to percentages; immutable dated snapshots. (licence) · Horangi 4, Weights & Biases Korea; public publisher-selected numeric evaluation results · Hugging Face official benchmark leaderboards; licence varies by benchmark · JMLE2026-Bench and IgakuQA119 by Naoto Iwase; results licence not stated (code MIT, question data CC BY 4.0). · EQ-Bench (Samuel J. Paech) — cite paech2023eqbench · Nejumi Leaderboard 4, Weights & Biases Japan; public publisher-selected numeric evaluation results · Shaberi v2.1, Shisa.AI, Apache-2.0. GPT-5.1-judge scores only; judges are not comparable. (licence) · SnakeBench (Greg Kamradt / ARC Prize Foundation), MIT (licence) · Swallow LLM Leaderboard v2, Swallow LLM team (Institute of Science Tokyo). Contents CC BY 4.0; Japanese post-trained task scores on the source's 0..1 scale. (licence) · UzLiB, Tahrirchi (Abror Shopulatov). Public LEADERBOARD.md numbers; repository MIT covers software and documentation, no separate results licence stated and none asserted. · Vectara Hallucination Leaderboard, Apache-2.0 (licence)
Also known as: aihubmix/qwen3.5-122b-a10b, alibaba/qwen3.5-122b-a10b, bailian/qwen3.5-122b-a10b, databricks/databricks-qwen35-122b-a10b, deepinfra/qwen/qwen3.5-122b-a10b, empiriolabs/qwen3-5-122b-a10b, gmi/qwen/qwen3.5-122b-a10b, libertai/qwen3.5-122b-a10b, libertai/qwen3.5-122b-a10b-thinking, novita/qwen/qwen3.5-122b-a10b, novita/qwen3.5-122b-a10b, qwen/qwen3.5-122b-a10b, qwen/qwen3.5-122b-a10b-fp8, qwen/qwen3.5-122b-a10b:thinking, qwen3-5-122b-a10b, qwen35-122b-a10b
Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works