Qwen3.5-122B-A10B API Benchmarks, Pricing & Provider Data
Compare Qwen3.5-122B-A10B with another model
Choose a model to open its comparison page.
Qwen3.5-122B-A10B benchmark, API pricing, and provider data cover undefined API provider} other undefined API providers}}, with prices starting at $0.055/M.
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 eff...
Category Performance
Observed-capability estimates with uncertainty reported separately from independent benchmark families.
- Coverage
- 7 / 8
- Methodology
- V3.0
#1Instruction following54.3Estimated2/4 Measured dimensions
#2Reasoning53.2RatedGlobal rank #313/4 Measured dimensions
#3Multimodal47.6Estimated3/4 Measured dimensions
#4Agents47.3Estimated2/4 Measured dimensions
#5Coding46Estimated2/4 Measured dimensions
#6Multilingual45.4Provisional1/4 Measured dimensions
#7Knowledge43.7Provisional1/4 Measured dimensions
Specifications
Input and output token limits for this model, plus how it ranks on long-context understanding.
Features
Technical Details
- Input
- Output
- Total parameters
- 122B
- Active parameters
- 10B
- Released
- Feb 2026
- Tokenizer
- Qwen3
- Architecture
- text+image+video->text
- Moderated
- No
- Supported parameters
- frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Rankings
Excels at
It's decent at
Falls behind in
Detailed scores
Updated: Sep 13, 2026Overall
undefined metric} other undefined metrics}}
Overall score49.0#87 / 112
Overall
undefined metric} other undefined metrics}}
Speed & latency
undefined metric} other undefined metrics}}
Output speed148.2 tok/s#26 / 80Time to first token1.02 s#30 / 80
Speed & latency
undefined metric} other undefined metrics}}
Pricing
undefined metric} other undefined metrics}}
Input price$0.400/M#75 / 186Output price$3.20/M#105 / 186
Pricing
undefined metric} other undefined metrics}}
Agents
V3.0undefined metric} other undefined metrics}} · Estimated
Score47.380% interval36.7–57.92/4 Measured dimensionsAgentic score24.9#71 / 77Terminal-Bench 2.049.4#46 / 53
Agents
V3.0undefined metric} other undefined metrics}} · Estimated
Coding
V3.0undefined metric} other undefined metrics}} · Estimated
Score4680% interval34.2–57.82/4 Measured dimensionsSciCode39.7%#62 / 89Coding score51.1#53 / 87
Coding
V3.0undefined metric} other undefined metrics}} · Estimated
Reasoning
V3.0undefined metric} other undefined metrics}} · Rated
Score53.2#3180% interval44.9–61.53/4 Measured dimensionsMMLU-Pro86.7%#15 / 129GPQA82.7%#83 / 218
Reasoning
V3.0undefined metric} other undefined metrics}} · Rated
Knowledge
V3.0undefined metric} other undefined metrics}} · Provisional
Score43.780% interval27.4–60.01/4 Measured dimensionsKnowledge score73.2#31 / 83SuperGPQA67.1#10 / 16
Knowledge
V3.0undefined metric} other undefined metrics}} · Provisional
Math
V3.0undefined metric} other undefined metrics}} · No data
No data80% interval30.8–69.20/4 Measured dimensions
Math
V3.0undefined metric} other undefined metrics}} · No data
Multilingual
V3.0undefined metric} other undefined metrics}} · Provisional
Score45.480% interval29.0–61.91/4 Measured dimensionsMultilingual score36.8#8 / 11MMLU-ProX82.2#8 / 11
Multilingual
V3.0undefined metric} other undefined metrics}} · Provisional
Multimodal
V3.0undefined metric} other undefined metrics}} · Estimated
Score47.680% interval38.2–57.03/4 Measured dimensionsMultimodal Grounded score57.0#42 / 56MMMU83.9#2 / 7
Multimodal
V3.0undefined metric} other undefined metrics}} · Estimated
Instruction following
V3.0undefined metric} other undefined metrics}} · Estimated
Score54.380% interval42.4–66.22/4 Measured dimensionsInstruction Following score93.0#7 / 52IFEval93.4#7 / 16
Instruction following
V3.0undefined metric} other undefined metrics}} · Estimated
OpenRouter endpoints
5 endpointsThird-party OpenRouter endpoint data, shown separately from LMSpeed measurements. Some 30-minute live performance fields only appear after syncing with an OpenRouter API key.
| Provider endpoint | Input | Output | 1d uptime | 30m latency | 30m throughput | Context / output |
|---|---|---|---|---|---|---|
DeepInfra deepinfra/fp4 | $0.290/M | $2.40/M | 99.3% | — | — | undefined tokens / undefined tokens |
Novita novita/bf16 | $0.400/M | $3.20/M | 99.2% | — | — | undefined tokens / undefined tokens |
SiliconFlow siliconflow/fp8 | $0.260/M | $2.08/M | 98.9% | — | — | undefined tokens / undefined tokens |
AtlasCloud atlas-cloud/fp8 | $0.300/M | $2.40/M | 98.8% | — | — | undefined tokens / undefined tokens |
Alibaba alibaba | $0.260/M | $2.08/M | 96.9% | — | — | undefined tokens / undefined tokens |
Pricing Comparison
Compare Qwen3.5-122B-A10B API pricing across 19 providers. Prices range from $0.055/M to $77.05/M. Zhongzhuan Chat offers the lowest rate at $0.055/M.
| Provider | Health | Model Variant | Group | Input ($/M) | Output ($/M) | Speed (t/s) | First token | Audit |
|---|---|---|---|---|---|---|---|---|
L1 100% | Qwen/Qwen3.5-122B-A10B | default | $10.27/M | $10.27/M | — | — | — | |
L1 99% L2 84% | Qwen/Qwen3.5-122B-A10B | diamond-glm | -53%$0.190/M | -53%$1.52/M | — | — | — | |
L1 99% L2 100% | qwen3.5-122b-a10b | alibaba | $0.759/M | $6.07/M | — | — | — | |
L1 100% | qwen3.5-122b-a10b | Alibaba-1 | -85%$0.059/M | -85%$0.474/M | — | — | — | |
L1 100% | qwen3.5-122b-a10b | default | $10.27/M | $10.27/M | — | — | — | |
L1 99% | qwen3.5-122b-a10b | Alibaba-1 | -85%$0.059/M | -85%$0.474/M | — | — | — | |
L1 100% | qwen3.5-122b-a10b | default | -86%$0.055/M | -86%$0.438/M | — | — | — |
Alternatives & Similar Models
GPT-5.4
gpt-5-4
OpenAI GPT-5.4 extends the GPT-5 family with stronger instruction following, deeper tool use, and improved performance on coding, math, and long-document analysis.
DeepSeek V4 Flash
deepseek-v4-flash
DeepSeek V4 Flash is a fast, cost-efficient language model in the DeepSeek V4 family, optimized for low-latency chat, coding assistance, and high-throughput API workloads while retaining strong reasoning quality.
DeepSeek V4 Pro
deepseek-v4-pro
DeepSeek V4 Pro is the professional-tier DeepSeek V4 model, targeting frontier reasoning, coding, and agent workflows with maximum capability.
GLM-5.1
glm-5-1
Zhipu GLM-5.1 is a next-generation GLM model aimed at frontier reasoning, coding, and bilingual agent applications.
Kimi K2.5
kimi-k2-5
Moonshot Kimi K2.5 is an open-weight multimodal agent model with native vision and text input, strong coding performance, and a 256K context window.
GLM-5
glm-5
Zhipu GLM-5 is Zhipu flagship GLM series model with enhanced reasoning, agent capabilities, and strong performance on Chinese enterprise and coding scenarios.
Frequently Asked Questions
- What benchmark data does Qwen3.5-122B-A10B include?
- LMSpeed shows Qwen3.5-122B-A10B benchmark context, API price, output speed, first-token latency, and provider data across 19 providers when those signals are available.
- What is the Qwen3.5-122B-A10B API price?
- Qwen3.5-122B-A10B has pricing from undefined provider} other undefined providers}}, ranging from $0.055/M to $77.05/M. Zhongzhuan Chat has the lowest listed price.
- What does the Qwen3.5-122B-A10B API pricing table include?
- The Qwen3.5-122B-A10B API pricing table compares 19 providers by input price, output price, free tier status, speed, first-token latency, and recent health data when available.
- Which provider has the cheapest Qwen3.5-122B-A10B API pricing?
- Zhongzhuan Chat currently has the lowest listed Qwen3.5-122B-A10B price at $0.055/M across undefined provider} other undefined providers}}.
- Is Qwen3.5-122B-A10B API free?
- Qwen3.5-122B-A10B does not currently have a free API tier on LMSpeed. All 19 providers charge per token.