Alibaba Cloud: Models Intelligence, Performance & Price

Name: Intelligence
Creator: Artificial Analysis
License: https://artificialanalysis.ai/docs/legal/Terms-of-Use.pdf

Alibaba Cloud

Analysis of Alibaba Cloud's models across key metrics including quality, price, output speed, latency, context window & more. This analysis is intended to support you in choosing the best model provided by Alibaba Cloud for your use-case.

Most Intelligent

Updated

Qwen3.7 Max

Qwen3.6 Max Preview

Qwen3.6 Plus

Qwen3.7 Plus

Qwen3.6 27B

Intelligence index

Total 50 models

Fastest

Qwen3.5 Omni Flash

252 t/s

Qwen3.7 Max

205 t/s

Qwen3 Next 80B A3B

186 t/s

Qwen3 Next 80B A3B

185 t/s

Qwen3.6 35B A3B

172 t/s

Output speed

Total 50 models

Lowest Price

Qwen2.5 Turbo

$0.07

Qwen3.5 Omni Flash

$0.17

Qwen3 VL 8B

$0.23

Qwen3 8B

$0.23

Qwen3 VL 30B A3B

$0.26

Blended price (per 1M tokens)

Total 50 models

Indicates a reasoning model

Alibaba Cloud offers 50 models, each with different intelligence, performance, and pricing characteristics. Below is a comparison of the key metrics across models.

For intelligence, the top models on Alibaba Cloud are Qwen3.7 Max (46), Qwen3.6 Max Preview (40), Qwen3.6 Plus (40).
For output speed, the fastest models are Qwen3.5 Omni Flash (252 t/s), Qwen3.7 Max (205 t/s), Qwen3 Next 80B A3B (186 t/s).
For latency, Qwen3.5 Omni Flash (1.81s), Qwen3 30B A3B 2507 (1.84s), Qwen3 Omni 30B A3B (1.89s) offer the lowest time to first token.
For pricing, Qwen2.5 Turbo ($0.07), Qwen3.5 Omni Flash ($0.17), Qwen3 VL 8B ($0.23) offer the lowest blended prices per 1M tokens. Prices vary up to 4.0x across models.
For context window size, Qwen3.6 Plus (1M), Qwen3.7 Plus (1M), Qwen2.5 Turbo (1M) support the largest context windows on Alibaba Cloud.

Highlights

Updated

Intelligence

Artificial Analysis Intelligence Index · Higher is better

Speed

Output tokens per second · Higher is better

Price

USD per 1M tokens (blended) · Lower is better

Intelligence Evaluations

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v4.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR

Estimate (independent evaluation forthcoming)

Reasoning models are indicated by a lightbulb icon

Artificial Analysis Intelligence Index v4.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Intelligence Evaluations

Intelligence evaluations measured independently by Artificial Analysis · Higher is better

GDPval-AA v2

Agentic real-world work tasks, (Elo-500)/2000

𝜏³-Banking

Agentic tool use

Terminal-Bench v2.1

Agentic coding & terminal use

SciCode

Coding

Humanity's Last Exam

Reasoning & knowledge

GPQA Diamond

Scientific reasoning

CritPt

Physics reasoning

AA-Omniscience Accuracy

Knowledge

AA-Omniscience Non-Hallucination Rate

1 - hallucination rate

AA-LCR

Long context reasoning

AA-BriefcaseNew

Agentic knowledge work, Elo

AutomationBench-AANew

Agentic SaaS workflows

Harvey LAB-AANew

Legal agentic work, task all-pass rate

EnterpriseOps-Gym-AANew

Agentic business operations

IFBench

Instruction following

APEX-Agents-AA

Long-horizon agentic tasks

ITBench-AA

Kubernetes incident root-cause analysis

MMMU-Pro

Visual reasoning

Reasoning models are indicated by a lightbulb icon.

While model intelligence generally translates across use cases, specific evaluations may be more relevant for certain use cases.

Intelligence vs. Price

Blended at 7:2:1 (cache-input-output) · USD per 1M tokens (blended)

Most attractive quadrant

Reasoning models are indicated by a lightbulb icon.

While higher intelligence models are typically more expensive, they do not all follow the same price-quality curve.

Price per token, shown in USD per million tokens. Price is a blend of cache hit, input, and output token prices using the selected ratio (default 7:2:1 cache-input-output).

The blended cache price shown here uses cache hit price only. Other caching costs differ by provider:

Anthropic: charges a separate cache write fee, with different rates for 5-minute and 1-hour TTLs (1-hour TTL is more expensive).
Google (Vertex/Gemini): charges a per-hour cache storage fee in addition to cache hit pricing. Some providers also use tiered pricing for prompts above 200K tokens.
OpenAI, DeepSeek, others: typically charge only cache hit pricing with no write or storage fee.

See Prompt Caching for the full breakdown.

Figures represent performance of the model's first-party API (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).

Context Window

Context window: tokens limit · Higher is better

Reasoning models are indicated by a lightbulb icon

Larger context windows are relevant to RAG (Retrieval Augmented Generation) LLM workflows which typically involve reasoning and information retrieval of large amounts of data.

Maximum number of combined input & output tokens. Output tokens commonly have a significantly lower limit (varied by model).

Pricing

Intelligence vs. Price

Blended at 7:2:1 (cache-input-output) · USD per 1M tokens (blended)

Most attractive quadrant

Reasoning models are indicated by a lightbulb icon.

While higher intelligence models are typically more expensive, they do not all follow the same price-quality curve.

Price per token, shown in USD per million tokens. Price is a blend of cache hit, input, and output token prices using the selected ratio (default 7:2:1 cache-input-output).

The blended cache price shown here uses cache hit price only. Other caching costs differ by provider:

Anthropic: charges a separate cache write fee, with different rates for 5-minute and 1-hour TTLs (1-hour TTL is more expensive).
Google (Vertex/Gemini): charges a per-hour cache storage fee in addition to cache hit pricing. Some providers also use tiered pricing for prompts above 200K tokens.
OpenAI, DeepSeek, others: typically charge only cache hit pricing with no write or storage fee.

See Prompt Caching for the full breakdown.

Figures represent performance of the model's first-party API (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).

Performance Summary

Output Speed vs. Price

Output speed: output tokens per second · USD per 1M tokens (blended)

Most attractive quadrant

Reasoning models are indicated by a lightbulb icon.

Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).

Price per token, shown in USD per million tokens. Price is a blend of cache hit, input, and output token prices using the selected ratio (default 7:2:1 cache-input-output).

Speed

Measured by Output Speed (tokens per second)

Output Speed

Output tokens per second · Higher is better

Reasoning models are indicated by a lightbulb icon

Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).

Figures represent performance of the model's first-party API (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).

Latency

Measured by Time (seconds) to First Token

Latency: Time To First Answer Token

Seconds to first answer token received · Accounts for reasoning model 'thinking' time

Reasoning models are indicated by a lightbulb icon

Time to first answer token received, in seconds, after API request sent. For reasoning models, this includes the 'thinking' time of the model before providing an answer. For models which do not support streaming, this represents time to receive the completion.

End-to-End Response Time

Seconds to output 500 tokens, calculated based on time to first token, 'thinking' time for reasoning models, and output speed

End-to-End Response Time vs. Price

End-to-end response time: end-to-end seconds to output 500 tokens · USD per 1M tokens (blended)

Most attractive quadrant

Reasoning models are indicated by a lightbulb icon.

Price per token, shown in USD per million tokens. Price is a blend of cache hit, input, and output token prices using the selected ratio (default 7:2:1 cache-input-output).

Seconds to receive a 500 token response. Key components:

Input time: Time to receive the first response token
Thinking time (only for reasoning models): Time reasoning models spend outputting tokens to reason prior to providing an answer. Amount of tokens based on the average reasoning tokens across a diverse set of 60 prompts (methodology details).
Answer time: Time to generate 500 output tokens, based on output speed

Figures represent median (P50) measurement over the past 72 hours to reflect sustained changes in performance.


									Further Analysis
Qwen3.7 Max	991k	Proprietary	46	$1.43	205	2.45	16.65	11.75	Model Provider
Qwen3.6 Max Preview	256k	Proprietary	40*	$1.13	41	3.24	64.73	49.19	Model Provider
Qwen3.6 Plus	1M	Proprietary	40	$0.43	53	2.44	116.19	104.35	Model Provider
Qwen3.7 Plus	1M	Proprietary	39	$0.27	53	2.73	49.71	37.59	Model Provider
Qwen3.6 27B	262k	Open	37	$0.90	56	3.79	114.91	102.12	Model Provider
Qwen3.5 27B	262k	Open	34*	$0.51	78	5.63	37.66	25.62	Model Provider
Qwen3.5 397B A17B	262k	Open	34	$0.90	60	2.54	64.03	53.15	Model Provider
Qwen3.5 122B A10B	262k	Open	32	$0.68	135	2.38	20.91	14.82	Model Provider
Qwen3.5 397B A17B	262k	Open	32*	$0.90	60	2.55	10.84	--	Model Provider
Qwen3.6 35B A3B	229k	Open	32	$0.37	143	2.36	43.67	37.80	Model Provider
Qwen3.5 Omni Plus	256k	Proprietary	31*	$0.84	55	2.43	11.48	--	Model Provider
Qwen3.6 27B	262k	Open	30	$0.90	57	3.85	12.59	--	Model Provider
Qwen3.5 27B	262k	Open	29*	$0.51	83	5.65	11.66	--	Model Provider
Qwen3.5 35B A3B	262k	Open	29*	$0.42	132	2.21	21.22	15.20	Model Provider
Qwen3.5 122B A10B	262k	Open	28	$0.68	149	2.35	5.70	--	Model Provider
Qwen3 Max Thinking (Preview)	262k	Proprietary	25*	$1.68	49	4.11	54.87	40.61	Model Provider
Qwen3.6 35B A3B	262k	Open	24	$0.56	172	2.22	5.13	--	Model Provider
Qwen3 Max	258k	Proprietary	24*	$1.68	58	2.56	11.12	--	Model Provider
Qwen3.5 35B A3B	262k	Open	23*	$0.42	161	2.14	5.25	--	Model Provider
Qwen3 VL 235B A22B	131k	Open	21*	$1.47	56	2.96	47.95	35.99	Model Provider
Qwen3 235B A22B 2507	131k	Open	20	$1.47	54	2.79	49.21	37.14	Model Provider
Qwen3 Max (Preview)	262k	Proprietary	19*	$1.68	58	4.14	12.69	--	Model Provider
Qwen3.5 Omni Flash	256k	Proprietary	19*	$0.17	252	1.81	3.80	--	Model Provider
Qwen3 235B 2507	131k	Open	18*	$0.91	60	2.40	10.75	--	Model Provider
Qwen3 Coder 480B	262k	Open	18*	$2.10	49	2.90	13.15	--	Model Provider
Qwen3 VL 32B	131k	Open	18*	$1.47	89	2.51	30.57	22.44	Model Provider
Qwen3 Next 80B A3B	262k	Open	17	$1.05	186	2.18	15.63	10.76	Model Provider
Qwen3 30B A3B 2507	262k	Open	14	$0.42	146	2.36	19.48	13.70	Model Provider
Qwen3 VL 235B A22B	131k	Open	14*	$0.91	51	2.62	12.41	--	Model Provider
Qwen3 Next 80B A3B	131k	Open	14*	$0.65	185	2.22	4.92	--	Model Provider
Qwen3 Coder 30B A3B	262k	Open	14*	$0.63	96	2.56	7.76	--	Model Provider
Qwen3 235B	131k	Open	13*	$1.47	58	2.77	45.52	34.20	Model Provider
Qwen3 VL 30B A3B	131k	Open	13*	$0.42	111	2.31	24.83	18.02	Model Provider
Qwen3 32B	131k	Open	12	$1.47	92	2.43	29.61	21.74	Model Provider
Qwen3 VL 32B	131k	Open	11*	$0.91	71	2.67	9.71	--	Model Provider
Qwen3 235B	131k	Open	11*	$0.91	57	2.77	11.50	--	Model Provider
Qwen3 VL 8B	131k	Open	11*	$0.37	115	2.29	23.99	17.36	Model Provider
Qwen3 14B	131k	Open	10	$0.73	62	2.70	43.34	32.51	Model Provider
Qwen3 VL 30B A3B	131k	Open	10*	$0.26	111	2.15	6.63	--	Model Provider
Qwen3 Omni 30B A3B	65.5k	Open	10*	$0.32	100	1.96	26.99	20.02	Model Provider
Qwen3 30B	131k	Open	9*	$0.42	103	2.17	26.49	19.46	Model Provider
Qwen3 30B A3B 2507	262k	Open	9*	$0.26	146	1.84	5.25	--	Model Provider
Qwen3 32B	131k	Open	9*	$0.91	94	2.42	7.72	--	Model Provider
Qwen3 VL 8B	131k	Open	8*	$0.23	119	2.22	6.42	--	Model Provider
Qwen3 8B	98.3k	Open	8	$0.37	38	3.77	69.19	52.34	Model Provider
Qwen3 14B	131k	Open	7*	$0.45	63	2.67	10.56	--	Model Provider
Qwen3 30B	131k	Open	7*	$0.26	107	2.17	6.83	--	Model Provider
Qwen2.5 Turbo	1M	Proprietary	6*	$0.07	108	2.25	6.88	--	Model Provider
Qwen3 Omni 30B A3B	65.5k	Open	5*	$0.32	96	1.89	7.12	--	Model Provider
Qwen3 8B	131k	Open	5*	$0.23	38	3.76	16.86	--	Model Provider

Key definitions

Maximum number of combined input & output tokens. Output tokens commonly have a significantly lower limit (varied by model).

Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).

Time to first token received, in seconds, after API request sent. For reasoning models which share reasoning tokens, this will be the first reasoning token. For models which do not support streaming, this represents time to receive the completion.

Price per token, shown in USD per million tokens. Price is a blend of cache hit, input, and output token prices using the selected ratio (default 7:2:1 cache-input-output).

Price per token generated by the model (received from the API), represented as USD per million Tokens.

Price per token included in the request/message sent to the API, represented as USD per million Tokens.

Metrics are 'live' and are based on the past 72 hours of measurements, measurements are taken 8 times a day for single requests and 2 times per day for parallel requests.

Frequently Asked Questions

Common questions about Alibaba Cloud

Alibaba Cloud offers 50 models that we track: Qwen3.7 Max, Qwen3.6 Max Preview, Qwen3.6 Plus, Qwen3.7 Plus, Qwen3.6 27B, Qwen3.5 27B, Qwen3.5 397B A17B, Qwen3.5 122B A10B, Qwen3.5 397B A17B, Qwen3.6 35B A3B, Qwen3.5 Omni Plus, Qwen3.6 27B, Qwen3.5 27B, Qwen3.5 35B A3B, Qwen3.5 122B A10B, Qwen3 Max Thinking (Preview), Qwen3.6 35B A3B, Qwen3 Max, Qwen3.5 35B A3B, Qwen3 VL 235B A22B, Qwen3 235B A22B 2507, Qwen3 Max (Preview), Qwen3.5 Omni Flash, Qwen3 235B 2507, Qwen3 Coder 480B, Qwen3 VL 32B, Qwen3 Next 80B A3B, Qwen3 30B A3B 2507, Qwen3 VL 235B A22B, Qwen3 Next 80B A3B, Qwen3 Coder 30B A3B, Qwen3 235B, Qwen3 VL 30B A3B, Qwen3 32B, Qwen3 VL 32B, Qwen3 235B, Qwen3 VL 8B, Qwen3 14B, Qwen3 VL 30B A3B, Qwen3 Omni 30B A3B, Qwen3 30B, Qwen3 30B A3B 2507, Qwen3 32B, Qwen3 VL 8B, Qwen3 8B, Qwen3 14B, Qwen3 30B, Qwen2.5 Turbo, Qwen3 Omni 30B A3B, and Qwen3 8B.

The most intelligent model available on Alibaba Cloud is Qwen3.7 Max with an Intelligence Index score of 46.

The fastest model on Alibaba Cloud by output speed is Qwen3.5 Omni Flash at 252.4 tokens per second.

The model with the lowest time to first token on Alibaba Cloud is Qwen3.5 Omni Flash at 1.81s. Lower latency means faster initial response time.

The most affordable model on Alibaba Cloud by blended price is Qwen2.5 Turbo at $0.07 per 1M tokens (7:2:1 cache hit/input/output ratio).

Prices on Alibaba Cloud vary up to 32x across models, from $0.07 per 1M tokens for Qwen2.5 Turbo to $2.10 per 1M tokens for Qwen3 Coder 480B.

Yes, Alibaba Cloud offers an OpenAI-compatible API, making it easy to switch from OpenAI or use existing OpenAI SDK integrations.

49 of 50 models on Alibaba Cloud support JSON mode for structured output.

Yes, all 50 models on Alibaba Cloud support function calling (tool use).

Yes, Alibaba Cloud offers 24 reasoning models: Qwen3.7 Max, Qwen3.6 Max Preview, Qwen3.6 Plus, Qwen3.7 Plus, Qwen3.6 27B, Qwen3.5 27B, Qwen3.5 397B A17B, Qwen3.5 122B A10B, Qwen3.6 35B A3B, Qwen3.5 35B A3B, Qwen3 Max Thinking (Preview), Qwen3 VL 235B A22B, Qwen3 235B A22B 2507, Qwen3 VL 32B, Qwen3 Next 80B A3B, Qwen3 30B A3B 2507, Qwen3 235B, Qwen3 VL 30B A3B, Qwen3 32B, Qwen3 VL 8B, Qwen3 14B, Qwen3 Omni 30B A3B, Qwen3 30B, and Qwen3 8B. Reasoning models use extended thinking to work through complex problems before providing an answer.

Yes, 40 of 50 models on Alibaba Cloud are open weight models: Qwen3.6 27B, Qwen3.5 27B, Qwen3.5 397B A17B, Qwen3.5 122B A10B, Qwen3.5 397B A17B, Qwen3.6 35B A3B, Qwen3.6 27B, Qwen3.5 27B, Qwen3.5 35B A3B, Qwen3.5 122B A10B, Qwen3.6 35B A3B, Qwen3.5 35B A3B, Qwen3 VL 235B A22B, Qwen3 235B A22B 2507, Qwen3 235B 2507, Qwen3 Coder 480B, Qwen3 VL 32B, Qwen3 Next 80B A3B, Qwen3 30B A3B 2507, Qwen3 VL 235B A22B, Qwen3 Next 80B A3B, Qwen3 Coder 30B A3B, Qwen3 235B, Qwen3 VL 30B A3B, Qwen3 32B, Qwen3 VL 32B, Qwen3 235B, Qwen3 VL 8B, Qwen3 14B, Qwen3 VL 30B A3B, Qwen3 Omni 30B A3B, Qwen3 30B, Qwen3 30B A3B 2507, Qwen3 32B, Qwen3 VL 8B, Qwen3 8B, Qwen3 14B, Qwen3 30B, Qwen3 Omni 30B A3B, and Qwen3 8B.

Yes, provider performance can vary over time due to infrastructure changes, load balancing, and updates. We continuously benchmark all providers and display historical performance trends in the "Over Time" charts.

When choosing a model on Alibaba Cloud, consider: intelligence (for quality-sensitive tasks), output speed (for throughput-intensive tasks), latency (for interactive applications requiring quick first responses), pricing (for cost-sensitive workloads), and features like context window size, JSON mode, or function calling support.

Alibaba Cloud: Models Intelligence, Performance & Price

Most Intelligent

Fastest

Lowest Price

Intelligence

Speed

Price

Intelligence Evaluations

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index

Intelligence Evaluations

Intelligence Evaluation Relevance

Artificial Analysis Intelligence Index

Intelligence vs. Price

Price-Quality Variance

Artificial Analysis Intelligence Index

Price

Cache Pricing by Provider

Model Performance Representation

Context Window

Context Window

Context Window for RAG

Context Window

Pricing

Intelligence vs. Price

Price-Quality Variance

Artificial Analysis Intelligence Index

Price

Cache Pricing by Provider

Model Performance Representation

Performance Summary

Output Speed vs. Price

Output Speed

Price

Speed

Output Speed

Output Speed

Model Performance Representation

Latency

Latency: Time To First Answer Token

Time to First Answer Token

End-to-End Response Time

End-to-End Response Time vs. Price

Price

End-to-End Response Time

Median

Key definitions

Context Window

Output Speed

Latency (Time to First Token)

Price

Output Price

Input Price

Time Period

Frequently Asked Questions

What models does Alibaba Cloud offer?

What is the most intelligent model on Alibaba Cloud?

What is the fastest model on Alibaba Cloud?

Which model has the lowest latency on Alibaba Cloud?

What is the cheapest model on Alibaba Cloud?

How much do prices vary across models on Alibaba Cloud?

Is Alibaba Cloud OpenAI compatible?

Does Alibaba Cloud support JSON mode?

Does Alibaba Cloud support function calling?

Does Alibaba Cloud offer reasoning models?

Does Alibaba Cloud offer open weight models?

Does Alibaba Cloud's performance change over time?

How do I choose a model on Alibaba Cloud?