Alibaba Cloud: Models Intelligence, Performance & Price
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. For more details including relating to our methodology, see our FAQs. Models analyzed: Qwen3 14B (Reasoning), Qwen3 1.7B (Reasoning), Qwen3 30B A3B (Reasoning), Qwen3 32B (Reasoning), Qwen3 8B, Qwen3 235B (Reasoning), Qwen3 4B (Reasoning), Qwen3 0.6B, Qwen3 0.6B (Reasoning), Qwen3 4B, Qwen3 30B A3B, Qwen3 8B (Reasoning), Qwen3 32B, Qwen3 235B, Qwen3 1.7B, Qwen3 14B, Qwen2.5 Max, Qwen2.5 72B, Qwen2.5 Turbo, Qwen2 72B, and Qwen1.5 Chat 110B.
Link:
Alibaba Cloud Model Comparison Summary
Intelligence: Qwen3 235B (Reasoning) and Qwen3 32B (Reasoning) are the highest quality models offered by Alibaba Cloud, followed by Qwen3 14B (Reasoning), Qwen3 30B A3B (Reasoning) & Qwen3 8B (Reasoning).Output Speed (tokens/s): Qwen3 0.6B (232 t/s) and Qwen3 0.6B (Reasoning) (228 t/s) are the fastest models offered by Alibaba Cloud, followed by Qwen3 1.7B, Qwen3 1.7B (Reasoning) & Qwen3 4B.Latency (seconds): Qwen3 1.7B (Reasoning) (0.95s) and Qwen3 0.6B (0.98s) are the lowest latency models offered by Alibaba Cloud, followed by Qwen3 0.6B (Reasoning), Qwen3 8B (Reasoning) & Qwen3 8B.Blended Price ($/M tokens): Qwen2.5 72B ($0.00) and Qwen2 72B ($0.00) are the cheapest models offered by Alibaba Cloud, followed by Qwen1.5 Chat 110B, Qwen2.5 Turbo & Qwen3 0.6B.Context Window Size: Qwen2.5 Turbo (1m) and Qwen3 14B (Reasoning) (131k) are the largest context window models offered by Alibaba Cloud, followed by Qwen3 30B A3B (Reasoning), Qwen3 32B (Reasoning) & Qwen3 8B.
Qwen3 235B (Reasoning) and Qwen3 32B (Reasoning) are the highest quality models offered by Alibaba Cloud, followed by Qwen3 14B (Reasoning), Qwen3 30B A3B (Reasoning) & Qwen3 8B (Reasoning).Output Speed (tokens/s): Qwen3 0.6B (232 t/s) and Qwen3 0.6B (Reasoning) (228 t/s) are the fastest models offered by Alibaba Cloud, followed by Qwen3 1.7B, Qwen3 1.7B (Reasoning) & Qwen3 4B.Latency (seconds): Qwen3 1.7B (Reasoning) (0.95s) and Qwen3 0.6B (0.98s) are the lowest latency models offered by Alibaba Cloud, followed by Qwen3 0.6B (Reasoning), Qwen3 8B (Reasoning) & Qwen3 8B.Blended Price ($/M tokens): Qwen2.5 72B ($0.00) and Qwen2 72B ($0.00) are the cheapest models offered by Alibaba Cloud, followed by Qwen1.5 Chat 110B, Qwen2.5 Turbo & Qwen3 0.6B.Context Window Size: Qwen2.5 Turbo (1m) and Qwen3 14B (Reasoning) (131k) are the largest context window models offered by Alibaba Cloud, followed by Qwen3 30B A3B (Reasoning), Qwen3 32B (Reasoning) & Qwen3 8B.Highlights
Intelligence
Artificial Analysis Intelligence Index; Higher is better
Speed
Output Tokens per Second; Higher is better
Price
USD per 1M Tokens; Lower is better
Parallel Queries:
Prompt Length:
Features | Model Intelligence | Price | Output tokens/s | Latency | End-to-End Response Time | ||||
|---|---|---|---|---|---|---|---|---|---|
Further Analysis | |||||||||
 | Qwen3 235B (Reasoning) | 131k | 62 | $2.63 | 70.9 | 1.13 | 36.39 | 28.21 | |
| Qwen3 32B (Reasoning) | 131k | 59 | $2.63 | 60.7 | 1.18 | 42.38 | 32.96 | |
| Qwen3 14B (Reasoning) | 131k | 56 | $1.31 | 65.6 | 1.07 | 39.17 | 30.48 | |
| Qwen3 30B A3B (Reasoning) | 131k | 56 | $0.75 | 91.7 | 1.05 | 28.30 | 21.80 | |
| Qwen3 8B (Reasoning) | 131k | 51 | $0.66 | 98.7 | 0.99 | 26.31 | 20.26 | |
| Qwen3 4B (Reasoning) | 131k | 47 | $0.40 | 104.6 | 1.03 | 24.92 | 19.11 | |
| Qwen3 235B | 131k | 47 | $1.23 | 71.5 | 1.15 | 8.14 | N/A | |
| Qwen2.5 Max | 32k | 45 | $2.80 | 32.5 | 1.35 | 16.73 | N/A | |
| Qwen3 32B | 131k | 44 | $1.23 | 60.4 | 1.14 | 9.42 | N/A | |
| Qwen3 30B A3B | 131k | 43 | $0.35 | 92.7 | 1.06 | 6.46 | N/A | |
| Qwen3 14B | 131k | 41 | $0.61 | 66.4 | 1.12 | 8.66 | N/A | |
| Qwen2.5 72B | 131k | 40 | $0.00 | 58.3 | 1.19 | 9.77 | N/A | |
| Qwen3 1.7B (Reasoning) | 33k | 38 | $0.40 | 137.9 | 0.95 | 19.07 | 14.50 | |
| Qwen3 8B | 131k | 37 | $0.31 | 100.4 | 0.99 | 5.97 | N/A | |
| Qwen3 4B | 131k | 35 | $0.19 | 106.5 | 1.00 | 5.70 | N/A | |
| Qwen2.5 Turbo | 1m | 34 | $0.09 | 106.1 | 1.11 | 5.82 | N/A | |
| Qwen2 72B | 131k | 33 | $0.00 | 31.0 | 1.38 | 17.53 | N/A | |
| Qwen3 1.7B | 33k | 25 | $0.19 | 140.9 | 1.01 | 4.56 | N/A | |
| Qwen3 0.6B (Reasoning) | 33k | 23 | $0.40 | 228.2 | 0.99 | 11.94 | 8.76 | |
| Qwen3 0.6B | 33k | 17 | $0.19 | 232.4 | 0.98 | 3.13 | N/A | |
| Qwen1.5 Chat 110B | 32k | $0.00 | 23.8 | 1.52 | 22.57 | N/A | ||
Key definitions
Context window: Maximum number of combined input & output tokens. Output tokens commonly have a significantly lower limit (varied by model).
Output Speed: 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).
Latency (Time to First Token): 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: Price per token, represented as USD per million Tokens. Price is a blend of Input & Output token prices (3:1 ratio).
Output Price: Price per token generated by the model (received from the API), represented as USD per million Tokens.
Input Price: Price per token included in the request/message sent to the API, represented as USD per million Tokens.
Time period: 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.