Qwen2.5 Turbo
Intelligence
12
#413/523
Coding
—
Math
—
Speed
71 tok/s
TTFT: 1.11s
Pricing
$0.05 / $0.20
per 1M tokens (in/out)
Qwen2.5 Turbo is Alibaba’s latest AI model designed for efficient processing of natural language tasks. It operates at a speed of 71.432 tokens per second and is priced at $0.05 per million input tokens, catering to professional users.
When to Use Qwen2.5 Turbo
✓ Best For
- Natural language processing tasks
- Coding assistance
- Data analysis
✗ Not Ideal For
- High-complexity mathematical computations
- Real-time applications requiring ultra-low latency
How Qwen2.5 Turbo Compares
Intelligence Index · Higher is better
GoogleReka AIAlibabaMetaUpstage
Benchmark Profile
Output Speed · tok/s
AlibabaMiniMaxAnthropic
Intelligence · Coding · Math
Intelligence
Coding
Math
All Benchmark Scores (8)
| Benchmark | Score | |
|---|---|---|
| Intelligence Index | 12 | |
| MMLU-Pro | 633% | |
| GPQA | 41% | |
| LiveCodeBench | 163% | |
| HLE | 42% | |
| SciCode | 15.3% | |
| AIME | 12% | |
| MATH 500 | 80.5% |
Data: Artificial Analysis · Updated: April 10, 2026
Frequently Asked Questions (15)
When was Qwen2.5 Turbo released?
Qwen2.5 Turbo was released on November 18, 2024.
Who created Qwen2.5 Turbo?
Qwen2.5 Turbo was created by Alibaba.
How intelligent is Qwen2.5 Turbo?
Qwen2.5 Turbo scores 12 (estimated) on the Artificial Analysis Intelligence Index, placing it above average among other non-reasoning models in a similar price tier (median: 10).
How fast is Qwen2.5 Turbo?
Qwen2.5 Turbo generates output at 64.0 tokens per second (based on Alibaba's API), which is below average compared to other non-reasoning models in a similar price tier (median: 89.3 t/s).
What is the latency of Qwen2.5 Turbo?
Qwen2.5 Turbo has a time to first token (TTFT) of 2.39s (based on Alibaba's API), which is somewhat higher than average compared to other non-reasoning models in a similar price tier (median: 0.91s).
How much does Qwen2.5 Turbo cost?
Qwen2.5 Turbo costs $0.05 per 1M input tokens (better than average, median: $0.05) and $0.20 per 1M output tokens (somewhat higher than average, median: $0.15), based on Alibaba's API.
What is Qwen2.5 Turbo API pricing?
Qwen2.5 Turbo costs $0.05 per 1M input tokens and $0.20 per 1M output tokens (based on Alibaba's API). For a blended rate (3:1 input to output ratio), this is $0.09 per 1M tokens. Pricing may vary by provider.
Is Qwen2.5 Turbo a reasoning model?
No, Qwen2.5 Turbo is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
What input modalities does Qwen2.5 Turbo support?
Qwen2.5 Turbo supports text input.
What output modalities does Qwen2.5 Turbo support?
Qwen2.5 Turbo supports text only output.
Can Qwen2.5 Turbo process images?
No, Qwen2.5 Turbo does not support image input. It can only process text.
Is Qwen2.5 Turbo multimodal?
No, Qwen2.5 Turbo is not multimodal. It only supports text input.
What is the context window of Qwen2.5 Turbo?
Qwen2.5 Turbo has a context window of 1.0M tokens. This determines how much text and conversation history the model can process in a single request.
Is Qwen2.5 Turbo open source?
No, Qwen2.5 Turbo is proprietary. The model weights are not publicly available.
How many parameters does Qwen2.5 Turbo have?
Qwen2.5 Turbo is a proprietary model and Alibaba has not disclosed the model size or parameter count.
