Model Library
AlibabaReleased November 18, 2024Qwen2.5 Turbo
Alibaba · Released November 18, 2024
Intelligence score
6
At a glance
- Intelligence
- 6
- Speed
- 102.4tokens/sec
- Latency
- 2.33stime to first token
- Input price
- $0.05per 1M tokens
- Output price
- $0.20per 1M tokens
- Context window
- 3tokens
- Parameters
- —
Summary
Comparison summary
Qwen2.5 Turbo scores 6 (estimated) on the Artificial Analysis Intelligence Index, placing it above average among other non-reasoning models in a similar price tier (median: 5). Qwen2.5 Turbo generates output at 102.4 tokens per second (based on Alibaba's API), which is below average compared to other non-reasoning models in a similar price tier (median: 121.7 t/s). 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: $0.20), based on Alibaba's API.
Specifications
Technical specifications
| Model name | Qwen2.5 Turbo |
|---|---|
| Provider | Alibaba |
| Release date | November 18, 2024 |
| Intelligence score | 6 |
| Speed | 102.4 tokens/sec |
| Latency (TTFT) | 2.33s |
| Input price | $0.05 / 1M tokens |
| Output price | $0.20 / 1M tokens |
| Context window | 3 tokens |
| Parameters | — |
| Reasoning | No |
| Input modalities | text |
| Output modalities | — |
| Open weights | No |
| License | — |
| API availability | — |
| Source | Model Intelligence legacy profile: qwen-turbo |
Pricing
Token prices
Price per 1M tokens
Qwen2.5 Turbo, as listed in the catalog record
- Input$0.05
- Output$0.20
| Token type | Price per 1M |
|---|---|
| Input | $0.05 |
| Output | $0.20 |
Model Intelligence legacy profile: qwen-turbo
FAQ · 18
Frequently asked questions
Qwen2.5 Turbo was released on November 18, 2024.
Qwen2.5 Turbo was created by Alibaba.
Qwen2.5 Turbo scores 6 (estimated) on the Artificial Analysis Intelligence Index, placing it above average among other non-reasoning models in a similar price tier (median: 5).
Qwen2.5 Turbo generates output at 102.4 tokens per second (based on Alibaba's API), which is below average compared to other non-reasoning models in a similar price tier (median: 121.7 t/s).
Qwen2.5 Turbo has a time to first token (TTFT) of 2.33s (based on Alibaba's API), which is at the higher end compared to other non-reasoning models in a similar price tier (median: 1.01s).
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: $0.20), based on Alibaba's API.
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 (7:2:1 cache hit/input/output ratio), this is $0.07 per 1M tokens. Pricing may vary by provider.
No, Qwen2.5 Turbo is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
Qwen2.5 Turbo supports text input.
Qwen2.5 Turbo supports text only output.
No, Qwen2.5 Turbo does not support image input. It can only process text.
No, Qwen2.5 Turbo is not multimodal. It only supports text input.
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.
No, Qwen2.5 Turbo is proprietary. The model weights are not publicly available.
Qwen2.5 Turbo is a proprietary model and Alibaba has not disclosed the model size or parameter count.
Qwen2.5 Turbo achieves a score of 6 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Yes, Qwen2.5 Turbo is available via API through 1 provider.
Qwen2.5 Turbo is available through 1 API provider.