Model Library
AlibabaReleased October 14, 2025Qwen3 VL 8B
Alibaba · Released October 14, 2025
Intelligence score
8
At a glance
- Intelligence
- 8
- Speed
- 114.6tokens/sec
- Latency
- 2.38stime to first token
- Input price
- $0.18per 1M tokens
- Output price
- $0.70per 1M tokens
- Context window
- 260Ktokens
- Parameters
- 8.77billions
Summary
Comparison summary
Qwen3 VL 8B Instruct scores 8 (estimated) on the Artificial Analysis Intelligence Index, placing it above average among other open weight non-reasoning models of similar size (median: 6). Qwen3 VL 8B Instruct generates output at 114.6 tokens per second (based on Alibaba's API), which is above average compared to other open weight non-reasoning models of similar size (median: 101.8 t/s). Qwen3 VL 8B Instruct costs $0.18 per 1M input tokens (somewhat higher than average, median: $0.15) and $0.70 per 1M output tokens (somewhat higher than average, median: $0.32), based on Alibaba's API.
Specifications
Technical specifications
| Model name | Qwen3 VL 8B |
|---|---|
| Provider | Alibaba |
| Release date | October 14, 2025 |
| Intelligence score | 8 |
| Speed | 114.6 tokens/sec |
| Latency (TTFT) | 2.38s |
| Input price | $0.18 / 1M tokens |
| Output price | $0.70 / 1M tokens |
| Context window | 260,000 tokens |
| Parameters | 8.77B |
| Reasoning | No |
| Input modalities | text, image |
| Output modalities | — |
| Open weights | Yes |
| License | Apache 2 |
| API availability | — |
| Source | Model Intelligence legacy profile: qwen3-vl-8b-instruct |
Pricing
Token prices
Price per 1M tokens
Qwen3 VL 8B, as listed in the catalog record
- Input$0.18
- Output$0.70
| Token type | Price per 1M |
|---|---|
| Input | $0.18 |
| Output | $0.70 |
Model Intelligence legacy profile: qwen3-vl-8b-instruct
FAQ · 19
Frequently asked questions
Qwen3 VL 8B Instruct was released on October 14, 2025.
Qwen3 VL 8B Instruct was created by Alibaba.
Qwen3 VL 8B Instruct scores 8 (estimated) on the Artificial Analysis Intelligence Index, placing it above average among other open weight non-reasoning models of similar size (median: 6).
Qwen3 VL 8B Instruct generates output at 114.6 tokens per second (based on Alibaba's API), which is above average compared to other open weight non-reasoning models of similar size (median: 101.8 t/s).
Qwen3 VL 8B Instruct has a time to first token (TTFT) of 2.38s (based on Alibaba's API), which is somewhat higher than average compared to other open weight non-reasoning models of similar size (median: 1.54s).
Qwen3 VL 8B Instruct costs $0.18 per 1M input tokens (somewhat higher than average, median: $0.15) and $0.70 per 1M output tokens (somewhat higher than average, median: $0.32), based on Alibaba's API.
Qwen3 VL 8B Instruct costs $0.18 per 1M input tokens and $0.70 per 1M output tokens (based on Alibaba's API). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.23 per 1M tokens. Pricing may vary by provider.
No, Qwen3 VL 8B Instruct is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
Qwen3 VL 8B Instruct supports text and image input.
Qwen3 VL 8B Instruct supports text output.
Yes, Qwen3 VL 8B Instruct supports image input and can analyze, describe, and answer questions about images.
Yes, Qwen3 VL 8B Instruct is multimodal. It can process text and image input and generate text output.
Qwen3 VL 8B Instruct has a context window of 260k tokens. This determines how much text and conversation history the model can process in a single request.
Yes, Qwen3 VL 8B Instruct is open weights. The model weights are publicly available and can be downloaded for self-hosting.
Qwen3 VL 8B Instruct has 8.77 billion parameters.
Qwen3 VL 8B Instruct is released under the Apache 2.0 license. This license allows commercial use.
Qwen3 VL 8B Instruct achieves a score of 8 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Yes, Qwen3 VL 8B Instruct is available via API through 1 provider.
Qwen3 VL 8B Instruct is available through 1 API provider.