InternVL 2
Multimodal & Perception · Free
Strong open-source vision-language model by Shanghai AI Lab
At a glance
- Made by
- OpenGVLab, Shanghai AI Laboratory
- API
- Yes
- Available on
- Web, API
- Open source
- Open source (the license name is not listed on the page)
- GitHub
- 10,165 stars · MIT
What is InternVL 2?
InternVL is a vision-language foundation model that scales the vision encoder (InternViT-6B) up to 6 billion parameters and progressively aligns it with an LLM using web-scale image-text data. It states that it achieved state-of-the-art performance on 32 general visual-linguistic benchmarks. InternVL2-Pro of the InternVL2 series is introduced as scoring 62.0% on MMMU, on par with commercial closed models such as GPT-4o, and it was followed by InternVL 2.5, 3.0, and 3.5. It provides code, models, a demo, and API documentation.
- InternViT-6B, a 6-billion-parameter vision encoder
- Three-stage training: contrastive learning → generative learning → supervised fine-tuning
- State-of-the-art performance on 32 general visual-linguistic benchmarks (as announced)
- InternVL2-Pro MMMU 62.0%
- InternVL 2.5 series from 1B to 78B parameters
- Chat demo and API provided
Who uses InternVL 2 and for what
- Building multimodal dialogue systems
Pricing
Open source (free, weights/code released)
Released free under an open-source license with no extra cost for self-hosting (usage-based pricing when offered as a cloud API)
Estimate based on AI knowledge - please verify on the official site
AI tools similar to InternVL 2 (alternatives)
InternVL 2 vs. alternatives at a glance
| AI | Pricing | Combos on the map | Connected tools | Free | Cheapest monthly | Korean |
|---|---|---|---|---|---|---|
| InternVL 2 | Free | 0 | 7 | — | — | — |
| Gemini Pro Vision | Free + paid | 0 | 7 | Yes | — | Yes |
| LLaVA | Free | 0 | 5 | — | — | — |
| Qwen-VL | Free | 0 | 5 | Yes | — | Yes |
| Reka Core | Free + paid | 0 | 5 | — | — | No |
2 of these 5 tools have a free plan.
Combo and connection counts are based on the relationships recorded on AI Galaxy Map (2026-10-26); they are not a quality ranking.
InternVL 2 on AI Galaxy Map
- One of 22 AI tools in the Multimodal & Perception field.
- Connected to 7 other tools — #1 in its field.
Frequently asked questions
Can I use InternVL 2 for free?
Open source (free, weights/code released). Prices can change, so check the official site before paying.
What AI can I use instead of InternVL 2?
Tools that do the same job, such as Gemini Pro Vision, LLaVA, Qwen-VL, Reka Core, are connected to it on the map.
Sources (official pages)
Checked on the official pages on 2026-10-14. Prices and features can change, so check the official site again before paying.