InternVL 3 8B
Free.ai (self-hosted)
·
vision
·
~500 tokens per image
InternVL 3 8B is a vision model built by Shanghai AI Lab. Strongest at High-quality open VLM for production.. Self-hosted on Free.ai GPUs — runs free against your daily token pool (500 tokens per image). Released under MIT — commercial use permitted on Free.ai.
Frequently Asked Questions
InternVL 3 8B is a vision model built by Shanghai AI Lab. Strongest at High-quality open VLM for production.. Self-hosted on Free.ai GPUs — runs free against your daily token pool (500 tokens per image). Released under MIT — commercial use permitted on Free.ai.
InternVL 3 8B works well for High-quality open VLM for production.. Try the sample prompts above to see its style.
About 500 tokens per average message. Free accounts get a 30,000-token daily pool that covers self-hosted chat; premium models are pay-as-you-go, with token top-ups from $1.
It depends on the task. /chat/compare/ lets you send the same prompt to InternVL 3 8B and any other model side-by-side - comparison is the fastest way to decide.
Yes. Outputs are yours - Free.ai does not claim rights to anything you generate. The underlying model is MIT-licensed.
32,768 tokens.
Replies stream token-by-token within ~1 second. Total response time depends on length and model size - small models stream faster, frontier models trade speed for depth.
Yes. Signed-in users see every chat in /account/?tab=history. You can also share a one-link copy of any conversation via the Share button.
Free.ai does not train models on your conversations. Self-hosted models stay on our GPUs. Premium models route to the upstream provider for inference.
Yes. POST to /v1/chat/ with model="internvl-3-8b" and a messages array. Streaming SSE is supported. Full reference: /api/.
InternVL 3 8B is MIT-licensed with 8B parameters. See /models/internvl-3-8b/ for setup notes and our open-source repos at github.com/freeaigit.
Free accounts get a 30,000-token daily pool. When that runs out, token top-ups start at $1, pay-as-you-go - no subscription required.