Next generation of the open-weight LLaVA vision-language model family.
Next generation of the open-weight LLaVA vision-language model family.
Why it matters: LLaVA is the default open-weight vision baseline — v2 will drive immediate research and dev search.
Expected pricing: Free / open weights
Cheap vision-language model on SkillBoss, closest stand-in.
We'll auto-switch your API calls to LLaVA-Next 2 the moment it launches — no code changes required.
curl -X POST https://api.skillboss.co/v1/run \
-H "Authorization: Bearer $SKILLBOSS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"skill_id": "google/gemini-2.5-flash",
"input": {
"prompt": "Say hello from LLaVA-Next 2 — routed via SkillBoss"
}
}'Create a free SkillBoss account and we'll email you the moment routing is live — and automatically upgrade your API calls.
Create Free Account