Ling 3.0 Flash VL builds on Ling 3.0 Flash (124B total / 5.5B active MoE from InclusionAI), further strengthening its language capabilities while adding native visual perception and advanced visual agent capabilities. Hybrid instant/reasoning model with tool calling.
$0.03market price $0.06
$0.006market price $0.012
$0.09market price $0.18
Throughput is how fast the model writes (tokens per second, higher is better). Time to first token is how long before the answer starts (lower is better).
Share of requests served without a server error. Client errors (4xx) do not count.
Works with the OpenAI SDK pointed at our base URL. Every parameter is in the API reference.
Tokens processed per day on NagaAI.
Ling 3.0 Flash VL builds on Ling 3.0 Flash (124B total / 5.5B active MoE from InclusionAI), further strengthening its language capabilities while adding native visual perception and advanced visual agent capabilities. Hybrid instant/reasoning model with tool calling.
On NagaAI, Ling 3.0 Flash VL costs $0.03 per 1M input tokens and $0.09 per 1M output tokens. You pay only for what you use, with no subscription.
Ling 3.0 Flash VL reads up to 131.1k tokens in one request, counting the prompt and the answer together.
Yes. Ling 3.0 Flash VL can call your functions as tools and can answer in a JSON schema you give it.
It takes text and images as input and returns text.
Create an API key, copy the model ID from the top of this page and send requests with the OpenAI or Anthropic SDK pointed at NagaAI. The API section on this page has a ready example.
Ling 3.0 Flash SanteinclusionAI$0.021 / $0.0616 per 1MLing 3.1 FlashinclusionAILing 3.0 Flash FininclusionAI$0.021 / $0.0616 per 1MLing 3.0 TinyinclusionAI$0.0075 / $0.0225 per 1MLing 3.0 FlashinclusionAI
LFM3-1.7BLiquid AI$0.04 / $0.10 per 1MNot enough throughput data
Not enough TTFT data