Ant Group API Pricing
2 models · From <$0.0001/1M to $0.060/1M input
The cheapest Ant Group model to run is Ling-3.0-tiny at <$0.0001 input and <$0.0001 output per 1M tokens. On a RAG answer of 8,000 tokens in and 600 out, Ant Group models range from <$0.0001 (Ling-3.0-tiny) to $0.0006 (Ling-3.0-flash) per request. The largest context window is Ling-3.0-tiny at 262K tokens. Count tokens with the Ant Group token counter.
| Model | Input /1M | Output /1M | RAG answer |
|---|---|---|---|
| Ling-3.0-tiny | <$0.0001 | <$0.0001 | <$0.0001 |
| Ling-3.0-flash | $0.060 | $0.180 | $0.0006 |