Ling-1T

Ling-1T is an open-weight instruction model from Ant Group for adaptable chat and self-hosted production workloads. It is the first version of the ling line, released in October 2025. It accepts text and returns text, with a context window of 128,000 tokens and a maximum output of 32,000 tokens. Weights are open. It supports tool calling but not reasoning mode. Pricing starts at $0.56 per million input tokens and $2.24 per million output tokens, with cached input at $0.11 per million tokens. It is served by two hosts.

First version of its line in the registry.

Range across the hosts that serve it: up to $0.57 per 1M input tokens.

• ·Open weights for self-hosting
• ·128k token context window
• ·32k token max output
• ·Supports tool calling
• ·Priced from $0.56 per M input

• Reach for it for adaptable chat in self-hosted environments
• Reach for it for production workloads needing tool calling
• Reach for it for long-context text generation up to 128k tokens

2 hosts serve this model at the price above · the maker's documentation

The registry keeps the six most recent versions of a line. Older ones stay in the file and can be surfaced without a rebuild.

What is the context window?

The context window is 128,000 tokens, with a maximum output of 32,000 tokens.

Is the model open weights?

Yes, the weights are open, and it is served by two hosts.

Does it support tool calling?

Yes, it supports tool calling, but it does not have a reasoning mode.