ModelsModels / inclusionAI
Ling-3.1-flash
Gets 95 of every 100 tool calls right on the public test. Steady whether it is calling one tool, choosing between tools, or making several calls at once.
Ling-3.1-flash is made by inclusionAI. It takes text, with a context window of 1M tokens. On Tīrtha it takes up to 262,144 tokens.
Start using Ling-3.1-flash in 3 steps
Read the docs- Get an API keyFree to create. It works for every model in the catalogue.Get an API key
- Add creditsPay as you go. Credits work on every model.Add credits
- Point your client at TīrthaAny OpenAI-compatible client works. Use your key and this base URL, and name the model.base_url: "https://api.tirtha.ai/v1" api_key: "YOUR_TIRTHA_KEY" model: "catalog/ling-3.1-flash"
Price
The live price, read from billing as this page loads. You pay only for the tokens you use, from your credits.
At a glance
Tested on Tīrtha Bench
Tool calling (public BFCL v4 test)
Overall: 95.1%*. Picks the right tool and fills in the inputs correctly on 95 of every 100 tasks.
One tool 96% · Picking the right tool 96% · Several calls at once 93%
A task counts as right only if the model calls the right tool with the right inputs. 800 tasks. Run on Oct 29, 2026. *Measured by Spanda Works on third-party hosts, not through Tīrtha. Results through Tīrtha may differ.
Handled several calls at once in our tests.
See Ling-3.1-flash beside every other model on Tīrtha Bench →
What it supports
- Tool callingYesAlso measured on Tīrtha Bench
- Text inYes
- Context window1M tokensUp to 262,144 tokens on Tīrtha.
- ReasoningYesThinks before it answers
- StreamingYes
- Sampling settingsFixed todayThe maker publishes no default. Tīrtha fixes temperature at 0 today.
From the maker
- Model card: inclusionAI/Ling-3.1-flash on Hugging Face
- Last updated by the maker: Oct 27, 2026
Facts here are read from the maker's published card; claims and benchmarks on that card are the maker's own, not measured by Tīrtha.
Licence
Weights: MIT. Read the licence.