I
Ling-3.0-flashOPEN
*Ling-3.0-flash* is a *124B-parameter Mixture-of-Experts (MoE) model*, with approximately *5.1B parameters activated per token*.
Prices update automatically — checked daily against provider list prices.
- $0.03 per 1M tokens, assuming 3 input for 1 output the convention used by Artificial Analysis
- cheaper than 91% of the 191 open-weight models tracked here
Benchmarks & performance
Independent benchmark scores for Ling-3.0-flash, measured by Artificial Analysis. Higher is better.
For the same budget, Ling-3.0-flash delivers 54 times more capability. Open weights also mean you can self-host it and pay nothing per token.
Models at this level cost $1.56 per 1M tokens (median of 24) — this one costs $0.03.
No model tracked here is both cheaper and better on this index.
About this model
Ling-3.0-flash is an open-weight AI model by Inclusionai. You can download and self-host it for free; the prices below are hosted-API list prices, tracked daily, for when you prefer convenience over self-hosting.
Frequently asked questions
What is Ling-3.0-flash?
Ling-3.0-flash is an AI language model from Inclusionai. It is open-weight: you can download it and run it on your own hardware, for free. It scores 37.8 on the Artificial Analysis intelligence index.
Is Ling-3.0-flash free?
The weights are free and open — you can self-host Ling-3.0-flash and pay nothing per token. If you prefer a hosted API, list prices are $0.02 per million input tokens and $0.06 per million output tokens.
What is Ling-3.0-flash good at?
Independent benchmarks from Artificial Analysis give it GPQA 85.5%, Humanity's Last Exam 23.7%, Long Context Reasoning 67%, SciCode 41.1%, τ-Bench Banking 27.2%, Terminal-Bench 55.4%. It is particularly used for code generation.
How fast is Ling-3.0-flash?
It generates about 406.5 tokens per second, with a median 1.84s delay before the first token. Measured independently by Artificial Analysis.
Can I self-host Ling-3.0-flash?
Yes. Ling-3.0-flash has open weights, so you can download it and run it on your own GPU or server with tools like Ollama, vLLM or llama.cpp — with no per-token cost.