---
id: "inclusionai/ling-2.6-1t"
also: ["inclusionai/ling-2.6-1t-20260423", "hf/inclusionAI/Ling-2.6-1T", "requesty/inclusionai/ling-2.6-1t"]
cheapest_list_usd_per_m: "0.075 in, 0.625 out, at novita on openrouter"
cheapest_effective_usd_per_m: "0.0595 in, 0.6242 out, at novita on openrouter"
context: 262144
max_output: 32768
input: ["text"]
output: ["text"]
released: "2026-04-23"
params: ["frequency_penalty", "logprobs", "max_tokens", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p"]
endpoints: 3
gateways: "hf (1), openrouter (1), requesty (1)"
no_training: 2
trains: 0
retains_prompts: 0
---
# inclusionAI: Ling-2.6-1T

Ling-2.6-1T is an instant (instruct) model from inclusionAI and the company’s trillion-parameter flagship, designed for real-world agents that require fast execution and high efficiency at scale. It uses a “fast...