---
id: "inclusionai/ling-3.1-flash"
also: ["inclusionai/ling-3.1-flash-20261002", "inclusionAI/Ling-3.1-flash", "hf/inclusionAI/Ling-3.1-flash", "requesty/inclusionai/ling-3.1-flash", "vercel/inclusionai/ling-3.1-flash"]
cheapest_list_usd_per_m: "0.045 in, 0.135 out, at deepinfra/fp4 on openrouter"
cheapest_effective_usd_per_m: "0.0186 in, 0.1447 out, at novita on openrouter"
context: 1000000
max_output: 262144
input: ["text"]
output: ["text"]
released: "2026-10-02"
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p"]
endpoints: 5
gateways: "openrouter (2), hf (1), requesty (1), vercel (1)"
no_training: 3
trains: 0
retains_prompts: 0
---
# inclusionAI: Ling 3.1 Flash

Ling 3.1 Flash is a hybrid reasoning MoE model from inclusionAI with 560B total and 25B active parameters. Served by Novita with a 256K context window and 32K max output, supporting reasoning and function calling. Free tier.