{"id":"inclusionai/ling-3.0-flash","aliases":["hf:inclusionai/ling-3.0-flash","inclusionai/ling-3.0-flash-20260723","openrouter:inclusionai/ling-3.0-flash"],"displayName":"inclusionAI: Ling 3.0 Flash","author":"inclusionai","createdAt":"2026-07-23T14:56:20.000Z","updatedAt":"2026-09-08T15:44:27.512Z","popularityRank":143,"metadata":{"modalities":["text"],"inputModalities":["text"],"outputModalities":["text"],"contextLength":262144,"maxOutputTokens":32768,"family":"ling","modelsDev":{"provider":"openrouter","sourceUrl":"https://models.dev/api.json","description":"Efficient model for low-latency assistance, extraction, and routine automation","lastUpdated":"2026-07-23","releaseDate":"2026-07-23","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"temperature":true,"open_weights":true,"structured_output":false}},"tokenizer":"Other","licenseStatus":"unknown","weightsAvailable":false,"hostedInferenceAllowed":false,"gated":false,"supportedParameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"providerNames":[],"isModerated":false},"availability":"unknown","externalBest":null,"multivibeNetwork":null,"description":"*Ling-3.0-flash* is a *124B-parameter Mixture-of-Experts (MoE) model*, with approximately *5.1B parameters activated per token*. The model is designed with *token efficiency and production-scale agentic inference* as key priorities, enabling developers...","runtimes":[],"protocols":[],"harnesses":[]}