Remy Reference/models/Qwen3.6-35B-A3B

Qwen3.6-35B-A3B

Qwen3.6-35B-A3B, a language model from DeepInfra.

modelOverride: { model: "qwen3.6-35b-a3b-deepinfra" }

Qwen·served via

DeepInfra·Released July 2025

Pricing

Input: $0.20 / 1M
Output: $1.00 / 1M

Specifications

Context window: 262,144 tokens
Max output: 262,144 tokens
Released: July 2025
Model string: Qwen/Qwen3.6-35B-A3B

Parameters

Model options, passed in modelOverride.config.

Parameter	Type	Default	Range / options
`top_p` Nucleus sampling. Considers only tokens whose cumulative probability exceeds this threshold.	Number	0.9	0–1, step 0.01
`top_k` Limits sampling to the K most likely tokens at each step. Set to 0 to disable.	Number	0	0–100
`min_p` Minimum probability threshold relative to the most likely token. Filters out unlikely tokens.	Number	0	0–1, step 0.01
`presence_penalty` Penalizes tokens that have already appeared in the output, encouraging new topics.	Number	0	-2–2, step 0.01
`repetition_penalty` Penalizes repeated tokens. Values above 1 discourage repetition; values below 1 encourage it.	Number	1	0–2, step 0.01
`frequency_penalty` Penalizes tokens based on how often they have already appeared, reducing verbatim repetition.	Number	0	-2–2, step 0.01

Use this model

await mindstudio.generateText({
  message: "...",
  modelOverride: {
    model: "qwen3.6-35b-a3b-deepinfra",
    config: {
      top_p: 0.9,
      top_k: 0,
    },
  },
});