modelparams.dev
API MCP GitHub

Providers

Alibaba Anthropic Bedrock Cerebras Cohere DeepSeek Fireworks Google Groq Meta MiniMax Mistral Moonshot AI NVIDIA OpenAI Perplexity Thinking Machines Vertex xAI Xiaomi Z.ai

Providers

Alibaba Anthropic Bedrock Cerebras Cohere DeepSeek Fireworks Google Groq Meta MiniMax Mistral Moonshot AI NVIDIA OpenAI Perplexity Thinking Machines Vertex xAI Xiaomi Z.ai
Alibaba 6 params

Alibaba Qwen3.8 2.4t A95B API parameters

These are the API parameters modelparams.dev tracks for Alibaba Qwen3.8 2.4t A95B — the settings you send in a request. Each row gives the type, default, valid range or values, and the conditions that gate it. It's the same data the JSON API serves.

After the parameter count instead — how many weights Qwen3.8 2.4t A95B has? That's a different number, and we don't track it. Here's the difference.

Length 1 param
Parameter Type Default Description Condition
Max completion tokens
max_completion_tokens 		integer (1…+∞) — Maximum number of tokens to generate, including both reasoning and the final answer. —
Sampling 3 params
Parameter Type Default Description Condition
Temperature
temperature 		number (0…2 step 0.1) — Controls randomness. Lower values make outputs more focused; higher values make them more varied. —
Top P
top_p 		number (0…1 step 0.01) — Controls nucleus sampling by limiting generation to tokens within the selected cumulative probability. —
Top K
extra_body.top_k 		integer (0…+∞) 20 Limits generation to the selected number of highest-probability tokens. Values above 100 disable top-k sampling. —
Reasoning 2 params
Parameter Type Default Description Condition
Enable thinking
extra_body.enable_thinking 		boolean true Toggles the model's hybrid thinking mode, sent as a provider-specific extra body field on OpenAI-compatible clients. —
Thinking budget
extra_body.thinking_budget 		integer (1…+∞) — Maximum number of tokens the model may spend on reasoning before it starts the final answer; defaults to the model's maximum reasoning length.
Only when extra_body.enable_thinking = true

Alibaba Qwen3.8 2.4t A95B API parameters in brief

Alibaba Qwen3.8 2.4t A95B documents 6 API parameters, grouped by what they control:

Frequently asked questions

Which API parameters does Alibaba Qwen3.8 2.4t A95B support?
Alibaba Qwen3.8 2.4t A95B accepts 6 API parameters in the request body: max_completion_tokens, temperature, top_p, extra_body.top_k, extra_body.enable_thinking, extra_body.thinking_budget.

Resources

All Alibaba models Glossary Full catalog

Qwen3.8 2.4t A95B — JSON

The full model definition as served by the API. Copy it or open the endpoint directly.

/api/v1/models/alibaba/qwen3.8-2.4t-a95b.json 
{
  "$schema": "https://modelparams.dev/api/v1/schema.json",
  "provider": "alibaba",
  "authType": "api_key",
  "model": "qwen3.8-2.4t-a95b",
  "params": [
    {
      "path": "max_completion_tokens",
      "label": "Max tokens",
      "description": "Maximum number of tokens to generate, including both reasoning and the final answer.",
      "group": "generation_length",
      "type": "integer",
      "range": {
        "min": 1
      }
    },
    {
      "path": "temperature",
      "label": "Temperature",
      "description": "Controls randomness. Lower values make outputs more focused; higher values make them more varied.",
      "group": "sampling",
      "type": "number",
      "range": {
        "min": 0,
        "max": 2,
        "step": 0.1
      }
    },
    {
      "path": "top_p",
      "label": "Top P",
      "description": "Controls nucleus sampling by limiting generation to tokens within the selected cumulative probability.",
      "group": "sampling",
      "type": "number",
      "range": {
        "min": 0,
        "max": 1,
        "step": 0.01
      }
    },
    {
      "path": "extra_body.top_k",
      "label": "Top K",
      "description": "Limits generation to the selected number of highest-probability tokens. Values above 100 disable top-k sampling.",
      "group": "sampling",
      "type": "integer",
      "default": 20,
      "range": {
        "min": 0
      }
    },
    {
      "path": "extra_body.enable_thinking",
      "label": "Enable thinking",
      "description": "Toggles the model's hybrid thinking mode, sent as a provider-specific extra body field on OpenAI-compatible clients.",
      "group": "reasoning",
      "type": "boolean",
      "default": true
    },
    {
      "path": "extra_body.thinking_budget",
      "label": "Thinking budget",
      "description": "Maximum number of tokens the model may spend on reasoning before it starts the final answer; defaults to the model's maximum reasoning length.",
      "group": "reasoning",
      "applicability": {
        "only": {
          "extra_body.enable_thinking": true
        }
      },
      "type": "integer",
      "range": {
        "min": 1
      }
    }
  ]
}

Other Alibaba models

DeepSeek v3.2 6 params View DeepSeek v4 Flash 6 params View DeepSeek v4 Flash 0731 6 params View DeepSeek v4 Pro 6 params View DeepSeek v4 Pro 0813 6 params View GLM-5.1 6 params View GLM-5.2 6 params View Kimi K2.7 Code 6 params View Qwen Flash 5 params View Qwen Max 5 params View Qwen Plus 5 params View Qwen Turbo 5 params View Qwen3 235B A22B Thinking 2507 5 params View Qwen3 30B A3B Instruct 2507 5 params View Qwen3 30B A3B Thinking 2507 5 params View Qwen3 Coder Flash 4 params View Qwen3 Coder Next 4 params View Qwen3 Coder Plus 4 params View Qwen3 Max 5 params View Qwen3 Next 80B A3B Instruct 5 params View Qwen3 Next 80B A3B Thinking 5 params View Qwen3 Vl 235B A22B Instruct 5 params View Qwen3 Vl 235B A22B Thinking 5 params View Qwen3.5 5 params View Qwen3.5 122B A10B 5 params View Qwen3.5 27B 5 params View Qwen3.5 35B A3B 5 params View Qwen3.5 397B A17B 5 params View Qwen3.5 Flash 5 params View Qwen3.6 27B 6 params View Qwen3.6 35B A3B 6 params View Qwen3.6 Flash 6 params View Qwen3.6 Max Preview 6 params View Qwen3.6 Plus 6 params View Qwen3.7 Flash 6 params View Qwen3.7 Max 6 params View Qwen3.7 Plus 6 params View Qwen3.8 27B 6 params View Qwen3.8 Max 6 params View QwQ Plus 4 params View

How to use

Building with an AI agent? Hit Copy to grab this whole guide as Markdown and paste it in — or point your agent straight at /llms.txt.

modelparams.dev is an open, community-maintained catalog of model parameters. Each entry shows the knobs you can turn — type, default, range, and the conditions that gate it.

The same model accessed via an API key and via a subscription usually exposes a different set of parameters. We list both as separate entries so the data stays honest.

Catalog API

The full catalog is static JSON, CORS-enabled, served from the edge.

curl https://modelparams.dev/api/v1/models.json

Each entry is keyed by provider/model for API-key variants; subscription variants append -subscription.

If you only need the params for one model contract, use the providerless endpoint. Subscription contracts are model slugs with -subscription. 

curl https://modelparams.dev/api/v1/models/openai/gpt-5.5.json
curl https://modelparams.dev/api/v1/models/openai/gpt-5.5-subscription.json

Single model

curl https://modelparams.dev/api/v1/models/anthropic/claude-opus-4-7.json
curl https://modelparams.dev/api/v1/models/anthropic/claude-opus-4-7-subscription.json

JSON Schema

Every entry validates against a JSON Schema you can use in your editor or pipeline. 

curl https://modelparams.dev/api/v1/schema.json

Add this header to any YAML you author for autocomplete in VS Code: 

# yaml-language-server: $schema=https://modelparams.dev/api/v1/schema.json

Logos

Provider logos are available at /assets/logos/{provider}.svg where {provider} is the provider slug. They use currentColor so they inherit your text color. 

curl https://modelparams.dev/assets/logos/anthropic.svg

Logos are sourced from the models.dev repo (MIT) and used under nominative fair use.

Contribute

The data lives in YAML under models/{provider}/{model}-{auth}.yaml in the GitHub repo. Open a PR; CI validates against the schema and rebuilds.

Edit on GitHub MIT licensed