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 API parameters

modelparams.dev tracks API parameters for 41 Alibaba models. Open a model to see its full set: the type, default, valid range or values, and the conditions that gate each parameter.

41 models

DeepSeek v3.2
Chat Completions 6 params
DeepSeek v4 Flash
Chat Completions 6 params
DeepSeek v4 Flash 0731
Chat Completions 6 params
DeepSeek v4 Pro
Chat Completions 6 params
DeepSeek v4 Pro 0813
Chat Completions 6 params
GLM-5.1
Chat Completions 6 params
GLM-5.2
Chat Completions 6 params
Kimi K2.7 Code
Chat Completions 6 params
Qwen Flash
Chat Completions 5 params
Qwen Max
Chat Completions 5 params
Qwen Plus
Chat Completions 5 params
Qwen Turbo
Chat Completions 5 params
Qwen3 235B A22B Thinking 2507
Chat Completions 5 params
Qwen3 30B A3B Instruct 2507
Chat Completions 5 params
Qwen3 30B A3B Thinking 2507
Chat Completions 5 params
Qwen3 Coder Flash
Chat Completions 4 params
Qwen3 Coder Next
Chat Completions 4 params
Qwen3 Coder Plus
Chat Completions 4 params
Qwen3 Max
Chat Completions 5 params
Qwen3 Next 80B A3B Instruct
Chat Completions 5 params
Qwen3 Next 80B A3B Thinking
Chat Completions 5 params
Qwen3 Vl 235B A22B Instruct
Chat Completions 5 params
Qwen3 Vl 235B A22B Thinking
Chat Completions 5 params
Qwen3.5
Chat Completions 5 params
Qwen3.5 122B A10B
Chat Completions 5 params
Qwen3.5 27B
Chat Completions 5 params
Qwen3.5 35B A3B
Chat Completions 5 params
Qwen3.5 397B A17B
Chat Completions 5 params
Qwen3.5 Flash
Chat Completions 5 params
Qwen3.6 27B
Chat Completions 6 params
Qwen3.6 35B A3B
Chat Completions 6 params
Qwen3.6 Flash
Chat Completions 6 params
Qwen3.6 Max Preview
Chat Completions 6 params
Qwen3.6 Plus
Chat Completions 6 params
Qwen3.7 Flash
Chat Completions 6 params
Qwen3.7 Max
Chat Completions 6 params
Qwen3.7 Plus
Chat Completions 6 params
Qwen3.8 2.4t A95B
Chat Completions 6 params
Qwen3.8 27B
Chat Completions 6 params
Qwen3.8 Max
Chat Completions 6 params
QwQ Plus
Chat Completions 4 params

Other providers

Bedrock 56 models OpenAI 55 models Anthropic 42 models Google 31 models Z.ai 22 models Mistral 20 models NVIDIA 17 models Fireworks 16 models MiniMax 16 models xAI 12 models Moonshot AI 11 models Vertex 11 models Cohere 8 models Meta 6 models Groq 5 models DeepSeek 4 models Perplexity 4 models Xiaomi 3 models Cerebras 1 model Thinking Machines 1 model

Resources

Glossary Full catalog

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