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
Reasoning enum 52 models

Reasoning effort reasoning_effort

Controls how much reasoning the model should perform before producing an answer.

Type
enum
Default
varies by model

reasoning_effort by model

The exact type, default, range, and conditions for reasoning_effort on each model that documents it.

Model Provider Type Default Range / values Condition
Zai GLM-4.7 Cerebras enum — none | low | medium | high —
DeepSeek Reasoner DeepSeek enum "high" high | max
Only when thinking.type = "enabled"
DeepSeek-V4 Flash DeepSeek enum "high" high | max
Only when thinking.type = "enabled"
DeepSeek-V4 Pro DeepSeek enum "high" high | max
Only when thinking.type = "enabled"
GPT-OSS 120B Groq enum "default" none | default —
GPT-OSS 20B Groq enum "default" none | default —
GPT-OSS Safeguard 20B Groq enum "default" none | default —
Qwen3 32B Groq enum "default" none | default —
Qwen3.6 27B Groq enum "default" none | default —
Muse Spark 1.1 Meta enum — minimal | low | medium | high | xhigh —
Muse Spark 1.2 Contributor Meta enum — minimal | low | medium | high | xhigh —
Kimi K3 Moonshot AI enum "max" low | high | max —
Nemotron 3 Super 120B A12B NVIDIA enum "high" none | low | high —
Nemotron 3 Ultra Subscription NVIDIA enum "high" none | medium | high —
Nemotron 3 Ultra 550B A55B NVIDIA enum "high" none | medium | high —
GPT-4 OpenAI enum "medium" low | medium | high —
GPT-5 OpenAI enum "medium" minimal | low | medium | high —
GPT-5 Mini OpenAI enum "medium" minimal | low | medium | high —
GPT-5 Nano OpenAI enum "medium" minimal | low | medium | high —
GPT-5.1 OpenAI enum "none" none | low | medium | high —
GPT-5.2 OpenAI enum "medium" none | low | medium | high | xhigh —
GPT-5.3 Codex OpenAI enum "medium" low | medium | high | xhigh —
GPT-5.4 OpenAI enum "medium" none | low | medium | high | xhigh —
GPT-5.4 Mini OpenAI enum "medium" none | low | medium | high | xhigh —
GPT-5.4 Nano OpenAI enum "medium" none | low | medium | high | xhigh —
GPT-5.4 Pro OpenAI enum "medium" medium | high | xhigh —
GPT-5.5 OpenAI enum "medium" none | low | medium | high | xhigh —
GPT-5.5 Pro OpenAI enum "medium" medium | high | xhigh —
GPT-5.6 OpenAI enum "none" none | low | medium | high | xhigh —
GPT-5.6 Luna OpenAI enum "none" none | low | medium | high | xhigh —
GPT-5.6 Sol OpenAI enum "none" none | low | medium | high | xhigh —
GPT-5.6 Terra OpenAI enum "none" none | low | medium | high | xhigh —
GPT-OSS 120B OpenAI enum "medium" low | medium | high —
GPT-OSS 20B OpenAI enum "medium" low | medium | high —
GPT-OSS Safeguard 120B OpenAI enum "medium" low | medium | high —
GPT-OSS Safeguard 20B OpenAI enum "medium" low | medium | high —
o1 OpenAI enum "medium" low | medium | high | xhigh —
o1-mini OpenAI enum "medium" minimal | low | medium | high —
o1-preview OpenAI enum "medium" minimal | low | medium | high —
o3 OpenAI enum "medium" low | medium | high | xhigh —
o3-mini OpenAI enum "medium" low | medium | high | xhigh —
o3-pro OpenAI enum "medium" low | medium | high | xhigh —
o4-mini OpenAI enum "medium" low | medium | high | xhigh —
Sonar Deep Research Perplexity enum — minimal | low | medium | high —
Inkling Thinking Machines enum "high" none | minimal | low | medium | high | xhigh —
Grok 4.3 xAI enum "low" none | low | medium | high —
Grok 4.3 Subscription xAI enum "low" none | low | medium | high —
Grok 4.5 xAI enum "low" none | low | medium | high —
Grok 4.5 Subscription xAI enum "low" none | low | medium | high —
GLM-5.2 Z.ai enum "max" none | minimal | low | medium | high | xhigh | max
Only when thinking.type = "enabled"
GLM-5.2 Subscription Z.ai enum "max" none | minimal | low | medium | high | xhigh | max
Only when thinking.type = "enabled"
GLM-5.3 Z.ai enum "max" none | minimal | low | medium | high | xhigh | max
Only when thinking.type = "enabled"

Models without reasoning_effort documented yet

These models don't list reasoning_effort in the catalog. That may mean the provider doesn't accept it, or it simply hasn't been added yet — the data is community-maintained.

Alibaba

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

Anthropic

Claude 3 Opus 20240229 Claude 3 Opus Latest Claude 3.5 Haiku 20241022 Claude 3.5 Haiku Latest Claude 3.5 Sonnet 20241022 Claude 3.5 Sonnet Latest Claude 3.7 Sonnet 20250219 Claude 3.7 Sonnet Latest Claude Fable 5 Claude Fable 5 Claude Haiku 4 Claude Haiku 4 Claude Haiku 4.5 Claude Haiku 4.5 Claude Haiku 4.5 20251001 Claude Haiku 4.5 20251001 Claude Opus 4 Claude Opus 4 20250514 Claude Opus 4 20250514 Claude Opus 4.1 20250805 Claude Opus 4.1 20250805 Claude Opus 4.5 20251101 Claude Opus 4.5 20251101 Claude Opus 4.6 Claude Opus 4.6 Claude Opus 4.7 Claude Opus 4.7 Claude Opus 4.8 Claude Opus 4.8 Claude Opus 5 Claude Opus 5 Claude Sonnet 4 Claude Sonnet 4 20250514 Claude Sonnet 4 20250514 Claude Sonnet 4.5 Claude Sonnet 4.5 Claude Sonnet 4.5 20250929 Claude Sonnet 4.5 20250929 Claude Sonnet 4.6 Claude Sonnet 4.6 Claude Sonnet 5 Claude Sonnet 5

Bedrock

Claude Haiku 4.5 Claude Opus 4.5 20251101 Claude Opus 4.6 Claude Sonnet 4.5 Claude Sonnet 4.6 DeepSeek R1 DeepSeek v3.2 Devstral 2 123B Gemma 3 12B IT Gemma 3 27B IT Gemma 3 4B IT GLM-4.7 GLM-4.7 Flash GLM-5 GPT-OSS 120B GPT-OSS 20B GPT-OSS Safeguard 120B GPT-OSS Safeguard 20B Kimi K2 Thinking Kimi K2.5 Llama3 1 70B Instruct Llama3 1 8B Instruct Llama3 3 70B Instruct Llama3 70B Instruct Llama3 8B Instruct Magistral Small 2509 MiniMax M2 MiniMax M2.1 MiniMax M2.5 Ministral 3 14B Instruct Ministral 3 3B Instruct Ministral 3 8B Instruct Mistral 7B Instruct Mistral Large 2402 Mistral Large 3 675B Instruct Mistral Small 2402 Mixtral 8x7b Instruct Nemotron Nano 12B Nemotron Nano 3 30B Nemotron Nano 9B Nemotron Super 3 120B Nova 2 Lite Nova Lite Nova Micro Nova Pro Palmyra Vision 7B Palmyra X4 Palmyra X5 Pixtral Large 2502 Qwen3 32B Qwen3 Coder 30B A3B Qwen3 Coder Next Qwen3 Next 80B A3B Qwen3 Vl 235B A22B Voxtral Mini 3B 2507 Voxtral Small 24B 2507

Cohere

Command A 03 2025 Command A Plus 05 2026 Command A Reasoning 08 2025 Command A Translate 08 2025 Command A Vision 07 2025 Command R 08 2024 Command R Plus 08 2024 Command R7B 12 2024

DeepSeek

DeepSeek Chat

Fireworks

DeepSeek v4 Flash 0731 DeepSeek v4 Pro DeepSeek v4 Pro 0813 GLM-5p2 GPT-OSS 120B GPT-OSS 20B Inkling Kimi K2p6 Kimi K2p7 Code Kimi K3 MiniMax M2p7 MiniMax M3 Muse Glimmer 30B Qwen3p7 Plus Qwen3p8 2p4t A95B Qwen3p8 Max

Google

Gemini 2.5 Flash Gemini 2.5 Flash Gemini 2.5 Flash Lite Gemini 2.5 Flash Lite Gemini 2.5 Pro Gemini 2.5 Pro Gemini 3 Flash Preview Gemini 3 Flash Preview Gemini 3.1 Flash Lite Gemini 3.1 Flash Lite Gemini 3.1 Flash Lite Preview Gemini 3.1 Flash Lite Preview Gemini 3.1 Pro Preview Gemini 3.1 Pro Preview Gemini 3.1 Pro Preview Customtools Gemini 3.5 Flash Gemini 3.5 Flash Lite Gemini 3.6 Flash Gemini 3.7 Flash Gemini Flash Latest Gemma 3 12B IT Gemma 3 1B IT Gemma 3 27B IT Gemma 3 4B IT Gemma 3n E2B IT Gemma 3n E4B IT Gemma 4 12B IT Gemma 4 26B A4B IT Gemma 4 31B IT Gemma 4 E2B IT Gemma 4 E4B IT

Meta

Llama 3.3 70B Instruct Llama 3.3 8B Instruct Llama 4 Maverick 17B 128E Instruct FP8 Llama 4 Scout 17B 16E Instruct FP8

MiniMax

MiniMax M2 MiniMax M2 MiniMax M2.1 MiniMax M2.1 MiniMax M2.1 Highspeed MiniMax M2.1 Highspeed MiniMax M2.5 MiniMax M2.5 MiniMax M2.5 Highspeed MiniMax M2.5 Highspeed MiniMax M2.7 MiniMax M2.7 MiniMax M2.7 Highspeed MiniMax M2.7 Highspeed MiniMax M3 MiniMax M3

Mistral

Codestral 2508 Codestral Latest Devstral 2512 Devstral Latest Magistral Medium Latest Magistral Small Latest Ministral 14B 2512 Ministral 14B Latest Ministral 3B 2512 Ministral 3B Latest Ministral 8B 2512 Ministral 8B Latest Mistral Large 2512 Mistral Large Latest Mistral Medium 3 Mistral Medium 3.5 Mistral Medium Latest Mistral NeMo Mistral Small 2603 Mistral Small Latest

Moonshot AI

Kimi K2.5 Kimi K2.6 Kimi K2.6 Kimi K2.7 Code Kimi K2.7 Code Kimi K2.7 Code Highspeed Kimi K2.7 Code Highspeed Moonshot v1 128K Moonshot v1 32K Moonshot v1 8K

NVIDIA

DeepSeek v4 Flash 0731 GLiNER PII Llama 3.1 NemoGuard 8B Topic Control Llama 3.1 Nemotron Nano 8B v1 Llama 3.1 Nemotron Safety Guard 8B v3 Llama 3.1 Nemotron Ultra 253B v1 Llama 3.3 Nemotron Super 49B v1 Llama 3.3 Nemotron Super 49B v1.5 NemoGuard Jailbreak Detect Nemotron 3 Nano 30B A3B Nemotron Content Safety Reasoning 4B Nemotron Mini 4B Instruct Riva Translate 4B Instruct v1.1 USDCode Llama 3.1 70B Instruct

OpenAI

ChatGPT 4o Latest GPT-3.5 Turbo GPT-3.5 Turbo 16K GPT-4 0613 GPT-4 Turbo GPT-4 Turbo 2024-04-09 GPT-4.1 GPT-4.1 Mini GPT-4.1 Nano GPT-4o GPT-4o 2024-11-20 GPT-4o mini GPT-5 Chat Latest GPT-5.1 Codex GPT-5.1 Codex Max GPT-5.2 GPT-5.2 Codex GPT-5.3 Codex GPT-5.3 Codex Spark GPT-5.4 GPT-5.4 Mini GPT-5.4 Pro GPT-5.5 GPT-5.5 Pro GPT-5.6 Luna GPT-5.6 Sol GPT-5.6 Terra

Perplexity

Sonar Sonar Pro Sonar Reasoning Pro

Vertex

Gemini 2.5 Flash Gemini 2.5 Flash Lite Gemini 2.5 Pro Gemini 3 Flash Preview Gemini 3.1 Flash Lite Gemini 3.1 Pro Preview Gemini 3.1 Pro Preview Customtools Gemini 3.5 Flash Gemini 3.5 Flash Lite Gemini 3.6 Flash Gemini 3.7 Flash

xAI

Grok 4.20 0309 Non Reasoning Grok 4.20 0309 Non Reasoning Grok 4.20 0309 Reasoning Grok 4.20 0309 Reasoning Grok 4.20 Multi Agent 0309 Grok 4.6 Grok Build 0.1 Grok Build 0.1

Xiaomi

MiMo v2.5 MiMo v2.5 MiMo v2.5 Pro

Z.ai

GLM-4.5 GLM-4.5 GLM-4.5-Air GLM-4.5-Air GLM-4.5-AirX GLM-4.5-Flash GLM-4.5-X GLM-4.6 GLM-4.6 GLM-4.7 GLM-4.7 GLM-4.7-Flash GLM-4.7-FlashX GLM-5 GLM-5 GLM-5-Turbo GLM-5-Turbo GLM-5.1 GLM-5.1

Related reasoning parameters

Thinking mode thinking.type Include thoughts generationConfig.thinkingConfig.includeThoughts Budget tokens thinking.budget_tokens Thinking level generationConfig.thinkingConfig.thinkingLevel Thinking display thinking.display Enable thinking extra_body.enable_thinking Thinking budget extra_body.thinking_budget Thinking budget generationConfig.thinkingConfig.thinkingBudget Enable thinking extra_body.chat_template_kwargs.enable_thinking Effort output_config.effort Reasoning effort reasoning.effort Reasoning summary reasoning.summary

Resources

All parameters Use the API 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