Skip to main content
Mantle Chat gives you access to the world’s leading AI models — no need to manage separate subscriptions.

​
Available Models

​
Anthropic (Claude)

ModelBest ForContext
Claude Sonnet 4.5Complex agents, advanced coding200K
Claude Haiku 4.5Real-time apps, fast responses200K
Claude Sonnet 4Superior coding, precise instructions200K
Claude Sonnet 3.7Advanced coding, mathematical reasoning200K
Claude Sonnet 3.5Code generation, complex problems200K

​
OpenAI (GPT)

ModelBest ForContext
GPT-5.2 ReasoningDeep reasoning, complex tasks500K
GPT-5.2Advanced coding, complex analysis500K
GPT-5.1 ReasoningDeep reasoning, agentic workflows400K
GPT-5.1Fast coding, low-latency tasks400K
GPT-5.1 CodexAgentic coding, complex refactoring400K
GPT-5 ReasoningDeep reasoning, agentic planning128K
GPT-5High-speed responses, multimodal128K
GPT-5 MiniBalanced performance, cost efficiency128K
GPT-5 NanoUltra-low latency, high concurrency64K
GPT-5-CodexAgentic coding, software engineering400K
GPT-4.1Complex problem solving, engineering1M
GPT-4.1 MiniBalanced performance, efficient128K
GPT-4.1 NanoUltra-fast responses, real-time apps64K
GPT-4oMultimodal tasks, complex reasoning128K
GPT-4o MiniFast processing, cost-effective128K

​
OpenAI (o-series Reasoning)

ModelBest ForContext
o3Complex reasoning, math, science200K
o3 MiniAdvanced reasoning, scientific analysis128K
o4 MiniMathematical reasoning, logic128K

​
Google (Gemini)

ModelBest ForContext
Gemini 3 ProAdvanced reasoning, agentic workflows1M
Gemini 2.5 ProCoding, reasoning, multimodal1M
Gemini 2.5 FlashLarge scale processing, agentic1M
Gemini 2.5 Flash LiteCost-efficiency, high throughput1M
Gemini 2.0 FlashLong context, realtime streaming1M
Gemini 2.0 Flash LiteCost efficiency, low latency1M

​
xAI (Grok)

ModelBest ForContext
Grok 4Natural language, math, reasoning256K
Grok 4 FastFunction calling, structured outputs2M
Grok 4 Fast ReasoningComplex reasoning, large context2M
Grok 4.1 FastAgentic tool calling, high performance2M
Grok 4.1 Fast ReasoningAgentic reasoning, multi-step planning2M
Grok 3Enterprise tasks, data extraction128K
Grok 3 MiniLogic-based tasks, quick reasoning128K

​
DeepSeek

ModelBest ForContext
DeepSeek V3.2Math reasoning, coding, writing128K
DeepSeek V3.2 SpecialeMaximum reasoning depth128K
DeepSeek V3.1 TerminusAgent workflows, English tasks128K
DeepSeek R1Agentic reasoning, structured output128K
DeepSeek V3General reasoning, cost-effective128K

​
How to Switch Models

1

Click the Model Selector

Find it at the bottom of your chat window
2

Choose a Model

Browse by provider or search by name (Cmd/Ctrl + K)
3

Continue Chatting

Your conversation context is preserved
Use Cmd/Ctrl + K to quickly search and switch models without leaving your keyboard.

​
Model Selection Tips

Claude Sonnet 4.5, GPT-5.1 Codex, or Gemini 2.5 Pro — excellent at code generation, debugging, and complex refactoring. For agentic coding workflows, try GPT-5-Codex.
Claude Sonnet 3.7 or Claude Sonnet 4 — natural writing style, great at following tone and format instructions.
o3, GPT-5.2 Reasoning, or Grok 4 — when you need step-by-step thinking on hard problems. For math specifically, try DeepSeek R1.
Claude Haiku 4.5, GPT-4.1 Nano, or Gemini 2.0 Flash Lite — fast and cost-effective for simple questions.
Gemini 2.5 Pro (1M context) or Grok 4 Fast (2M context) — when you need to analyze large files or codebases.
For detailed model benchmarks and comparisons, check out Artificial Analysis — an independent resource for AI model performance data.

​
Special Capabilities

Some models can search the web for current information:
  • Returns results with citations and sources
  • Great for research, news, and fact-checking
  • Available on Pro plan

​
Reasoning Mode

See the AI’s thinking process:
  • Models with reasoning support show chain-of-thought thinking
  • Helpful for understanding complex answers
  • Toggle visibility in settings

​
File Analysis

Upload files for AI to analyze:
  • Documents (PDF, Word, text)
  • Images (for multimodal models)
  • Code files

​
Model Availability by Plan

PlanAvailable Models
AnonymousGPT-4.1 Nano, Gemini 2.0 Flash Lite
FreeGPT-4.1 Nano, Gemini 2.0 Flash Lite, Gemini 2.0 Flash
ProAll standard models + premium models with credits

Compare Plans

See full plan comparison and pricing

​
Resources

Artificial Analysis

Independent AI model benchmarks and performance comparisons

OpenAI Models

Official OpenAI documentation

Anthropic Claude

Official Claude model documentation

Google Gemini

Official Gemini model documentation