AI ENGINE

AI Model
Reference

Complete guide to all 40+ AI models available in FRENZY.BOT. Each model is hand-picked for production readiness and performance.

40+
AI Models
11
Providers
ZDR
Zero Data Retention

Anthropic (Claude)

Advanced reasoning models with superior analytical capabilities and safety features.

Claude Opus 4.6

Anthropic ZDR
Context: 1M tokens
Pricing: $5.00 input / $25.00 output per 1M tokens
Best For:

Complex reasoning, advanced software engineering, agentic workflows, long-horizon computer use

Strengths:

Superior analytical capabilities, excels at multi-step problem solving, ideal for complex technical tasks and research

Claude Sonnet 4.6

Anthropic ZDR NEW
Context: 1M tokens
Pricing: $3.00 input / $15.00 output per 1M tokens
Best For:

Balanced performance for business applications, content creation, complex dialogue

Strengths:

Latest generation with improved reasoning and instruction following, excellent for customer support and content generation

Claude Sonnet 4

Anthropic ZDR
Context: 1M tokens
Pricing: $3.00 input / $15.00 output per 1M tokens
Best For:

General business tasks, customer support, content creation

Strengths:

Reliable performance, excellent instruction following, cost-effective for production use

Claude Sonnet 4.5

Anthropic ZDR
Context: 1M tokens
Pricing: $3.00 input / $15.00 output per 1M tokens
Best For:

Business applications, analytical tasks, complex Q&A

Strengths:

Strong reasoning capabilities, good balance of performance and cost

Claude Haiku 4.5

Anthropic ZDR
Context: 200K tokens
Pricing: $1.00 input / $5.00 output per 1M tokens
Best For:

Fast responses, real-time chat, high-volume interactions

Strengths:

Sub-second response times, cost-effective for scale, good for simple queries

Claude 3.5 Haiku

Anthropic ZDR
Context: 200K tokens
Pricing: $0.80 input / $4.00 output per 1M tokens
Best For:

Budget-conscious real-time applications, quick responses

Strengths:

Excellent speed-to-cost ratio, reliable for simple tasks

OpenAI (GPT)

Industry-leading models with exceptional performance across diverse tasks and applications.

GPT-5.2

OpenAI ZDR
Context: 400K tokens
Pricing: $1.75 input / $14.00 output per 1M tokens
Best For:

Advanced reasoning, complex tasks, professional applications

Strengths:

Latest generation with superior capabilities, excellent for complex problem solving

GPT-5.1

OpenAI ZDR
Context: 400K tokens
Pricing: $1.50 input / $12.00 output per 1M tokens
Best For:

Advanced applications, complex reasoning, professional use

Strengths:

Strong performance across diverse tasks, good for business-critical applications

GPT-5

OpenAI ZDR
Context: 400K tokens
Pricing: $1.25 input / $10.00 output per 1M tokens
Best For:

General advanced tasks, business applications, content creation

Strengths:

Excellent all-around performance, reliable for production use

GPT-4.1

OpenAI ZDR
Context: 1M tokens
Pricing: $2.00 input / $8.00 output per 1M tokens
Best For:

Advanced instruction following, software engineering, long-context reasoning

Strengths:

Flagship model with excellent reliability, strong for technical and analytical tasks

o3

OpenAI
Context: 200K tokens
Pricing: $2.00 input / $8.00 output per 1M tokens
Best For:

Complex reasoning, scientific tasks, mathematical problem solving

Strengths:

Advanced reasoning capabilities, excellent for complex analytical work

o4 Mini

OpenAI
Context: 200K tokens
Pricing: $1.10 input / $4.40 output per 1M tokens
Best For:

Balanced reasoning and speed, complex tasks with cost control

Strengths:

Good reasoning capabilities with better cost efficiency than full o-series models

GPT-5 Mini

OpenAI ZDR
Context: 400K tokens
Pricing: $0.25 input / $2.00 output per 1M tokens
Best For:

Cost-effective advanced tasks, business applications

Strengths:

Excellent value, good capabilities for the price point

GPT-4.1 Mini

OpenAI ZDR
Context: 1M tokens
Pricing: $0.40 input / $1.60 output per 1M tokens
Best For:

Balanced performance and cost, general business tasks

Strengths:

Good cost-to-performance ratio, reliable for production use

GPT-5 Nano

OpenAI ZDR
Context: 400K tokens
Pricing: $0.05 input / $0.40 output per 1M tokens
Best For:

High-volume simple tasks, budget operations

Strengths:

Extremely cost-effective, good for basic Q&A and simple interactions

GPT-4.1 Nano

OpenAI ZDR
Context: 1M tokens
Pricing: $0.10 input / $0.40 output per 1M tokens
Best For:

Budget operations, simple queries, high-volume applications

Strengths:

Very cost-effective with good context window, ideal for scale

Google (Gemini)

Multimodal models with exceptional reasoning and integration with Google ecosystem.

Gemini 3 Pro Preview

Google ZDR
Context: 1M tokens
Pricing: $2.00 input / $10.00 output per 1M tokens
Best For:

Advanced reasoning, coding, mathematics, scientific tasks

Strengths:

State-of-the-art reasoning capabilities, excellent for complex technical and analytical work

Gemini 2.5 Pro

Google ZDR
Context: 1M tokens
Pricing: $1.25 input / $10.00 output per 1M tokens
Best For:

Advanced reasoning, coding, mathematics, scientific analysis

Strengths:

Strong performance across technical domains, good balance of capability and cost

Gemini 3 Flash Preview

Google ZDR
Context: 1M tokens
Pricing: $0.40 input / $1.60 output per 1M tokens
Best For:

Real-time applications, fast responses, high-volume interactions

Strengths:

Excellent speed with good reasoning capabilities, ideal for customer-facing chat

Gemini 2.5 Flash

Google ZDR
Context: 1M tokens
Pricing: $0.30 input / $2.50 output per 1M tokens
Best For:

Fast responses, general tasks, cost-effective operations

Strengths:

Good balance of speed and capability, cost-effective for scale

Gemini 2.5 Flash Lite

Google ZDR
Context: 1M tokens
Pricing: $0.10 input / $0.40 output per 1M tokens
Best For:

High-volume simple queries, budget operations

Strengths:

Extremely cost-effective, good for basic Q&A and simple tasks

DeepSeek

Open-source models with exceptional reasoning capabilities and cost efficiency.

DeepSeek R1

DeepSeek ZDR
Context: 64K tokens
Pricing: $0.70 input / $2.50 output per 1M tokens
Best For:

Complex reasoning, mathematical problems, coding challenges

Strengths:

Open-source reasoning model with performance on par with OpenAI o1, excels at logical deduction and step-by-step problem solving

DeepSeek V3.2

DeepSeek ZDR
Context: 164K tokens
Pricing: $0.27 input / $1.10 output per 1M tokens
Best For:

General AI tasks, content generation, customer support

Strengths:

Excellent value proposition, strong performance across diverse tasks, improved long-context handling

DeepSeek V3.1

DeepSeek ZDR
Context: 32K tokens
Pricing: $0.15 input / $0.75 output per 1M tokens
Best For:

Budget-conscious applications, standard chatbot tasks

Strengths:

Outstanding cost efficiency, good performance for routine tasks

Meta (Llama)

Open-weights models with transparency and robust performance for diverse applications.

Llama 4 Maverick

Meta ZDR
Context: 1M tokens
Pricing: $0.15 input / $0.60 output per 1M tokens
Best For:

General AI tasks, content creation, customer support

Strengths:

Open-weights transparency, robust performance, excellent value

Llama 4 Scout

Meta ZDR
Context: 328K tokens
Pricing: $0.08 input / $0.30 output per 1M tokens
Best For:

Lightweight applications, fast responses, budget operations

Strengths:

Very cost-effective, good for standard chatbot tasks

Qwen (Alibaba)

Advanced models with exceptional reasoning and multilingual capabilities.

Qwen3 Max

Qwen
Context: 262K tokens
Pricing: $1.20 input / $6.00 output per 1M tokens
Best For:

Advanced reasoning, multilingual tasks, complex problem solving

Strengths:

Major improvements in reasoning, instruction following, multilingual support, excellent for math, coding, and science

Qwen3.5 397B A17B

Qwen ZDR NEW
Context: 262K tokens
Pricing: $0.55 input / $3.50 output per 1M tokens
Best For:

General advanced tasks, business applications, content creation

Strengths:

Strong performance with good cost efficiency, reliable for diverse use cases

Qwen3.5 Plus 2026-02-15

Qwen NEW
Context: 1M tokens
Pricing: $0.40 input / $2.40 output per 1M tokens
Best For:

Latest performance, general tasks, large document processing

Strengths:

Recent release with improved capabilities, excellent context window

Qwen3 Coder 480B

Qwen ZDR
Context: 262K tokens
Pricing: $0.22 input / $0.95 output per 1M tokens
Best For:

Coding tasks, technical applications, software development

Strengths:

Mixture-of-Experts design optimized for agentic coding tasks, function calling, and tool use

Qwen3 Next 80B A3B Instruct

Qwen ZDR
Context: 262K tokens
Pricing: $0.09 input / $1.10 output per 1M tokens
Best For:

Cost-effective general tasks, lightweight applications

Strengths:

Sparse MoE design with efficient inference, good performance for the cost

xAI (Grok)

Real-time knowledge models with massive context windows and fast processing.

Grok 4.1 Fast

xAI
Context: 2M tokens
Pricing: $0.20 input / $0.50 output per 1M tokens
Best For:

Real-time applications, large document processing, fast responses

Strengths:

Massive context window, excellent speed, good for high-volume interactions

Grok 4 Fast

xAI
Context: 2M tokens
Pricing: $0.20 input / $0.50 output per 1M tokens
Best For:

Fast responses, large context applications, real-time processing

Strengths:

Excellent speed with massive context, ideal for document analysis

Grok 3 Mini

xAI
Context: 131K tokens
Pricing: $0.30 input / $0.50 output per 1M tokens
Best For:

Cost-effective real-time knowledge, fast responses

Strengths:

Good balance of speed and cost, real-time knowledge access

MiniMax

Versatile models with strong performance across multiple languages and tasks.

NEW

MiniMax-01

MiniMax
Context: 1M tokens
Pricing: $0.20 input / $1.10 output per 1M tokens
Best For:

General tasks, content generation, multilingual applications

Strengths:

Strong overall performance, competitive pricing, good for diverse use cases

MiniMax M2.5

MiniMax
Context: 197K tokens
Pricing: $0.30 input / $1.10 output per 1M tokens
Best For:

Coding tasks, technical applications, complex reasoning

Strengths:

Scoring 80.2% on SWE-Bench Verified, excellent for coding and technical problem solving

MiniMax M2.1

MiniMax
Context: 197K tokens
Pricing: $0.27 input / $1.12 output per 1M tokens
Best For:

General applications, balanced performance

Strengths:

Good balance of capabilities and cost, reliable for diverse tasks

MiniMax M2-her

MiniMax
Context: 65K tokens
Pricing: $0.30 input / $1.20 output per 1M tokens
Best For:

Conversational AI, dialogue-first applications

Strengths:

Optimized for immersive dialogue, excellent for chatbot interactions

Mistral

European models with strong multilingual support and reliable performance.

Mistral Medium 3.1

Mistral
Context: 131K tokens
Pricing: $0.40 input / $2.00 output per 1M tokens
Best For:

General business tasks, content creation, European languages

Strengths:

Strong multilingual support, reliable performance, good for European markets

Mistral Medium 3

Mistral
Context: 131K tokens
Pricing: $0.40 input / $2.00 output per 1M tokens
Best For:

Business applications, content generation

Strengths:

Consistent performance, good for professional use cases

Mistral Small 3.2 24B

Mistral ZDR
Context: 131K tokens
Pricing: $0.06 input / $0.18 output per 1M tokens
Best For:

Lightweight applications, fast responses, budget operations

Strengths:

Very cost-effective, good for simple queries and high-volume use

Z.ai

Reliable models with good performance across general AI tasks.

GLM 5

Z.ai ZDR
Context: 205K tokens
Pricing: $0.30 input / $2.55 output per 1M tokens
Best For:

General AI tasks, multilingual applications, content generation

Strengths:

Strong overall performance, good for diverse use cases

GLM 4.7

Z.ai ZDR
Context: 203K tokens
Pricing: $0.38 input / $1.70 output per 1M tokens
Best For:

Balanced performance, business applications, technical tasks

Strengths:

Reliable performance with good reasoning capabilities

GLM 4.7 Flash

Z.ai ZDR
Context: 203K tokens
Pricing: $0.06 input / $0.40 output per 1M tokens
Best For:

Fast responses, budget operations, high-volume interactions

Strengths:

Very cost-effective, good for simple queries and scale

Model Selection Guide

By Use Case

Customer Support & Chat

Claude Sonnet 4.6, GPT-4.1, Gemini 2.5 Flash

Fast response times, Reliable performance, Cost-effective at scale

Complex Reasoning & Analysis

Claude Opus 4.6, GPT-5.2, Gemini 3 Pro, DeepSeek R1

Superior analytical capabilities, Multi-step problem solving, High accuracy on difficult tasks

Content Creation & Writing

Claude Sonnet 4, GPT-5, Gemini 2.5 Pro

Natural language generation, Creative capabilities, Consistent quality

Coding & Technical Tasks

Qwen3 Coder, MiniMax M2.5, GPT-5.2, DeepSeek R1

Strong code understanding, Tool use and function calling, Technical problem solving

Budget-Conscious Operations

DeepSeek V3.1, GPT-5 Nano, Gemini 2.5 Flash Lite, Mistral Small 3.2

Excellent cost efficiency, Good performance for routine tasks, Scalable for high volume

Large Document Processing

Grok 4.1 Fast, Claude Opus 4.6, Gemini 2.5 Pro

Massive context windows, Long-document understanding, Comprehensive analysis

By Performance Tier

Premium Tier (Highest Performance)

PREMIUM

Claude Opus 4.6, GPT-5.2, Gemini 3 Pro, Claude Sonnet 4.6

Standard Tier (Balanced Performance)

STANDARD

GPT-5, GPT-4.1, Gemini 2.5 Pro, Claude Sonnet 4, Qwen3 Max

Value Tier (Best Cost/Performance)

VALUE

DeepSeek V3.2, GPT-5 Mini, Gemini 2.5 Flash, Claude 3.5 Haiku, Llama 4 Maverick

Budget Tier (Lowest Cost)

BUDGET

DeepSeek V3.1, GPT-5 Nano, Gemini 2.5 Flash Lite, Mistral Small 3.2, GLM 4.7 Flash

Pricing Calculator

Use this quick reference to estimate costs:

Input Costs (per 1M tokens)

Premium: $5.00 - $2.00
Standard: $1.75 - $0.80
Value: $0.55 - $0.15
Budget: $0.10 - $0.05

Output Costs (per 1M tokens)

Premium: $25.00 - $8.00
Standard: $15.00 - $4.00
Value: $3.50 - $0.60
Budget: $0.40 - $0.18

Technical Specifications

Context Windows

Massive (2M+): Grok 4.1 Fast, Grok 4 Fast
Large (1M): Claude series, GPT-4.1 series, Gemini series, Llama 4 Maverick
Medium (200K-400K): GPT-5 series, MiniMax, Qwen3, Z.ai
Standard (64K-131K): DeepSeek R1, Mistral, Grok 3 Mini

Zero Data Retention Support

Models marked with ✅ support ZDR through OpenRouter's provider.zdr: true parameter, ensuring your data is never stored or used for training.

Zero Data Retention available on select models for maximum privacy.

Frequently Asked Questions

How often are new models added?

New models are evaluated and added within 24 hours of stable release from major providers.

Can I switch between models?

Yes, you can change models at any time in Settings → AI Engine. Changes take effect for new conversations.

Which models support Zero Data Retention?

Models marked with ✅ ZDR support include most Claude, GPT, DeepSeek, and select models from other providers.

How do I choose the right model for my use case?

Consider your budget, required response speed, complexity of tasks, and volume. Use the selection guide above or start with Standard tier models.

Are there usage limits?

Usage is billed per token through OpenRouter. FRENZY.BOT adds no markup. Check OpenRouter for current pricing and any rate limits.

Can I use multiple models for different tasks?

Currently, one model is selected per bot. Choose the model that best fits your primary use case.

Ready to Choose Your AI Model?

Get started with FRENZY.BOT and deploy any of these powerful AI models for your business.

Last updated: February 2026

Model availability and pricing are subject to change. Check OpenRouter for current information.