AI-Pass — The Enterprise AI Operating System

Authentication mode

Model Catalog (33 models)

GPT-5

frontier

Frontier reasoning and coding

Provider: OpenAI
Context: 256K
Speed: balanced
Quality: frontier
Input: $15/1M
Output: $60/1M

Complex reasoningAgent workflowsCode generation

GPT-4o

premium

Multimodal flagship

Provider: OpenAI
Context: 128K
Speed: balanced
Quality: frontier
Input: $5/1M
Output: $15/1M

ChatVisionTools

GPT-4o Mini

standard

Fast, cost-effective

Provider: OpenAI
Context: 128K
Speed: fast
Quality: great
Input: $0.15/1M
Output: $0.6/1M

High-volume chatClassification

o3-mini

premium

Reasoning optimized

Provider: OpenAI
Context: 200K
Speed: balanced
Quality: frontier
Input: $3/1M
Output: $12/1M

MathLogicPlanning

Claude Sonnet 4

premium

Best balance of speed and intelligence

Provider: Claude
Context: 200K
Speed: balanced
Quality: frontier
Input: $3/1M
Output: $15/1M

CodingAnalysisWriting

Claude Opus 4

frontier

Maximum capability

Provider: Claude
Context: 200K
Speed: quality
Quality: frontier
Input: $15/1M
Output: $75/1M

ResearchComplex agents

Claude Haiku

standard

Fast responses

Provider: Claude
Context: 200K
Speed: fast
Quality: great
Input: $0.8/1M
Output: $4/1M

SupportTriageSummaries

Gemini Pro

premium

Google flagship multimodal

Provider: Gemini
Context: 1000K
Speed: balanced
Quality: frontier
Input: $2.5/1M
Output: $10/1M

Long contextMultimodalResearch

Gemini Flash

standard

Ultra-fast Gemini

Provider: Gemini
Context: 1000K
Speed: fast
Quality: great
Input: $0.15/1M
Output: $0.6/1M

Real-timeHigh volume

DeepSeek V3

premium

Strong coding and math

Provider: OpenRouter
Context: 64K
Speed: balanced
Quality: great
Input: $0.27/1M
Output: $1.1/1M

CodeMathCost-efficient

DeepSeek R1

premium

Chain-of-thought reasoning

Provider: OpenRouter
Context: 64K
Speed: quality
Quality: frontier
Input: $0.55/1M
Output: $2.19/1M

ReasoningProofs

DeepSeek Free

free

Free tier DeepSeek via OpenRouter

Provider: OpenRouter
Context: 64K
Speed: fast
Quality: good
Input: $0/1M
Output: $0/1M

Free chatExperiments

Claude Sonnet (OpenRouter)

premium

Claude Sonnet via OpenRouter

Provider: OpenRouter
Context: 200K
Speed: balanced
Quality: frontier
Input: $3/1M
Output: $15/1M

CodingAnalysis

Qwen 2.5 72B (OpenRouter)

standard

Alibaba Qwen via OpenRouter

Provider: OpenRouter
Context: 131K
Speed: balanced
Quality: great
Input: $0.35/1M
Output: $0.4/1M

Chinese/EnglishCoding

Mistral Large

premium

European flagship

Provider: Mistral
Context: 128K
Speed: balanced
Quality: great
Input: $2/1M
Output: $6/1M

EU complianceMultilingual

Mistral Small

standard

Efficient general purpose

Provider: Mistral
Context: 128K
Speed: fast
Quality: good
Input: $0.2/1M
Output: $0.6/1M

ChatClassification

Codestral

premium

Code-specialized

Provider: Mistral
Context: 256K
Speed: fast
Quality: great
Input: $0.3/1M
Output: $0.9/1M

IDE completionRefactoring

Llama 4 70B

standard

Open frontier model

Provider: Llama
Context: 128K
Speed: balanced
Quality: great
Input: $0.4/1M
Output: $0.4/1M

Self-hostFine-tuning

Llama 3.3 70B

free

Proven open model

Provider: Llama
Context: 128K
Speed: balanced
Quality: good
Input: $0.2/1M
Output: $0.2/1M

General chatRAG

Qwen Max

premium

Alibaba flagship

Provider: Qwen
Context: 131K
Speed: balanced
Quality: great
Input: $1.6/1M
Output: $6.4/1M

Chinese/EnglishEnterprise

Qwen 2.5 72B

standard

Strong open model

Provider: Qwen
Context: 131K
Speed: balanced
Quality: great
Input: $0.35/1M
Output: $0.4/1M

CodingMath

Groq Llama 70B

standard

Ultra-low latency

Provider: Groq
Context: 128K
Speed: fast
Quality: good
Input: $0.59/1M
Output: $0.79/1M

Real-time chatVoice

Groq Mixtral

standard

Fast mixture-of-experts

Provider: Groq
Context: 33K
Speed: fast
Quality: good
Input: $0.24/1M
Output: $0.24/1M

Fast inference

Grok 2

premium

xAI conversational model

Provider: Grok
Context: 131K
Speed: balanced
Quality: great
Input: $2/1M
Output: $10/1M

Real-time infoChat

OpenRouter Auto

standard

Routes to best available

Provider: OpenRouter
Context: 128K
Speed: balanced
Quality: great
Input: $1/1M
Output: $3/1M

Fallback routing

Cerebras Llama 3.1 8B

standard

Ultra-fast Cerebras inference

Provider: Cerebras
Context: 8K
Speed: fast
Quality: good
Input: $0.1/1M
Output: $0.1/1M

Low latencyHigh volume

Cerebras Llama 3.3 70B

premium

Fast 70B on Cerebras

Provider: Cerebras
Context: 128K
Speed: fast
Quality: great
Input: $0.6/1M
Output: $0.6/1M

Production chat

SambaNova Llama 405B

frontier

Large model on SambaNova Cloud

Provider: SambaNova
Context: 128K
Speed: balanced
Quality: frontier
Input: $5/1M
Output: $15/1M

EnterpriseResearch

SambaNova DeepSeek V3

premium

DeepSeek on SambaNova

Provider: SambaNova
Context: 64K
Speed: balanced
Quality: great
Input: $1/1M
Output: $3/1M

CodeReasoning

Ollama Llama 3.2

free

Local offline model

Provider: Ollama
Context: 128K
Speed: fast
Quality: good
Input: $0/1M
Output: $0/1M

PrivacyOffline

HF Mistral 7B

free

Hosted open model

Provider: HuggingFace
Context: 33K
Speed: fast
Quality: good
Input: $0.1/1M
Output: $0.1/1M

Experiments

Together Llama 70B

standard

Fast open inference

Provider: Together
Context: 128K
Speed: fast
Quality: good
Input: $0.88/1M
Output: $0.88/1M

ScaleFine-tunes

Fireworks Llama 70B

standard

Optimized inference

Provider: Fireworks
Context: 128K
Speed: fast
Quality: good
Input: $0.9/1M
Output: $0.9/1M

ProductionLow latency

BYOK API Keys

Keys are stored locally in this demo. Never commit API keys to source control.

OpenAIClaudeGoogle GeminiOpenRouterDeepSeekGrok