OpenAI Models

Access OpenAI's powerful models through our unified API with the following pricing:

GPT-5
Input $1.28
Output $10.40
per 1M tokens

High-performance model delivering state-of-the-art natural language understanding and generation.

GPT-5-Mini
Input $0.26
Output $2.08
per 1M tokens

Compact and efficient model designed for fast responses with balanced accuracy and cost.

GPT-5-Nano
Input $0.05
Output $0.42
per 1M tokens

Lightweight model optimized for simple tasks with minimal resource usage and low cost.

GPT-5-Chat-Latest
Input $1.30
Output $10.40
per 1M tokens

Optimized for conversational AI applications, providing natural, context-aware chat experiences.

GPT-4.1
Input $2.08
Output $8.32
per 1M tokens

OpenAI's flagship model with advanced reasoning capabilities

GPT-4.1 Mini
Input $0.42
Output $1.66
per 1M tokens

Smaller, more efficient version of GPT-4-1

GPT-4.1 Nano
Input $0.10
Output $0.42
per 1M tokens

Offers robust language understanding with enhanced context retention and improved generation quality for diverse applications.

GPT-O3
Input $2.08
Output $8.32
per 1M tokens

Premium model with exceptional capabilities

GPT-O4Mini
Input $1.14
Output $4.58
per 1M tokens

Compact version of the premium O-series

GPT-o3-pro
Input $20.80
Output $83.20
per 1M tokens

OpenAI's flagship model with advanced reasoning capabilities

GPT-4o
Input $2.60
Output $10.40
per 1M tokens

OpenAI's latest model with multimodal capabilities

GPT-4o-mini
Input $0.16
Output $0.62
per 1M tokens

Smaller, more efficient version of GPT-4o

GPT-o1
Input $15.60
Output $62.40
per 1M tokens

Premium model with exceptional capabilities

GPT-o3-DeepResearch
Input $10.40
Output $41.60
per 1M tokens

Specialized model for deep research tasks

GPT-o3-Mini
Input $1.14
Output $4.58
per 1M tokens

Compact version of the premium O3-series

GPT-o1-Mini
Input $1.14
Output $4.58
per 1M tokens

Lightweight version of GPT-o1 optimized for efficiency

Claude Models

Anthropic's Claude models offer exceptional conversation abilities:

Claude Opus 4
Input $15.60
Output $78.00
per 1M tokens

Anthropic's most capable model for complex tasks

Claude Sonnet 4
Input $3.12
Output $15.60
per 1M tokens

Balanced performance for most applications

Claude Haiku 3.5
Input $0.83
Output $4.16
per 1M tokens

Fast and efficient for everyday tasks

Claude Opus 3
Input $15.60
Output $78.00
per 1M tokens

Previous generation flagship model

Claude Sonnet 3.7
Input $3.12
Output $15.60
per 1M tokens

Versatile model for a wide range of applications

Claude Haiku 3
Input $0.26
Output $1.30
per 1M tokens

Lightweight model for quick responses

DeepSeek Models

DeepSeek's powerful models for specialized tasks:

DeepSeek V3
Input $0.28
Output $1.14
per 1M tokens

Versatile chat model for general applications

DeepSeekR1
Input $0.57
Output $2.28
per 1M tokens

Specialized reasoning model for complex problems

Gemini Models

Google's Gemini models offer cutting-edge capabilities:

Gemini 2.5 Flash Preview
Input $0.31
Output $2.60
per 1M tokens

Fast and efficient model for quick responses

Gemini 2.5 Pro Preview
Input $1.30
Output $10.40
per 1M tokens

Advanced capabilities for complex tasks

Gemini 2.0 Flash
Input $0.10
Output $0.42
per 1M tokens

Lightweight model optimized for speed

Gemini 2.0 Flash Lite
Input $0.07
Output $0.31
per 1M tokens

Ultra-light model for basic tasks

Gemini 1.5 Flash
Input $0.07
Output $0.31
per 1M tokens

Versatile model for general applications

Gemini 1.5 Flash 8B
Input $0.03
Output $0.16
per 1M tokens

Smaller version optimized for efficiency

Gemini 1.5 Pro
Input $1.30
Output $5.20
per 1M tokens

Powerful model for demanding tasks

Mistral Models

High-performance open-weight and proprietary models from Mistral:

Mistral Medium 3
Input $0.42
Output $2.08
per 1M tokens

General-purpose model for versatile tasks

Magistral Medium (Preview)
Input $2.08
Output $5.20
per 1M tokens

Preview of Mistral's high-end multilingual reasoning model

Codestral
Input $0.31
Output $0.94
per 1M tokens

Code-specialized model for software development tasks

Devstral Medium
Input $0.42
Output $2.08
per 1M tokens

Developer-optimized model for general code and chat

Mistral Large
Input $2.08
Output $6.24
per 1M tokens

Flagship large-scale model for complex reasoning

Pixtral Large
Input $2.08
Output $6.24
per 1M tokens

Multimodal large model by Mistral

Ministral 8B 24.10
Input $0.10
Output $1.04
per 1M tokens

Efficient 8B model optimized for performance

Ministral 3B 24.10
Input $0.04
Output $0.04
per 1M tokens

Tiny model ideal for embedded use cases

Mistral Small 3.2
Input $0.10
Output $0.31
per 1M tokens

Small but capable model for lightweight applications

Magistral Small
Input $0.52
Output $1.56
per 1M tokens

Smaller version of Magistral optimized for cost and speed

Devstral Small
Input $0.10
Output $0.31
per 1M tokens

Compact dev-focused model

Pixtral 12B
Input $0.16
Output $0.16
per 1M tokens

Multimodal mid-size model

Mistral NeMo
Input $0.16
Output $0.16
per 1M tokens

NeMo-integration capable model for research and tools

Ready to get started?

Sign up now and get access to all these models through our unified API.

Create Free Account