Model Catalog

Browse and compare 31 AI models from OpenAI, Anthropic, and Google. All available through Hicap's unified API.

31 models

GPT-5.2

OpenAI

Latest and most advanced GPT model with massive context window and superior reasoning capabilities.

Capabilities
Ttext👁visionfunction calling📡streaming
Endpoints
/chat/completion
Context Window
400K tokens
Max Output
128K
Pricing
Input:$1.75 / 1M tokens
Output:$14.00 / 1M tokens
Available

GPT-5.2 Chat

OpenAI

Chat-optimized version of GPT-5.2 with lower latency for conversational AI.

Capabilities
Ttext👁visionfunction calling📡streaming
Endpoints
/chat
Context Window
128K tokens
Max Output
16K
Pricing
Input:$1.75 / 1M tokens
Output:$14.00 / 1M tokens
Available

GPT-5.1

OpenAI

Advanced GPT-5 series model with exceptional performance across all tasks.

Capabilities
Ttext👁visionfunction calling📡streaming
Endpoints
/chat/completion
Context Window
400K tokens
Max Output
128K
Pricing
Input:$1.25 / 1M tokens
Output:$10.00 / 1M tokens
Available

GPT-5.1 Chat

OpenAI

Chat-focused GPT-5.1 with optimized response times.

Capabilities
Ttext👁visionfunction calling📡streaming
Endpoints
/chat
Context Window
128K tokens
Max Output
16K
Pricing
Input:$1.25 / 1M tokens
Output:$10.00 / 1M tokens
Available

GPT-5

OpenAI

Foundation GPT-5 model with breakthrough capabilities in reasoning and generation.

Capabilities
Ttext👁visionfunction calling📡streaming
Endpoints
/chat/completion
Context Window
400K tokens
Max Output
128K
Pricing
Input:$1.25 / 1M tokens
Output:$10.00 / 1M tokens
Available

GPT-5 Chat

OpenAI

Conversational variant of GPT-5 optimized for dialogue.

Capabilities
Ttext👁visionfunction calling📡streaming
Endpoints
/chat
Context Window
400K tokens
Max Output
128K
Pricing
Input:$1.25 / 1M tokens
Output:$10.00 / 1M tokens
Available

GPT-5 Mini

OpenAI

Compact GPT-5 model balancing performance and efficiency.

Capabilities
Ttextfunction calling📡streaming
Endpoints
/chat/completion
Context Window
400K tokens
Max Output
128K
Pricing
Input:$0.40 / 1M tokens
Output:$1.60 / 1M tokens
Available

GPT-5 Nano

OpenAI

Smallest GPT-5 variant for ultra-fast responses and high throughput.

Capabilities
Ttext📡streaming
Endpoints
/chat/completion
Context Window
400K tokens
Max Output
128K
Pricing
Input:$0.10 / 1M tokens
Output:$0.40 / 1M tokens
Available

GPT-4o

OpenAI

Multimodal GPT-4 model with vision, audio, and enhanced reasoning.

Capabilities
Ttext👁vision🎵audiofunction calling📡streaming
Endpoints
/chat/completion
Context Window
128K tokens
Max Output
16K
Pricing
Input:$2.50 / 1M tokens
Output:$10.00 / 1M tokens
Available

GPT-4o Mini

OpenAI

Efficient GPT-4o variant for cost-effective multimodal applications.

Capabilities
Ttext👁visionfunction calling📡streaming
Endpoints
/chat/completion
Context Window
128K tokens
Max Output
16K
Pricing
Input:$0.15 / 1M tokens
Output:$0.60 / 1M tokens
Available

GPT-4.1

OpenAI

Extended context GPT-4 with 1M token window for processing very long documents.

Capabilities
Ttext👁visionfunction calling📡streaming
Endpoints
/chat/completion
Context Window
1M tokens
Max Output
32K
Pricing
Input:$2.00 / 1M tokens
Output:$8.00 / 1M tokens
Available

GPT-4.1 Mini

OpenAI

Compact version of GPT-4.1 maintaining the extended context window.

Capabilities
Ttextfunction calling📡streaming
Endpoints
/chat/completion
Context Window
1M tokens
Max Output
32K
Pricing
Input:$0.40 / 1M tokens
Output:$1.60 / 1M tokens
Available

GPT-4.1 Nano

OpenAI

Ultra-efficient GPT-4.1 for high-speed processing of long contexts.

Capabilities
Ttext📡streaming
Endpoints
/chat/completion
Context Window
1M tokens
Max Output
32K
Pricing
Input:$0.10 / 1M tokens
Output:$0.40 / 1M tokens
Available

Claude Sonnet 4.5

Anthropic

Latest Claude Sonnet with enhanced reasoning and expanded context.

Capabilities
Ttext👁visionfunction calling📡streaming
Endpoints
/chat
Context Window
200K tokens
Max Output
64K
Pricing
Input:$5.00 / 1M tokens
Output:$25.00 / 1M tokens
Available

Claude Haiku 4.5

Anthropic

Fastest Claude model with updated knowledge and improved speed.

Capabilities
Ttext👁visionfunction calling📡streaming
Endpoints
/chat
Context Window
200K tokens
Max Output
64K
Pricing
Input:$1.00 / 1M tokens
Output:$5.00 / 1M tokens
Available

Claude Opus 4.5

Anthropic

Most powerful Claude model for the most demanding tasks.

Capabilities
Ttext👁visionfunction calling📡streaming
Endpoints
/chat
Context Window
200K tokens
Max Output
64K
Pricing
Input:$5.00 / 1M tokens
Output:$25.00 / 1M tokens
Available

Claude Opus 4.6

Anthropic

Latest Opus model with enhanced long-context capabilities and improved performance.

Capabilities
Ttext👁visionfunction calling📡streaming
Endpoints
/chat
Context Window
200K tokens
Max Output
64K
Pricing
Input:$5.00 / 1M tokens
Output:$25.00 / 1M tokens
Available

Claude Sonnet 4

Anthropic

Foundation Claude Sonnet 4 model with balanced performance and speed.

Capabilities
Ttext👁visionfunction calling📡streaming
Endpoints
/chat
Context Window
200K tokens
Max Output
64K
Pricing
Input:$3.00 / 1M tokens
Output:$15.00 / 1M tokens
Available

Claude Opus 4.1

Anthropic

Advanced Opus variant with superior performance on complex reasoning.

Capabilities
Ttext👁visionfunction calling📡streaming
Endpoints
/chat
Context Window
200K tokens
Max Output
32K
Pricing
Input:$15.00 / 1M tokens
Output:$75.00 / 1M tokens
Available

Claude Opus 4

Anthropic

Foundation Claude Opus 4 model for enterprise-grade applications.

Capabilities
Ttext👁visionfunction calling📡streaming
Endpoints
/chat
Context Window
200K tokens
Max Output
32K
Pricing
Input:$15.00 / 1M tokens
Output:$75.00 / 1M tokens
Available

Claude 3.7 Sonnet

Anthropic

Enhanced Claude 3 Sonnet with improved capabilities and larger output.

Capabilities
Ttext👁visionfunction calling📡streaming
Endpoints
/chat
Context Window
200K tokens
Max Output
64K
Pricing
Input:$3.00 / 1M tokens
Output:$15.00 / 1M tokens
Available

Claude 3.5 Sonnet

Anthropic

Balanced Claude 3.5 for production workloads with vision support.

Capabilities
Ttext👁visionfunction calling📡streaming
Endpoints
/chat
Context Window
200K tokens
Max Output
8K
Pricing
Input:$3.00 / 1M tokens
Output:$15.00 / 1M tokens
Available

Claude 3.5 Haiku

Anthropic

Fast and efficient Claude 3.5 for high-throughput applications.

Capabilities
Ttext👁vision📡streaming
Endpoints
/chat
Context Window
200K tokens
Max Output
8K
Pricing
Input:$0.80 / 1M tokens
Output:$4.00 / 1M tokens
Available

Gemini 3 Pro Preview

Google

Next-generation Gemini with breakthrough multimodal capabilities.

Capabilities
Ttext👁vision🎵audiofunction calling📡streaming
Endpoints
/chat/completion
Context Window
1M tokens
Max Output
64K
Pricing
Input:$2.00 / 1M tokens
Output:$12.00 / 1M tokens
Available

Gemini 3 Pro Image

Google

Specialized Gemini 3 variant optimized for image understanding and generation tasks.

Capabilities
Ttext👁vision📡streaming
Endpoints
/chat/completion
Context Window
1M tokens
Max Output
64K
Pricing
Input:$2.00 / 1M tokens
Output:$12.00 / 1M tokens
Available

Gemini 3 Flash Preview

Google

Ultra-fast Gemini 3 optimized for low-latency applications.

Capabilities
Ttext👁vision📡streaming
Endpoints
/chat/completion
Context Window
1M tokens
Max Output
64K
Pricing
Input:$0.50 / 1M tokens
Output:$3.00 / 1M tokens
Available

Gemini 2.5 Pro

Google

Advanced Gemini 2.5 Pro with enhanced reasoning and multimodal capabilities.

Capabilities
Ttext👁visionfunction calling📡streaming
Endpoints
/chat/completion
Context Window
1M tokens
Max Output
64K
Pricing
Input:$1.25 / 1M tokens
Output:$10.00 / 1M tokens
Available

Gemini 2.5 Flash

Google

Latest Gemini Flash with extended context and improved performance.

Capabilities
Ttext👁visionfunction calling📡streaming
Endpoints
/chat/completion
Context Window
1M tokens
Max Output
65K
Pricing
Input:$0.30 / 1M tokens
Output:$2.50 / 1M tokens
Available

Gemini 2.5 Flash Lite

Google

Lightweight Gemini 2.5 for cost-effective deployments.

Capabilities
Ttext👁vision📡streaming
Endpoints
/chat/completion
Context Window
1M tokens
Max Output
64K
Pricing
Input:$0.10 / 1M tokens
Output:$0.40 / 1M tokens
Available

Gemini 2.0 Flash

Google

Production Gemini 2.0 with excellent speed-to-quality ratio.

Capabilities
Ttext👁visionfunction calling📡streaming
Endpoints
/chat/completion
Context Window
1M tokens
Max Output
8K
Pricing
Input:$0.10 / 1M tokens
Output:$0.40 / 1M tokens
Available

Gemini 2.0 Flash Lite

Google

Efficient Gemini 2.0 variant for high-volume use cases.

Capabilities
Ttext📡streaming
Endpoints
/chat/completion
Context Window
1M tokens
Max Output
8K
Pricing
Input:$0.04 / 1M tokens
Output:$0.15 / 1M tokens
Available

Ready to start building?

Access all these models through a single API endpoint. Switch between providers with one line of code.