BlockRunBlockRun

Available Models

Pay with USDC on Base. No account needed.

39 models

GPT-5.2

openai

Latest frontier model with 400K context and adaptive reasoning

Input: $1.75/MOutput: $14.00/M

GPT-5 Mini

openai

Cost-optimized reasoning and chat

Input: $0.25/MOutput: $2.00/M

GPT-5 Nano

openai

High-throughput tasks and simple instruction-following

Input: $0.05/MOutput: $0.40/M

GPT-5.2 Pro

openai

Uses more compute for consistently better answers

Input: $21.00/MOutput: $168.00/M

GPT-5.2 Codex

openai

Specialized for code generation, understanding, and debugging with extended context

Input: $1.75/MOutput: $14.00/M

GPT-4.1

openai

Latest GPT-4 generation model

Input: $2.00/MOutput: $8.00/M

GPT-4.1 Mini

openai

Fast and affordable GPT-4.1 model

Input: $0.40/MOutput: $1.60/M

GPT-4.1 Nano

openai

Ultra-fast and cost-effective GPT-4.1

Input: $0.10/MOutput: $0.40/M

GPT-4o

openai

Multimodal model with vision and audio

Input: $2.50/MOutput: $10.00/M

GPT-4o Mini

openai

Fast and affordable GPT-4o model

Input: $0.15/MOutput: $0.60/M

o1

openai

Advanced reasoning model for complex tasks

Input: $15.00/MOutput: $60.00/M

o1-mini

openai

Fast reasoning model optimized for STEM

Input: $1.10/MOutput: $4.40/M

o3

openai

Latest reasoning model with improved performance

Input: $2.00/MOutput: $8.00/M

o3-mini

openai

Efficient reasoning model for STEM tasks

Input: $1.10/MOutput: $4.40/M

o4-mini

openai

Latest generation efficient reasoning model

Input: $1.10/MOutput: $4.40/M

GPT-OSS 20B

openaiTestnet

Open-weight 20B model (Apache 2.0), similar performance to o3-mini. Available on testnet for developer testing.

Price: $0.0010/request

GPT-OSS 120B

openaiTestnet

Open-weight 120B model (Apache 2.0), flagship open model. Available on testnet for developer testing.

Price: $0.0020/request

Claude Haiku 4.5

anthropic

Fastest and most efficient Claude, near-frontier intelligence

Input: $1.00/MOutput: $5.00/M

Claude Sonnet 4

anthropic

Best balance of intelligence, speed, and cost

Input: $3.00/MOutput: $15.00/M

Claude Opus 4

anthropic

Most powerful Claude model for complex tasks

Input: $15.00/MOutput: $75.00/M

Claude Opus 4.5

anthropic

Latest Anthropic flagship with enhanced reasoning and creativity

Input: $5.00/MOutput: $25.00/M

Claude Opus 4.6

anthropic

Latest flagship Claude with extended 64k output, vision, and advanced reasoning

Input: $5.00/MOutput: $25.00/M

Gemini 3 Pro Preview

google

Flagship frontier model for high-precision multimodal reasoning

Input: $2.00/MOutput: $12.00/M

Gemini 2.5 Pro

google

State-of-the-art for reasoning, coding, and mathematics

Input: $1.25/MOutput: $10.00/M

Gemini 2.5 Flash

google

Fast and efficient Gemini model

Input: $0.30/MOutput: $2.50/M

DeepSeek V3.2 Chat

deepseek

DeepSeek V3.2 non-thinking mode, excellent for chat and coding

Input: $0.28/MOutput: $0.42/M

DeepSeek V3.2 Reasoner

deepseek

DeepSeek V3.2 thinking mode for complex reasoning tasks

Input: $0.28/MOutput: $0.42/M

Grok 3

xai

xAI's flagship model with advanced reasoning. Supports Live Search for real-time X/Twitter data (+$0.025/source)

Input: $3.00/MOutput: $15.00/M

Grok 3 Mini

xai

Smaller, faster Grok model. Supports Live Search (+$0.025/source)

Input: $0.30/MOutput: $0.50/M

Grok 4.1 Fast (Reasoning)

xai

Latest Grok with chain-of-thought reasoning. 2M context, excellent for complex tasks

Input: $0.20/MOutput: $0.50/M

Grok 4.1 Fast

xai

Latest Grok for direct responses. 2M context, fast and affordable

Input: $0.20/MOutput: $0.50/M

Grok 4 Fast (Reasoning)

xai

Grok 4 with step-by-step reasoning. 2M context for complex analysis

Input: $0.20/MOutput: $0.50/M

Grok 4 Fast

xai

Grok 4 for quick responses. 2M context, great value

Input: $0.20/MOutput: $0.50/M

Grok Code Fast

xai

Specialized for code generation and analysis

Input: $0.20/MOutput: $1.50/M

Grok 4 (0709)

xai

Premium Grok 4 model for highest quality outputs

Input: $3.00/MOutput: $15.00/M

Grok 2 Vision

xai

Grok with vision capabilities for image understanding

Input: $2.00/MOutput: $10.00/M

Kimi K2.5 (Moonshot)

moonshot

Moonshot's flagship MoE model with 262K context, vision, and agentic capabilities

Input: $0.60/MOutput: $3.00/M

GPT-OSS 120B (Free)

openaiFree

OpenAI's open-weight 120B model hosted free by NVIDIA. Apache 2.0 license, great for experimentation

Input: Free/MOutput: Free/M

Kimi K2.5

nvidia

Moonshot's flagship MoE model (1T params) hosted by NVIDIA. Vision and agentic capabilities

Input: $0.60/MOutput: $3.00/M