Available Models
Pay with USDC on Base. No account needed.
45 models
GPT-5.4
openaiMost capable and efficient frontier model with 1M context, native computer use, and thinking mode
GPT-5.4 Pro
openaiPremium GPT-5.4 with maximum compute for the hardest problems
GPT-5.2
openaiFrontier model with 400K context and adaptive reasoning
GPT-5 Mini
openaiCost-optimized reasoning and chat
GPT-5 Nano
openaiHigh-throughput tasks and simple instruction-following
GPT-5.2 Pro
openaiUses more compute for consistently better answers
GPT-5.2 Codex
openaiSpecialized for code generation, understanding, and debugging with extended context
GPT-4.1
openaiLatest GPT-4 generation model
GPT-4.1 Mini
openaiFast and affordable GPT-4.1 model
GPT-4.1 Nano
openaiUltra-fast and cost-effective GPT-4.1
GPT-4o
openaiMultimodal model with vision and audio
GPT-4o Mini
openaiFast and affordable GPT-4o model
o1
openaiAdvanced reasoning model for complex tasks
o1-mini
openaiFast reasoning model optimized for STEM
o3
openaiLatest reasoning model with improved performance
o3-mini
openaiEfficient reasoning model for STEM tasks
o4-mini
openaiLatest generation efficient reasoning model
GPT-OSS 20B
openaiTestnetOpen-weight 20B model (Apache 2.0), similar performance to o3-mini. Available on testnet for developer testing.
GPT-OSS 120B
openaiTestnetOpen-weight 120B model (Apache 2.0), flagship open model. Available on testnet for developer testing.
Claude Haiku 4.5
anthropicFastest and most efficient Claude, near-frontier intelligence
Claude Sonnet 4.6
anthropicBest balance of intelligence, speed, and cost with 1M context
Claude Opus 4.5
anthropicLatest Anthropic flagship with enhanced reasoning and creativity
Claude Opus 4.6
anthropicLatest flagship Claude with extended 64k output, vision, and advanced reasoning
Gemini 3.1 Pro
googleLatest Gemini with improved thinking, token efficiency, and agentic capabilities. Optimized for software engineering (requires new SDK)
Gemini 3 Pro Preview
googleFlagship frontier model for high-precision multimodal reasoning
Gemini 3 Flash Preview
googleFrontier-class performance with Pro-level intelligence at Flash speed and pricing. Includes thinking mode (requires new SDK)
Gemini 2.5 Pro
googleState-of-the-art for reasoning, coding, and mathematics
Gemini 2.5 Flash
googleFast and efficient Gemini model
Gemini 2.5 Flash Lite
googleMost economical Gemini model - ultra-fast and lightweight (requires new SDK)
DeepSeek V3.2 Chat
deepseekDeepSeek V3.2 non-thinking mode, excellent for chat and coding
DeepSeek V3.2 Reasoner
deepseekDeepSeek V3.2 thinking mode for complex reasoning tasks
Grok 3
xaixAI's flagship model with advanced reasoning. Supports Live Search for real-time X/Twitter data (+$0.025/source)
Grok 3 Mini
xaiSmaller, faster Grok model. Supports Live Search (+$0.025/source)
Grok 4.1 Fast (Reasoning)
xaiLatest Grok with chain-of-thought reasoning. 2M context, excellent for complex tasks
Grok 4.1 Fast
xaiLatest Grok for direct responses. 2M context, fast and affordable
Grok 4 Fast (Reasoning)
xaiGrok 4 with step-by-step reasoning. 2M context for complex analysis
Grok 4 Fast
xaiGrok 4 for quick responses. 2M context, great value
Grok Code Fast
xaiSpecialized for code generation and analysis
Grok 4 (0709)
xaiPremium Grok 4 model for highest quality outputs
Grok 2 Vision
xaiGrok with vision capabilities for image understanding
Kimi K2.5 (Moonshot)
moonshotMoonshot's flagship MoE model with 262K context, vision, and agentic capabilities
MiniMax M2.5
minimaxMiniMax's flagship reasoning model. Great value for complex tasks (~60 tps)
GPT-OSS 120B (Free)
openaiFreeOpenAI's open-weight 120B model hosted free by NVIDIA. Apache 2.0 license, great for experimentation
GPT-OSS 20B (Free)
openaiFreeOpenAI's open-weight 20B model hosted free by NVIDIA. Fast and efficient for simpler tasks
Kimi K2.5
nvidiaMoonshot's flagship MoE model (1T params) hosted by NVIDIA. Vision and agentic capabilities