Generación de Código APIs
Modelos optimizados para programación
DeepSeek V4 Flash
AMD Radeon Cloud Token Factory free API for DeepSeek V4 Flash with 1M context and dual OpenAI/Anthropic protocol support.
DeepSeek V4 Flash
Access deepseek-v4-flash free through Vercel's $5 monthly credit.
DeepSeek V4 Flash
DeepSeek V4 Flash 284B MoE (0731 release) on NVIDIA NIM — ultra-fast coding & tool calling with 1M context.
DeepSeek V4 Pro
DeepSeek V4 Pro 1.65T MoE flagship (0813 release) via NVIDIA NIM — 1M context, 1,000 free credits.
MiniMax M3
MiniMax M3 1M context coding flagship via GMI Cloud — 0-cost direct API access.
DeepSeek V4 Pro
DeepSeek official V4 Pro API with free registration token grants, Context Caching, and direct OpenAI SDK compatibility.
North Mini Code
North Mini Code compact coding specialist model free via OpenCode Zen.
Ling 3.0 Flash
Ling 3.0 Flash ultra-low latency text generation model free via OpenCode Zen.
Laguna S 2.1
Laguna S 2.1 lightweight agent router model free via OpenCode Zen.
Big Pickle
OpenCode's stealth high-throughput reasoning model available free during developer preview.
Muse Spark 1.2
Meta Muse Spark 1.2 free coding agent model via OpenCode Zen with $0/M tokens promotion.
Qwen2.5 Coder 32b Instruct
Free Qwen2.5 Coder 32b Instruct API via Cloudflare Workers AI with 10,000 daily free Neurons. Zero setup fee, no credit card required.