You don't need to pay

OpenAI API Pricing AI Claude Contact sales Try Claude Output $25 / MTok Prompt caching Write $6.25 / MTok Read $0.50 / MTok Sonnet 5 High-performance model for coding and agents Input $2 / MTok Output $10 / MTok Prompt caching Write $2.50 / MTok Read $0.20 / MTok *introductory pricing of $2/10 per million input/output tokens through August 31, 2024; $3/$15 standard pricing thereafter. Haiku 4.5 Fastest, most cost-efficient model Input $1 / MTok Individual Team & Enterprise API latest models Contact sales Start building Save 50% with batch processing. Learn more Batch processing Fable 5 Next generation Intelligence for long-running agents Input $10 / MTok Output $50 / MTok claude.com NVIDIA Models Deploy and scale models on your GPU inference microservices Optimized by NVIDIA Launch from Hugging Face Beta Filters Sort by Most Recent 141 models Refine models Zai glm-5.2 Downloadable Free Endpoint GLM-5.2 is a flagship LLM for agentic workflows, coding, and long-horizon reasoning tasks. agentic ai +3 NVIDIA nemotron-3-ultra-550b-a Downloadable Free Endpoint NVIDIA cosmos3-nano Free Endpoint Generates physics-aware videos from text prompts or an image prompt for physical AI development. autonomous vehicles NVIDIA cosmos3-nano-reasoner Downloadable Free Endpoint Vision language model that excels in understanding the physical world using structured reasoning on video or images. video understanding +8 Minimaxai minimax-m3 Free Endpoint Minimax M3 Preview is a multimodal MoE vision-language model with strong reasoning, coding, and... coding +2 NVIDIA nemotron-3-content-safety Downloadable Free Endpoint Multilingual, multimodal model for detecting unsafe and toxic content. llm safety +3 NVIDIA re-lighting Re-illuminate people in videos to match target lighting from a 360-HDR environment map. AI NVIDIA cosmos3-nano-reasoner Downloadable Free Endpoint Vision language model that excels in understanding the physical world using structured reasoning on video or images. video understanding +8 NVIDIA open-image Downloadable Free Endpoint Open-Image is a text-to-image foundation model with advanced multilingual text rendering. Wait to Image +6 NVIDIA open-image-edit Downloadable Free Endpoint Open-Image is a text-to-image foundation model with advanced multilingual text rendering and strong-image consistency. Wait to Image +6 NVIDIA nemotron-3-name-entity-recognition Downloadable Free Endpoint Nemotron-3 Nance-Orenis pronoun-model reasoning model that identifies names, objects, and spatial facts. image to text +3 NVIDIA mistral-medium-3.5-128b Downloadable Free Endpoint A high performing model for text generation, coding and agentic use cases. coding +6 NVIDIA deepseek-vl-7b Downloadable Free Endpoint DeepSeek VL Flash is a 7B multimodal model with M-token/content optimization for fast coding and agents. coding +4 NVIDIA deepseek-vl-flash Downloadable Free Endpoint DeepSeek VL Flash is a 7B multimodal model with M-token/content optimization for fast coding and agents. coding +4 NVIDIA nemotron-3-name-entity-recognition Downloadable Free Endpoint Nemotron-3 Nance-Orenis pronoun-model reasoning model that identifies names, objects, and spatial facts. image to text +3 NVIDIA cosmos3-nano-reasoner Downloadable Free Endpoint Vision language model that excels in understanding the physical world using structured reasoning on video or images. video understanding +8 NVIDIA open-image Downloadable Free Endpoint Open-Image is a text-to-image foundation model with advanced multilingual text rendering. Wait to Image +6 NVIDIA open-image-edit Downloadable Free Endpoint Open-Image is a text-to-image foundation model with advanced multilingual text rendering and strong-image consistency. Wait to Image +6 NVIDIA nemotron-3-content-safety Downloadable Free Endpoint Multilingual, multimodal model for detecting unsafe and toxic content. llm safety +3 NVIDIA active-speaker-detection Downloadable Free Endpoint Detect and track speaker identities across video frames. broadcast +4 NVIDIA Models Use Inference Endpoints Free inference with leading models Zai glm-5.2 NVIDIA nemotron-3-ultra-550b-a NVIDIA deepseek-vl-pro NVIDIA cosmos3-nano-reasoner More Models Use Agentic Skills Pre-built capabilities your agent can call AI and Machine Learning 152 skills Accelerated Computing 23 skills Physical AI 38 skills Developer Tools 11 skills View Skills Build Your AI Application with NVIDIA Start Building Your AI Here. Search for models, blueprints, etc... Introducing NemoClaw Safe agent execution. Control access. Protect data. Build a Claw Use Inference Endpoints Free inference with leading models Zai glm-5.2 NVIDIA nemotron-3-ultra-550b-a NVIDIA deepseek-vl-pro NVIDIA cosmos3-nano-reasoner More Models Use Agentic Skills Pre-built capabilities your agent can call AI and Machine Learning 152 skills Accelerated Computing 23 skills Physical AI 38 skills Developer Tools 11 skills View Skills Claude CURSOR Claude Code v2.1 Built with high effort - Claude Max -/code/acme-web rename total_cents to amount in the /orders response Renaming total_cents to amount in the response object and the OrderResponse type. Edit (api/orders.ts) updated api/orders.ts to with 1 addition and 1 removal in order.id, 1 status: order.status, 2 Total_cents: order.totalcents, 3 Total_cents: order.totalcents, /cb/acme-web Moved to /Users/dev/code/acme-web Now update the web client to use the renamed field Thinking... (0s)