# Runcrate > Runcrate is an AI cloud platform combining a 200+ model OpenAI-compatible inference API with on-demand GPU rentals (H100, H200, A100, L40S, RTX 5090, RTX 4090, and more) and reserved capacity for GPUs that are not on demand (B200, GB200, GB300, MI300X). One API key, one bill, one dashboard for chat completion, image / video generation, speech, transcription, embeddings, plus dedicated GPU instances, persistent volumes, fine-tuning, and reserved clusters. Runcrate is self-serve. Inference billing is per-token / per-image / per-second / per-minute (varies by model). GPU rentals are per-second. There are no commitments, no minimums, and credits never expire. The inference API is a drop-in replacement for the OpenAI Python and TypeScript SDKs: set `base_url=https://api.runcrate.ai/v1` and existing code keeps working. ## Get started - [Homepage](https://www.runcrate.ai/): Top-level platform overview. - [Sign up](https://www.runcrate.ai/auth/signup): Create an account, get an API key, add credits. - [Sign in](https://www.runcrate.ai/auth/login): Log in to dashboard. - [Dashboard](https://www.runcrate.ai/dashboard): Console for instances, models, API keys, billing. ## Pricing - [GPU cloud pricing](https://www.runcrate.ai/pricing): Live on-demand GPU rental rates for every GPU in stock (current prices on the page and at https://www.runcrate.ai/api/gpu-pricing). Per-second billed. - [Inference API pricing](https://www.runcrate.ai/inference/pricing): Per-token / per-image / per-second / per-minute pricing for 200+ models. Server-rendered, includes a JSON-LD ItemList of every model with prices in the page source: readable by LLM agents without JS. - [On-demand GPU compute](https://www.runcrate.ai/compute): On-demand GPU rental product page. - [Reserved GPU capacity](https://www.runcrate.ai/contact?topic=reserved): Reserved GPU capacity and clusters, including GPUs that are not on demand. Sales-led. ## GPU pricing pages Per-GPU rental detail with cross-cloud pricing comparison, workloads, benchmarks, and full specs. URL pattern: `/pricing/gpu/{id}`. Each page shows a live price and on-demand deploy only when that GPU is in stock; other GPUs offer reserved capacity or a notify-me form plus the closest in-stock GPU. Prices below were live on 2026-10-19 and change; the pages and https://www.runcrate.ai/api/gpu-pricing are current. - [B200 pricing](https://www.runcrate.ai/pricing/gpu/b200): NVIDIA B200, 192GB HBM3e: reserve on request (not on demand) - [H200 pricing](https://www.runcrate.ai/pricing/gpu/h200): NVIDIA H200, 141GB HBM3e: from $4.24/hr on demand (live price on the page) - [H100 pricing (SXM & PCIe)](https://www.runcrate.ai/pricing/gpu/h100): NVIDIA H100, both SXM and PCIe variants: H100 SXM from $3.25/hr on demand (live price on the page); H100 PCIe reserve on request (not on demand) - [H100 SXM pricing](https://www.runcrate.ai/pricing/gpu/h100-sxm): NVIDIA H100 SXM, 80GB HBM3: from $3.25/hr on demand (live price on the page) - [H100 PCIe pricing](https://www.runcrate.ai/pricing/gpu/h100-pcie): NVIDIA H100 PCIe, 80GB HBM3: reserve on request (not on demand) - [A100 SXM pricing](https://www.runcrate.ai/pricing/gpu/a100-sxm): NVIDIA A100 SXM, 80GB HBM2e: from $1.76/hr on demand (live price on the page) - [A100 PCIe pricing](https://www.runcrate.ai/pricing/gpu/a100-pcie): NVIDIA A100 PCIe, 80GB HBM2e: reserve on request (not on demand) - [GB200 pricing](https://www.runcrate.ai/pricing/gpu/gb200): NVIDIA GB200 Grace+Blackwell superchip, 192GB HBM3e: reserve on request (not on demand) - [GB300 pricing](https://www.runcrate.ai/pricing/gpu/gb300): NVIDIA GB300 Blackwell, 256GB HBM3e: reserve on request (not on demand) - [RTX 5090 pricing](https://www.runcrate.ai/pricing/gpu/rtx-5090): NVIDIA RTX 5090, 32GB GDDR7: from $0.85/hr on demand (live price on the page) - [RTX 4090 pricing](https://www.runcrate.ai/pricing/gpu/rtx-4090): NVIDIA RTX 4090, 24GB GDDR6X: from $0.52/hr on demand (live price on the page) - [RTX 3090 pricing](https://www.runcrate.ai/pricing/gpu/rtx-3090): NVIDIA RTX 3090, 24GB GDDR6X: not on demand; notify-me on the page - [L40S pricing](https://www.runcrate.ai/pricing/gpu/l40s): NVIDIA L40S, 48GB GDDR6: from $1.14/hr on demand (live price on the page) - [A40 pricing](https://www.runcrate.ai/pricing/gpu/a40): NVIDIA A40, 48GB GDDR6: from $2.42/hr on demand (live price on the page) - [RTX A6000 pricing](https://www.runcrate.ai/pricing/gpu/rtx-a6000): NVIDIA RTX A6000, 48GB GDDR6: from $0.74/hr on demand (live price on the page) - [V100 pricing](https://www.runcrate.ai/pricing/gpu/v100): NVIDIA Tesla V100, 32GB HBM2: from $3.04/hr on demand (live price on the page) - [RTX 4080 pricing](https://www.runcrate.ai/pricing/gpu/rtx-4080): NVIDIA RTX 4080, 16GB GDDR6X: not on demand; notify-me on the page - [RTX 4070 Ti pricing](https://www.runcrate.ai/pricing/gpu/rtx-4070-ti): NVIDIA RTX 4070 Ti: not on demand; notify-me on the page - [MI300X pricing](https://www.runcrate.ai/pricing/gpu/mi300x): AMD MI300X, 192GB HBM3: reserve on request (not on demand) - [MI250X pricing](https://www.runcrate.ai/pricing/gpu/mi250x): AMD MI250X, 128GB HBM2e: not on demand; notify-me on the page - [MI210 pricing](https://www.runcrate.ai/pricing/gpu/mi210): AMD MI210: not on demand; notify-me on the page ## GPU model spec pages Spec deep-dive (VRAM, bandwidth, FP16/FP32, TDP, architecture). Same id list as above. - [/gpu-models/b200](https://www.runcrate.ai/gpu-models/b200): H100 / H200 / B200 / GB200 / GB300 / MI300X model pages all follow the same `/gpu-models/{id}` pattern. - [/gpu-models/h200](https://www.runcrate.ai/gpu-models/h200) - [/gpu-models/h100-sxm](https://www.runcrate.ai/gpu-models/h100-sxm) - [/gpu-models/h100-pcie](https://www.runcrate.ai/gpu-models/h100-pcie) - [/gpu-models/a100-sxm](https://www.runcrate.ai/gpu-models/a100-sxm) - [/gpu-models/a100-pcie](https://www.runcrate.ai/gpu-models/a100-pcie) - [/gpu-models/gb200](https://www.runcrate.ai/gpu-models/gb200) - [/gpu-models/gb300](https://www.runcrate.ai/gpu-models/gb300) - [/gpu-models/rtx-5090](https://www.runcrate.ai/gpu-models/rtx-5090) - [/gpu-models/rtx-4090](https://www.runcrate.ai/gpu-models/rtx-4090) - [/gpu-models/rtx-3090](https://www.runcrate.ai/gpu-models/rtx-3090) - [/gpu-models/l40s](https://www.runcrate.ai/gpu-models/l40s) - [/gpu-models/a40](https://www.runcrate.ai/gpu-models/a40) - [/gpu-models/rtx-a6000](https://www.runcrate.ai/gpu-models/rtx-a6000) - [/gpu-models/v100](https://www.runcrate.ai/gpu-models/v100) - [/gpu-models/mi300x](https://www.runcrate.ai/gpu-models/mi300x) - [/gpu-models/mi250x](https://www.runcrate.ai/gpu-models/mi250x) - [/gpu-models/mi210](https://www.runcrate.ai/gpu-models/mi210) - [/gpu-models/rtx-4080](https://www.runcrate.ai/gpu-models/rtx-4080) - [/gpu-models/rtx-4070-ti](https://www.runcrate.ai/gpu-models/rtx-4070-ti) ## GPU comparisons Side-by-side comparison pages with TL;DR verdicts, bar charts, and full spec tables. - [GPU comparisons index](https://www.runcrate.ai/gpu-compare): Browse all comparisons grouped by architecture. - [H100 SXM vs A100 SXM](https://www.runcrate.ai/gpu-compare/h100-sxm-vs-a100-sxm) - [B200 vs H200](https://www.runcrate.ai/gpu-compare/b200-vs-h200) - [H200 vs MI300X](https://www.runcrate.ai/gpu-compare/h200-vs-mi300x) - [GB200 vs GB300](https://www.runcrate.ai/gpu-compare/gb200-vs-gb300) - [H100 SXM vs RTX 5090](https://www.runcrate.ai/gpu-compare/h100-sxm-vs-rtx-5090) - [RTX 5090 vs RTX 4090](https://www.runcrate.ai/gpu-compare/rtx-5090-vs-rtx-4090) - [H200 vs RTX 5090](https://www.runcrate.ai/gpu-compare/h200-vs-rtx-5090) - URL pattern: `/gpu-compare/{a}-vs-{b}`: works for any pair of GPU ids in the spec list above. ## Model catalog - [Inference catalog (HTML)](https://www.runcrate.ai/inference/pricing): Searchable, category-filtered model catalog with live pricing. - [Model JSON catalog](https://www.runcrate.ai/api/models/catalog): Machine-readable JSON of every active model: id, display_name, prices, parameters, supported_parameters, provider_ids, context_length, category. Prices are the exact rates each request is billed. ## API landing pages: by capability Topic-specific pages with code examples and feature comparisons. Each is OpenAI-compatible. - [APIs index](https://www.runcrate.ai/apis): Every API page, the platform pages and the GPU-cloud comparisons, in one list. - [Speech-to-text API](https://www.runcrate.ai/speech-to-text-api): Whisper / Voxtral, fast, accurate transcription. - [Real-time STT](https://www.runcrate.ai/real-time-stt): Low-latency streaming transcription. - [Whisper API](https://www.runcrate.ai/whisper-api): Dedicated OpenAI Whisper Large V3 inference. - [Text-to-speech API](https://www.runcrate.ai/text-to-speech-api): Qwen3-TTS, Kokoro, Orpheus. - [DeepSeek API](https://www.runcrate.ai/deepseek-api): DeepSeek V3.2 and R1 inference. - [Claude API](https://www.runcrate.ai/claude-api): Claude 4 Sonnet and Opus. - [Mistral API](https://www.runcrate.ai/mistral-api): Mistral Large 2 and family. - [Llama API](https://www.runcrate.ai/llama-api): Meta Llama 4 and Llama 3. - [Qwen API](https://www.runcrate.ai/qwen-api): Qwen3 chat, vision, TTS, code. - [Gemma API](https://www.runcrate.ai/gemma-api): Google Gemma model inference. - [Ollama Cloud](https://www.runcrate.ai/ollama-cloud): Run Ollama-compatible models in the cloud. - [Stable Diffusion API](https://www.runcrate.ai/stable-diffusion-api): SDXL and FLUX image generation. - [FLUX API](https://www.runcrate.ai/flux-api): FLUX.1 Dev / Schnell / Pro. - [Image generation API](https://www.runcrate.ai/image-generation-api): FLUX, Stable Diffusion, Ideogram, Recraft. - [Sora API](https://www.runcrate.ai/sora-api): OpenAI Sora 2 video generation. - [Veo API](https://www.runcrate.ai/veo-api): Google Veo 3 / Veo 2 video. - [Kling API](https://www.runcrate.ai/kling-api): Kling video generation. - [RunwayML API alternative](https://www.runcrate.ai/runway-api): Multi-provider video generation. - [Chat API](https://www.runcrate.ai/chat-api): Multi-provider chat completions. - [Embedding API](https://www.runcrate.ai/embedding-api): Vector embeddings for RAG and search. - [Hugging Face Inference alternative](https://www.runcrate.ai/huggingface-inference): 200+ models via OpenAI-compatible API. - [Serverless inference](https://www.runcrate.ai/serverless-inference): GPU inference without managing infrastructure. - [AI agents API](https://www.runcrate.ai/ai-agents-api): Function calling, tool use, MCP-compatible. - [OCR API](https://www.runcrate.ai/ocr-api): Document text extraction. - [Face detection API](https://www.runcrate.ai/face-detection-api): Vision-language face detection. - [Background removal API](https://www.runcrate.ai/remove-background-api): AI-powered image isolation. - [ML infrastructure](https://www.runcrate.ai/ml-infrastructure): Platform overview for AI teams. ## Solutions - [Solutions index](https://www.runcrate.ai/solutions): Overview of every Runcrate use case. - [Inference](https://www.runcrate.ai/solutions/inference): Production LLM serving, vLLM, TGI. - [Fine-tuning](https://www.runcrate.ai/solutions/fine-tuning): LoRA, QLoRA, full fine-tuning on bare-metal GPUs. - [Model training](https://www.runcrate.ai/solutions/model-training): Multi-node distributed training (DeepSpeed, FSDP, Megatron-LM). - [RAG pipelines](https://www.runcrate.ai/solutions/rag): Embeddings + vector search + generation on one platform. - [AI agents](https://www.runcrate.ai/solutions/ai-agents): Function calling, tool use, MCP-compatible models. - [Computer vision](https://www.runcrate.ai/solutions/computer-vision): Vision models for OCR, document analysis, video understanding. - [Image and video generation](https://www.runcrate.ai/solutions/image-video): FLUX, SDXL, Sora 2, Veo 3, Kling. - [Speech and audio](https://www.runcrate.ai/solutions/speech-audio): TTS (Qwen3-TTS, Kokoro, Orpheus) and STT (Whisper, Voxtral). - [LLM API solutions](https://www.runcrate.ai/solutions/nlp-llms): Claude, DeepSeek, Gemini, Llama, Qwen via unified API. - [Data processing](https://www.runcrate.ai/solutions/data-processing): RAPIDS, cuDF, Dask-CUDA on GPU clusters. - [AI research](https://www.runcrate.ai/solutions/research): Jupyter, VS Code, per-minute billing for ablation studies. - [Edge & embedded AI](https://www.runcrate.ai/solutions/edge-embedded): Train on cloud, deploy to Jetson / mobile / IoT. ## Documentation - [Getting started](https://www.runcrate.ai/docs/getting-started/introduction) - [Quickstart](https://www.runcrate.ai/docs/getting-started/quickstart) - [Models overview](https://www.runcrate.ai/docs/models/overview) - [API keys](https://www.runcrate.ai/docs/account/api-keys) - [Instances](https://www.runcrate.ai/docs/instances/overview) - [Storage](https://www.runcrate.ai/docs/storage/overview) - [Billing](https://www.runcrate.ai/docs/billing/overview) ## SDKs and integrations - [@runcrate/sdk on npm](https://www.npmjs.com/package/@runcrate/sdk): Official TypeScript SDK with `chat`, `images`, `audio.speech`, `audio.transcriptions`, `videos`, `instances`, `storage`, `environments`, `sshKeys`, `templates`, `billing`, `models`. - [@runcrate/ai on npm](https://www.npmjs.com/package/@runcrate/ai): Vercel AI SDK provider: `runcrate(modelId)`, `runcrate.imageModel()`, `runcrate.speechModel()`, `runcrate.transcriptionModel()`. - OpenAI Python / TypeScript SDK: drop-in compatible: set `base_url=https://api.runcrate.ai/v1`. ## API specification - [OpenAPI 3.1 spec](https://www.runcrate.ai/openapi.json): Complete machine-readable spec: 24 paths, 33 operations across Chat, Images, Videos, Audio, Embeddings, Models, Instances, Storage, Environments, SSH Keys, Templates, Billing. Includes `x-runcrate-pricing` extensions per operation pointing at live model rates. ## API endpoints: Inference Base URL: `https://api.runcrate.ai/v1` - `POST /chat/completions`: Chat / LLM completion (OpenAI-compatible). - `POST /images/generations`: Image generation (FLUX, SDXL, Ideogram, Recraft). - `POST /videos`: Submit video generation job (Sora 2, Veo 3, Kling, Wan); async. - `GET /videos/{id}`: Poll a video job's status. - `GET /videos/{id}/download`: Stream the resulting MP4. - `POST /audio/speech`: Text-to-speech (Qwen3-TTS, Kokoro, Orpheus). - `POST /audio/transcriptions`: Speech-to-text (Whisper Large V3, Voxtral); multipart form. - `POST /embeddings`: Vector embeddings. - `GET /models`: List available models (OpenAI-compatible). ## API endpoints: Infrastructure Base URL: `https://runcrate.ai/api/v1` - `GET /instances` / `POST /instances`: List / create GPU instances. - `GET /instances/{id}` / `DELETE /instances/{id}`: Get / terminate. - `GET /instances/{id}/status`: Lightweight status poll. - `GET /instances/types`: Available GPU + region + count combinations. - `GET /storage` / `POST /storage`: List / create persistent volumes. - `GET /storage/{id}` / `PATCH /storage/{id}` / `DELETE /storage/{id}`: Get / resize / delete a volume. - `GET /storage/regions`: List storage regions. - `GET /environments` / `POST /environments`: List / create environments. - `GET /environments/{id}` / `PATCH /environments/{id}` / `DELETE /environments/{id}`: Get / update / delete. - `GET /ssh-keys` / `POST /ssh-keys`: List / create SSH keys. - `DELETE /ssh-keys/{id}`: Delete SSH key. - `GET /templates`: List instance templates (vLLM, Comfy, Jupyter, Axolotl, etc.). - `GET /billing/balance`: Credit balance and active usage cost. - `GET /billing/transactions`: Transaction history. - `GET /billing/usage`: Aggregate usage metrics. ## Comparisons and alternatives: by competitor GPU cloud: - [vs RunPod](https://www.runcrate.ai/runpod-alternative) - [vs Lambda Labs](https://www.runcrate.ai/lambda-labs-alternative) - [vs Vast.ai](https://www.runcrate.ai/vast-ai-alternative) - [vs CoreWeave](https://www.runcrate.ai/coreweave-alternative) - [vs Paperspace](https://www.runcrate.ai/paperspace-alternative) - [vs Modal](https://www.runcrate.ai/modal-alternative) - [RunPod vs Vast.ai head-to-head](https://www.runcrate.ai/runpod-vs-vast-ai) Inference / multi-model API: - [vs Replicate](https://www.runcrate.ai/replicate-alternative) - [vs Together AI](https://www.runcrate.ai/together-ai-alternative) - [vs Fireworks AI](https://www.runcrate.ai/fireworks-ai-alternative) - [vs OpenRouter](https://www.runcrate.ai/openrouter-alternative) - [vs Groq](https://www.runcrate.ai/groq-alternative) - [vs Baseten](https://www.runcrate.ai/baseten-alternative) - [vs DeepInfra](https://www.runcrate.ai/deepinfra-alternative) - [vs Hugging Face Inference](https://www.runcrate.ai/huggingface-inference) Voice / audio: - [vs ElevenLabs](https://www.runcrate.ai/elevenlabs-alternative) - [vs Deepgram](https://www.runcrate.ai/deepgram-alternative) - [vs AssemblyAI](https://www.runcrate.ai/assemblyai-alternative) Image / video: - [vs Fal.ai](https://www.runcrate.ai/fal-ai-alternative) - [vs RunwayML](https://www.runcrate.ai/runwayml-alternative) - [vs Pika](https://www.runcrate.ai/pika-alternative) - [vs Luma](https://www.runcrate.ai/luma-alternative) - [vs Leonardo](https://www.runcrate.ai/leonardo-alternative) Frontier providers: - [vs OpenAI](https://www.runcrate.ai/openai-alternative) - [vs Anthropic](https://www.runcrate.ai/anthropic-alternative) ## Optional - [Sitemap](https://www.runcrate.ai/sitemap.xml): Full URL list, machine-readable. - [Company](https://www.runcrate.ai/company): About Runcrate. - [Partners](https://www.runcrate.ai/partners): Hardware and software partners. - [Careers](https://www.runcrate.ai/careers): Open roles. - [Contact](https://www.runcrate.ai/contact): Sales and support contact. - [Terms of service](https://www.runcrate.ai/terms) - [Privacy policy](https://www.runcrate.ai/privacy)