{"@":{"v":"gdom/1.2","profile":"https://dng.ai/gibberdom/gdom-1.2.json","proj":"text","index":"https://dng.ai/_gdom/manifest.json","site":"https://dng.ai/_gdom/site.gdom","self":"https://dng.ai/_gdom/platform/models/index.text.gdom"},"text":"# Any model. Any modality. Zero lock-in.\n\nDraft & Goal is model-agnostic by design. Choose the best model for each step — frontier or open-weight, hosted or quantized on your own GPUs — and work across text, vision, image, audio, music, video, and reasoning in a single workflow. Swap providers without re-platforming.\n\n## Maximum flexibility, by design.\n\n### Model-agnostic\n\nEvery major provider behind one interface. Pick a model per node and swap anytime — no rewrites.\n\n### Open + closed\n\nFrontier closed APIs or open-weight models. Choose the cost, latency, and control trade-off you want.\n\n### Truly multimodal\n\nText, vision, image, audio, music, and video — composed in a single governed workflow.\n\n### Reasoning on demand\n\nSwitch on extended thinking for hard steps; route fast, cheap models for everything else.\n\n### Quantized & self-hosted\n\nRun 4-bit / 8-bit open models on your own GPUs via vLLM, Ollama, or TGI — in your VPC.\n\n### No lock-in\n\nBring your own keys and private endpoints. Route, fall back, and cost-optimize across vendors.\n\n## Frontier or open-weight — your call.\n\nConnect the models your teams already trust and the new ones shipping every month (June 2026 lineup shown). Closed frontier APIs and open-weight models live side by side; pick the right one for each task.\n\nGPT-5 · o-series · Sora · Whisper\n\nClaude Opus 4.8 · Sonnet 4.6 · Fable 5\n\nGemini 3 Pro · Gemma 3 · Imagen 4 · Veo 3\n\nLlama 4 (open weights)\n\nMistral Large · Magistral · Pixtral\n\nDeepSeek-R1 · DeepSeek-V3\n\nQwen3 · Qwen-VL\n\n## Not just text.\n\nCompose across modalities in the same workflow — transcribe a call, reason over it, generate the visuals, and render a video, each on the best model for the job.\n\n### Text & language\n\nGeneration, extraction, classification, translation — GPT-5, Claude Opus 4.8, Gemini 3, Llama 4, Mistral, Qwen3.\n\n### Vision\n\nRead images, screenshots, charts, and PDFs — GPT-5, Claude, Gemini 3, Qwen-VL, Pixtral, Llama 4.\n\n### Image generation\n\nOn-brand visuals at scale — GPT Image, Imagen 4, FLUX.1, Stable Diffusion 3.5, Midjourney v7, Ideogram.\n\n### Audio & speech\n\nTranscription and natural voice — Whisper, OpenAI Realtime, ElevenLabs, Deepgram, Gemini audio.\n\n### Music & sound\n\nTracks, jingles, and sound design — Suno, Udio, Stable Audio, ElevenLabs SFX.\n\n### Video generation\n\nClips and product shots — Sora, Veo 3, Runway Gen-4, Kling 2, Seedance, Pika.\n\n### Reasoning\n\nDeep multi-step thinking — o-series, DeepSeek-R1, Claude extended thinking, Gemini thinking, Magistral, Qwen3.\n\n## Run it however your security team needs.\n\nUse a hosted frontier API for peak quality, or run an open-weight model quantized on your own GPUs for control and cost. Same workflow, same governance — you choose where inference happens.\n\n### Inference runs where you want it\n\nOne model, four ways to ship it — vendor cloud, your own GPUs, a quantized footprint, or a private VPC endpoint that never leaves your network.\n\n## Extended thinking, only where you need it.\n\nTurn on reasoning-grade models for the hard steps — planning, multi-constraint decisions, code, analysis — and keep fast, inexpensive models for routine work. Tune the reasoning effort per node and watch the cost/quality trade-off in real time.\n\n## The right model, automatically.\n\nSet a model per node, add fallbacks for resilience, and route by cost, latency, or capability. When a provider rate-limits or a new model ships, switch in one place — no re-platforming.\n\n## A multimodal campaign, end to end.\n\nEach node picks its own model and modality. Swap any of them — Whisper for Deepgram, FLUX for Imagen 4, Veo for Sora — without touching the rest of the workflow.\n\n## Pick, route, swap.\n\n### Pick per node\n\nAssign the best model and modality to each step — frontier, open-weight, or quantized.\n\n### Route & fall back\n\nAdd fallbacks and route by cost, latency, or capability for resilient runs.\n\n### Govern & observe\n\nEvery model call is scoped, logged, and traceable — with cost and token usage per step.\n\n### Swap without re-platforming\n\nNew model ships? Change it in one place. Your workflows keep running.\n\n## What teams ask before they commit.\n\nIt means no single AI vendor is baked into the platform. Draft & Goal puts every major provider behind one interface, so you assign the best model to each workflow step — frontier or open-weight — and swap providers without re-platforming. When a new model ships, you change it in one place and your workflows keep running.\n\nDraft & Goal connects models from OpenAI, Anthropic, Google, Meta, Mistral AI, DeepSeek, Alibaba, xAI, and Moonshot AI — including GPT-5, Claude Opus 4.8, Gemini 3 Pro, Llama 4, DeepSeek-R1, and Qwen3. Closed frontier APIs and open-weight models live side by side, so you pick the right one per task.\n\nYes. You can run open-weight models quantized to 4-bit or 8-bit on your own GPUs via vLLM, Ollama, or TGI — in your VPC or on-prem. Draft & Goal also supports private endpoints and bring-your-own API keys, so your security team chooses where inference happens while workflows and governance stay the same.\n\nText, vision, image generation, audio and speech, music, video, and reasoning — composed in a single workflow. One pipeline can transcribe a call with Whisper, reason over it, generate visuals, and render a video, with each node running on the best model for that modality.\n\nSet the model per node: switch on reasoning-grade models for hard steps like planning and analysis, and route fast, inexpensive models for routine work. You can add automatic fallbacks, route by cost, latency, or capability, and every model call is logged with cost and token usage per step.\n\nShow us the workflow.We'll show you the 10x.\n\nBring the marketing workflow that eats your week. We'll build it live, with your data and your models, in 30 minutes.\n\n## Outbound links\n\n- [Book a demo →](https://dng.ai/book-demo/)\n\n- [Tour the platform](https://dng.ai/platform/)\n\n- [Draft & Goal](https://dng.ai/)\n\n- [Read the docs](https://docs.dng.ai/)\n\nSite navigation: https://dng.ai/_gdom/site.gdom\n\nFull page index: https://dng.ai/_gdom/manifest.json","links":[{"rel":"internal","href":"https://dng.ai/book-demo/","path":"/book-demo","label":"Book a demo →","gdom":"/_gdom/book-demo/index.text.gdom"},{"rel":"internal","href":"https://dng.ai/platform/","path":"/platform","label":"Tour the platform","gdom":"/_gdom/platform/index.text.gdom"},{"rel":"internal","href":"https://dng.ai/","path":"/","label":"Draft & Goal","gdom":"/_gdom/index.text.gdom"},{"rel":"external","href":"https://docs.dng.ai/","label":"Read the docs"}]}