GPT-5.6 Sol
openai/gpt-5.6-sol
Text
Flagship reasoning model — the default behind RouteNova for hard tasks.
openaichattoolsreasoningliveness monitored
OpenAIResponses API
$16/ 1M output tokens
$2 / 1M input tokens
NovaServe Infrastructure
Enterprise-grade AI infrastructure at startup-friendly prices
Chat, image, video and audio models behind one OpenAI-compatible API, metered per credit, with live health checks on every model we list.
Model catalogOperational
- Models served
- 0
- Chat models
- 0
- Image models
- 0
- Video & audio models
- 0
Catalog composition by modality
01 — Why teams switch
What the platform actually gives you
Everything below is implemented in the product — no roadmap items on this page.
01
Metered per credit
Every request is priced from published per-token, per-image and per-second rates — no seats, no minimums.
02
Live model health
Every model in the catalog is probed with a real request; the status page shows what is up right now.
03
Your data, your control
Zero training on your inputs, per-tenant isolation, and a 24-hour log retention default.
04
OpenAI-compatible API
Point an existing OpenAI client at NovaServe by changing the base URL and key — payloads are unchanged.
05
Resumable streaming
SSE streams carry heartbeats and cursors, so a dropped connection resumes without double-charging.
06
One bill, every modality
Text, image, video, audio and agent runs all draw from the same credit ledger, with a full audit export.
- Published rates for every model
- 402 instead of a silent overcharge
- Exportable ledger of every request
Build
Start building in one click
Three workspaces sit on top of the same models, credits and ledger.
Workflows
Chain reason, browse and knowledge-lookup steps into one automation. Run it by hand, on a schedule, or from a signed webhook.
Open workflowsBots
Named chatbots with their own instructions, model and knowledge base — shareable with a link or embedded in any site.
Open botsAutobots
Self-learning agents that make one focused change per run, measure it against your metric and keep a persistent playbook.
Open autobots02 — Model library
See all models Featured models
31 production checkpoints across text, code, image, video, audio, embeddings and domain-specific tasks.
Gemini 3.1 Pro
google/gemini-3.1-pro-preview
Text
Google's strongest reasoning model, with very large context.
googlechattoolsliveness monitored
GoogleChat completions
$16/ 1M output tokens
$2 / 1M input tokens
Nano Banana Pro
google/gemini-3-pro-image
Image
Highest-fidelity image generation and editing.
googleimage generationediting
GoogleImages API
$0.25/ image
Nova Voice
openai/gpt-4o-mini-tts
Audio
Text-to-speech with steerable delivery and adjustable speed.
openaitext to speech
OpenAISpeech API
$0.03/ 1K characters
Nova Transcribe
openai/gpt-4o-transcribe
Audio
Accurate speech-to-text with punctuation and formatting.
openaispeech to text
OpenAITranscription API
$0.04/ audio minute
Veo 3.1 Fast
google/veo-3.1-fast
Video
Faster Veo tier for iteration at moderate cost.
googletext to videowith audio
GoogleVideo jobs API
$0.38/ second of video
03 — Platform
One platform, every modality
Studio
Image, video and audio generation with inpainting, upscaling, batch runs and template libraries.
ExploreAgents
Drag-and-drop workflow builder, six production templates, and one-click deploy to an endpoint.
ExploreFine-tuning
Reusable prompt and workflow presets, versioned and deployable behind your own endpoint.
ExploreOne key, every modality.
Start on the free tier with 5M tokens and 200 image credits. No card required, no per-seat fees, cancel with a DELETE call.