The public product surface is Model API, Multimodal API, Billing, VaaS, Dedicated Capacity, and Agentic Payments. Batch processing, reserved inference, dedicated endpoints, GPU capacity, and managed deployment are presented as capabilities or delivery paths under those entries.
Public products
6
Currently public products
Status
GA / Preview
Shown from backend truth
One API base
/v1
Models, media, billing, and receipts
Global Access, Unified Ingress
BatchIn coordinates API gateways, security controls, and compute availability to support localized delivery with unified engineering standards.
View pricingGlobal entry
Use this path for USD pricing, public MCP discovery, OpenAI-compatible access, and global-facing sales delivery.
Production posture
Built for stable production-scale traffic.
Traffic mix
Text plus vision, audio, image, and video workloads.
Streaming path
Regional ingress, stable streaming, and request continuity.
Control guardrails
Scoped limits, request isolation, and backpressure controls.
Public contract and readiness
Shared core
This is where public Model API, batch, usage, billing, and public MCP contract stay consistent.
Private lanes
Customer UI keeps one product truth while delivery, quota, and isolation can vary by contract.
Compute truth
Public pages show inventory and availability only from the verified compute registry.
Edge ingress
Latency work starts at the customer-facing edge before requests enter the primary execution path.
Streaming delivery
Connection reuse and consumer isolation are tuned to reduce jitter and long-tail failures.
Traffic policy
Customers see a simple API and clear limits while BatchIn handles traffic protection behind the scenes.
All public product navigation rolls up to these six entries. Coding, batch, dedicated endpoints, Dedicated Capacity, managed deployment, and agent billing are use cases or self-serve paths under them.
OpenAI-compatible text, coding, reasoning, embeddings, rerank, and priced image-understanding calls through one catalog and usage ledger.
Developer API for image, video, audio, and speech tasks with status, failure reasons, cost estimates, refunds, and receipts.
Budgets, API key limits, model controls, customer and feature attribution, anomaly alerts, and cost reporting.
Verifiable usage receipts for every billable AI request, linked to usage, billing, customer traces, and public route labels.
Quote-led dedicated endpoints and whole-machine GPU capacity, with a 32-GPU minimum and managed delivery.
Machine-readable catalog, pricing manifest, wallet policies, agent receipts, and access-gated x402 and USDC rails.
Community programs
Use events for applications, showcases, and community collaboration. For product purchase, API calls, budgets, receipts, and capacity requests, use the product entries above.