Forward documentation
Guides for enterprise agents, governance, Agent Learning and the Grid API. Access and deployments are scoped.
Encuentre la guía para su próximo paso.
Use un ID de modelo habilitado para su cuenta. Elija una tarea para encontrar su guía.
Realice su primera llamada a la API
Obtenga acceso, cree una clave e invoque un modelo habilitado.
Elija un modelo y presupuesto
Compare el acceso a modelos, los candidatos y el medidor de uso.
Adapte un modelo
Revise las rutas de entrenamiento, los conjuntos de datos y el plan de servicio.
Evalúe un flujo de trabajo empresarial
Defina su línea base, integraciones y criterios de aceptación.
Prepare una compra empresarial.
Confirme las condiciones comerciales, el alcance de despliegue y la evidencia que necesitan sus revisores.
Serverless no incluye SLA. Un carril en frío puede devolver 503 con Retry-After. Las condiciones de los modos Dedicado y Privado se confirman por escrito.
Descripción general de la plataforma y límites operativos
Forward Intelligence provides Agentic OS for enterprise business agents, agent governance and reward-based Agent Learning. Forward HIVE powers stateful execution. Grid supplies the model and compute layer for supported workloads.
Enterprise agents and learning#
- Agentic OS: first agent request, state and approval boundaries.
- Agent governance: identities, permitted actions, evidence and learning authorization.
- Agent Learning / Agent RL: reward contracts, calibrated feedback and independent evaluation.
- Forward-deployed delivery: integration, acceptance and ongoing operation.
Inference uses an OpenAI-compatible API. Training has its own API and serving scope. Developer examples cover the first agent run and the separate Grid quickstart.
Start here#
- Get started covers access, keys, enabled models and a first call.
- Concepts defines the words the rest of these pages use. Run mode, lane, pinning, cold start, and what the meter counts.
- OpenAI compatibility tells you what is supported today, so you can check a parameter before you depend on it.
The four run modes#
Tokens measure traffic across all four modes. Compare the workload's token usage, capacity commitments and included resources before moving it. The billing basis for Dedicated and Private is defined in the proposal.
| Mode | What it is for | Availability |
|---|---|---|
| Grid Serverless | Elastic traffic. Capacity follows demand and scales to zero when idle. | Available |
| Grid Batch | Asynchronous inference at a discount, in controlled windows. | Available |
| Grid Dedicated | Committed capacity for steady production traffic. | Talk to us |
| Grid Private | An isolated environment for regulated workloads. | Talk to us |
Run modes covers each one in full.
Train and route#
- Training: three paths. Custom training, Training API, managed jobs. Invitation.
- RL rollouts: sampling for teams that keep their own trainer.
- Connect: Grid in coding harnesses. Smart Router is the engine.
- Custom projects: a quoted workload we design and run with you on Grid. Not a training job.
What Grid does not do#
Being direct about this is faster for you than discovering it later.
- Pricing publishes rate card v1 references for eligible serving variants. Billing and metering explains tokens, cache, Batch and capacity commitments.
- There is no service level agreement on Serverless. Dedicated and Private are contractual, and those conversations are with us directly.
- Serverless scales to zero, so a cold lane can answer
503with aRetry-Afterheader. Keep your retry logic. Errors and cold start covers the behaviour. - There is no model marketplace. The catalog is curated, and that is the point.