Skip to main content

Coming Soon

India-differentiated capabilities and essential observability.
FeatureDescription
Paid PlansStarter, Pro, Enterprise tiers with higher RPM/TPM limits
Credit SystemPrepaid credits (1 = ₹1), UPI/card/netbanking via Razorpay
GST InvoicesCGST/SGST and IGST-compliant PDF invoices with your GSTIN
Speech-to-Textforii/saarika-v2 — 22 Indic languages, 8kHz telephony audio
Text-to-Speechforii/bulbul-v2 — 30+ voices across Hindi, Tamil, Telugu, Bengali
Vision / MultimodalImage understanding — Aadhaar, PAN, invoice OCR via image_url
RerankingCross-encoder reranking for RAG — Indic-optimized
Batch InferenceAsynchronous large-scale processing at 50% lower cost
Fine-Tuning (SFT)Supervised fine-tuning on Indic-language data
Response headersTTFT, region, request-id, cached-tokens headers
CLI toolforii chat --verbose, forii usage, forii models list
Usage APIDetailed usage breakdown by model, key, date
Request annotationsCost attribution by team/project/environment
Token-level rate limitsTPM per key per model

Planned

Platform features, advanced inference, and enterprise tooling.
FeatureDescription
DeploymentsDedicated GPU with autoscaling and scale-to-zero
Prompt cachingAutomatic prefix caching with discount on cached tokens
Anthropic compatibility/inference/v1/messages endpoint for Claude SDK users
Responses APIStateful conversations with previous_response_id
Legacy completions/inference/v1/completions — text-in/text-out
DPO fine-tuningDirect Preference Optimization on preference pairs
RFTReinforcement Fine-Tuning with custom evaluators
Advanced dashboardLatency percentiles, error trends, alerts, region breakdown
Prometheus metricsMetrics endpoint for Grafana, Datadog, OTel
External integrationsLangSmith, Langfuse, Grafana Cloud, Datadog

Stay updated

Watch GitHub or join our Discord for release announcements.