Riven Instant

Model ID: riven-instant Provider: riven Tier: instant Capabilities: chat

Fastest single-turn answers, autocomplete, and routing. The lowest-latency lane in the fleet.

Pricing

| | per 1M tokens | |---|---| | Prompt | $1.69 | | Completion | $6.75 |

Cost basis; served from an on-prem lane with $0 marginal cloud cost. PAYG meters at the $3.00/1M floor.

Context

32K tokens.

Intended use

- Autocomplete and short factual answers - Routing / triage before a heavier model - High-throughput, latency-sensitive single turns

Limitations

- Not for multi-step reasoning or long synthesis — use riven-fast or riven-core. - On-prem lane; bounded by single-slot throughput under load.

Access

Available on Free and above. Call it through the Riven API:

curl https://api.rivenai.io/v1/chat/completions \
  -H "Authorization: Bearer $RIVEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "riven-instant", "messages": [{"role": "user", "content": "Hello"}]}'

Pricing from the live billing rate book, verified 2026-09-02.