Riven Max

Model ID: riven-max Provider: riven Tier: max Capabilities: chat, reasoning, extended thinking

Maximum-quality reasoning for the hardest problems and long-context synthesis.

Pricing

| | per 1M tokens | |---|---| | Prompt | $5.00 | | Completion | $30.00 |

Cloud frontier lane.

Context

200K tokens.

Intended use

- The hardest reasoning and synthesis tasks - Long-context analysis - Problems where extended thinking materially improves quality

Limitations

- Slowest tier. - Allow max_tokens ≥ 2000, or disable extended thinking via chat_template_kwargs: {"enable_thinking": false}. - Available on Max tiers and above.

Access

Available on Max tiers 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-max", "messages": [{"role": "user", "content": "Hello"}], "max_tokens": 2000}'

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