OpenRouter Google Gemini 2.5 Flash

Compiled Truth

Google Gemini 2.5 Flash is a fast, cost-efficient LLM accessed through OpenRouter’s API gateway. Used by Hugh (and other OpenClaw agents) for lightweight processing tasks — social scanning, heartbeat checks, and routine operations where cost-efficiency matters more than deep reasoning. [Source: compiled from session references, 2026-06-01]

State

• Provider: Google (via OpenRouter API gateway)
• Model ID: openrouter/google/gemini-2.5-flash
• Status: Operational and in active use
• Use case: Cost-efficient batch processing, routine scanning tasks, heartbeat operations
• Cost profile: Significantly cheaper than larger models (Opus, Sonnet) — suitable for high-frequency low-complexity work

Key Facts

• Gemini 2.5 Flash is Google’s “Flash” tier — optimized for speed and cost over depth [Source: Google model documentation]
• OpenRouter provides unified API access to multiple providers, including Google Gemini models [Source: openrouter.ai]
• Used in Hugh’s agent stack for tasks that don’t require deep reasoning (social scans, Gmail checks, Slack monitoring) [Source: Hugh session e86dca98, 2026-06-01]

See Also

• openclaw — agent framework Hugh runs on
• gpt-5-4-mini — comparable cost-efficient model option

Timeline

• 2026-06-01 | Mentioned in session e86dca98-9a0c-4fdd-9cbb-ef2a22424094 — “I am currently running on openrouter/google/gemini-2.5-flash.” [Source: Hugh session e86dca98, 2026-06-01]
• 2026-06-27 | Page enriched with model context, cost profile, and use case details. [Source: Web search (Google model docs, OpenRouter), 2026-06-27]

Sources

• [Source: Hugh session e86dca98, 2026-06-01]
• [Source: OpenRouter and Google Gemini model documentation, 2026-06-27]