Gemini 2.5 Flash
gemini-2-5-flashgemini-2.5-flashgoogle/gemini-2.5-flashNo model knowledge yet — showing the AntSeed catalog only.
This model has not been attributed to a known provider yet.
| Seller | Reputation↓ | Routing | Input $/M | Cached $/M | Output $/M | Categories | API |
|---|---|---|---|---|---|---|---|
| Open Forge 0x1d90…b0aa | 76.34 | #2 | $0.30 | $0.30 | $2.50 | chat, fast, tasks | openai-chat-completions |
| Best 0x472f…69fd | 70.56 | #1 | $0.30 | $0.105 | $2.50 | chat, coding, flash | openai-chat-completions |
| OpenCheap 0x0ee1…6c41 | 59.51 | gated | $0.0838 | $0.0838 | $0.6983 | chat, coding | openai-chat-completions |
| Prime Seed 0x71e2…fc07 | 54.78 | gated | $0.33 | $0.033 | $2.75 | chat, fast, premium | openai-chat-completions |
| Surplus-backed seller 0x0e49…8927 | 50.00 | gated | $0.7599 | $0.7599 | $6.3322 | chat, surplus | openai-chat-completions |
| NovaRoute AI 0xc50d…ed7b | 50.00 | gated | $0.0855 | $0.0855 | $0.7125 | chat, coding, code | openai-chat-completions |
| AntFeed 0xddb6…1442 | 36.49 | gated | $0.33 | $0.33not advertised | $2.75 | chat, fast, vision | openai-chat-completions |
| PawFlor-SI-Gateway ⚡ 0x70bc…8261 | 31.27 | gated | $0.189 | $0.189not advertised | $1.575 | chat, fast | openai-chat-completions |
| Leftermute 0x388b…5389 | 28.39 | gated | $0.0758 | $0.0758not advertised | $0.6313 | chat, coding, json | openai-chat-completions |
| Joi Gateway 0x8a90…7007 | 28.04 | gated | $0.1464 | $0.1464 | $1.22 | chat | openai-chat-completions |
| Apex TEE Test 0xe672…7955 | 15.22 | gated | $0.0986 | $0.0189 | $0.8218 | chat, fast, study | openai-chat-completions |
"Best price" and the seller table are live AntSeed catalog data (advertised $/1M tokens — or $ per generated image for unit-billed image models — not settled amounts). Reputation = buyer trust score (0-100, the AntSeed SDK's own formula). "Routing" = the SDK's default buyer routing (what the VPR desktop app ships with): a trust ≥ 60 gate on the effective reputation, then cheapest-first among routable sellers; live failover state (per-peer cooldowns) is buyer-side runtime and not included. Model knowledge (TLDR, provider, About) via the VeniceStats enrichment layer. Advertised catalog, not the model used in any specific purchase. "Usage on AntSeed" counts only settlements whose buyers share the per-model split on-chain (metadata v2/v3, opt-in), so every usage figure is a lower bound.