Models

gemini-3.5-flash

vertex_ai ↗ · 1049K ctx · 4 providers · updated 2026-08-04 22:15 UTC

Cheapest
$3.38 Official list · Vertex AI
Avg price
$3.38 /1M
providers
4
Tokens (24h)
28B
Volume (24h)
$96.0K est.
(3 × $1.50 + $9.00) ÷ 4 = $3.38/1M — the $/1M figure blends input and output at 3:1 — that is the only way models with two different rates can be ranked on one axis. Your actual rate depends on your own input:output mix — input only $1.50, 3:1 $3.38, 1:1 $5.25, output only $9.00 per 1M.

The board shows this model's cheapest measured offer ($3.38/1M); the smaller figure under it is the mean of the 6 offers listed below ($3.38/1M). Add those up and divide — it matches. 24h token volume (28B) is sourced from OpenRouter public rankings — today's only public source of absolute per-model token counts (Vercel AI Gateway publishes share-of-traffic percentages); as more sources come online, the per-router breakdown will sum to this total here.

ProviderRouter / Source$ in /1M$ out /1MTTFTTPSUptimeEvidence
vertex_ai Pricebook (LiteLLM) $1.50$9.00 Official list
gemini Pricebook (LiteLLM) $1.50$9.00 Official list
vertex_ai-language-models Pricebook (LiteLLM) $1.50$9.00 Official list
openrouter-best OpenRouter $1.50$9.00 API-measured
requesty Requesty $1.50$9.00 API-measured
burncloud burncloud $1.50$9.00 API-measured

Volume trend

93B 30d d-29 · 75B tokensd-28 · 53B tokensd-27 · 42B tokensd-26 · 57B tokensd-25 · 52B tokensd-24 · 40B tokensd-23 · 29B tokensd-22 · 28B tokensd-21 · 40B tokensd-20 · 54B tokensd-19 · 52B tokensd-18 · 58B tokensd-17 · 87B tokensd-16 · 49B tokensd-15 · 47B tokensd-14 · 65B tokensd-13 · 93B tokensd-12 · 62B tokensd-11 · 62B tokensd-10 · 50B tokensd-9 · 23B tokensd-8 · 22B tokensd-7 · 37B tokensd-6 · 35B tokensd-5 · 44B tokensd-4 · 38B tokensd-3 · 37B tokensd-2 · 20B tokensd-1 · 21B tokensd-0 · 28B tokens

Last 30 days: 75B → 28B (-62%); range 20B–93B tokens/day. Source: OpenRouter public rankings; refreshed hourly.

Data & method

Cheapest ranked by blended = (3×in + out) ÷ 4; performance columns show only when a source provides them, never estimated. “Official list” = LiteLLM open pricebook (MIT); “API-measured” = provider/aggregator public APIs. Machine-readable data: /api/v1/models/gemini-3.5-flash.json. Free reuse requires attribution to tkx.org.

About

Gemini-3.5-flash is an AI model served by multiple inference providers on AI model marketplaces, designed for natural language processing tasks. It is listed under the serving-platform tag "vertex_ai".

AI-generated summary from public information — is this yours?

FAQ

How much does gemini-3.5-flash cost?

Cheapest measured offer right now: $1.5/1M input, $9/1M output via vertex_ai — across 4 tracked providers, refreshed hourly.

Who serves gemini-3.5-flash?

4 providers currently serve it. The table above lists each with input/output price, TTFT, TPS, uptime and an evidence tier.

How heavily is gemini-3.5-flash used?

gemini-3.5-flash routed 28B tokens in the last 24h. The daily bars above show routed volume over recent days. Source: OpenRouter public rankings — one of the few routers publishing per-model usage; TKX refreshes hourly.

Related analysis

Back to rankings