Models

gemini-3.1-pro

deepinfra · 1000K ctx · 1 providers · updated 2026-09-19 02:15 UTC

Cheapest
$4.50 Official list · DeepInfra
Avg price
$4.50 /1M
providers
1
Tokens (24h)
54B
Volume (24h)
$244.3K est.
(3 × $2.00 + $12.00) ÷ 4 = $4.50/1M — 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 $2.00, 3:1 $4.50, 1:1 $7.00, output only $12.00 per 1M.

The board shows this model's cheapest measured offer ($4.50/1M); the smaller figure under it is the mean of the 1 offers listed below ($4.50/1M). Add those up and divide — it matches. 24h token volume (54B) 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
deepinfra Pricebook (LiteLLM) $2.00$12.00 Official list

Volume trend

54B 30d d-29 · 45B tokensd-28 · 32B tokensd-27 · 28B tokensd-26 · 0 tokensd-25 · 0 tokensd-24 · 0 tokensd-23 · 25B tokensd-22 · 40B tokensd-21 · 46B tokensd-20 · 43B tokensd-19 · 33B tokensd-18 · 26B tokensd-17 · 32B tokensd-16 · 32B tokensd-15 · 0 tokensd-14 · 0 tokensd-13 · 0 tokensd-12 · 0 tokensd-11 · 0 tokensd-10 · 37B tokensd-9 · 0 tokensd-8 · 0 tokensd-7 · 0 tokensd-6 · 0 tokensd-5 · 0 tokensd-4 · 0 tokensd-3 · 0 tokensd-2 · 0 tokensd-1 · 0 tokensd-0 · 54B tokens

Last 30 days: 45B → 54B (+20%); range 0–54B 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-3.1-pro.json. Free reuse requires attribution to tkx.org.

FAQ

How much does gemini-3.1-pro cost?

Cheapest measured offer right now: $2/1M input, $12/1M output via deepinfra — across 1 tracked providers, refreshed hourly.

Who serves gemini-3.1-pro?

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

How heavily is gemini-3.1-pro used?

gemini-3.1-pro routed 54B 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