LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Gemini 3.5 Live Translate Preview

google·google/gemini-3.5-live-translate-preview·GA·Closed·gemini-pro series·Speech / Audio
Low-latency audio-to-audio model for real-time speech translation across 70+ languages

Specs & pricing

Input / output per 1M tokens
Official price·Google
$3.50 / $21.00
Blended $7.88 · Cache read —
Lowest paid·GoogleFirst-party
$3.50 / $21.00
Blended $7.88
Context
16,384
Output limit
16,384
Knowledge cutoff
2025-01
Released / updated
2026-06-09 / 2026-06-09
Capabilities
ReasoningTool use? Structured outputTemperature✓ Attachments
Modalities
Audio

Available at 1 providers1 with public prices

  • ProviderInput / Output
  • GoogleOfficialFirst-party
    $3.50 / $21.00
    Context 16,384Output limit 16,384
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
GoogleOfficialFirst-party$3.50$21.00——16,38416,384

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Audio token pricing1 of 1 providers

ProviderAudio inAudio out
Google$3.501.0×$21.001.0×

Audio tokens are priced on a separate scale from text tokens, so these are not comparable with the text prices above. The multiplier compares each price with the same provider's text price for the same direction.

Your usage cost

Common scenarios
1Google · Official$1,750.00
The cheapest paid channel is official.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$21.00$02026-08-052026-08-13
2026-08-13Input list $3.50Output list $21.00Min blended $7.88

Related models

Gemini Pro Latestsame series—Nano Banana Prosame series$2.00 / $12.00Deep Research Max Previewsame series$2.00 / $12.00GPT-4.1cheaper alternative$2.00 / $8.00GPT-4.1 minicheaper alternative$0.40 / $1.60GPT-4o minicheaper alternative$0.15 / $0.60GPT-4ocheaper alternative$2.50 / $10.00
Data partly from models.dev (MIT) · Google official docs ↗