Gemini 3.8 Flash
Google · Proprietary · Released Sep 2, 2026 · google/gemini-3.8-flash
Best $0.75 in / $3.75 out via Google
1.05M contextVisionToolsReasoningStructured outputPrompt cachingAudio input
Available from 7 providersUSD / MTOK · PRICES 22 MINUTES AGO · SPEED 24 HOURS AGO
EST. MONTHLY COSTclick a row for detail · click headers to sort
| PROVIDER | INPUT | OUTPUT | CACHE | CONTEXT | QUANT | TTFT | TPS | UPTIME |
|---|---|---|---|---|---|---|---|---|
| $0.375 | $1.88 | $0.037 | 1.05M | — | — | — | 84.6% | |
| $0.375 | $1.88 | $0.037 | 1.05M | — | — | — | 100.0% | |
| $0.75 | $3.75 | $0.075 | 1.05M | — | 2.1s | 320 tok/s | 99.1% | |
| $0.75 | $3.75 | $0.075 | 1.05M | — | 2.2s | 341 tok/s | 100.0% | |
| $0.825 | $4.13 | $0.083 | 1.05M | — | — | — | 100.0% | |
| $1.35 | $6.75 | $0.135 | 1.05M | — | — | — | 98.9% | |
| $1.35 | $6.75 | $0.135 | 1.05M | — | — | — | 100.0% |
TTFT/TPS: median (P50) over trailing 504h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · methodology v1.1 · measured 24 hours ago
SERVE THIS MODEL AND NOT LISTED? LIST YOUR INFERENCE →
Pricing variants · USD / MTok in / out
STANDARD
$0.75 / $3.75
per MTok in / out
BATCH
$0.375 / $1.88
async batch
CACHE READ $0.075CACHE WRITE $0.042WEB SEARCH $0.014 / search
Recent changesRSS ↗
Sep 3, 2026model added
About
Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.
Specifications
Context window1,048,576
Max output65,536
Modalities intext, image, video, file, audio
Modalities outtext
LicenseProprietary
ReleasedSep 2, 2026
TokenizerGemini
Related
Embed badge
[](https://modelindex.ai/models/google/gemini-3.8-flash)Sources
OpenRouter API22 minutes ago
AGGREGATORLiteLLM dataset22 minutes ago
AGGREGATORModelIndex benchmarks5 days ago
MEASUREDVerified 22 minutes ago · list prices, not negotiated rates.