Back to models
available

Google: Gemini 3.8 Flash

google/gemini-3-8-flash

Prices

Input

$0.75 per 1M tokens

low
Input (audio)

$0.75 per 1M tokens

low
Input (batch)

$0.375 per 1M tokens

verified
Input (cached read, batch)

$0.0375 per 1M tokens

verified
Input (cached read, flex)

$0.0375 per 1M tokens

verified
Input (cached read, priority)

$0.135 per 1M tokens

verified
Input (cached read)

$0.075 per 1M tokens

low
Input (flex)

$0.375 per 1M tokens

verified
Input (priority)

$1.35 per 1M tokens

verified
Output

$3.75 per 1M tokens

low
Output (batch)

$1.88 per 1M tokens

verified
Output (flex)

$1.88 per 1M tokens

verified
Output (priority)

$6.75 per 1M tokens

verified
Output (reasoning)

$3.75 per 1M tokens

low
Web search (context size: high)

$0.014 per query

low
Web search (context size: low)

$0.014 per query

low
Web search (context size: medium)

$0.014 per query

low

Also available on

The same model, sold by someone else. The price above is the maker's own.

46 sales channels for this model.
ChannelWhatPrice
Google Vertex AIInput$0.75 per 1M tokens
Input (audio)$0.75 per 1M tokens
Input (batch)$0.375 per 1M tokens
Input (cache write)$0.0833 per 1M tokens
Input (cached read, batch)$0.0375 per 1M tokens
Input (cached read, flex)$0.0375 per 1M tokens
Input (cached read, priority)$0.135 per 1M tokens
Input (cached read)$0.075 per 1M tokens
Input (flex)$0.375 per 1M tokens
Input (priority)$1.35 per 1M tokens
Output$3.75 per 1M tokens
Output (batch)$1.88 per 1M tokens
Output (flex)$1.88 per 1M tokens
Output (priority)$6.75 per 1M tokens
Output (reasoning)$7.50 per 1M tokens
Web search (context size: high)$0.014 per query
Web search (context size: low)$0.014 per query
Web search (context size: medium)$0.014 per query
DatabricksInput$0.75 per 1M tokens
Input (cache write, priority)$1.35 per 1M tokens
Input (cache write)$0.75 per 1M tokens
Input (cached read, priority)$0.135 per 1M tokens
Input (cached read)$0.075 per 1M tokens
Input (priority)$1.35 per 1M tokens
Output$3.75 per 1M tokens
Output (priority)$6.75 per 1M tokens
OpenRouter · googleImage (input)$0.000001 per image
Input$0.825 per 1M tokens
Input (audio, cached read)$0.0825 per 1M tokens
Input (audio)$0.825 per 1M tokens
Input (cache write)$0.0417 per 1M tokens
Input (cached read)$0.0825 per 1M tokens
Output$4.13 per 1M tokens
Output (reasoning)$4.13 per 1M tokens
Query$0.014 per query
OpenRouterInput$0.75 per 1M tokens
Input (audio, cached read)$0.075 per 1M tokens
Input (audio)$0.75 per 1M tokens
Input (cache write)$0.0417 per 1M tokens
Input (cached read)$0.075 per 1M tokens
Output$3.75 per 1M tokens
Output (reasoning)$3.75 per 1M tokens
GitHub Copilot · github-copilotInput$0.75 per 1M tokens
Input (cached read)$0.075 per 1M tokens
Output$3.75 per 1M tokens
Other · 302aiInput$0.75 per 1M tokens
Input (cached read)$0.075 per 1M tokens
Output$3.75 per 1M tokens
Other · aihubmixInput$0.75 per 1M tokens
Input (audio)$0.75 per 1M tokens
Input (cached read)$0.075 per 1M tokens
Output$3.75 per 1M tokens
Other · aimlapiInput$0.75 per 1M tokens
Input (cached read)$0.075 per 1M tokens
Output$3.75 per 1M tokens
Other · aixyInput$0.75 per 1M tokens
Input (audio)$0.75 per 1M tokens
Input (cached read)$0.075 per 1M tokens
Output$3.75 per 1M tokens
Other · bumoInput$0.795 per 1M tokens
Input (cached read)$0.0795 per 1M tokens
Output$3.98 per 1M tokens
Other · cloudflare-ai-gatewayInput$0.75 per 1M tokens
Input (cached read)$0.075 per 1M tokens
Output$3.75 per 1M tokens
Other · commandcodeInput$1.50 per 1M tokens
Input (cached read)$0.15 per 1M tokens
Output$7.50 per 1M tokens
Other · cortecsInput$0.825 per 1M tokens
Input (cache write)$0.084 per 1M tokens
Input (cached read)$0.082 per 1M tokens
Output$4.13 per 1M tokens
Other · crossmodelInput$0.75 per 1M tokens
Input (cache write)$0.75 per 1M tokens
Input (cached read)$0.075 per 1M tokens
Output$3.75 per 1M tokens
Other · dothooshInput$0.9625 per 1M tokens
Input (cached read)$0.0963 per 1M tokens
Output$4.81 per 1M tokens
Other · edenaiInput$1.50 per 1M tokens
Input (audio)$1.50 per 1M tokens
Input (cache write)$0.0833 per 1M tokens
Input (cached read)$0.15 per 1M tokens
Output$7.50 per 1M tokens
Output (reasoning)$7.50 per 1M tokens
Other · frogbotInput$1.50 per 1M tokens
Input (cached read)$0.15 per 1M tokens
Output$7.50 per 1M tokens
Other · gisooInput$1.05 per 1M tokens
Input (cached read)$0.105 per 1M tokens
Output$5.25 per 1M tokens
Other · gmiInput$0.75 per 1M tokens
Input (cached read)$0.075 per 1M tokens
Output$3.75 per 1M tokens
Other · google-ai-studioInput$0.75 per 1M tokens
Input (batch)$0.375 per 1M tokens
Input (cache write)$0.0833 per 1M tokens
Input (cached read, batch)$0.0375 per 1M tokens
Input (cached read, flex)$0.0375 per 1M tokens
Input (cached read, priority)$0.135 per 1M tokens
Input (cached read)$0.075 per 1M tokens
Input (flex)$0.375 per 1M tokens
Input (priority)$1.35 per 1M tokens
Output$3.75 per 1M tokens
Output (batch)$1.88 per 1M tokens
Output (flex)$1.88 per 1M tokens
Output (priority)$6.75 per 1M tokens
Output (reasoning)$3.75 per 1M tokens
Web search (context size: high)$0.014 per query
Web search (context size: low)$0.014 per query
Web search (context size: medium)$0.014 per query
Other · iteracomputeInput$0.60 per 1M tokens
Input (cached read)$0.06 per 1M tokens
Output$3.00 per 1M tokens
Other · kenariInput$0.3429 per 1M tokens
Input (cache write)$0.0171 per 1M tokens
Input (cached read)$0.0343 per 1M tokens
Output$1.71 per 1M tokens
Other · kiloInput$0.75 per 1M tokens
Input (cache write)$0.0417 per 1M tokens
Input (cached read)$0.075 per 1M tokens
Output$3.75 per 1M tokens
Output (reasoning)$3.75 per 1M tokens
Other · kymaInput$2.03 per 1M tokens
Output$10.13 per 1M tokens
Other · llmgatewayInput$0.75 per 1M tokens
Input (cache write)$0.0833 per 1M tokens
Input (cached read)$0.075 per 1M tokens
Output$3.75 per 1M tokens
Other · merge-gatewayInput$0.75 per 1M tokens
Input (cached read)$0.075 per 1M tokens
Output$3.75 per 1M tokens
Other · nano-gptInput$0.75 per 1M tokens
Input (cache write)$0.0417 per 1M tokens
Input (cached read)$0.075 per 1M tokens
Output$3.75 per 1M tokens
Other · nearaiInput$0.75 per 1M tokens
Input (cached read)$0.075 per 1M tokens
Output$3.75 per 1M tokens
Other · neonInput$1.50 per 1M tokens
Input (cached read)$0.15 per 1M tokens
Output$7.50 per 1M tokens
Other · obscurifyInput$0.8288 per 1M tokens
Input (cached read)$0.0829 per 1M tokens
Output$4.14 per 1M tokens
Other · ofoxInput$0.75 per 1M tokens
Input (audio)$0.75 per 1M tokens
Input (cache write)$0.0415 per 1M tokens
Input (cached read)$0.075 per 1M tokens
Output$3.75 per 1M tokens
Other · opencodeInput$0.75 per 1M tokens
Input (audio)$0.75 per 1M tokens
Input (cached read)$0.075 per 1M tokens
Output$3.75 per 1M tokens
Other · openrouterInput$0.75 per 1M tokens
Input (cache write)$0.0417 per 1M tokens
Input (cached read)$0.075 per 1M tokens
Output$3.75 per 1M tokens
Output (reasoning)$3.75 per 1M tokens
Other · opperInput$0.825 per 1M tokens
Input (cached read)$0.0825 per 1M tokens
Output$4.13 per 1M tokens
Other · perplexityInput$0.75 per 1M tokens
Input (cached read)$0.075 per 1M tokens
Output$3.75 per 1M tokens
Other · perplexity-agentInput$0.75 per 1M tokens
Input (cached read)$0.075 per 1M tokens
Output$3.75 per 1M tokens
Other · poeInput$0.7576 per 1M tokens
Input (cached read)$0.0758 per 1M tokens
Output$3.79 per 1M tokens
Other · primeInput$0.75 per 1M tokens
Output$3.75 per 1M tokens
Other · requestyInput$0.75 per 1M tokens
Input (cached read)$0.075 per 1M tokens
Input (cached read) (region: eu)$0.0825 per 1M tokens
Input (region: eu)$0.825 per 1M tokens
Output$3.75 per 1M tokens
Output (region: eu)$4.13 per 1M tokens
Other · sparrowcodesInput$0.75 per 1M tokens
Input (cached read)$0.075 per 1M tokens
Output$3.75 per 1M tokens
Other · standardcomputeInput$0.75 per 1M tokens
Input (cache write)$0.0417 per 1M tokens
Input (cached read)$0.075 per 1M tokens
Output$3.75 per 1M tokens
Other · temprInput$0.75 per 1M tokens
Input (audio)$0.75 per 1M tokens
Input (cached read)$0.075 per 1M tokens
Output$3.75 per 1M tokens
Other · uplinkswitchInput$0.4925 per 1M tokens
Input (cached read)$0.0493 per 1M tokens
Output$2.25 per 1M tokens
Other · veniceInput$0.9375 per 1M tokens
Input (cached read)$0.0938 per 1M tokens
Output$4.69 per 1M tokens
Other · vercelInput$0.75 per 1M tokens
Input (cached read)$0.075 per 1M tokens
Output$3.75 per 1M tokens
Other · vivgridInput$0.75 per 1M tokens
Input (audio)$0.75 per 1M tokens
Input (cache write)$0.0833 per 1M tokens
Input (cached read)$0.15 per 1M tokens
Output$3.75 per 1M tokens

Specifications

Provider
google
Context window
1,048,576
Max output tokens
65,536
Open weights
no
Released
09/02/2026
Retires
no date announced
First seen by this tracker

Price history

No price of this model has changed since we started tracking it.

Input
0.75 per 1M tokens, unchanged since 09/14/2026
Output
3.75 per 1M tokens, unchanged since 09/14/2026
Input (cached read)
0.075 per 1M tokens, unchanged since 09/14/2026
Input (batch)
0.375 per 1M tokens, unchanged since 09/14/2026
Output (batch)
1.88 per 1M tokens, unchanged since 09/14/2026
Input (cached read, batch)
0.0375 per 1M tokens, unchanged since 09/14/2026
Input (flex)
0.375 per 1M tokens, unchanged since 09/14/2026
Output (flex)
1.88 per 1M tokens, unchanged since 09/14/2026
Input (cached read, flex)
0.0375 per 1M tokens, unchanged since 09/14/2026
Input (priority)
1.35 per 1M tokens, unchanged since 09/14/2026
Output (priority)
6.75 per 1M tokens, unchanged since 09/14/2026
Input (cached read, priority)
0.135 per 1M tokens, unchanged since 09/14/2026
Output (reasoning)
3.75 per 1M tokens, unchanged since 09/14/2026
Web search (context size: low)
0.014 per query, unchanged since 09/14/2026
Web search (context size: medium)
0.014 per query, unchanged since 09/14/2026
Web search (context size: high)
0.014 per query, unchanged since 09/14/2026
Input (audio)
0.75 per 1M tokens, unchanged since 10/20/2026

Last updated 11/19/2026, 01:12