Google

gemini-3.8-flash

$0.825 in · $4.125 out per million tokens · 1,048,576 tokens of context · first token in 2,820 ms

Get an API key

Price, limits and measured speed

Input price
$0.825 per million tokens
gateway.plungeai.com
Output price
$4.125 per million tokens
gateway.plungeai.com
Google's list price, input
$0.825 per million tokens
Google's list price, as our price feed records it
Google's list price, output
$4.125 per million tokens
Google's list price, as our price feed records it
Against the list price
At the list price
gateway.plungeai.com
Context window
1,048,576 tokens
gateway.plungeai.com
Tool calling
Yes
gateway.plungeai.com
Reads images
No
gateway.plungeai.com
Streams its answer
Yes
gateway.plungeai.com
Takes
text
gateway.plungeai.com
Request parameters
13 supported
gateway.plungeai.com
Served by
Google
gateway.plungeai.com
Time to first token
2,820 ms
our probe of 22 November 2026 · measured by us
Price of our test call
$0.000672
our probe of 22 November 2026, as the API stated it · measured by us
Input price rank
32nd lowest of 55 chat models
the models on this site we could call · measured by us
Output price rank
32nd lowest of 55
the models on this site we could call · measured by us
First-token rank
51st fastest of 55 measured
our probe of 22 November 2026 · measured by us
Context rank
7th largest of 55
the models on this site we could call · measured by us

Call it

curl

curl https://api.plungeai.com/v1/chat/completions \
  -H "Authorization: Bearer $PLUNGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemini-3.8-flash",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

What it costs for three jobs

The same three jobs on every model page, so two models can be compared.

The cost of three reference workloads on google/gemini-3.8-flash
JobTokens inTokens outThrough One APIAt Google's list price
A chat turn1,000300$0.00206$0.00206
An answer over retrieved documents8,000500$0.00866$0.00866
A summary of a long document100,0002,000$0.0908$0.0908

Models near it

Each against gemini-3.8-flash: its input price and the time to its first token.

Models related to google/gemini-3.8-flash by provider, price and context
ModelWhy it is hereInput price against itFirst token against itInput, $ per 1MOutput, $ per 1MContext, tokensFirst tokenTokens a second
google/gemini-3.6-flashSame provider−9 %−1,107 ms$0.75$3.751,048,5761,713 msnot measured
google/gemini-robotics-er-2-previewSame provider+21 %−1,538 ms$1$5131,0721,282 msnot measured
google/gemini-3-flash-previewSame provider−39 %−1,443 ms$0.5$31,000,0001,377 msnot measured
google/gemini-3.5-flash-liteCheaper, same abilities−64 %−1,970 ms$0.3$2.51,048,576850 ms715.2
deepseek/deepseek-v4.1-flashCheaper, same abilities−70 %−2,394 ms$0.25$0.751,048,576426 ms189.3
openai/gpt-6.1-terraLarger context+21 %−1,686 ms$1$51,050,0001,134 ms94.8

Request options

What google/gemini-3.8-flash returns and the request parameters it accepts
SettingValue
Returnstext
Request parameterstemperature, top_p, max_tokens, max_completion_tokens, stop, tools, tool_choice, response_format, top_k, seed, presence_penalty, frequency_penalty, reasoning_effort

What changed

  • gemini-3.8-flash Output price: $4.13 per million tokens → $4.125 per million tokens
  • gemini-3.8-flash Google's list price, output: $4.13 per million tokens → $4.125 per million tokens
  • gemini-3.8-flash A summary of a long document: $0.091 → $0.0908

Every change

In short

  • One API charges Google's list price for gemini-3.8-flash: $0.825 in and $4.125 out per million tokens.
  • By input price it is the 32nd lowest of the 55 chat models we could call on 22 November 2026.
  • Its first token arrived after 2,820 ms in our test; the median of the 18 Google models we called was 1,210 ms.
  • Its context window of 1,048,576 tokens holds about 2,097 pages of text at 500 tokens a page.

How this page is made

Prices, context sizes and abilities are read from One API's public price feed and its model endpoints each time this page is built. The time to the first token, the output speed and the price of a call are measured by us: 3 calls for each model through a One API key on 22 November 2026, entering at not recorded. A model that did not answer has no page. How we measure.

Data checked · Last changed

Get an API key