Google AI language model
Gemini 3.8 Flash
Google's Flash-tier Gemini model, built for long-horizon software engineering, autonomous agents and enterprise workflows. Google replaced Gemini 3.7 Flash with it at the same introductory rate; it costs less than Gemini 4 Argon and Gemini 3.1 Pro.
01
price
input tokens
output tokens
cached input
per 1M tokens. octomind bills the listed provider price, with no markup, on every plan, including the free one (pay as you go from credits).
- introductory rate through 2026-12-31; Google's price doubles to $1.50 / $7.50 per 1M tokens from 2027-01-01.
- cache hits bill at $0.075 per 1M tokens through 2026 and $0.15 from 2027.
- thinking tokens bill as output; thinking runs at low, medium or high, and the minimal level is rejected.
02
what real work costs
| workload | cost |
|---|---|
| one chat reply 3,000 tokens in, 500 out | $0.0041 |
| summarise a 100-page report 50,000 tokens in, 1,500 out, one request | $0.04 |
| 1,000 classification calls 500 tokens in, 20 out, per call | $0.45 |
| coding-agent session 2M tokens in across ~60 turns, 60,000 out, no cache | $1.73 |
| same session, cached 85% of input read from the prompt cache, the rest written to it | $0.58 |
at the listed rate. token counts are typical sizes, not measurements.
03
specs
- provider
- Google AI
- context window
- 1M tokens — ≈ 1,500 pages of prose or 100,000 lines of code
- max output
- 65.536k tokens
- input
- text, images, video, audio, pdf
- output
- text
- structured output
- yes — JSON schema
- reasoning mode
- yes
- prompt caching
- yes — cache hits at $0.075/M
- weights
- closed
- released
- September 2, 2026
- knowledge cutoff
- March 2026
- status
- live
- model id
gemini-3.8-flash
integration notes
- Google's migration checklist says to remove the deprecated temperature, top_p and top_k sampling parameters.
- use thinking_level (low, medium, high; default medium) instead of thinking_budget; minimal returns an error.
- candidate_count is unsupported, and Google says to remove prefilled model turns from multi-turn conversations.
04
benchmarks
as published by the maker; not measured by octomind.
05
when to pick it
pick it if
- you want agentic coding at under half of Gemini 4 Argon's price
- you send images, video, audio or PDFs alongside text
- you resend long prompts; cache hits bill at 10% of input
skip it if
- the cheaper Gemini 3.5 Flash Lite already covers your workload
- your budget assumes today's rate holds past 2026-12-31
06
where it sits on price
blended price $1.5/M at 3 input tokens per output token: 21 live language models cost less, 22 cost more.
- Grok Build 0.1 $1.25/M
- Qwen3.5 397B $1.35/M
- Gemini 3.8 Flash $1.5/M
- Kimi 2.6 $1.712/M
- Kimi 2.7 Code $1.712/M
07
use Gemini 3.8 Flash in octomind
one octohub login reaches every model in the catalog. pick this one per run, per session, or as your default.
octomind login
octomind run -m octohub:gemini-3.8-flash/model octohub:gemini-3.8-flash[model]
name = "octohub:gemini-3.8-flash"08
compare Gemini 3.8 Flash
- Gemini 3.8 Flash vs Gemini 3.6 Flash
- Gemini 3.8 Flash vs GPT-6.1 Terra
- Gemini 3.8 Flash vs Gemini 4 Argon
09
similar models
nearest live models by listed input price.
- Qwen3.5 397B $0.6/M input
- Kimi 2.6 $0.95/M input
- Kimi 2.7 Code $0.95/M input
- Inkling Small $0.5/M input
10
earlier versions
retired models retained for historical reference.
11
Gemini 3.8 Flash faq
how much does Gemini 3.8 Flash cost?
Gemini 3.8 Flash lists at $0.75/M input, $3.75/M output, $0.075/M cached input per 1M tokens. a typical coding-agent session (2M tokens in, 60,000 out) comes to $1.73, or $0.58 when 85% of the input is read from the prompt cache. octomind bills the listed provider price, with no markup, on every plan, including the free one (pay as you go from credits).
what is the context window of Gemini 3.8 Flash?
1M tokens, ≈ 1,500 pages of prose or 100,000 lines of code. a single reply can run to 65.536k tokens.
does Gemini 3.8 Flash accept images?
yes. it takes text, images, video, audio and pdf as input and returns text.
is Gemini 3.8 Flash open source?
no. Gemini 3.8 Flash is a closed-weights model, available only through Google AI's api and hosted gateways such as octohub.
when was Gemini 3.8 Flash released?
September 2, 2026, by Google AI.
is Gemini 3.8 Flash free?
no. Gemini 3.8 Flash bills per token at $0.75/M input, $3.75/M output, $0.075/M cached input per 1M. octomind's free plan reaches it pay as you go from credits, so you pay only for the tokens you use, at the provider price. credits carry a 3% top-up fee.
how do i use Gemini 3.8 Flash in octomind?
run octomind login once, then octomind run -m octohub:gemini-3.8-flash. inside a running session, /model octohub:gemini-3.8-flash switches to it without losing context.
use Gemini 3.8 Flash in octomind
choose a model when you start, then switch mid-session when the work changes.