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

$0.75/M

input tokens

$3.75/M

output tokens

$0.075/M

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

workloadcost
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.

benchmarkscore
Terminal-bench 2.1source89.4%
DeepSWE v1.1source73.7%
HLE-Verifiedsource54.9%
OSWorld-2.0 (Partial score, batch tool enabled)source59.0%
Terminal-bench 4.0source19.1%

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

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.

  1. Grok Build 0.1 $1.25/M
  2. Qwen3.5 397B $1.35/M
  3. Gemini 3.8 Flash $1.5/M
  4. Kimi 2.6 $1.712/M
  5. 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.

run it
octomind login
octomind run -m octohub:gemini-3.8-flash
switch mid-session
/model octohub:gemini-3.8-flash
make it the default — config.toml
[model]
name = "octohub:gemini-3.8-flash"

08

compare Gemini 3.8 Flash

all model comparisons →

09

similar models

nearest live models by listed input price.

view all models →

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.