Google AI language model

Gemini 4 Argon

Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, with a 1M-token context shared by input and output. its introductory $2 / $10 rate undercuts Gemini 3.1 Pro on output until it doubles to $4 / $20 on 2026-12-01.

01

price

$2/M

input tokens

$10/M

output tokens

$0.1/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 price through 2026-11-30; standard rate $4 / $20 per 1M tokens (cached input $0.20) from 2026-12-01.
  • implicit caching only: repeated prompt prefixes bill at the cached rate automatically; explicit cache creation is not supported.
  • one flat rate at every context length, with no surcharge past 200K input tokens.

02

what real work costs

workloadcost
one chat reply 3,000 tokens in, 500 out $0.01
summarise a 100-page report 50,000 tokens in, 1,500 out, one request $0.12
1,000 classification calls 500 tokens in, 20 out, per call $1.20
coding-agent session 2M tokens in across ~60 turns, 60,000 out, no cache $4.60
same session, cached 85% of input read from the prompt cache, the rest written to it $1.37

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 $0.1/M
weights
closed
released
October 2026
knowledge cutoff
March 2026
status
live
model id
gemini-4-argon

integration notes

  • temperature, top_p and top_k are ignored; Google says to remove them from requests.
  • max_output_tokens caps thinking plus answer together; output past 64K needs background execution with max_output_tokens above 65,536.
  • hard prompts can run several minutes; Google recommends HTTP client timeouts of at least 15 minutes.

04

benchmarks

as published by the maker; not measured by octomind.

benchmarkscore
DeepSWE v1.1source77.9%
Terminal-bench 4.0source57.4%
OSWorld-2.0, offline subset (partial score)source69.2%
GraphWalks, 256k to 1M, BFS (F1)source84.2%
Vals Indexsource68.9%

05

when to pick it

pick it if

  • want Google's flagship reasoning model with low, medium or high thinking
  • need video, audio or PDF input alongside images in one context
  • send long prompts: no long-context surcharge and $0.10 cached input

06

where it sits on price

blended price $4/M at 3 input tokens per output token: 34 live language models cost less, 9 cost more.

  1. Qwen3.8 Max $3/M
  2. Claude Sonnet 5.5 $4/M
  3. Gemini 4 Argon $4/M
  4. GPT-6.1 Sol $4/M
  5. Kimi K3.1 Pro $4/M

07

use Gemini 4 Argon 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-4-argon
switch mid-session
/model octohub:gemini-4-argon
make it the default — config.toml
[model]
name = "octohub:gemini-4-argon"

08

compare Gemini 4 Argon

all model comparisons →

09

similar models

nearest live models by listed input price.

view all models →

10

Gemini 4 Argon faq

how much does Gemini 4 Argon cost?

Gemini 4 Argon lists at $2/M input, $10/M output, $0.1/M cached input per 1M tokens. a typical coding-agent session (2M tokens in, 60,000 out) comes to $4.60, or $1.37 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 4 Argon?

1M tokens, ≈ 1,500 pages of prose or 100,000 lines of code. a single reply can run to 65.536k tokens.

does Gemini 4 Argon accept images?

yes. it takes text, images, video, audio and pdf as input and returns text.

is Gemini 4 Argon open source?

no. Gemini 4 Argon is a closed-weights model, available only through Google AI's api and hosted gateways such as octohub.

when was Gemini 4 Argon released?

October 2026, by Google AI.

is Gemini 4 Argon free?

no. Gemini 4 Argon bills per token at $2/M input, $10/M output, $0.1/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 4 Argon in octomind?

run octomind login once, then octomind run -m octohub:gemini-4-argon. inside a running session, /model octohub:gemini-4-argon switches to it without losing context.

use Gemini 4 Argon in octomind

choose a model when you start, then switch mid-session when the work changes.