Current rates for gemini-4-argon.
Compare the same model version and billing category. Each price carries its applicable unit and date.
USD per million tokens. Codimixa rates use the account group and context condition shown. Official prices come from the publisher where a reference has been reviewed, with current promotions and context tiers labeled; for the other models they are the console list price before the account discount. Cache categories replace uncached input billing for those tokens.
| Model / category | Codimixa · USD / 1M | Official · USD / 1M | Codimixa rate conditions |
|---|---|---|---|
| gemini-4-argonUncached input | $1.60 | $2.00Through November 30, 2026Publisher pricing | Account group: defaultStandard |
| gemini-4-argonOutput | $8.00 | $10.00Through November 30, 2026Publisher pricing | Account group: defaultStandard |
| gemini-4-argonCache read | $0.08 | $0.10Through November 30, 2026Publisher pricing | Account group: defaultStandard |
Standard processing. Promotional prices through November 30, 2026. Implicit cache reads; Google does not offer explicit cache storage for Argon.
Codimixa rates checked: 2026-11-03T05:29:59.507Z. Publisher references checked: October 20, 2026.
Model ID, specifications and API settings.
Use gemini-4-argon in Codimixa requests. Publisher specifications and the recommended request format are listed below.
| Field | Model value |
|---|---|
| Exact Codimixa API ID | gemini-4-argon |
| Publisher model ID | gemini-4-argon |
| Publisher context | 1,048,576 tokens (input + output) |
| Standard maximum output | 65,536 tokens |
| Publisher inputs | Text, image, audio, video, PDF |
| Output type | Text |
| Agent API | Chat Completions |
| Integration requirements | Use low, medium or high reasoning effort. Standard synchronous output is up to 65,536 tokens. Google long decode uses a separate asynchronous workflow. |
Input types and context limits describe the publisher’s model. The agent API column gives the recommended request format. Open a model for its configuration and source links.
Connect gemini-4-argon to your workflow.
Copy the exact model ID above, then use the API quickstart or your client’s setup guide.
Estimate your usage.
Use the current model rates with your expected token counts. Keep hosting and external tool charges separate from the API estimate.
A FEW DETAILS
Before you continue
Which price applies to my request?
Standard processing. Promotional prices through November 30, 2026. Implicit cache reads; Google does not offer explicit cache storage for Argon.
Which model ID should I use?
Use gemini-4-argon with your Codimixa key and https://api.codimixa.com/v1. The publisher model ID is shown separately for reference.