Model comparison
Gemini 4 Hydrogen vs Gemini 3.8 Flash
Provider-published facts for Gemini 4 Hydrogen and Gemini 3.8 Flash, side by side: price, limits, inputs, access and data policy. No mystery scores and no invented benchmark rankings.
Model comparison
Provider-published facts for Gemini 4 Hydrogen and Gemini 3.8 Flash, side by side: price, limits, inputs, access and data policy. No mystery scores and no invented benchmark rankings.
What changed
Hydrogen is Google's recommended upgrade from Gemini 3.8 Flash. It shares one token budget across input, thinking and output, adds long decode and computer use, and costs more per token than 3.8 Flash's current promotional price. Google reports it finishes tasks 2.5 times faster; that is a provider claim, not a Cody measurement.
| Spec | Gemini 3.8 Flash | Gemini 4 Hydrogen |
|---|---|---|
| Context window | 1,048,576 tokens | 1,048,576 tokens shared by input, thinking and output |
| Maximum output | 65,536 tokens | 65,536 synchronous; long decode uses the remaining context |
| Knowledge cutoff | March 2026; some domains may lag to January 2025 | March 2026 |
| Input price | $0.75 / 1M promo | $1.50 / 1M |
| Output price | $3.75 / 1M promo | $7.50 / 1M |
| Tools & agents | Functions, search, code execution, file search | Functions, code execution, search, file search, computer use |
Unchanged: inputs.
Set your usage. Your estimate updates as you type.
Example: 6,000 input tokens for 10 pages, plus a 500-token summary. Page lengths vary; adjust the numbers below.
One run sends your input to the model once and receives an answer. Tokens are pieces of text: input is what you send, output is the answer you receive.
Estimates exclude taxes, tools, cache storage/writes, free allowances and custom discounts. Image estimates cover output only, not prompt or reference-image charges. Quality modes differ by model. Unlisted settings are not treated as free.
| Model | Access | Estimated total (USD) |
|---|---|---|
| Gemini 3.8 FlashGoogle | $0.0064 | |
| Gemini 4 HydrogenGoogle | $0.0128 |
Quick take
Google's fast Gemini 4 model for agentic workflows and everyday coding, and its recommended upgrade from Gemini 3.8 Flash.
Its paid rates are higher than Gemini 3.8 Flash's current promotional price, and thinking defaults to high, which adds output tokens. Explicit context caching and the Live API are not supported, and free-tier prompts may be used to improve Google's products.
Google's stable, high-efficiency multimodal model for agents, software work, and large mixed-media inputs at an introductory Flash-tier price.
Free and paid Gemini services have materially different data-use terms. Verify billing status and regional availability for the exact project.
Compare the published facts
Values use each provider's own published units and limits. A blank means the provider did not publish a directly comparable value in the sources reviewed.
| Text & reasoning | Gemini 4 Hydrogen | Gemini 3.8 Flash |
|---|---|---|
| Context windowMaximum combined prompt and working context documented by the provider. | 1,048,576 tokens shared by input, thinking and output | 1,048,576 tokens |
| Maximum outputProvider-published response limit, where available. | 65,536 synchronous; long decode uses the remaining context | 65,536 tokens |
| Knowledge cutoffLatest reliable knowledge date explicitly published by the model provider. Search and connected tools can retrieve newer information but do not change the model's built-in cutoff. | March 2026 | March 2026; some domains may lag to January 2025 |
| Input priceCurrent standard list price per million input tokens unless noted. | $1.50 / 1M | $0.75 / 1M promo |
| Output priceCurrent standard list price per million output tokens unless noted. | $7.50 / 1M | $3.75 / 1M promo |
| InputsMedia types accepted by the listed model endpoint. | Text, image, video, audio, PDF | Text, image, video, audio, PDF |
| Tools & agentsSelected native tools and agent-building capabilities, not an exhaustive list. | Functions, code execution, search, file search, computer use | Functions, search, code execution, file search |
How to choose
Start with the job you need to complete, then validate cost, access, and policy details on your exact provider route.
On the Gemini API's free tier, Google may use prompts and responses to improve its products; on the paid tier, it does not.
Provider and API links
Google says paid Gemini API prompts and responses are not used to improve its products. Unpaid-service content generally may be used, with different treatment for EEA, UK, and Swiss users; check the current terms for your account and region.
Provider and API links
Frequently asked questions
Gemini 4 Hydrogen: Google's fast Gemini 4 model for agentic workflows and everyday coding, and its recommended upgrade from Gemini 3.8 Flash. Gemini 3.8 Flash: Google's stable, high-efficiency multimodal model for agents, software work, and large mixed-media inputs at an introductory Flash-tier price.
Hydrogen is Google's recommended upgrade from Gemini 3.8 Flash. It shares one token budget across input, thinking and output, adds long decode and computer use, and costs more per token than 3.8 Flash's current promotional price. Google reports it finishes tasks 2.5 times faster; that is a provider claim, not a Cody measurement. Changed in the published specs: context window, maximum output, knowledge cutoff, input price, output price and tools & agents. Unchanged: inputs.
Best fit for Gemini 4 Hydrogen: Fast agentic workflows. Best fit for Gemini 3.8 Flash: High-volume multimodal agents. Test both with your own data and provider route before committing.
From each provider's own documentation, pricing and policy pages for the Text & reasoning category. Cody does not add its own benchmark scores or name a universal winner.