Gemini 4 Neon is a large language model made by Google, added to the catalog on 18 Nov 2026. It has a context window of 1,048,576 tokens and costs $3.00 per 1M input tokens and $15.00 per 1M output tokens. It accepts text, images, files, audio and video and produces text. Typical uses: repository coding, terminal coding and working with long files.
Price checked · source: OpenRouter
What Gemini 4 Neon is
Google Gemini 4 Neon is a model in Google’s Gemini 4 family, described as built for coding and agentic work. The catalog specifically identifies repository and terminal coding as areas it suits. It accepts text, files, images, audio, and video, and produces text. These are the listed input and output modalities; the available details do not specify what operations it performs on each media type or which file types it supports.
The model has a context length of 1,048,576 tokens and a maximum output of 943,718 tokens. Its stated context capacity may suit work that uses extensive supplied material, such as repository coding or tasks involving long text and files. Gemini 4 Neon supports reasoning and tools, along with structured outputs and response formats. These capabilities are relevant to workflows that use tools or require responses in a defined structure, although the catalog does not name particular tools or formats. Its coding focus and listed modalities provide a basis for considering it for tasks that combine coding instructions with text, files, images, audio, or video as input. Text is the only listed output modality. The catalog does not provide further details about the model’s behavior on particular coding tasks, media inputs, or tool integrations, so those specifics are not stated here.
Key features
- Accepts text, files, images, audio, and video
- Produces text
- Has a context length of 1,048,576 tokens
- Supports reasoning and tools
- Supports structured outputs and response formats
Typical uses
- Repository coding
- Terminal coding
- Working with long files
- Processing multimodal inputs
- Generating structured text
Gemini 4 Neon pricing
US dollars, list price through OpenRouter.
| Item | Standard | Batch |
|---|---|---|
| Input, per 1M tokens | $3.00 | $1.50 |
| Output, per 1M tokens | $15.00 | $7.50 |
| Cached input read, per 1M tokens | $0.15 | $0.075 |
| Cache write, per 1M tokens | $0.0833 | $0.0833 |
| Image input, per image | $0.000003 | $0.000002 |
| Web search, per search | $0.014 | $0.014 |
| Variant | Model id |
|---|---|
| Batch | google/gemini-4-neon:batch |
A variant is the same model under another id, with prices or limits of its own. Its prices are the columns of the list above.
No price change since it was added on 18 Nov 2026.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0060 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.087 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.120 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.473 |
Gemini 4 Neon specifications
| Model id | google/gemini-4-neon |
|---|---|
| Version | gemini-4-neon-20261118 |
| Context window | 1,048,576 tokensAbout 786,432 English words |
| Max output | 943,718 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 18 Nov 2026 |
| Input types | audio, file, image, text, video |
|---|---|
| Output types | text |
| Tool calling | Yes |
| Structured outputs | Yes |
| Reasoning effort control | Yes |
| Content moderation | Not applied by provider |
Sample outputs
The same prompts are given to every model, and the unedited output is shown with the date it was produced. Upend does not publish leaderboard scores it did not run.
No output has been recorded for Gemini 4 Neon yet.
Compare Gemini 4 Neon
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.