# Gemini 4 Neon (slim)

> Gemini 4 Neon is Google's middle Gemini 4 model, between Hydrogen and Carbon, for complex coding, knowledge work and science, on the paid tier of the Gemini API with a 1,048,576-token limit shared between input and output.

- Full: https://www.anchorterminal.com/tools/gemini-4-neon.md (~9,600 tokens) · this version ~1,730 tokens · JSON https://www.anchorterminal.com/tools/gemini-4-neon.json · canonical https://www.anchorterminal.com/tools/gemini-4-neon
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-19 · pricing https://www.anchorterminal.com/tools/gemini-4-neon#pricing · reviews https://www.anchorterminal.com/tools/gemini-4-neon#reviews
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

**B · 65/100 · rank #557 of 1559 · #25 in Model APIs & inference · not agent-ready · confidence medium** · same model listed separately: Gemini Developer API, Model API (https://www.anchorterminal.com/tools/gemini-api.min.md)


Assessment: Google's middle Gemini 4 model, between Hydrogen and Carbon, at $3 and $15 per million tokens with a 1M-token shared budget, four thinking levels, function calling, structured output and implicit caching at 95% off. Paid tier only, sampling parameters are ignored, explicit caching isn't supported, no retirement date is stated, and every benchmark is Google's.

## Facts

- Kind: Model API · vendor: Google · category: Model APIs & inference · legal entity: Google LLC · provenance 91/100
- Endpoint: `https://generativelanguage.googleapis.com/v1beta` ()
- Auth: API key · pricing: Pay per use · x402: no · licence: Closed model, used through the Gemini API and Google's apps under Google's terms
- Benchmark probes: not run yet, so Performance is pending
- Live, from our pollers (not part of the score): up at 2026-11-19 01:38 UTC · uptime 30 days 100.0% (12 probes) · p50 31 ms · p95 130 ms over 24 hours
- Surface graded: The model as the Gemini API serves it, read on 18 November from Google's model page, the What's new in Gemini 4 Neon guide, the pricing page and release notes in AI Studio's docs, the DeepMind model card and the Google Cloud model page. Platform readings (status page, rate limits, keys, SDKs, terms, retention, deprecations) are the Gemini API listing's of 1 November. No account was made and nothing was called
- Model ID: gemini-4-neon, stable, on the GenerateContent API and the Interactions API (not the Live API). Generally available on the Gemini API and on Google Cloud's Agent Platform from 18 November 2026
- Context: 1,048,576 tokens for input, thinking and output together. 65,536 output tokens a synchronous response; background execution or client-side continuation runs to the full budget in 64K hops. Knowledge cutoff March 2026
- Thinking: low, medium, high (the default) and xhigh. minimal returns an error
- Inputs and outputs: Text, images, video, audio and PDF in; text, function calls and JSON to a schema out. Tools: Google Search and Maps grounding, code execution, URL context, computer use, file search and function calling. Batch, Flex and Priority inference supported
- Caching: Implicit caching only, on prompts of 4,096 tokens or more, with cached input 95% off at $0.15 per million
- Pricing: $3 input and $15 output per million tokens, thinking included, flat across the 1M window. Paid tier only. Search grounding is billed per query after 5,000 free requests a month shared across Gemini 3 and newer models. From 1 December Argon's standard price, $4 and $20, is higher than Neon's
- Where: Gemini API paid tier and Google AI Studio, including Google AI Pro and Ultra plans there; the Gemini app; Gemini for business; Google Antigravity for paid Google AI Pro and Ultra subscribers; Google Cloud's Agent Platform; the Antigravity agent in Gemini Managed Agents
- Google's figures: Vendor-reported, from the model card against Claude Opus 5.5 and GPT-6.2 Sol: AA Index v5.0.1 61 (59, 57), Terminal-bench 4.1 65.2% (65.8%, 61.5%), SWE-sweep with Google's harness 39.0%, GraphWalks 256k to 1M 95.2%, CWE-Bench v2 70.7%, HLE-Diamond 71.3%
- Safety: Adapted from Gemini 4 Carbon. Google DeepMind's change assessment found Neon below the threshold for new critical capability tests, so Argon's results carry forward: the biological and cyber critical levels can't be ruled out and are mitigated. Automated tests show 3 points fewer unjustified refusals than Hydrogen. The full safety report is marked coming soon
- Prices: Gemini 4 Neon input $3 per 1M tokens; Gemini 4 Neon cached input $0.15 per 1M tokens; Gemini 4 Neon output $15 per 1M tokens

- Scores: Reliability 45, Performance not tested, Schema & documentation 85, Agent ergonomics 93, Security & auth 55, Payments & pricing 30, Task success not tested, Maintenance & community 83, Transparency & trust 73
- Why: Reliability, Model reading for gemini-4-neon on the Gemini API. · Schema & documentation, Model reading for gemini-4-neon on the Gemini API. · Agent ergonomics, Model reading for gemini-4-neon on the Gemini API. · Security & auth, Model reading for gemini-4-neon on the Gemini API. · Payments & pricing, Model reading for gemini-4-neon on the Gemini API. · Maintenance & community, Model reading for gemini-4-neon on the Gemini API. · Transparency & trust, Model reading for gemini-4-neon on the Gemini API.
- Sources: 11, open questions: 5, both in the full twin
- Capabilities: inference.llm
- JSON: https://www.anchorterminal.com/api/v1/tools/gemini-4-neon.json
- Its vendor verifies the listing with `verify_listing` or `POST https://www.anchorterminal.com/api/v1/verify` (the full twin says how); no effect on the grade.

## Before you call it

1. Call generateContent at https://generativelanguage.googleapis.com/v1beta, or the Interactions API, with model gemini-4-neon and an x-goog-api-key on a billed project
2. Leave thinking_level at high and try medium for interactive work; reserve xhigh for hard multi-step problems
3. Don't send temperature, top_p or top_k, and declare tools natively rather than asking for raw-text JSON calls
4. Return every thought_signature unchanged, and never copy one across parallel functionCall parts
5. Set background to true with max_output_tokens above 65,536 for long outputs, and allow HTTP timeouts of 15 minutes

## Connect

```bash
curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-4-neon:generateContent" \
  -H "x-goog-api-key: $GEMINI_API_KEY" -H "content-type: application/json" \
  -d '{"contents":[{"parts":[{"text":"hello"}]}]}'
```

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| Vertex AI (Gemini Enterprise Agent Platform) | AA | 91.2 | inference.llm | https://www.anchorterminal.com/tools/vertex-ai.min.md |
| OpenAI API | AA | 85.8 | inference.llm | https://www.anchorterminal.com/tools/openai-api.min.md |
| GPT-6.2 Astra | AA | 85.8 | inference.llm | https://www.anchorterminal.com/tools/gpt-6-2-astra.min.md |
| Amazon Bedrock | A | 83.5 | inference.llm | https://www.anchorterminal.com/tools/amazon-bedrock.min.md |
| Azure OpenAI in Foundry Models | A | 81.2 | inference.llm | https://www.anchorterminal.com/tools/azure-openai.min.md |


## Panel reviews (0, desk reviews from public material, no calls made)

