Gemini 4 Neon API
Google DeepMind’s Gemini4 Neon delivers fast multimodal understanding, high-performance coding, and configurable reasoning for production workloads.
Gemini4 Neon is part of the Gemini4 family from Google DeepMind, released on November18,2026. It accepts multimodal input and is designed for high-performance coding, multi-step reasoning, low-latency multimodal understanding, and agentic workflows. Four effort levels—low, medium, high, and xhigh—help balance quality, latency, and cost.
The model is suited to production workloads that require both quality and efficiency. Compared with Gemini4 Carbon, it provides a small intelligence gain, faster response times, and improvements in agentic knowledge work, visual reasoning, and coding. Its output speed is110 output tokens per second, while tasks take21 minutes at xhigh effort. Gemini4 Neon uses about15 percent more output tokens per task than Gemini4 Carbon.
Updated:
MODEL ID
gemini-4-neon- Context
- 1.049M
- Max output
- 943.718K
- Recommended API
- messages
- Input
- audio / file / image / text / video
- Output
- text
Highlights
- High-performance coding
- Four effort levels
- Low-latency multimodal understanding
- Agentic workflows
- 110 output tokens per second
Providers
Best priceCompare API prices across providers. Select a provider to view all charges and conditions.
| Uptime | ||||||
|---|---|---|---|---|---|---|
| $3 | $15 | $3 | $0.15 | $0.15 | ||
| $1.5 | $7.5 | $1.5 | $0.075 | $0.075 | ||
| $3 | $15 | $3 | $0.15 | $0.15 | ||
| $5.4 | $27 | $5.4 | $0.27 | $0.27 | ||
| $5.4 | $27 | $5.4 | $0.27 | $0.27 |
Historical observations are not a live health check. Missing data does not mean an outage.
What $10 buys
- Input
- 3.3M tokens
- Output
- 666.7K tokens
Estimated from current input and output prices, before discounts.
Benchmarks
- 61
Artificial Analysis Intelligence Index
points; third overall, behind GPT-6.2 Astra and Claude Fable5.2 at maximum settings
- 59
Artificial Analysis Coding Agent Index
points with Antigravity CLI; three points ahead of Gemini4 Carbon
- 110
Output speed
output tokens per second
- 21
Task duration
minutes per task at xhigh effort
Scores as published by the model provider.
Reasoning
- Default effort
- medium
- Always enabled
- Yes
- Available effort levels
- xhigh / high / medium / low
Quick Start
Drop-in code to call this model with Felo API Platform compatible APIs. Start in the Playground when you want to test prompts before writing code.
Get your API key
Create a key from your Felo API Platform account and set it as an environment variable.
export FELO_API_KEY="YOUR_API_KEY"Make your first request
Use this model ID with the Felo API Platform endpoint. Optional request headers such as X-Request-Id can help troubleshooting.
gemini-4-neonThis model is reasoning-capable. If your selected protocol and model route expose reasoning controls, preserve the returned reasoning metadata when continuing a conversation.
const response = await fetch("https://openapi.felo.ai/api/v1/messages", {
method: 'POST',
headers: {
Authorization: `Bearer ${process.env.FELO_API_KEY}`,
'Content-Type': 'application/json',
},
body: JSON.stringify({
"model": "gemini-4-neon",
"max_tokens": 1024,
"messages": [
{
"role": "user",
"content": "Hello"
}
]
}),
});
if (!response.ok) throw new Error(await response.text());
console.log(await response.json());Using third-party SDKs
Use compatible SDKs by setting baseURL to https://openapi.felo.ai/api/v1. Use the Anthropic-compatible base URL for Claude-style clients. https://openapi.felo.ai/api.
Enable streaming
Add stream: true to receive responses as server-sent events.
curl -N https://openapi.felo.ai/api/v1/messages \
-H "Authorization: Bearer $FELO_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-4-neon",
"max_tokens": 1024,
"messages": [
{
"role": "user",
"content": "Hello"
}
],
"stream": true
}'Endpoint
Felo API Platform exposes compatible model-calling surfaces. Pick the surface your app or agent client already supports.
Messages
Anthropic-compatible messages for Claude-style clients.
POST
https://openapi.felo.ai/api/v1/messagesParameters
modelstringgemini-4-neonPublic model ID to call.max_tokensinteger—Maximum generated tokens.messagesarray—Conversation messages for Chat Completions.seed———stop———toolsarray—Tool calling definitions following compatible schema.top_p———reasoning———temperaturenumber—Controls response variety when supported.tool_choicestring or object—Controls whether a tool should be called.response_formatobject—Request structured output when supported.reasoning_effort———include_reasoning———structured_outputs———Frequently asked questions
What is Gemini 4 Neon?
Gemini4 Neon is part of the Gemini4 family from Google DeepMind, released on November18,2026. It accepts multimodal input and is designed for high-performance coding, multi-step reasoning, low-latency multimodal understanding, and agentic workflows. Four effort levels—low, medium, high, and xhigh—help balance quality, latency, and cost. The model is suited to production workloads that require both quality and efficiency. Compared with Gemini4 Carbon, it provides a small intelligence gain, faster response times, and improvements in agentic knowledge work, visual reasoning, and coding. Its output speed is110 output tokens per second, while tasks take21 minutes at xhigh effort. Gemini4 Neon uses about15 percent more output tokens per task than Gemini4 Carbon.
How is usage billed?
Your bill depends on the provider you use, its prices and your usage. Longer inputs or other conditions may have different prices.
What inputs does Gemini4 Neon support?
Gemini4 Neon supports multimodal input.
What effort levels are available?
It offers four effort levels: low, medium, high, and xhigh.
What tasks is Gemini4 Neon suited for?
It is suited for high-performance coding, multi-step reasoning, low-latency multimodal understanding, agentic workflows, and production workloads requiring quality and efficiency.
How does it differ from Gemini4 Carbon?
Gemini4 Neon provides a small intelligence gain, faster response times, and improvements in agentic knowledge work, visual reasoning, and coding. It uses about15 percent more output tokens per task.
Related models
Gemini 4 Hydrogen
Googlegemini-4-hydrogenGemini 4 Hydrogen is Google's fast, cost-efficient daily-driver model with a 1M-token context, multimodal input and four adjustable thinking levels.
Context
1.049M
Max output
943.718K
Input tokens
$1.5 / 1M tokens
Output tokens
$7.5 / 1M tokens
Input audio tokens
$1.5 / 1M tokens
Gemini 4 Hydrogen (batch)
Googlegemini-4-hydrogen:batchGemini 4 Hydrogen is Google's fast, high-efficiency core of the Gemini 4 family, replacing the Flash brand with four thinking levels and multimodal input.
Context
1.049M
Max output
943.718K
Input tokens
$0.75 / 1M tokens
Output tokens
$3.75 / 1M tokens
Input audio tokens
$0.75 / 1M tokens
Gemini 4 Carbon
Googlegemini-4-carbonGemini 4 Carbon is Google's strongest frontier model, built on Gemini 4 Argon for long-horizon agentic workflows, cybersecurity, scientific reasoning, and complex knowledge work.
Context
1.049M
Max output
943.718K
Input tokens
$4 / 1M tokens
Output tokens
$20 / 1M tokens
Input audio tokens
$4 / 1M tokens
Gemini 4 Carbon (batch)
Googlegemini-4-carbon:batchGemini 4 Carbon is Google's multimodal frontier model for long-horizon agentic work, with 1 million token context and adjustable reasoning effort.
Context
1.049M
Max output
943.718K
Input tokens
$2 / 1M tokens
Output tokens
$10 / 1M tokens
Input audio tokens
$2 / 1M tokens
Gemini 4 Argon
Googlegemini-4-argonGoogle's Gemini 4 Argon is a frontier model with a 1,048,576-token context window, multimodal input support, and top scores on 14 of 18 internal benchmarks.
Context
1.049M
Max output
943.718K
Input tokens
$4 / 1M tokens
Output tokens
$20 / 1M tokens
Input audio tokens
$4 / 1M tokens
Gemini 3.8 Flash
Googlegemini-3.8-flashGemini 3.8 Flash is Google's most intelligent Flash model, a reasoning model with 1,000,000-token context and multimodal input for long-horizon agents and enterprise workflows.
Context
1.049M
Max output
65.536K
Input tokens
$1.5 / 1M tokens
Output tokens
$7.5 / 1M tokens
Input audio tokens
$1.5 / 1M tokens