Gemini 4 Neon is a fast, mid-priced model in the Gemini 4 family from Google, built for coding and agentic work. It is suited for repository and terminal coding, web builds, multi-turn tool use and multimodal STEM problems, and is positioned as a step up from Gemini 4 Hydrogen that targets Gemini 4 Carbon quality at higher speed and lower cost. It supports long decode of up to 1M output tokens through continuation, and controls thinking depth with low, medium, high and xhigh reasoning effort.
Providers
Different companies host the same model. OpenRouter routes your request to one of them based on the routing mode you pick: Balanced (price + speed), Nitro (fastest), or Floor (cheapest).
| $3.00 | $15.00 | $0.150 | $0.150 | 1.97s | 101 tok/s | ||
| $3.00 | $15.00 | $0.150 | $0.150 | 3.53s | 31 tok/s | ||
Not used in Standard routing:Why these endpoints are not used | |||||||
Flex | $1.50 | $7.50 | $0.075 | $0.075 | 4.41s | 111 tok/s | |
| $3.30 | $16.50 | $0.165 | $0.165 | 1.46s | 46 tok/s | ||
| $3.30 | $16.50 | $0.165 | $0.165 | 1.66s | 45 tok/s | ||
Priority | $5.40 | $27.00 | $0.270 | $0.270 | 1.67s | 50 tok/s | |
Priority | $5.40 | $27.00 | $0.270 | $0.270 | 2.38s | -- | |
- Input $3.00 / Output $15.00101 tok/s94.44% uptime
- Input $3.00 / Output $15.0031 tok/s97.29% uptime
- Not used in Standard routing:Why these endpoints are not used
- Input $1.50 / Output $7.50111 tok/s100.00% uptimeFlex
- Input $3.30 / Output $16.5046 tok/s100.00% uptime
- Input $3.30 / Output $16.5045 tok/s100.00% uptime
- Input $5.40 / Output $27.0050 tok/s-- uptimePriority
- Input $5.40 / Output $27.00-- tok/s-- uptimePriority
Pricing
The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.
Weighted average
Gemini 4 Neon — Price history
| $0.760 | $15.00 | 78.6% | 94.4% | ||
| $1.829 | $15.00 | 41.1% | 2.0% | ||
Not used in Standard routing:Why these endpoints are not used | |||||
Flex | $0.952 | $7.50 | 38.4% | 2.2% | |
| $3.111 | $16.50 | 6.0% | 0.7% | ||
| $3.299 | $16.50 | 0.0% | 0.7% | ||
Priority | $5.386 | $27.00 | 0.0% | 0.0% | |
Priority | $5.395 | $27.00 | 0.0% | 0.0% | |
- Effective in $0.760 / Effective out $15.00Token share94.4%
- Effective in $1.829 / Effective out $15.00Token share2.0%
- Not used in Standard routing:Why these endpoints are not used
- Effective in $0.952 / Effective out $7.50FlexToken share2.2%
- Effective in $3.111 / Effective out $16.50Token share0.7%
- Effective in $3.299 / Effective out $16.50Token share0.7%
- Effective in $5.386 / Effective out $27.00PriorityToken share0.0%
- Effective in $5.395 / Effective out $27.00PriorityToken share0.0%
Performance
Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).
P50, best across providers
P50, best provider
Uptime
Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.
Availability over the last 3 days
Last 72 hoursAvailability over the last 24 hours
When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and provider routing options.
Apps
Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.
Activity
Token volume and request traffic to this model over time.
API
Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.
Available through EU in-region routing
Google: Gemini 4 Neon is available through EU in-region routing. Requests sent to eu.openrouter.ai are decrypted in the EU and routed only to shared provider endpoints in Europe (the EU/EEA, the UK, and Switzerland).
- Providers in Europe
- Google Vertex
- Prices in Europe
- Google Vertex: $3.30/M tokens input, $16.50/M tokens output
- Base URL
https://eu.openrouter.ai/api/v1- Plan
- Requires Business or Enterprise. Self-serve on Business: no contract, no monthly minimum. OpenRouter Business for EU in-region routing
Fails closed: if no shared provider endpoint in Europe is available, the request errors instead of leaving the region. Requests served by your own BYOK key go to your deployment’s region, which you control. In-region routing docs
Frequently asked questions
Gemini 4 Neon is a fast, mid-priced model in the Gemini 4 family from Google, built for coding and agentic work. It is suited for repository and terminal coding, web builds, multi-turn tool use and multimodal STEM problems, and is positioned as a step up from Gemini 4 Hydrogen that targets Gemini 4 Carbon quality at higher speed and lower cost.
Gemini 4 Neon costs $3.00/M input tokens and $15.00/M output tokens, with separate rates for Cache Read at $0.15/M tokens, Cache Write at $0.08333/M tokens, Image Input at $3.00/M tokens, Input Audio at $3.00/M tokens, Input Audio Cache at $0.15/M tokens, and Web Search at $14.00/1K calls.
Gemini 4 Neon has a 1,048,576 token context window. It supports up to 65,536 completion tokens.
Yes. Gemini 4 Neon accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.
Gemini 4 Neon accepts audio, files such as PDFs, images, text, and video as input and returns text.
Gemini 4 Neon is served by 2 providers on OpenRouter: Google AI Studio and Google Vertex. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.
Gemini 4 Neon was released on November 18, 2026.