Gemma 3N instruction-tuned model (4B effective).
OffRail routes requests to the best providers that are able to handle your prompt size and parameters.
Gemma 3N instruction-tuned model (4B effective). You can access it through OffRail's OpenAI-compatible API with automatic provider routing, fallback, and cost analytics.
Pricing for Gemma 3n E4B IT on OffRail starts at $0.07 per million input tokens and $0.30 per million output tokens, depending on the provider. The pricing table above always reflects the current per-provider rates.
Gemma 3n E4B IT supports a context window of up to 1,000,000 tokens on its largest provider deployment.
Gemma 3n E4B IT is served by Google AI Studio through OffRail. Requests are automatically routed to the best available provider, with fallback when a provider has issues.
No. Gemma 3n E4B IT does not currently support tool calling or structured JSON outputs through OffRail.
Gemma 3n E4B IT was released on June 26, 2025.
Gemini 3.7 Flash
1,048,576 context$0.75 in / $3.75 out per 1M
Gemini 3.5 Flash Lite
1,048,576 context$0.30 in / $2.50 out per 1M
Gemini 3.6 Flash
1,048,576 context$0.75 in / $3.75 out per 1M
Gemini 3.1 Flash Lite Image
65,536 context$0.25 in / $1.50 out per 1M
Gemini 3.5 Flash
1,048,576 context$1.50 in / $9.00 out per 1M
Gemini 3.1 Flash Lite
1,048,576 context$0.25 in / $1.50 out per 1M