Gemini 4 Barium API pricing
Google's Gemini series — very long context windows and strong multimodal input.
google/gemini-4-bariumCall summary
Gemini 4 Barium API endpoints
One API key — this model is served on the endpoint below.
Production reliability
Privacy-safe aggregates from real Router One model calls, so you can assess stability and response latency before integrating.
Not enough production samples yet
This window needs at least 100 eligible requests across 5 independent principals. Metrics appear automatically after that threshold is met.
More Gemini models on Router One
14 other Gemini models on the same gateway and API key — each page lists endpoints, posted price, and context window.
Gemini 4 Barium at a glance
Gemini 4 Barium (model ID google/gemini-4-barium) is a Gemini-series text model on Router One. Posted rate: $0.60 in / $3.00 out per 1M tokens (was $2.00 in / $10.00 out). Router One subscriptions include Gemini 4 Barium in the Premium models allowance: Pro 300, Max 1,000, Ultra 5,000 requests per 30-day cycle. Usage beyond the allowance bills the wallet at posted rates. Context window: 1.05M tokens. Accepts text, image; returns text. Endpoint: POST /v1/chat/completions (OpenAI-compatible).
Gemini 4 Barium FAQ
How much does Gemini 4 Barium cost on Router One?
Gemini 4 Barium is billed per token on Router One: $0.60 in / $3.00 out per 1M tokens, pay as you go.
Is Gemini 4 Barium included in Router One subscriptions?
Router One subscriptions include Gemini 4 Barium in the Premium models allowance: Pro 300, Max 1,000, Ultra 5,000 requests per 30-day cycle. Usage beyond the allowance bills the wallet at posted rates.
Which endpoints serve Gemini 4 Barium?
Gemini 4 Barium is served on POST /v1/chat/completions (OpenAI-compatible). Any Router One API key works there.
What is Gemini 4 Barium's context window?
Gemini 4 Barium accepts up to 1.05M tokens of context per request on Router One.
Start using Gemini 4 Barium
Create an API key and call Gemini 4 Barium at $0.60 in / $3.00 out per 1M tokens on Router One — pay as you go, with per-request cost and latency visibility.