About this model
Fast high-throughput Gemini model for low-latency agentic and document-heavy workloads. Gemini 3.5 Flash-Lite is a lightweight multimodal model in Google's Gemini 3.5 family, built for high-throughput and latency-sensitive production workloads.
Pricing
| Rate | RODI | USD (ref.) | Unit |
|---|---|---|---|
| Text tokens | |||
| In | 227.3 | ~ 0.300 | per 1M tokens (RODI/M, USD/M) |
| Out | 1893.8 | ~ 2.50 | per 1M tokens (RODI/M, USD/M) |
| Prompt caching | |||
| Cached | 22.8 | ~ 0.0300 | per 1M tokens (RODI/M, USD/M) |
RODI prices include RodiumAi markup and upstream fees. USD figures are wholesale reference rates.
Providers & pricing
| Provider | Input | Output | Cached | Free tier | Status |
|---|---|---|---|---|---|
 Runware Default All rates (3)
| 227.3 | 1,894 | 22.8 | - | No data |
Capabilities
Streaming
Tool calling
Vision
JSON mode
Reasoning
API usage
Use the canonical slug with client.chat() or chat.completions.create().
Examples
…Example response
…RodiumAi SDK
Official Python, JavaScript, and Laravel SDKs: flat API aligned with this model slug.
…Use cases
- Long-document and multimodal assistants: PDFs, screenshots and photos in the same prompt.
- Fast, low-cost classification and extraction with the Flash and Flash-Lite tiers.
- Multilingual support and translation, including French and African languages.
- Agents that call tools and read images.
Notes
- Gemini models answer on
POST https://api.rodiumai.io/v1/chat/completions(OpenAI format), served from Google Vertex AI or the Gemini API. reasoning_effortis forwarded to Gemini. Gemini 3 models already think by default, so you rarely need to set it.- Images go in
image_urlparts, as base64 data URLs orhttps://links. Video parts are also accepted asvideo/*data URLs on models with video input. - OpenAI-only fields such as
n,seedorlogit_biasare ignored.