Google / Gemini 2.0 Flash Lite
Google / Gemini 2.0 Flash Litetexttextimagetext
Input: $0.075 / Output: $0.30
Gemini 2.0 Flash Lite is a Multimodal LLM designed for cost-efficient, high-speed applications. It excels in real-time tasks and budget-friendly multimodal interactions, offering improved quality over Gemini 1.5 Flash while maintaining similar speed and cost.
Noteworthy features include:
- Multimodal input with text output (multimodal output in private preview)
- 1M token input context window and 8k token output window
- Public preview availability with a 60 queries-per-minute (QPM) rate limit
| Metric | Value |
|---|---|
| Parameter Count | Unknown |
| Mixture of Experts | No |
| Context Length | 1M tokens (input) |
| Multilingual | Yes |
| Quantized* | Unknown |
*Quantization details are provider-specific and not disclosed for this model.
Google models available on Oxen.ai
| Modality | Price (1M tokens) | ||||
|---|---|---|---|---|---|
| Model | Inference provider | Input | Output | Input | Output |
 Google | text | text | $0.08 | $0.30 | |
| Google | text | text | $0.04 | $0.15 | |
| Google | text | text | $1.25 | $5.00 | |
| Google | text, image | text | $0.10 | $0.40 | |
| Google | text, image | text | $0.08 | $0.30 | |
 Groq | text | text | $0.20 | $0.20 | |
| Google | text | embeddings | $0.02 | $0.02 | |