Skip to main content
Glama

gemini-2.0-flash-exp vs gemini-2.0-flash-thinking-exp-1219

Pricing, Performance & Features Comparison

Price unit:
Authorgoogle
Context Length1M
Reasoning
-
Providers1
ReleasedDec 2024
Knowledge CutoffAug 2024
License-

Gemini 2.0 Flash-Exp is an experimental low-latency model from Google Vertex AI that supports multimodal inputs and outputs, including real-time vision, audio streaming, and text-to-speech. It provides improved performance over earlier Gemini releases, offering features such as bounding box detection, native image generation, and complex function calling. The model excels at agentic tasks and is suitable for scenarios requiring fast responses and versatile tool use.

Input$0.00
Output$0.00
Latency (p50)-
Output Limit8K
Function Calling
-
JSON Mode
-
InputText, Image, Audio, Video
OutputText, Image, Audio
in$0.00out$0.00--
Authorgoogle
Context Length32K
Reasoning
-
Providers1
ReleasedDec 2024
Knowledge Cutoff-
LicenseCreative Commons Attribution 4.0 International

Gemini 2.0 Flash Thinking Mode is an experimental multimodal LLM that provides not only standard responses but also exposes its thought process, enhancing reasoning capabilities. It supports text and image inputs and outputs text-only responses, with a larger token context than previous Gemini versions.

Input$0.00
Output$0.00
Latency (p50)-
Output Limit8K
Function Calling
-
JSON Mode
-
InputText, Image
OutputText
in$0.00out$0.00--