Gemini 2.0 Models by Google DeepMind
Last refreshed 2026-10-17. Next refresh: weekly.
Details
Capabilities
Links
WebsiteAbout
Gemini 2.0 is Google DeepMind’s next Gemini generation, built for agent-style use with stronger multimodality and native tool use. The first public line was Gemini 2.0 Flash, a low-latency workhorse that takes multimodal inputs (images, video, audio) and, in developer previews, can also produce image and speech output and call tools such as Google Search, code execution, and third-party functions. Google later expanded the family for developers with generally available 2.0 Flash, cost-oriented Flash-Lite, experimental Pro for coding and complex prompts, and a Flash Thinking experimental reasoning variant, with a 1M-token context window called out on Flash.
Decision facts
- Best fit
- realtime voiceimagevision and multimodal work
- Capability starting point
- Gemini 2.0 Flash with 2M context and reasoning, JSON / Tool use, structured outputs, and multimodal inputs
- Lowest tracked input
- Gemini 2.0 Flash-Lite · $0.075/1M · Google AI Studio
- Closest related family
- DiffusionGemma
Archived Variants
Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.
Keep only for existing workloads; choose a current variant for new builds.
Keep only for existing workloads; choose a current variant for new builds.
Keep for legacy integrations; evaluate Gemini 3.5 Flash-Lite before new work.
Keep for legacy integrations; evaluate Gemini 3.5 Flash-Lite before new work.
Keep only for existing workloads; choose a current variant for new builds.
Keep only for existing workloads; choose a current variant for new builds.
Keep for legacy integrations; evaluate Gemini 3.8 Flash before new work.
Keep only for existing workloads; choose a current variant for new builds.
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| Gemini 2.0 Flash Live API | Keep only for existing workloads; choose a current variant for new builds. | 2025-03 | realtime voice1M contextJSON / Tool use | Archived |
| Gemini 2.0 Flash Image Generation | Keep only for existing workloads; choose a current variant for new builds. | 2025-02 | image1M contextJSON / Tool use | Archived |
| Gemini 2.0 Flash-Lite | Keep for legacy integrations; evaluate Gemini 3.5 Flash-Lite before new work. | 2025-02 | 1M contextJSON / Tool usestructured outputs | Replaced |
| Gemini 2.0 Flash Lite | Keep for legacy integrations; evaluate Gemini 3.5 Flash-Lite before new work. | 2025-02 | 1M contextstructured outputsmultimodal inputs | Replaced |
| Gemini 2.0 Flash-Lite (Preview 02-05) | Keep only for existing workloads; choose a current variant for new builds. | 2025-02 | 1M contextmultimodal inputs | Archived |
| Gemini 2.0 Pro (Experimental 02-05) | Keep only for existing workloads; choose a current variant for new builds. | 2025-02 | 1M contextstructured outputsmultimodal inputs | Archived |
| Gemini 2.0 Flash | Keep for legacy integrations; evaluate Gemini 3.8 Flash before new work. | 2025-01 | vision2M contextreasoning | Replaced |
| Gemini 2.0 Flash Experimental | Keep only for existing workloads; choose a current variant for new builds. | 2024-12 | 1M context | Archived |
Release Timeline
4 release groupsReplaced By
Keep for legacy integrations; evaluate Gemini 3.5 Flash-Lite before new work.
Keep for legacy integrations; evaluate Gemini 3.5 Flash-Lite before new work.
Keep for legacy integrations; evaluate Gemini 3.8 Flash before new work.
Specifications(8 models)
| Model | Released | Context | Vision | Multimodal | Reasoning | JSON / Tool use | Structured Outputs | Code Exec |
|---|---|---|---|---|---|---|---|---|
| Gemini 2.0 Flash Live API | 2025-03 | 1M | Yes | Yes | No | Yes | Yes | No |
| Gemini 2.0 Flash Image Generation | 2025-02 | 1.048576M | Yes | Yes | No | Yes | No | No |
| Gemini 2.0 Flash-Lite | 2025-02 | 1.048576M | Yes | Yes | No | Yes | Yes | No |
| Gemini 2.0 Flash Lite | 2025-02 | 1M | Yes | Yes | No | No | Yes | No |
| Gemini 2.0 Flash-Lite (Preview 02-05) | 2025-02 | 1M | Yes | Yes | No | No | No | No |
| Gemini 2.0 Pro (Experimental 02-05) | 2025-02 | 1M | Yes | Yes | No | No | Yes | No |
| Gemini 2.0 Flash | 2025-01 | 2M | Yes | Yes | Yes | Yes | Yes | Yes |
| Gemini 2.0 Flash Experimental | 2024-12 | 1M | No | No | No | No | No | No |
Available From(4 providers)
Pricing
| Model | Provider | Input / 1M | Output / 1M | Type |
|---|---|---|---|---|
| Gemini 2.0 Flash-Lite | Google AI Studio | $0.075 | $0.3 | Serverless |
| Gemini 2.0 Flash-Lite | GCP Vertex AI | $0.075 | $0.3 | Serverless |
| Gemini 2.0 Flash Lite | OpenRouter | $0.075 | $0.3 | Serverless |
| Gemini 2.0 Flash-Lite | Vercel AI Gateway | $0.075 | $0.3 | Serverless |
| Gemini 2.0 Flash | OpenRouter | $0.1 | $0.4 | Serverless |
| Gemini 2.0 Flash | Google AI Studio | $0.1 | $0.4 | Serverless |
| Gemini 2.0 Flash | GCP Vertex AI | $0.15 | $0.6 | Serverless |
| Gemini 2.0 Flash Image Generation | GCP Vertex AI | $0.15 | $30 | Serverless |
| Gemini 2.0 Flash | Vercel AI Gateway | $0.15 | $0.6 | Serverless |
| Gemini 2.0 Flash Live API | GCP Vertex AI | $0.5 | — | Serverless |
Popular comparisons in this family
- Gemini 2.0 Flash Live API vs GPT-4o Search Preview30
- Gemini 2.0 Flash vs GPT-4o-mini Search Preview28
- Gemini 2.0 Flash Experimental vs GPT-4o-mini Search Preview25
- Gemini 2.0 Flash vs GPT-4o Search Preview11
- Gemini 2.0 Flash Lite vs GPT-4o Search Preview2
- Gemini 2.0 Flash Experimental vs GPT-4o Mini (07-18)1
- Gemini 2.0 Flash vs GPT-4o Mini (07-18)1
Models(8)
Gemini 2.0 Flash Live API
Gemini 2.0 Flash Image Generation
Gemini 2.0 Flash-Lite
Gemini 2.0 Flash Lite
Gemini 2.0 Flash-Lite (Preview 02-05)
Gemini 2.0 Pro (Experimental 02-05)
Gemini 2.0 Flash
Gemini 2.0 Flash Experimental