G

Google Gemini 2.0 Flash Experimental (Free)

Google
Vision
1M
Context
Free
Input /1M
Free
Output /1M
8K
Max Output

Google Gemini 2.0 Flash Experimental (Free)

Source: LangMart Last Updated: 2024-12-23

Description

Gemini Flash 2.0 offers a significantly faster time to first token (TTFT) compared to Gemini Flash 1.5, while maintaining quality on par with larger models like Gemini Pro 1.5. It introduces notable enhancements in:

  • Multimodal understanding
  • Coding capabilities
  • Complex instruction following
  • Function calling

Technical Specifications

Context & Token Limits

Specification Value
Context Window 1,048,576 tokens
Context Length 1,048,576 tokens (1M)
Max Completion Tokens 8,192 tokens

Supported Modalities

Direction Modalities
Input Text, Image
Output Text

Supported Parameters

Parameter Supported
max_tokens Yes
temperature Yes
top_p Yes
top_k Not specified
seed Yes
response_format Yes
stop Yes
tools Yes
tool_choice Yes

Tool/Function Calling

The model supports tool and function calling with the following tool choice options:

  • literal_none - Disable tool use
  • literal_auto - Model decides when to use tools
  • literal_required - Force tool use
  • type_function - Specify function to call

Features

Feature Status
Multipart/Image Input Supported
Tool/Function Calling Supported
Reasoning Capabilities Not supported

Pricing

Type Price
Input Tokens $0/M (Free)
Output Tokens $0/M (Free)

This is a completely free tier model.

API Usage Example

curl https://api.langmart.ai/v1/chat/completions \
  -H "Authorization: Bearer $LANGMART_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemini-2.0-flash-exp:free",
    "messages": [
      {
        "role": "user",
        "content": "Hello, how are you?"
      }
    ],
    "max_tokens": 1024,
    "temperature": 0.7
  }'

With Image Input

curl https://api.langmart.ai/v1/chat/completions \
  -H "Authorization: Bearer $LANGMART_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemini-2.0-flash-exp:free",
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "type": "text",
            "text": "What is in this image?"
          },
          {
            "type": "image_url",
            "image_url": {
              "url": "https://example.com/image.jpg"
            }
          }
        ]
      }
    ]
  }'

With Tool Calling

curl https://api.langmart.ai/v1/chat/completions \
  -H "Authorization: Bearer $LANGMART_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemini-2.0-flash-exp:free",
    "messages": [
      {
        "role": "user",
        "content": "What is the weather in San Francisco?"
      }
    ],
    "tools": [
      {
        "type": "function",
        "function": {
          "name": "get_weather",
          "description": "Get the current weather in a location",
          "parameters": {
            "type": "object",
            "properties": {
              "location": {
                "type": "string",
                "description": "The city and state, e.g. San Francisco, CA"
              }
            },
            "required": ["location"]
          }
        }
      }
    ],
    "tool_choice": "auto"
  }'
Model Relationship
google/gemini-flash-1.5 Predecessor (Flash 2.0 is faster)
google/gemini-pro-1.5 Larger model (Flash 2.0 matches quality)

Model Identification

Field Value
Display Name Google: Gemini 2.0 Flash Experimental (free)
Model ID google/gemini-2.0-flash-exp:free
Provider Google Vertex
Model Family Gemini
Variant Type Free tier
Created December 11, 2024
Status Experimental

Performance Metrics

  • Time to First Token (TTFT): Significantly faster than Gemini Flash 1.5
  • Quality: On par with larger models like Gemini Pro 1.5

Usage Statistics (Recent)

Metric Value
Daily Requests ~24,000-27,000
Daily Image Prompts ~5,800-11,400
Data Retention 55 days

Provider Information

Field Value
Provider Google Vertex
Headquarters United States
Adapter GoogleVertexGeminiAdapter
Status Page https://status.cloud.google.com/products/sdXM79fz1FS6ekNpu37K/history
Terms https://cloud.google.com/terms/

Data Policy

Policy Value
Training on User Data Allowed (by Google)
Retains Prompts Yes (55 days)
Can Publish User Data No
Requires User IDs Yes
Governed By Google Cloud Terms

Notes

  • This model is marked as experimental and may have changes or limitations
  • Free tier may have rate limits (check LangMart documentation)
  • The model retains prompts for 55 days per Google's data policy
  • User IDs are required for API access