Try Bifrost Enterprise free for 14 days.
Request access
[ MODEL COMPARISON ]

Compare antigravity-preview-09-2026 with other models

Select another model to compare pricing, limits, and capabilities with antigravity-preview-09-2026.

Google Gemini logo
VS
Models
Google Gemini logoantigravity-preview-09-2026
gemini
-
-
Context Length
1049K
-
Max Output
66K
-
Input Cost
$0.75/M
-
Output Cost
$3.75/M
-
Mode
Responses
-
Max Input Tokens
1049K
-
Max Tokens
66K
-
Provider
Google Gemini
-
Response Schema
No
-
Prompt Caching
Yes
-
[ WE'RE OPEN SOURCE ]

Scale with the Fastest LLM Gateway

Built for enterprise-grade reliability, governance, and scale. Deploy in seconds.

Comparison Insights

Comprehensive analysis based on the latest model metadata from the comparison table above.

What should I know about antigravity-preview-09-2026?

Overview

  • antigravity-preview-09-2026 is a responses model provided by Google Gemini.
  • This model offers an exceptional context window of 1049K tokens, making it ideal for processing extensive documents, long conversations, or large codebases.

Pricing

  • Input processing costs $0.75 per million tokens.
  • Output generation costs $3.75 per million tokens.

Output Capabilities

  • The model can generate up to 66K tokens in a single response.
What capabilities does antigravity-preview-09-2026 support?
  • Supports function calling, enabling integration with external tools and APIs for extended functionality.
  • Includes vision capabilities to process and analyze images alongside text inputs.
  • Features advanced reasoning capabilities for complex problem-solving and multi-step logical tasks.
  • Provides web search integration for accessing real-time information and current data.
  • Implements prompt caching to reduce costs and latency for repeated or similar queries.

antigravity-preview-09-2026 Pricing Overview

At $0.75 per 1M input tokens and $3.75 per 1M output tokens, antigravity-preview-09-2026 ranks 40 out of 190 responses models by input cost. It is more affordable compared to the median of $2.00 for responses models, and is cheaper than 79% of models in this category.