Gemini pricing - 2026
Gemini API starts at $0.0750/1M input tokens. Prices effective since May 23, 2026.
Prices effective since May 23, 2026. Verified May 27, 2026. Confirm at LiteLLM before billing.
Cost calculator
Estimated monthly cost · 70% input / 30% output split
+24 more models not shown
Price history
Input price per 1M tokens - tracked from Apr 5, 2026
Prices scraped daily from official provider documentation. Chart shows input token pricing.
Gemini usage limits by plan
| Messages Per Day | limited messages | No published fixed limit |
| File Upload Mb | 2048 MB | 2GB per file |
| Context Window | 1000000 tokens | Gemini 1.5 Pro context |
| Image Generation Per Day | Not available | Not available on Free |
| File Upload Size | 2048 MB | Per file |
| Gems Custom Ai | Not available | Not available on Free |
| Messages Per Day | Unlimited | No published cap |
| File Upload Mb | 2048 MB | 2GB per file |
| Gems | Unlimited | Custom Gems available |
| Context Window | 1000000 tokens | Gemini 1.5 Pro context |
| File Upload Size | 2048 MB | Per file |
| Gems Custom Ai | Included | Create custom Gems |
| Image Generation Per Day | Unlimited | Imagen 3 included |
Gemini features and capabilities
Generation
| Image generation | ✓ Yes | Imagen 3 integration in Gemini Advanced | Advanced |
| Voice mode | ✓ Yes | Live voice conversation mode on mobile |
Input & Context
| Image input (vision) | ✓ Yes | Native multimodal — all plans | |
| Video understanding | ✓ Yes | Upload videos or link YouTube. Up to 1 hour | |
| Audio transcription | ✓ Yes | Upload audio files for transcription and analysis | |
| File upload (PDF, docs) | ✓ Yes | Large file support including Google Drive integration |
Integrations & API
| API access | ✓ Yes | Google AI Studio and Vertex AI | |
| Web browsing | ✓ Yes | Google Search integration, real-time results | |
| Code execution | ✓ Yes | Python execution via code blocks | |
| Extensions / integrations | ✓ Yes | Google Workspace, YouTube, Maps extensions |
Languages
| Arabic language support | ✓ Yes | Full Arabic support | |
| Urdu language support | ✓ Yes | Full Urdu support |
Memory
| Persistent memory | ✓ Yes | Gems system for persistent context | Advanced |
| Custom instructions | ✓ Yes | Gems — custom AI personas | Advanced |
Privacy & Security
| Opt out of training data | ✓ Yes | Workspace accounts excluded by default | |
| Offline mode | ✕ No |
Related pages
About Gemini API pricing
Gemini API pricing is set by Google and billed per million tokens processed. Input tokens (your prompt) and output tokens (the response) are priced separately. Cached input pricing applies when the same context is reused across requests, offering significant savings for repeated prompts.
Prices on this page are sourced from official Google documentation and updated when Gemini announces pricing changes. Check the official Gemini pricing page for the most current rates.
Weekly AI pricing & uptime digest
Price drops, new model releases, and incident summaries - every Monday. Free.