gemini-3-flash-preview
Vertex AI · chat model
gemini-3-flash-preview is listed here as a chat model from Vertex AI. This page shows simple API pricing, token limits, and capability flags so you can compare it with similar options.
Input
$0.5000 / 1M tokens
Output
$3.0000 / 1M tokens
Cached input
$0.0500 / 1M tokens
Context
65.5K
Quick read
Best for
Use this page when you need a fast view of cost, context size, and supported features before testing the model in your own workload.
Things to verify
Always check the provider page for discounts, cache pricing, region rules, and any model limits that may not appear in public metadata.
Pricing
| Item | Price |
|---|---|
| Input | $0.5000 / 1M tokens |
| Output | $3.0000 / 1M tokens |
| Cached input | $0.0500 / 1M tokens |
| Audio input | $1.0000 / 1M tokens |
| Embedding | $0.5000 / 1M tokens |
| Priority input | $0.9000 / 1M tokens |
| Priority output | $5.4000 / 1M tokens |
Token limits
Context window
65.5K
Max input tokens
1.0M
Max output tokens
65.5K
Max tokens
65.5K
Capabilities
| Capability | Supported |
|---|---|
| Vision | ✅ |
| Function calling | ✅ |
| Parallel function calling | — |
| Tool choice | ✅ |
| Prompt caching | ✅ |
| Reasoning | ✅ |
| Response schema | ✅ |
| System messages | ✅ |
| Audio input | ✅ |
| Audio output | — |
| Web search | ✅ |
| PDF input | ✅ |
| Video input | ✅ |
Benchmarks
Most benchmark rows are attached to the base model family rather than this provider route. Open benchmark explorer
Sources
| Source links | |
| Pricing data | LiteLLM model cost map |
| Synced at | 2026-05-28 |
Similar models
This list is ranked by overall similarity. Use filters to emphasize the lens that matters most for the replacement you are making.
Comparing from
| Model | Cost | Input shape | Features | Context | Why it is close |
|---|---|---|---|---|---|
| gemini-3-flash-preview Vertex AI | In $0.5000 / 1M tokens Out $3.0000 / 1M tokens | pdf
Output: text | VisionFunction callingTool choicePrompt caching | 65.5K | Current model Reference row |
| Model | Cost | Input shape | Features | Context | Why it is close |
|---|---|---|---|---|---|
| gemini-3-flash-preview Google | In $0.5000 / 1M tokens Out $3.0000 / 1M tokens | pdf audioimage
Output: text | VisionFunction callingTool choicePrompt caching | 65.5K | Partial I/O overlap Overall 68% |
| gemini-3-flash-preview vertex_ai-language-models | In $0.5000 / 1M tokens Out $3.0000 / 1M tokens | pdf audioimage
Output: text | VisionFunction callingTool choicePrompt caching | 65.5K | Partial I/O overlap Overall 68% |
| gemini-3-flash-preview OpenRouter | In $0.5000 / 1M tokens Out $3.0000 / 1M tokens | pdf audiofile
Output: text | VisionFunction callingTool choicePrompt caching | 65.5K | Partial I/O overlap Overall 68% |
| gemini-2.5-pro vertex_ai-language-models | In $1.2500 / 1M tokens Out $10.0000 / 1M tokens | pdf audioimage
Output: text | VisionFunction callingTool choicePrompt caching | 65.5K | Partial I/O overlap Overall 63% |
| gemini-2.5-pro Google | In $1.2500 / 1M tokens Out $10.0000 / 1M tokens | pdf audioimage
Output: text | VisionFunction callingTool choicePrompt caching | 65.5K | Partial I/O overlap Overall 63% |
| gemini-pro-latest Google | In $1.2500 / 1M tokens Out $10.0000 / 1M tokens | pdf
Output: text | VisionFunction callingTool choicePrompt caching | 65.5K | Exact I/O shape Overall 63% |
| gemini-pro-latest Google | In $1.2500 / 1M tokens Out $10.0000 / 1M tokens | pdf
Output: text | VisionFunction callingTool choicePrompt caching | 65.5K | Exact I/O shape Overall 63% |
| gemini-3-pro-preview Vertex AI | In $2.0000 / 1M tokens Out $12.0000 / 1M tokens | pdf
Output: text | VisionFunction callingTool choicePrompt caching | 65.5K | Same provider Overall 61% |
| gemini-3-pro-preview OpenRouter | In $2.0000 / 1M tokens Out $12.0000 / 1M tokens | pdf
Output: text | VisionFunction callingTool choicePrompt caching | 65.5K | Exact I/O shape Overall 61% |
| gemini-3-pro-preview vertex_ai-language-models | In $2.0000 / 1M tokens Out $12.0000 / 1M tokens | pdf audioimage
Output: text | VisionFunction callingTool choicePrompt caching | 65.5K | Partial I/O overlap Overall 61% |
| gemini-3.1-pro-preview Vertex AI | In $2.0000 / 1M tokens Out $12.0000 / 1M tokens | pdf url
Output: text | VisionFunction callingTool choicePrompt caching | 65.5K | Same provider Overall 59% |
| gemini-3.1-pro-preview-customtools Vertex AI | In $2.0000 / 1M tokens Out $12.0000 / 1M tokens | pdf url
Output: text | VisionFunction callingTool choicePrompt caching | 65.5K | Same provider Overall 59% |
| gemini-3.5-flash Vertex AI | In $1.5000 / 1M tokens Out $9.0000 / 1M tokens | pdf url
Output: text | VisionFunction callingTool choicePrompt caching | 65.5K | Same provider Overall 59% |
| kimi-k2.5 azure_ai | In $0.6000 / 1M tokens Out $3.0000 / 1M tokens | pdf imagetext
Output: text | VisionFunction callingTool choiceVideo input | 262.1K | Partial I/O overlap Overall 47% |
| moonshotai.kimi-k2.5 Bedrock | In $0.6000 / 1M tokens Out $3.0000 / 1M tokens | pdf imagetext
Output: text | VisionFunction callingTool choiceSystem messages | 262.1K | Partial I/O overlap Overall 47% |
| gpt-5.5 Azure | In $5.0000 / 1M tokens Out $30.0000 / 1M tokens | pdf
Output: text | VisionFunction callingTool choicePrompt caching | 128.0K | Exact I/O shape Overall 44% |
| gpt-5.5-2026-04-23 Azure | In $5.0000 / 1M tokens Out $30.0000 / 1M tokens | pdf
Output: text | VisionFunction callingTool choicePrompt caching | 128.0K | Exact I/O shape Overall 44% |
| gemini-3-flash-preview gmi | In $0.5000 / 1M tokens Out $3.0000 / 1M tokens | pdf
Output: unknown | VisionFunction calling | 65.5K | Partial I/O overlap Overall 40% |
| grok-4.20-reasoning Vertex AI | In $2.0000 / 1M tokens Out $6.0000 / 1M tokens | pdf
Output: unknown | VisionFunction callingTool choiceReasoning | 2.0M | Same provider Overall 22% |
| grok-4.20-non-reasoning Vertex AI | In $2.0000 / 1M tokens Out $6.0000 / 1M tokens | pdf
Output: unknown | VisionFunction callingTool choiceResponse schema | 2.0M | Same provider Overall 20% |
No models match this filter.