Text
Build drafting, rewriting, extraction, classification, and conversational workflows.
All API models
LLMGoogleAvailable
MODEL API
Gemini 3.1 Pro Preview API
Google's frontier preview route for complex reasoning, software engineering, and multimodal analysis. It accepts text, images, and video through PixMind and is best reserved for difficult workflows that need Pro-tier depth and tool use.
- Text
- Vision
- Image input
- Video input
- Reasoning
- Tool calling
API usage is billed separately from Studio credits.
LIVE REQUEST BUILDER
Try the API in the playground
Configure a request, inspect the exact JSON, then run it with your account.
API key
Loading keys…
Multimodal inputsUp to 10 images, 10MB each · One video, up to 20MB
Response
The API response will appear here.
API PRICING
Programmatic pricing, separate from Studio
Compare the complete API billing table for this route. Token models separate input, output, cache-read, cache-write, and long-context rates; media models vary by configuration.
Per 1M tokens
Input1911~$2.02
Output11466~$12.10
Cache read254.8~$0.27
Credits and approximate USD per 1M tokens
The accepted task response is the source of truth for its final pricing snapshot.
CAPABILITIES
What this route supports
Use one stable PixMind model ID while keeping provider-specific setup out of your application.
Vision
Analyze supplied images together with written instructions.
Image input
Use Image input through the live Gemini 3.1 Pro Preview route without maintaining a separate provider integration.
Video input
Use Video input through the live Gemini 3.1 Pro Preview route without maintaining a separate provider integration.
Reasoning
Work through multi-step analysis where intermediate constraints matter.
Tool calling
Connect the model to approved functions and application actions.
Streaming
Return partial output as it is generated for responsive product experiences.
MODEL WORKFLOWS
What to build with Gemini 3.1 Pro Preview
Choose a task that matches the live route capabilities, then adapt one of these prompt starters.
Best-fit tasks
- Build drafting, rewriting, extraction, classification, and conversational workflows.
- Analyze supplied images together with written instructions.
- Work through multi-step analysis where intermediate constraints matter.
- Connect the model to approved functions and application actions.
Prompt starters
Replace the bracketsStarter
Analyze [problem]. List the constraints, test the strongest alternatives against [criteria], identify missing information, and return a concise recommendation with supporting evidence.
Starter
Inspect the supplied image for [task]. Separate direct observations from inferences, extract [required fields], and return the result as [format].
Starter
Complete [goal]. Use [available tools] only when needed, validate every tool result before continuing, and return [required final format].
Starter
Answer [user task] in a clear structure. Put the direct result first, keep each section self-contained, and avoid delaying essential information until the end.
MODEL SELECTION
Choose Gemini 3.1 Pro Preview when the job fits
Compare nearby live routes by task, supported capability, and current entry price before you lock a model ID into production.
| Model | Best for | Key capabilities | Entry price | Availability | Action |
|---|---|---|---|---|---|
Gemini 3.1 Pro Preview Google · current page | Build drafting, rewriting, extraction, classification, and conversational workflows. | Text · Vision · Image input | $2.02 / 1M tokens | Available | Selected |
Gemini 3.5 Flash Google | Build drafting, rewriting, extraction, classification, and conversational workflows. | Text · Vision · Image input | $1.43 / 1M tokens | Available | View route |
Gemini 3.5 Flash-Lite Google | Build drafting, rewriting, extraction, classification, and conversational workflows. | Text · Vision · Image input | $0.41 / 1M tokens | Available | View route |
Gemini 3.6 Flash Google | Build drafting, rewriting, extraction, classification, and conversational workflows. | Text · Vision · Image input | $1.01 / 1M tokens | Available | View route |
Capabilities and starting prices are a current PixMind route snapshot. The accepted request contains the final configuration and billing quote.
GET STARTED
From playground to production
Create a scoped key
Create an API key for the image or video permission this route needs.
Send the request
Use the model ID and endpoint shown above from your backend service.
Track the task
Store the returned task ID and query its status until it reaches a terminal state.
FAQ
Gemini 3.1 Pro Preview API questions
What model ID should I use for the Gemini 3.1 Pro Preview API?+
Use gemini-3.1-pro-preview in the model field. This is the stable PixMind route identifier shown in the playground request JSON.
Which endpoint does the Gemini 3.1 Pro Preview API use?+
Send POST requests to /v1/chat/completions. Keep your API key on your server and pass it as a Bearer token.
Is the playground using a real API request?+
Yes. When you click Run model, PixMind forwards the displayed payload with the API key you entered. A successful request may create a paid task.
Does PixMind save the API key entered here?+
No. The playground keeps the key only in component memory and sends it for the current request; it is not written to browser storage.
Is API pricing the same as PixMind Studio pricing?+
No. API usage resolves through the apiPlatform pricing role and a separate pay-as-you-go ledger. Studio pricing includes the creation interface and product workflow services.
Why can the final price differ from the starting price?+
The entry price reflects the configuration displayed on this page. Resolution, duration, quality, audio, references, and output count can affect the final task price.
How do I receive a finished image or video?+
Generation routes can return an asynchronous task. Save its ID and query the task endpoint until the status is succeeded, failed, or cancelled.
Can I use the same integration for other PixMind models?+
Yes. Models in the same workload family share the generation contract, so switching usually means changing the model ID and supported parameters.
RELATED MODELS
Compare other API routes
Google
Gemini 3.5 Flash
A high-efficiency Gemini model that brings strong coding, reasoning, and multimodal understanding to Flash-tier workloads. It fits responsive agents and parallel processing where throughput and capable visual analysis must stay balanced.
View APIGoogle
Gemini 3.5 Flash-Lite
Google's most cost-efficient Flash tier for focused, repeatable subtasks. Use it for high-volume chat, extraction, classification, and lightweight agents where a smaller price footprint matters more than maximum reasoning depth.
View APIGoogle
Gemini 3.6 Flash
A responsive multimodal route for coding, agent workflows, and polished web or application output. Choose it for production tasks that need stronger reasoning and visual context while retaining Flash-tier efficiency.
View APISTART WITH THE CONTROL PLANE
Turn your first Gemini 3.1 Pro Preview prompt into a real API request
Test the exact payload in the playground, then create a scoped key and move the same model ID into your application.