Balanced Agent Work
Gemini 3.8 Flash$1.50/M input · $7.50/M output
Google / Model Developer
Google AI Models on SandBase
Explore Gemini for language, Nano Banana for images, Veo for video, and listed speech and music tools. Compare task variants, context and snapshot pricing to choose a Google capability for your workflow.
LanguageImageVideoAudio
50model & capability records
17 / 8 / 21 / 4language · image · video · audio
17 Sync33 async records
Catalog snapshot · Oct 10, 2026 · Task variants, not 50 independent foundation models.
Start With the Task
Choose a Google Model
High-Volume Text on a Budget
Gemini 2.5 Flash Lite$0.10/M input · $0.40/M output
Advanced Reasoning
Gemini 3.1 Pro Preview$2/M input · $12/M output
Image Generation & Editing
Nano Banana 2From $0.067/request
Cinematic Video
Veo 3.1From $3.20/request · Lite from $0.40
Speech & Music
Gemini TTS / LyriaTTS from $0.03/request · Lyria from $0.10
Catalog snapshot · Oct 10, 2026. Recommendations are task-oriented starting points, not performance rankings. Base media prices vary with request inputs; confirm live pricing and schema.
Explore the Catalog
Google Models & Capabilities
Model IDs, task variants, and pricing units.
All in one place.
50 model & capability recordsCatalog snapshot · Oct 10, 2026
Token prices are per million input/output tokens; request prices are base prices. Context is shown only when meaningful. Confirm pricing, availability, and request fields on the live model page.
Google / Gemini
Gemini
Language, multimodal understanding, reasoning, and tool use.
Tasks: chat, multimodal reasoning, coding, Agents, and function calling.
Availablesync
Gemini 3.8 Flash
google/gemini-3.8-flashchatvisionaudio inputreasoningstructured outputfunction calling
1,048,576 context tokens
$1.5 /M input$7.5 /M output
Availablesync
Gemini 3.7 Flash
google/gemini-3.7-flashchatvisionaudio inputreasoningstructured outputfunction calling
1,048,576 context tokens
$1.5 /M input$7.5 /M output
Availablesync
Gemini 3.6 Flash
google/gemini-3.6-flashchatvisionaudio inputreasoningstructured outputfunction calling
1,048,576 context tokens
$0.75 /M input$3.75 /M output
Availablesync
Gemini 3.5 Flash Lite
google/gemini-3.5-flash-litechatvisionaudio inputreasoningstructured outputfunction calling
1,048,576 context tokens
$0.3 /M input$2.5 /M output
Availablesync
Gemini 3.5 Flash
google/gemini-3.5-flashchatvisionaudio inputreasoningstructured outputfunction calling
1,048,576 context tokens
$1.5 /M input$9 /M output
Availablesync
Gemini 3.1 Flash Lite Preview
google/gemini-3.1-flash-lite-previewchatvisionaudio inputreasoningstructured outputfunction calling
1,048,576 context tokens
$0.25 /M input$1.5 /M output
Availablesync
Gemini 3.1 Pro Preview Custom Tools
google/gemini-3.1-pro-preview-customtoolschatvisionaudio inputreasoningstructured outputfunction calling
1,048,576 context tokens
$2 /M input$12 /M output
Availablesync
Gemini 3.1 Pro Preview
google/gemini-3.1-pro-previewchatvisionaudio inputreasoningstructured outputfunction calling
1,048,576 context tokens
$2 /M input$12 /M output
Availablesync
Gemini 2.5 Flash Lite
google/gemini-2.5-flash-litechatvisionaudio inputreasoningstructured outputfunction calling
1,048,576 context tokens
$0.1 /M input$0.4 /M output
Availablesync
Gemini 3 Flash Preview
google/gemini-3-flash-previewchatvisionaudio inputreasoningstructured outputfunction calling
1,048,576 context tokens
$0.5 /M input$3 /M output
Availablesync
Gemini 2.5 Flash
google/gemini-2.5-flashchatvisionaudio inputreasoningstructured outputfunction calling
1,048,576 context tokens
$0.3 /M input$2.5 /M output
Availablesync
Gemini 2.5 Pro
google/gemini-2.5-prochatvisionaudio inputreasoningstructured outputfunction calling
1,048,576 context tokens
$1.25 /M input$10 /M output
Availablesync
Gemini 3.1 Flash Lite
google/gemini-3.1-flash-litechatvisionaudio inputreasoningstructured outputfunction calling
1,048,576 context tokens
$0.25 /M input$1.5 /M output
Availablesync
Nano Banana 2 (Gemini 3.1 Flash Image)
google/gemini-3.1-flash-imagechatvisionreasoningimage output
131,072 context tokens
$0.5 /M input$3 /M output
Availablesync
Nano Banana Pro (Gemini 3 Pro Image)
google/gemini-3-pro-imagechatvisionreasoningimage output
65,536 context tokens
$2 /M input$12 /M output
Coming Soonsync
Gemini 4 Argon
google/gemini-4-argonchatvisionreasoning
Pricing not announced
Google / Nano Banana
Nano Banana
Generate images and edit visual inputs.
Tasks: text-to-image, image editing, and reference-led visual creation.
Availableasync
Nano Banana 2 Lite Text to Image
google/nano-banana-2-litetext-to-image
From $0.0336/request
Final cost can vary by duration, resolution, quality, or inputs.
Availableasync
Nano Banana 2 Lite Edit
google/nano-banana-2-lite/editimage-to-image
From $0.0336/request
Final cost can vary by duration, resolution, quality, or inputs.
Availableasync
Nano Banana 2 Text to Image
google/nano-banana-2text-to-imagecommercial
From $0.067/request
Final cost can vary by duration, resolution, quality, or inputs.
Availableasync
Nano Banana 2 Edit
google/nano-banana-2/editimage-to-imagecommercial
From $0.067/request
Final cost can vary by duration, resolution, quality, or inputs.
Availableasync
Nano Banana Pro Text to Image
google/nano-banana-protext-to-imagecommercial
From $0.134/request
Final cost can vary by duration, resolution, quality, or inputs.
Availableasync
Nano Banana Pro Edit
google/nano-banana-pro/editimage-to-imagecommercial
From $0.1351/request
Final cost can vary by duration, resolution, quality, or inputs.
Availableasync
Nano Banana 2.1 Edit
google/nano-banana-2.1/editimage-to-imagecommercial
From $0.042/request
Final cost can vary by duration, resolution, quality, or inputs.
Availableasync
Nano Banana 2.1 Text to Image
google/nano-banana-2.1text-to-imagecommercial
From $0.04/request
Final cost can vary by duration, resolution, quality, or inputs.
Availablesync
Nano Banana 2.1 (Gemini Nano Banana 2.1)
google/gemini-nano-banana-2.1chatvisionreasoningimage output
65,536 context tokens
$1.5 /M input$7.5 /M output
Google / Veo and Gemini Omni
Veo and Gemini Omni
Create, extend, edit, and transform video from text, images, and references.
Tasks: cinematic generation, reference-to-video, video extension, and transformation.
Availableasync
Gemini Omni Flash 1.1 Text to Video
google/gemini-omni-flash/1.1/text-to-videotext-to-video
From $0.8/request
Final cost can vary by duration, resolution, quality, or inputs.
Availableasync
Gemini Omni Flash 1.1 Image to Video
google/gemini-omni-flash/1.1/image-to-videoimage-to-video
From $0.8/request
Final cost can vary by duration, resolution, quality, or inputs.
Availableasync
Gemini Omni Flash 1.1 Edit
google/gemini-omni-flash/1.1/editvideo-to-video
From $1.12/request
Final cost can vary by duration, resolution, quality, or inputs.
Availableasync
Gemini Omni Flash 1.1 Reference to Video
google/gemini-omni-flash/1.1/reference-to-videoreference-to-video
From $0.8/request
Final cost can vary by duration, resolution, quality, or inputs.
Availableasync
Gemini Omni Flash Text to Video
google/gemini-omni-flash/text-to-videotext-to-video
From $1.04/request
Final cost can vary by duration, resolution, quality, or inputs.
Availableasync
Gemini Omni Flash Image to Video
google/gemini-omni-flash/image-to-videoimage-to-video
From $1.04/request
Final cost can vary by duration, resolution, quality, or inputs.
Availableasync
Gemini Omni Flash Edit
google/gemini-omni-flash/editvideo-to-video
From $1.2/request
Final cost can vary by duration, resolution, quality, or inputs.
Availableasync
Gemini Omni Flash Reference to Video
google/gemini-omni-flash/reference-to-videoreference-to-video
From $1.04/request
Final cost can vary by duration, resolution, quality, or inputs.
Availableasync
Veo 3.1 Text to Video
google/veo3.1/text-to-videotext-to-video
From $3.2/request
Final cost can vary by duration, resolution, quality, or inputs.
Availableasync
Veo 3.1 Fast Text to Video
google/veo3.1/fast/text-to-videotext-to-video
From $0.8/request
Final cost can vary by duration, resolution, quality, or inputs.
Availableasync
Veo 3.1 Lite Text to Video
google/veo3.1/lite/text-to-videotext-to-video
From $0.4/request
Final cost can vary by duration, resolution, quality, or inputs.
Availableasync
Veo 3.1 Fast Image to Video
google/veo3.1/fast/image-to-videoimage-to-video
From $0.8/request
Final cost can vary by duration, resolution, quality, or inputs.
Availableasync
Veo 3.1 Image to Video
google/veo3.1/image-to-videoimage-to-video
From $3.2/request
Final cost can vary by duration, resolution, quality, or inputs.
Availableasync
Veo 3.1 Lite Image to Video
google/veo3.1/lite/image-to-videoimage-to-video
From $0.4/request
Final cost can vary by duration, resolution, quality, or inputs.
Availableasync
Veo 3.1 Reference to Video
google/veo3.1/reference-to-videoreference-to-video
From $3.2/request
Final cost can vary by duration, resolution, quality, or inputs.
Availableasync
Veo 3.1 Fast Reference to Video
google/veo3.1/fast/reference-to-videoreference-to-video
From $0.8/request
Final cost can vary by duration, resolution, quality, or inputs.
Availableasync
Veo 3.1 First-Last Frame to Video
google/veo3.1/first-last-frame-to-videoimage-to-video
From $3.2/request
Final cost can vary by duration, resolution, quality, or inputs.
Availableasync
Veo 3.1 Fast First-Last Frame to Video
google/veo3.1/fast/first-last-frame-to-videoimage-to-video
From $0.8/request
Final cost can vary by duration, resolution, quality, or inputs.
Availableasync
Veo 3.1 Lite First-Last Frame to Video
google/veo3.1/lite/first-last-frame-to-videoimage-to-video
From $0.4/request
Final cost can vary by duration, resolution, quality, or inputs.
Availableasync
Veo 3.1 Video Extend
google/veo3.1/video-extendvideo-to-video
From $2.8/request
Final cost can vary by duration, resolution, quality, or inputs.
Availableasync
Veo 3.1 Fast Video Extend
google/veo3.1/fast/video-extendvideo-to-video
From $0.7/request
Final cost can vary by duration, resolution, quality, or inputs.
Google / Audio
Audio (Gemini TTS and Lyria)
Turn text into speech with Gemini TTS and generate music with Lyria.
Tasks: Gemini text-to-speech and Lyria music generation.
Availableasync
Gemini 3.1 Flash TTS
google/gemini-3.1-flash-ttstext-to-speech
From $0.15/request
Final cost can vary by duration, resolution, quality, or inputs.
Availableasync
Lyria 3.5
google/lyria-3.5text-to-music
From $0.1/request
Final cost can vary by duration, resolution, quality, or inputs.
Availableasync
Gemini 3.8 Flash TTS
google/gemini-3.8-flash-ttstext-to-speech
From $0.045/request
Final cost can vary by duration, resolution, quality, or inputs.
Availableasync
Gemini 3.8 Flash Lite TTS
google/gemini-3.8-flash-lite-ttstext-to-speech
From $0.03/request
Final cost can vary by duration, resolution, quality, or inputs.
One SandBase API Key
Connect Your Chosen Model
Open the model page or Playground for its current request URL, authentication requirements, and schema. This example shows the concept—not an executable API contract.
# Conceptual unified-key flow — not a verified request contract
export SANDBASE_API_KEY="YOUR_SANDBASE_API_KEY"
curl "<REQUEST_URL_FROM_LIVE_MODEL_PAGE>" \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
-H "Content-Type: application/json" \
--data '<PAYLOAD_FROM_LIVE_MODEL_SCHEMA>'Models Are a Choice, Not a Lock-In
Use Google Models in an Agent Workflow
- 01Task
- 02Model (Swappable)
- 03Skills / Tools / APIs
- 04Result
Keep your model selection separate from the Agent. Check tool support and schema compatibility when swapping models.
Keep Exploring
More Model Developers
45 models & variantsOpenAI
Language and reasoning models, alongside image and video generation.
LanguageImageAudioEmbedding
GPT · Sora
16 models & variantsAnthropic
Claude language models for reasoning, writing, and coding.
Language
Claude
20 models & variantsxAI
Grok language models and Grok Imagine visual generation.
LanguageImageVideoAudio
Grok · Grok Imagine
72 models & variantsAlibaba / Qwen
Qwen language models and Wan visual generation models.
LanguageImageVideoAudioEmbedding
Qwen · Wan
FAQ
Google AI Model FAQ
Which Google Model Families Are on SandBase?
The catalog snapshot includes Gemini language and multimodal models, Nano Banana image generation and editing, Veo and Gemini Omni video, Gemini TTS, and Lyria music.
Does Google Have 50 Foundation Models Here?
No. The Oct 10, 2026 snapshot contains 50 model and capability records, including multiple task variants: 17 language/multimodal, 8 image, 21 video, and 4 audio.
How Do Gemini and Nano Banana Differ?
Gemini includes language and multimodal understanding capabilities. Nano Banana records focus on image generation and editing; some multimodal Gemini records also support image output. Check each model’s tags.
How Are Google Media Models Priced?
Shown request prices are base prices from the catalog snapshot. Final cost can vary by duration, resolution, quality, or inputs. Confirm the live model page and schema before production.
Can I Try Gemini 4 Argon?
It is marked Coming Soon in this snapshot, with no price and no meaningful context value. No active Try action is provided until availability is confirmed.
Can I Swap Google Models in an Agent Workflow?
Models remain separate from Agents. Select a model that supports your task and tool requirements, then connect skills, tools, or APIs in your workflow. Schemas and capabilities can differ.