AI models
Models & pricing
BuilderStudio gives every workspace one bill for the best generative models across text, image, video, and audio. Pay only for what you use — no per-model subscriptions.
Vendors at a glance
Every model family available in BuilderStudio, and what it covers.
| Vendor | Capabilities | Models |
|---|---|---|
| Gemini | Text generation, Image generation | 5 |
| Grok | Text generation, Image generation, Video generation | 5 |
| Anthropic Claudevia AI Gateway | Text generation | 2 |
| OpenAIvia AI Gateway | Text generation | 2 |
| FLUXvia Fal.ai | Image generation | 2 |
| Seedreamvia Fal.ai | Image generation | 1 |
| Recraftvia Fal.ai | Image generation | 1 |
| Veo | Video generation | 2 |
| Klingvia Fal.ai | Video generation | 1 |
| Seedancevia Fal.ai | Video generation | 5 |
| Wanvia Fal.ai | Video generation | 3 |
| ElevenLabs | Text to speech, Voice changer, Sound effects, Voice design | 7 |
Text & reasoning
Language models available in text-generation and agent nodes, billed per token.
| Model | Vendor | Parameters | Billed per | Pricing |
|---|---|---|---|---|
Gemini 3.5 FlashStable frontier Gemini Flash model for agentic text workgemini-3.5-flash | Gemini | Temperature: 0–2Max output tokens: up to 8,192Reasoning effort: minimal, low, medium, high | tokens | Usage-based — metered per token |
Gemini 3.1 ProLatest high-capability Gemini modelgemini-3.1-pro-preview | Gemini | Temperature: 0–2Max output tokens: up to 8,192Reasoning effort: low, medium, high | tokens | Usage-based — metered per token |
Gemini 3.1 Pro Custom ToolsGemini 3.1 Pro variant for complex tool usegemini-3.1-pro-preview-customtools | Gemini | Temperature: 0–2Max output tokens: up to 8,192Reasoning effort: low, medium, high | tokens | Usage-based — metered per token |
Grok 4.3xAI flagship model for agentic text and reasoninggrok-4.3 | Grok | Temperature: 0–2Max output tokens: up to 128,000Reasoning effort: none, low, medium, high | tokens | Input: $1.25 / 1M tokensCached input: $0.20 / 1M tokensOutput: $2.50 / 1M tokens |
Grok Build 0.1xAI coding model trained for agentic build workflowsgrok-build-0.1 | Grok | Temperature: 0–2Max output tokens: up to 128,000 | tokens | Usage-based — metered per token |
Claude Opus 4.8Anthropic Claude Opus — best for complex workflows via Vercel AI Gatewayanthropic/claude-opus-4.8 | Anthropic Claudevia AI Gateway | Temperature: 0–2Max output tokens: up to 32,768 | tokens | Usage-based — billed at the provider's metered rate |
Claude Sonnet 4.6Anthropic Claude Sonnet — fast and capable via Vercel AI Gatewayanthropic/claude-sonnet-4.6 | Anthropic Claudevia AI Gateway | Temperature: 0–2Max output tokens: up to 32,768 | tokens | Usage-based — billed at the provider's metered rate |
GPT-5.5OpenAI model via Vercel AI Gatewayopenai/gpt-5.5 | OpenAIvia AI Gateway | Temperature: 0–2Max output tokens: up to 128,000Reasoning effort: none, low, medium, high, xhighVerbosity: low, medium, high | tokens | Usage-based — billed at the provider's metered rate |
GPT-5.5 ProOpenAI model via Vercel AI Gatewayopenai/gpt-5.5-pro | OpenAIvia AI Gateway | Temperature: 0–2Max output tokens: up to 128,000Reasoning effort: none, low, medium, high, xhighVerbosity: low, medium, high | tokens | Usage-based — billed at the provider's metered rate |
Image generation
Text-to-image and image-editing models, billed per generated image.
| Model | Vendor | Parameters | Billed per | Pricing |
|---|---|---|---|---|
Nano Banana ProHighest quality image gen (Gemini 3 Pro)gemini-3-pro-image | Gemini | Aspect ratio: 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9, 1:4, 4:1, 1:8, 8:1Resolution: 1K, 2K, 4K | images | Usage-based — metered per image |
Nano BananaSpeed-optimized image gen (Gemini 2.5 Flash)gemini-2.5-flash-image | Gemini | Aspect ratio: 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9, 1:4, 4:1, 1:8, 8:1 | images | Usage-based — metered per image |
Grok Imagine QualityxAI Grok Imagine image generation and editinggrok-imagine-image-quality | Grok | Aspect ratio: 1:1, 3:4, 4:3, 9:16, 16:9, 2:3, 3:2, 9:19.5, 19.5:9, 9:20, 20:9, 1:2, 2:1, autoResolution: 1K, 2K | images | $0.05 / image |
FLUX.2 DevHigh-quality text-to-imagefal-ai/flux-2 | FLUXvia Fal.ai | Aspect ratio: 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9, 1:4, 4:1, 1:8, 8:1Guidance scale: 1–20Steps: 1–50Seed: -1–2,147,483,647 | images | Usage-based — metered at Fal.ai's live per-request rate |
FLUX.2 ProHigh-quality generation, balanced speedfal-ai/flux-2-pro | FLUXvia Fal.ai | Aspect ratio: 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9, 1:4, 4:1, 1:8, 8:1Seed: -1–2,147,483,647 | images | Usage-based — metered at Fal.ai's live per-request rate |
Seedream 4.5Unified high-quality image generationfal-ai/bytedance/seedream/v4.5/text-to-image | Seedreamvia Fal.ai | Aspect ratio: 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9, 1:4, 4:1, 1:8, 8:1Seed: -1–2,147,483,647 | images | Usage-based — metered at Fal.ai's live per-request rate |
Recraft V4.1Design-focused image generationfal-ai/recraft/v4.1/text-to-image | Recraftvia Fal.ai | Aspect ratio: 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9, 1:4, 4:1, 1:8, 8:1 | images | Usage-based — metered at Fal.ai's live per-request rate |
Video generation
Text-, image-, and reference-to-video models, billed per second of output.
| Model | Vendor | Parameters | Billed per | Pricing |
|---|---|---|---|---|
Veo 3.1Highest-quality Veo 3.1 video generationveo-3.1-generate-preview | Veo | Aspect ratio: 16:9, 9:16Duration: 4, 6, 8Resolution: 720p, 1080p, 4k | seconds | Usage-based — metered per second |
Veo 3.1 FastLower-latency Veo 3.1 video generationveo-3.1-fast-generate-preview | Veo | Aspect ratio: 16:9, 9:16Duration: 4, 6, 8Resolution: 720p, 1080p, 4k | seconds | Usage-based — metered per second |
Grok Imagine VideoxAI text-to-video and image-to-video generationgrok-imagine-video | Grok | Aspect ratio: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3Duration: 1–15Resolution: 480p, 720p, 1080p | seconds | Output: $0.05 / second |
Grok Imagine Video 1.5 PreviewxAI image-to-video preview modelgrok-imagine-video-1.5-preview | Grok | Aspect ratio: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3Duration: 1–15Resolution: 480p, 720p, 1080p | seconds | Output 480p: $0.08 / secondOutput 720p: $0.14 / secondInput: $0.01 / image |
Kling 3.0 ProPremium image-to-video generationfal-ai/kling-video/v3/pro/image-to-video | Klingvia Fal.ai | Duration: 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15Generate audio: on / offNegative promptCFG scale | seconds | Usage-based — metered at Fal.ai's live per-request rate |
Seedance 2.0 Image to VideoSeedance 2.0 image-to-video generationbytedance/seedance-2.0/image-to-video | Seedancevia Fal.ai | Aspect ratio: auto, 21:9, 16:9, 4:3, 1:1, 3:4, 9:16Resolution: 480p, 720p, 1080pDuration: auto, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15Generate audio: on / offSeed | seconds | Usage-based — metered at Fal.ai's live per-request rate |
Seedance 2.0 Reference to VideoSeedance 2.0 multimodal reference-to-video generationbytedance/seedance-2.0/reference-to-video | Seedancevia Fal.ai | Aspect ratio: auto, 21:9, 16:9, 4:3, 1:1, 3:4, 9:16Resolution: 480p, 720p, 1080pDuration: auto, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15Generate audio: on / offSeed | seconds | Usage-based — metered at Fal.ai's live per-request rate |
Seedance 2.0 Fast Text to VideoLower-latency Seedance 2.0 text-to-video generationbytedance/seedance-2.0/fast/text-to-video | Seedancevia Fal.ai | Aspect ratio: auto, 21:9, 16:9, 4:3, 1:1, 3:4, 9:16Resolution: 480p, 720pDuration: auto, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15Generate audio: on / offSeed | seconds | Usage-based — metered at Fal.ai's live per-request rate |
Seedance 2.0 Fast Image to VideoLower-latency Seedance 2.0 image-to-video generationbytedance/seedance-2.0/fast/image-to-video | Seedancevia Fal.ai | Aspect ratio: auto, 21:9, 16:9, 4:3, 1:1, 3:4, 9:16Resolution: 480p, 720pDuration: auto, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15Generate audio: on / offSeed | seconds | Usage-based — metered at Fal.ai's live per-request rate |
Seedance 2.0 Fast Reference to VideoLower-latency Seedance 2.0 multimodal reference-to-video generationbytedance/seedance-2.0/fast/reference-to-video | Seedancevia Fal.ai | Aspect ratio: auto, 21:9, 16:9, 4:3, 1:1, 3:4, 9:16Resolution: 480p, 720pDuration: auto, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15Generate audio: on / offSeed | seconds | Usage-based — metered at Fal.ai's live per-request rate |
Wan 2.7 Text to VideoWan 2.7 text-to-video generationfal-ai/wan/v2.7/text-to-video | Wanvia Fal.ai | Aspect ratio: 16:9, 9:16, 1:1, 4:3, 3:4Duration: 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15Negative promptSeedResolution: 720p, 1080pSafety checker: on / offPrompt expansion: on / off | seconds | Usage-based — metered at Fal.ai's live per-request rate |
Wan 2.7 Image to VideoWan 2.7 image-to-video generationfal-ai/wan/v2.7/image-to-video | Wanvia Fal.ai | Duration: 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15Negative promptSeedResolution: 720p, 1080pSafety checker: on / offPrompt expansion: on / off | seconds | Usage-based — metered at Fal.ai's live per-request rate |
Wan 2.7 Reference to VideoWan 2.7 image and video reference-to-video generationfal-ai/wan/v2.7/reference-to-video | Wanvia Fal.ai | Aspect ratio: 16:9, 9:16, 1:1, 4:3, 3:4Duration: 2, 3, 4, 5, 6, 7, 8, 9, 10Negative promptMulti-shot segmentation: on / offSeedResolution: 720p, 1080pSafety checker: on / off | seconds | Usage-based — metered at Fal.ai's live per-request rate |
Audio & voice
Text-to-speech, voice conversion, sound effects, and voice design, powered by ElevenLabs.
| Model | Vendor | Capability | Parameters | Billed per | Pricing |
|---|---|---|---|---|---|
Multilingual V2Best quality, 29 languageseleven_multilingual_v2 | ElevenLabs | Text to speech | Voice: any workspace ElevenLabs voiceStability: 0–1Similarity boost: 0–1Style: 0–1Speed: 0.7–1.2Speaker boost: on / offSeed: 0–4,294,967,295 | characters | $0.10 / 1K characters |
Flash V2.5Ultra-low latency (~75ms)eleven_flash_v2_5 | ElevenLabs | Text to speech | Voice: any workspace ElevenLabs voiceStability: 0–1Similarity boost: 0–1Style: 0–1Speed: 0.7–1.2Speaker boost: on / offSeed: 0–4,294,967,295 | characters | $0.05 / 1K characters |
Eleven V3Most expressive, 70+ languageseleven_v3 | ElevenLabs | Text to speech | Voice: any workspace ElevenLabs voiceStability: 0–1Similarity boost: 0–1Style: 0–1Speed: 0.7–1.2Speaker boost: on / offSeed: 0–4,294,967,295 | characters | $0.10 / 1K characters |
Multilingual STS V2Speech-to-speech voice conversioneleven_multilingual_sts_v2 | ElevenLabs | Voice changer | Voice: any workspace ElevenLabs voiceStability: 0–1Similarity boost: 0–1Style: 0–1Speed: 0.7–1.2Speaker boost: on / offSeed: 0–4,294,967,295Remove background noise: on / off | characters | Usage-based — metered per character |
Sound Effects V2Text-to-sound-effects generationeleven_text_to_sound_v2 | ElevenLabs | Sound effects | Duration: 0.5–30 secondsLoop: on / offPrompt influence: 0–1 | generations | Usage-based — metered per generation |
Voice Design Multilingual V2Create custom voices from a text prompteleven_multilingual_ttv_v2 | ElevenLabs | Voice design | Voice description: 20–1,000 characters | generations | Usage-based — metered per generation |
Voice Design V3Most expressive voice design modeleleven_ttv_v3 | ElevenLabs | Voice design | Voice description: 20–1,000 characters | generations | Usage-based — metered per generation |
ElevenLabs usage is metered in characters or generations; the effective rate can vary with the connected ElevenLabs plan.
Fixed rates are vendor list prices last verified on 2026-06-10. Usage-based models are metered at the vendor's current rate at request time. Model availability and pricing may change as vendors update their offerings.