Skip to content

Live model catalog

Multi-model AI platform, one transparent rate.

Compare live image, video, audio, and text models in one multi-model AI platform. Filter by original maker, search capabilities, compare credit costs, and start generating in seconds.

Active models
630
Image · Video · Audio · Text
72 · 33 · 44 · 481
Cheapest generation
0 credits

01 · Browse everything

Model catalog

All models currently live on the platform, with their rate per generation or per second of output and real sample outputs.

Updated in real time

FreeInd is an independent platform and is not affiliated with, endorsed by, or sponsored by the creators or owners of the underlying AI models. Model names appear solely to identify the integrations available on this platform.

Provider
Mode
  • Live
    Qwen
    Text to TextVideo to Text

    The Qwen3.5 27B native vision-language Dense model incorporates a linear attention mechanism, delivering fast response times while balancing inference speed and performance. Its overall capabilities are comparable to those of

    Rate

    7 credits

    per generation

    Generate
  • Live
    SpaceXSI
    Text to Text

    Grok 4.3 is a reasoning model from SpaceXSI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual

    Rate

    7 credits

    per generation

    Generate
  • DeepSeek
    Text to Text

    DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.

    Rate

    7 credits

    per generation

    Generate
  • Live
    SpaceXSI
    Text to Text

    Grok 4.6 is a model from SpaceXSI with frontier performance on coding, knowledge work, and STEM. It is succeeded by Grok 4.7.

    Rate

    7 credits

    per generation

    Generate
  • Live
    SpaceXSI
    Text to Text

    Grok 4.20 is a reasoning model from SpaceXSI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering

    Rate

    7 credits

    per generation

    Generate
  • Live
    ElevenLabs
    Audio to Text

    Ready to generate on demand — pick this model and start creating immediately.

    Rate

    7 credits

    per generation

    Generate
  • ElevenLabs
    Text to Audio

    Generates a sound effect from a text description (foley, ambience, impacts).

    Rate

    16 credits

    per 22 sec

    Generate
  • ElevenLabs
    Text to Audio

    Our ultra low latency model in english. Ideal for conversational use cases.

    Rate

    20 credits

    per 60 sec

    Generate
  • ElevenLabs
    Text to Audio

    Our ultra low latency model in 32 languages. Ideal for conversational use cases.

    Rate

    20 credits

    per 60 sec

    Generate
  • ElevenLabs
    Text to Audio

    Our English-only, low latency model. Best for developer use cases where speed matters and you only need English. Performance is on par with Turbo v2.5.

    Rate

    20 credits

    per 60 sec

    Generate
  • ElevenLabs
    Text to Audio

    Our high quality, low latency model in 32 languages. Best for developer use cases where speed matters and you need non-English languages.

    Rate

    20 credits

    per 60 sec

    Generate
  • ElevenLabs
    Text to Audio

    Our highly expressive model. Supports 70+ languages. Requires more prompt engineering than our previous models.

    Rate

    20 credits

    per 60 sec

    Generate
  • ElevenLabs
    Text to Audio

    Our highly expressive model, optimized for natural dialogue in conversational agents. Supports 70+ languages. Requires more prompt engineering than our previous models.

    Rate

    20 credits

    per 60 sec

    Generate
  • ElevenLabs
    Text to Audio

    Our fastest and most emotive model. Supports 90+ languages.

    Rate

    20 credits

    per 60 sec

    Generate
  • ElevenLabs
    Video to Video

    Translates and dubs a video or audio clip into another language, returning the dubbed speech track.

    Rate

    78 credits

    per 60 sec

    Generate
  • ElevenLabs
    Text to Audio

    Generates a complete song or instrumental track from a text prompt.

    Rate

    156 credits

    per 300 sec

    Generate
  • SpaceXSI
    Text to VideoImage to VideoWith audio

    Grok Imagine Video 1.5 Lite is a faster, lower-cost video generation model from SpaceXSI, distilled from Grok Imagine Video 1.5. It supports text-to-video and image-to-video, trading some quality for speed

    Rate

    357 credits

    per 15 sec

    Generate
  • SpaceXSI
    Text to VideoImage to VideoWith audio

    Grok Imagine Video 1.5 is a video generation model from SpaceXSI. It creates videos from text prompts, with an optional starting image to guide the scene. It can direct subject

    Rate

    638 credits

    per 15 sec

    Generate

Showing 1–18 of 630 active models· rates are per generation (images) or per sec of output (video/audio)

02 · Start from your task

Explore by capability

Every generation mode, with every live model that supports it.

Updated in real time

Text to Text

470 models live

Assistant-style text generation and answers from prompts with system instructions, temperature, and token control.

System promptsTemperature controlToken limits

Learn more

Text to Image

73 models live

Prompt-to-image generation with aspect ratio, seed, and negative prompt control for drafts, concepts, and polished visuals.

Multi-model catalogAspect ratiosSeeds & reproducibility

Learn more

Text to Video

25 models live

Short-form video generation from prompts with duration, ratio, and motion control for clips that move the way you describe.

Duration controlAspect ratiosMotion tuning

Learn more

Text to Audio

43 models live

Voiceover and narration generation from scripts with voice, speed, and format control for natural, production-ready speech.

Natural narrationVoice selectionSpeech-rate control

Learn more

Image to Image

69 models live

Restyle and edit uploaded images with strength control for the perfect balance of fidelity and creativity.

Reference uploadsStrength controlVariations

Learn more

Image to Video

25 models live

Animate stills into short clips with configurable duration, ratio, and motion for living product shots and scenes.

Still animationDuration & ratioMotion prompts

Learn more

Video to Video

17 models live

Restyle existing footage while preserving structure and motion — ideal for campaign variations and reskins.

Style transferStructure preservationCampaign variations

Learn more

Audio to Text

73 models live

Transcribe recordings, meetings, and voice notes into accurate text with language hints and word-level context.

Speech-to-textLanguage hints99+ languages

Learn more

Video to Text

94 models live

Transcribe spoken audio or ask questions about a video and get a text answer from video-capable models.

TranscriptsVideo understandingLanguage hints

Learn more

Video Joiner

1 model live

Combine multiple clips into one video — reorder the shots, trim each clip, and export a single smooth sequence.

Join multiple clipsReorder & trimSingle export

Open tool

Video Audio Mixer

1 model live

Replace a video's original soundtrack or blend your own audio into it, with volume control for each track.

Replace or blend audioPer-track volumeAny video format

Open tool

Production Render

1 model live

Assemble a shot-by-shot storyboard with voiceover, music, transitions, and captions, rendered into one finished video.

Shot-by-shot assemblyVoiceover & musicOne-pass render

Open tool

Audio Stitcher

1 model live

Join multiple audio clips into one continuous track — segment narration, dialogue, or sound effects and export a single file.

Join audio clipsOrdered segmentsSingle export

Open tool

Audio Mixer

0 models live

Blend several audio tracks into one balanced mix for music beds, voiceovers, and sound effects.

Multi-track mixingVolume balancingMusic & effects

Open tool

Image Compositor

1 model live

Layer images, text, and logos onto a canvas at exact pixel sizes — thumbnails, banners, and branded covers.

Layered compositionExact pixel sizesText & logo overlays

Open tool

Frame Extract

1 model live

Pull a still frame out of any video at the moment you choose, ready to download or reuse as a new image input.

First or last framePNG / JPEG outputReuse as image input

Open tool

Start generating

Sign in to your workspace and pick any live model.

03 · Built by original labs

Original model makers

Every model is built by its original lab — from industry leaders to independent creators. Pick a maker to see only their models.

70 makers total — use the directory above to find any of them.

Same prompt, every model

Same prompt, every model

Real generations from curated prompt collections — watch multiple models interpret the same words, side by side, with outputs you can replay or download.

View all collections
Text to VideoReel 01

ByteDance: Seedance 2.0 Mini examples

1 prompt5 models5 outputs
01

“Hyper-realistic cinematic street racing shot. Audio: High-pitched engine revving, aggressive tire screech, and rain hitting metal. Camera starts low to the ground on a wet asphalt hairpin curve at night. A matte-black vintage sports car drifts aggressively into frame. The camera executes a fast whip-pan to the right, perfectly tracking the car's speed. The car slides out of frame, kicking up a massive rooster tail of neon-lit water droplets. The camera abruptly stops panning and immediately rack-focuses to a wet, crushed soda can resting on the asphalt in the extreme foreground. Perfect water physics, 1080p, 24fps.”

View full collection
Text to VideoReel 03

MiniMax: Hailuo 2.3 examples

3 prompts1 model5 outputs
01

“slow handheld camera movement: Two firebenders face off in a dark alley as heavy rain pours. One exhales steam. Sparks ignite from soaked fists. They launch into motion kicks, spins, flaming strikes that hiss on contact with water. Explosions reflect in puddles. Fire clashes mid-air, casting harsh orange light. A final blast sends water and embers flying toward camera. Stylized urban fantasy with dramatic lighting and intense motion.”

02

“From a soaring aerial, the rider rockets across a collapsing skyline, rooftops narrowing into jagged ledges. Camera hovers tight above as he angles through curved glass and steel, void yawning between buildings. Each rooftop leap sparks drama, until he threads impossibly across the final span, city blurring below.”

View full collection
Text to VideoReel 04

ByteDance: Seedance 2.0 examples

5 prompts1 model5 outputs
01

“A hot air balloon festival at sunrise, dozens of colorful balloons rising above misty green hills, camera tilts up slowly revealing the vast landscape”

02

“A woman in a flowing red dress walking along the edge of a cliff overlooking the sea, wind blowing her hair and dress, dramatic wide angle, golden sunset”

03

“A sushi chef carefully preparing an intricate sushi roll, close-up overhead shot, steam rising, warm restaurant lighting”

04

“A golden retriever puppy chasing butterflies through a sunlit meadow, soft bokeh background, cinematic camera slowly tracking the puppy”

05

“A cozy cabin in a snowy forest at night, warm light glowing from the windows, gentle snowfall, camera slowly pushing in through the trees”

View full collection
Image to VideoReel 05

Google: Veo 3.1 Lite examples

3 prompts2 models6 outputs
01

“A cinematic sequence of an astronaut on Mars walking toward a flag planting site. The astronaut takes slow, deliberate steps across the red dusty terrain. Wind blows fine red dust across the surface. Dramatic orchestral music, the sound of heavy breathing inside the helmet.”

02

“Bring this cozy coffee shop scene to life. The steam rises gently from the latte, raindrops streak down the window, a hand reaches in to turn the page of the book. Soft jazz music plays, the sound of rain pattering against glass.”

03

“A close-up of two old friends reuniting at a train station. The woman gasps, 'I can't believe it's really you!' and they embrace tightly. The sound of a train whistle echoes in the background, ambient station noise, emotional orchestral music swells gently.”

View full collection
Google: Nano Banana (Gemini 2.5 Flash Image) examples
Text to ImageReel 06

Google: Nano Banana (Gemini 2.5 Flash Image) examples

1 prompt4 models4 outputs
View full collection

04 · Transparent rates

How model pricing works

Four simple rules — no hidden fees, no silent changes.

Fixed credit pricing

Every model has a fixed credit cost published right on its card — per generation for images, per second of output for video and audio. Costs never change silently.

Plan availability

Some models are available on every plan; others are restricted. The catalog shows what your workspace can use before you generate.

Output limits

Maximum resolution, duration, output count, and storage limits are enforced per plan and published per model.

Provider-managed credentials

Providers are platform-managed. You never configure API keys or provider accounts — we handle reliability, health, and failover.

The full plan-aware catalog with per-model limits is available inside the generation workspace — sign in to see exactly what your plan can run. Credit costs are also covered on the pricing page.

Cookies keep FreeInd working. Optional analytics require your permission; ads for free accounts are served by Google, which shows its own consent message where required. Read our cookie policy.