Introducing Runware Serverless. The lowest-cost way to run your own custom AI workloads.
$0 while idle. Then from $0.63/GPU-hour.
Deploy Python code or a container, choose your GPU and configure scaling. We handle the scheduling, queues, workers and routing.
Runware is sponsoring five Wan3.0 video Crucibles on @HelloCivitai
- 600,000 Buzz (Civitai tokens) to be won per Crucible
- Top 10 in each split the pool, with 150,000 Buzz for 1st
- Free to enter, up to 2 clips per person per Crucible
- Clips up to 30 seconds, judged by community vote
The first, Waifus & Husbandos, opens today. Entries close Nov 24.
Wan3.0 is also live on the Runware API as alibaba:[email protected], from $0.015 per second through Nov 23
Five themes, seven days each:
Nov 18: Waifus & Husbandos
Nov 21: Fantasy Unleashed
Nov 25: Neon Dreams
Nov 28: The Impossible
Dec 2: Chaos & Comedy
Enter the first Crucible: civitai.com/crucibles/413
Full rules: civitai.com/articles/39072/u…
Run Wan3.0 on Runware: runware.ai/wan-3-0
3
65
Replying to @OpenAI
@OpenAI GPT-6.2 Astra and GPT-6.2 Sol are live on Runware on D0
Astra handles complex professional work. Sol covers everyday coding, writing and agents at scale.
- 1.05M-token context window, up to 128K output tokens
- Image input, structured outputs, function calling, reasoning from low to max
- Astra input is $8 per 1M tokens, down from $10 on GPT-6 Astra
- Chat Completions and Responses on our OpenAI-compatible endpoints
Already on GPT-6 Astra or GPT-6.1 Sol? Switch your model ID to openai:[email protected] or openai:[email protected]
from $2 per 1M input tokens
Wan3.0 is 70% off on Runware through November 23
- 480p: $0.015/s (regular $0.05)
- 720p: $0.03/s (regular $0.10)
- 1080p: $0.06/s (regular $0.20)
A 30-second 1080p clip with native audio comes to $1.80
Need faster outputs? Wan3.0 Prime is 50% off for the same window, from $0.034/s
Launch Wan3.0:
runware.ai/wan-3-0
Launch Wan3.0 Prime:
runware.ai/models/alibaba-wa…
2
202
Replying to @Kling_ai
@Kling_ai Kling IMAGE 4.0 is live on Runware on D0
Native 8K stills with up to 2,000 characters of legible text in seven languages.
- 2K, 4K and 8K output, up to 10880×6144 at 16:9
- Combine up to 10 reference images and reusable elements per request
- Set settings.seriesLength to 2-10 for a planned set that keeps subjects and style consistent
- Set settings.pageType to render a full e-commerce product page or website as one tall image
Already on Kling IMAGE 3.0? Switch your model ID to klingai:[email protected]
from $0.063 per image
Replying to @Alibaba_Qwen
@Alibaba_Qwen Qwen4-Max is live on Runware 🧠
Alibaba's Qwen4 flagship takes text, images and video in a 1M-token context window, with configurable reasoning effort, function calling and JSON Schema output.
- 1M-token context, up to 128K output tokens
- Image and video input for screenshot, document and video analysis
- Same price in thinking and non-thinking modes, one input tier up to 1M tokens
- Call alibaba:qwen@4-max on /v1/chat/completions or /v1/responses
from $1.50 per 1M input tokens, $4.50 output and $0.075 cached input
Replying to @BytePlusGlobal
@BytePlusGlobal Seedance 2.5 now renders in 4K on Runware 🎬
Every 4K frame is about 8.3 MP, 4x the pixels of 1080p, and BytePlus tuned the 4K tier for finer facial expressions, movement and texture.
- 3840×2160 (16:9) and 2160×3840 (9:16)
- 2880×2880 (1:1)
- 3326×2494 (~4:3) and 2494×3326 (~3:4)
- 4398×1886 (~21:9)
Keep the model ID set to bytedance:[email protected] and set resolution to "4k", or pass one of the width/height pairs.
2
6
488
Replying to @BytePlusGlobal
@BytePlusGlobal Seedance 2.5 Flash is live on Runware
The lower-cost tier of Seedance 2.5, running at nearly twice the generation speed.
- Up to 30 second clips with synchronized audio, at 480p or 720p
- Generate from text, first and last frames, or up to 10 reference images, 5 reference videos and 5 audio clips
- Edit or extend an existing clip by passing it in inputs.video
Already on Seedance 2.5? Switch your model ID to bytedance:[email protected]
from $0.0678 per second
2
8
613
Replying to @GoogleDeepMind
@GoogleDeepMind's Gemini 4 Carbon and Gemini 4 Hydrogen are live on Runware
Google pairs the two: Carbon takes architecture and hard debugging, Hydrogen runs the fast execution steps.
Gemini 4 Carbon
- 1M-token context, 65,536 max output
- Text, image, video, audio and PDF input, configurable thinking
- $2 input / $10 output per 1M tokens through Nov 30
Gemini 4 Hydrogen
- 1M-token context, four thinking levels from low to xhigh
- 57% on Terminal-Bench 4.1, up from 18.2% on Gemini 3.8 Flash (Google-reported)
- $1.50 input / $7.50 output per 1M tokens
Both run on our OpenAI-compatible endpoint: google:gemini@4-carbon & google:gemini@4-hydrogen
Get started through Runware's API:
Gemini 4 Carbon:
runware.ai/models/google-gem…
Gemini 4 Hydrogen: runware.ai/models/google-gem…
1
91
Replying to @AnthropicAI
@AnthropicAI's Claude Fable 5.2 is live on Runware
Anthropic's latest Fable model, built for long agent runs, large-codebase migrations and open-ended research.
- 1M-token context, 128K max output
- Text and image input, tool calling, configurable effort
- 49.1% on FrontierCode 2.0 at Xhigh effort, up from 32.4% on Fable 5.1
- Output up to 30% faster than Fable 5.1
- Runs on our OpenAI-compatible and Anthropic Messages endpoints
Already calling Fable 5.1 on Runware? Switch your model ID to anthropic:[email protected]
$8 input / $40 output per 1M tokens, $0.20 cached input
Replying to @ByteDanceSeed_
@ByteDanceSeed_ Seedream 5.5 is live on Runware
Building on 5.0 Pro, 5.5 brings transparent output to text-to-image, layer-count control and text recognition for decomposition, and multi-turn edits. ByteDance reports unedited areas stay pixel-stable across 100 rounds, a +55.62% preference for image-to-image realism, and more than double 5.0 Pro's usability in film and office work.
- Set settings.background to transparent for RGBA output, from a prompt or from a reference photo with no alpha channel
- Split one image into a base plus up to 99 layers, with the text, font and color returned for text layers
- Edit with up to 10 reference images
- 1K, 1.5K and 2K tiers, or custom sizes up to 4.6MP from 1:16 to 16:1
Already calling Seedream 5.0 Pro on Runware? Switch your model ID to bytedance:[email protected]
from $0.02 per image
1
12
647
Get started with Seedream 5.5 with our five comprehensive creator guides;
Prompting: runware.ai/docs/models/byted…
Editing images: runware.ai/docs/models/byted…
Multi-reference composition: runware.ai/docs/models/byted…
Transparent backgrounds: runware.ai/docs/models/byted…
Layer decomposition: runware.ai/docs/models/byted…
1
1
126
We're giving $3K in Runware credits to the runners-up in the @HeyGen Video Contest!
To participate, ask your AI agent to make a video with HeyGen Video 1.0 through HeyGen's MCP, then tweak and edit it however you want.
Check out the details to get involved: heygen.com/video-contest
#HeyGenVideoContest
We're teaming up with @Runware, @MiniMax_AI, @ComfyUI and @ChromaAwards to give away $20K+ in cash and credits for the best videos made with HeyGen Video 1 through our MCP.
To enter, follow @HeyGenMCP and post your video with #HeyGenVideoContest.
Rules: heygen.com/blog/video-contes…
Replying to @MiniMax_AI
@MiniMax_AI H3 Image & H3 Image Highspeed are live on Runware on D0
MiniMax built its new image model on H3, its popular open-weight video model, calling it the strongest open-weight image model released so far.
- Edit with up to 16 reference images
- Output up to 20 MP, with 1K, 2K and 4K presets or exact width and height
- Aspect ratios from 1:3 to 3:1
- H3 Image Highspeed runs at 2x the speed, for quick edits and fast iterations
Image output from $3.80 per million tokens, with 50% off 4K outputs on both models through November 17
Launch the models:
MiniMax H3 Image: runware.ai/models/minimax-h3…
MiniMax H3 Image Highspeed: runware.ai/models/minimax-h3…
2
189
The Model Router is live on Runware ↗️
New models land every few days. Stop hardcoding, and swap your model ID for "auto":
- Add plain-language requirements
- Weight quality, speed and cost 0 to 5
- Cap spend with maxPrice
- 12 supported task types
- No routing fee
Let Runware pick the best model for your task
Model Router: runware.ai/model-router
Learn more: runware.ai/blog/runware-mode…
3
205
Replying to @PrunaAI
@PrunaAI's P-Video-2-Pro-Replace is live on Runware on D0 🎬
Swap the people in a video you already have. Send a clip and one or two photos, and get the same video back with the new person: motion, camera and soundtrack kept, lips following the original audio.
- Source clips from 1 to 120s, mp4, mov or webm, any aspect ratio from 1:4 to 4:1
- One photo replaces one person, two photos replace two, matched left to right or by prompt
- 480p and 768p native, with 1080p, 2K and 4K upscaled from 768p
- Pruna reports ~10s of processing per second of video at 480p, ~12s at 768p
from $0.025 per second with 50% off until November 19 (regular from $0.05)
Introducing P-Video-2-Pro-Replace, based on @MiniMax_AI H3! 🎬
Replace the people. Keep the scene.
Swap one or two people in an existing video using reference images, while preserving the original motion, camera, framing, background, and audio
And for launch, it's 50% off for the first two weeks, until November 19 at 6:00 PM CET!
Here's what you need to know:
- 𝗣𝗿𝗶𝗰𝗶𝗻𝗴: Starting from $0.05/s at 480p
- 𝗦𝗽𝗲𝗲𝗱: ~1.5–2 minutes for a 10-second video
- 𝗥𝗲𝗳𝗲𝗿𝗲𝗻𝗰𝗲𝘀: Replace up to two people using reference images
- 𝗗𝘂𝗿𝗮𝘁𝗶𝗼𝗻: Supports videos up to 120 seconds
Available via our inference partners @runware, @wavespeed_ai, Sociaro, @TellersAI, @WiroAI, @Segmind_ai, @replicate, and @eachlabs
📚 Model docs: docs.api.pruna.ai/guides/mod…
🧩 Try the model through the API or Playground: dashboard.pruna.ai/login
Replying to @GoogleDeepMind
@GoogleDeepMind's Gemini Omni Flash 1.2 is live on Runware on D0
Google's update takes text-to-video to 15 seconds and edits source clips up to 15 seconds long.
- Text-to-video from 3 to 15s, with native audio
- Edit 3-15s source videos, with up to 7 reference images
- Extend clips up to 30s long by 3-10s per call
- Re-edit any output in a follow-up call using its videoId
- 360p, 720p, 1080p and 4K, in 16:9 or 9:16
Already calling Gemini Omni Flash 1.1 on Runware? Switch your model ID to google:[email protected]
from $0.02 per second
We’re excited to welcome three engineering leaders from NVIDIA, OpenAI and NetApp to the Runware team;
• Risto Haukioja, Head of Infrastructure Engineering. 8 years at NVIDIA, most recently on NIM
• Matti Oikarinen, CISO. Frontier AI security at OpenAI, AWS Elastic File System architect at Amazon
• Matt Baldwin, Principal Engineer, AI Infrastructure. Ran large-scale Kubernetes across NVIDIA DGX Cloud, founded StackPointCloud (acquired by NetApp)
They’ll own orchestration, scheduling and security for the GPU fleet running on our Sonic Pods. Welcome aboard, Risto, Matti and Matt!
Read the full announcement: runware.ai/blog/engineering-…















