# pricing

> subscribe for monthly credits and higher limits, or pay as you go. every app shows its cost upfront.

**URL:** https://inference.sh/pricing

---

## plans

### starter

get started with basic access

- price: $0
- 1 concurrent tasks
- 20 /min requests/min
- 7 days data retention
- 1 team seats
- 100 mb storage

### pro

for individuals building with AI

- price: $20/mo billed monthly
- price: $17/mo billed yearly
- credits included: $20/mo
- 5 concurrent tasks
- 100 /min requests/min
- 30 days data retention
- 1 team seats
- 5 gb storage
- 5 triggers

### team

collaborate with your team

- price: $200/mo billed monthly
- price: $167/mo billed yearly
- credits included: $200/mo
- 20 concurrent tasks
- 500 /min requests/min
- 90 days data retention
- 5 team seats
- 51 gb storage
- 50 triggers

### enterprise

custom solutions for large organizations

- price: custom, contact hello@inference.sh

## app pricing

per-call pricing for every app on the grid. pay only for what you run.

### image

- [Qwen-Image-2.0](https://inference.sh/apps/alibaba/qwen-image-2.md): $0.035/image
- [Qwen-Image-2.0 Pro](https://inference.sh/apps/alibaba/qwen-image-2-pro.md): $0.075/image
- [Wan 2.7 Image](https://inference.sh/apps/alibaba/wan-2-7-image.md): $0.03/image
- [Wan 2.7 Image Pro](https://inference.sh/apps/alibaba/wan-2-7-image-pro.md): $0.075/image
- [Bria Ads Generate](https://inference.sh/apps/bria/ads-generate.md): from $0.00000277/sec
- [Bria Image Edit](https://inference.sh/apps/bria/edit.md): $0.03/image
- [Bria Eraser](https://inference.sh/apps/bria/erase.md): $0.02/image
- [Bria Expand](https://inference.sh/apps/bria/expand.md): $0.02 per image
- [Bria Gen Fill](https://inference.sh/apps/bria/gen-fill.md): $0.03/image
- [Bria Generate](https://inference.sh/apps/bria/generate.md): $0.03/image
- [Bria Generate Lite](https://inference.sh/apps/bria/generate-lite.md): $0.02 per image
- [Bria Increase Resolution](https://inference.sh/apps/bria/increase-resolution.md): $0.02/image
- [Bria Product Cutout](https://inference.sh/apps/bria/product-cutout.md): $0.018/image
- [Bria Product Packshot](https://inference.sh/apps/bria/product-packshot.md): $0.03/image
- [Bria Product Shadow](https://inference.sh/apps/bria/product-shadow.md): $0.018/image
- [Bria Replace Background](https://inference.sh/apps/bria/replace-background.md): $0.03/image
- [Bria Background Removal](https://inference.sh/apps/bria/rmbg.md): $0.018/image
- [Seedream 3.0 T2I](https://inference.sh/apps/bytedance/seedream-3-0-t2i.md): $0.03/image
- [Seedream 4.0](https://inference.sh/apps/bytedance/seedream-4-0.md): $0.03/image
- [Seedream 4.5](https://inference.sh/apps/bytedance/seedream-4-5.md): $0.04/image
- [Seedream 5 Lite](https://inference.sh/apps/bytedance/seedream-5-lite.md): $0.035/image
- [Seedream 5.0 Pro](https://inference.sh/apps/bytedance/seedream-5-pro.md): $0.045-$0.09/image, <=2.36MP: $0.045, >2.36MP: $0.09
- [Image Degradation](https://inference.sh/apps/eval/blur.md): from $0.00000277/sec
- [Research Chart Generator](https://inference.sh/apps/eval/charts.md): from $0.00000277/sec
- [Image Resize & Crop](https://inference.sh/apps/eval/resize.md): from $0.00000277/sec
- [FLUX.2 [klein] LoRA](https://inference.sh/apps/falai/flux-2-klein-lora.md): $0.16/MP (4b), $0.20/MP (9b), input + output
- [FLUX.1 [dev] LoRA](https://inference.sh/apps/falai/flux-dev-lora.md): $0.035/MP
- [Imagine Art 1.5 Pro Preview](https://inference.sh/apps/falai/imagine-art-1-5-pro-preview.md): $0.045 per image
- [Gemini 2.5 Flash Image](https://inference.sh/apps/google/gemini-2-5-flash-image.md): $0.039 /image
- [Gemini 3.1 Flash Image](https://inference.sh/apps/google/gemini-3-1-flash-image.md): $0.50/M input, $0.045–$0.151/image (0.5K–4K), +$0.014/query Google Search
- [Gemini 3.1 Flash Lite Image](https://inference.sh/apps/google/gemini-3-1-flash-lite-image.md): $0.0336/image (1K)
- [Gemini 3 Pro Image](https://inference.sh/apps/google/gemini-3-pro-image.md): $0.134/image (1K/2K), $0.24/image (4K), +$0.0011/input image, +$0.014/search
- [Gemini Nano Banana 2.1](https://inference.sh/apps/google/gemini-nano-banana-2-1.md): $1.50/M input, $0.0336–$0.1134/image (1K–4K), +$0.014/query Google Search
- [BAGEL Image Understanding & Generation](https://inference.sh/apps/infsh/bagel.md): GPU time, billed per millisecond
- [BiRefNet Background Removal](https://inference.sh/apps/infsh/birefnet.md): GPU time, billed per millisecond
- [ByteDance USO](https://inference.sh/apps/infsh/bytedance-uso.md): GPU time, billed per millisecond
- [Chroma 1 HD](https://inference.sh/apps/infsh/chroma-1-hd.md): GPU time, billed per millisecond
- [CogView4 6B](https://inference.sh/apps/infsh/cogview4-6b.md): GPU time, billed per millisecond
- [Falconsai NSFW Detection](https://inference.sh/apps/infsh/falconsai-nsfw-detection.md): from $0.00000277/sec
- [FLUX.1 [dev]](https://inference.sh/apps/infsh/flux-1-dev.md): GPU time, billed per millisecond
- [FLUX.1 Fill](https://inference.sh/apps/infsh/flux-1-fill.md): GPU time, billed per millisecond
- [HiDream-I1 Fast](https://inference.sh/apps/infsh/hidream-i1-fast.md): GPU time, billed per millisecond
- [Image Resize](https://inference.sh/apps/infsh/image-resize.md): from $0.00000277/sec
- [OmniZero](https://inference.sh/apps/infsh/omni-zero.md): GPU time, billed per millisecond
- [Inference Shell Stitch Images](https://inference.sh/apps/infsh/stitch-images.md): from $0.00000277/sec
- [Thera Image Upscaler](https://inference.sh/apps/infsh/thera.md): GPU time, billed per millisecond
- [Kling Image 3O](https://inference.sh/apps/klingai/image-3o.md): $0.028/image (1K/2K), $0.056/image (4K)
- [Kling Image O1](https://inference.sh/apps/klingai/image-o1.md): $0.028/run
- [Kling Image V1](https://inference.sh/apps/klingai/image-v1.md): $0.0035/image
- [Kling Image V1.5](https://inference.sh/apps/klingai/image-v1-5.md): $0.014/generation, $0.028/generation with image reference
- [Kling Image V2](https://inference.sh/apps/klingai/image-v2.md): $0.014-$0.056/image, t2i: $0.014/image, i2i: $0.028/image, multi-image: $0.056/image
- [Kling Image V2.1](https://inference.sh/apps/klingai/image-v2-1.md): $0.014-$0.056/image, t2i: $0.014/image, i2i: $0.028/image, multi: $0.056/image
- [Kling Image V3](https://inference.sh/apps/klingai/image-v3.md): $0.0035/image
- [Krea 2 Large](https://inference.sh/apps/krea/krea-2-large.md): $0.06/image
- [Krea 2 Large LoRA Training](https://inference.sh/apps/krea/krea-2-large-train.md): $0.50/training run
- [Krea 2 Medium](https://inference.sh/apps/krea/krea-2-medium.md): $0.03/image
- [Krea 2 Medium LoRA Training](https://inference.sh/apps/krea/krea-2-medium-train.md): $0.50/training run
- [Krea 2 Medium Turbo](https://inference.sh/apps/krea/krea-2-medium-turbo.md): $0.015/image
- [Krea 2 Medium Turbo LoRA Training](https://inference.sh/apps/krea/krea-2-medium-turbo-train.md): $0.50/training run
- [MAI Image 2.5](https://inference.sh/apps/microsoft/mai-image-2-5.md): $0.05/image
- [GPT Image 2](https://inference.sh/apps/openai/gpt-image-2.md): $0.006-$0.21/image
- [GPT Image 2.5 Flare](https://inference.sh/apps/openai/gpt-image-2-5-flare.md): $0.006-$0.21/image at 1024x1024: low $0.0059, medium $0.0132, high $0.0527, xhigh $0.0937, max $0.2107. Larger sizes cost more; edits add ~$0.0083 per reference image.
- [GPT Image 2.5 Sunburst](https://inference.sh/apps/openai/gpt-image-2-5-sunburst.md): $0.006-$0.21 per 1024x1024 image: low $0.006, medium $0.013, high $0.053, xhigh $0.094, max $0.21. Larger sizes cost more; edits add ~$0.008 per reference image.
- [PATINA Extract Material](https://inference.sh/apps/patina/extract-material.md): $0.10 base + $0.02/MP texture + $0.01/MP/map (5 maps) + upscaling ($0.004/MP/map for 2x, $0.016/MP/map for 4x)
- [PATINA Image to Material](https://inference.sh/apps/patina/image-to-material.md): $0.01 base + $0.01/MP/map
- [PATINA Text to Material](https://inference.sh/apps/patina/text-to-material.md): $0.01 base + $0.02/MP texture + $0.01/MP/map + upscaling: 2x adds $0.004/MP/map, 4x adds $0.016/MP/map
- [Phota Edit](https://inference.sh/apps/phota/edit.md): $0.09/image standard, $0.18/image 4K
- [Phota Enhance](https://inference.sh/apps/phota/enhance.md): $0.13/image
- [Phota Generate](https://inference.sh/apps/phota/generate.md): $0.09-$0.18/image, standard: $0.09, 4K: $0.18
- [Pruna FLUX.2 Klein 4B](https://inference.sh/apps/pruna/flux-2-klein-4b.md): $0.001/image
- [P-Image FLUX.1 [dev]](https://inference.sh/apps/pruna/flux-dev.md): $0.005/image
- [P-Image-LoRA FLUX.1 [dev]](https://inference.sh/apps/pruna/flux-dev-lora.md): $0.01/image
- [P-Image](https://inference.sh/apps/pruna/p-image.md): $0.005/image
- [P-Image-Edit](https://inference.sh/apps/pruna/p-image-edit.md): $0.01/image
- [P-Image-Edit LoRA](https://inference.sh/apps/pruna/p-image-edit-lora.md): $0.01/image
- [P-Image Ideogram](https://inference.sh/apps/pruna/p-image-ideogram.md): $0.003–$0.015/image at 1K, $0.006–$0.03/image at 2K
- [P-Image-LoRA](https://inference.sh/apps/pruna/p-image-lora.md): $0.005/image
- [P-Image-Upscale](https://inference.sh/apps/pruna/p-image-upscale.md): $0.005/image (1-4 MP), $0.01/image (5-8 MP), $0.02/image (9-16 MP), $0.04/image (17-32 MP), $0.06/image (33-64 MP), $0.12/image (65-128 MP)
- [Pruna Qwen-Image](https://inference.sh/apps/pruna/qwen-image.md): $0.25/image
- [Pruna Qwen-Image Edit Plus](https://inference.sh/apps/pruna/qwen-image-edit-plus.md): $0.03/image
- [Pruna Qwen-Image Fast](https://inference.sh/apps/pruna/qwen-image-fast.md): $0.005/image
- [Pruna Wan Image Small](https://inference.sh/apps/pruna/wan-image-small.md): $0.005/image
- [Pruna Z-Image Turbo](https://inference.sh/apps/pruna/z-image-turbo.md): $0.005/image
- [Pruna Z-Image Turbo LoRA](https://inference.sh/apps/pruna/z-image-turbo-lora.md): $0.008/image
- [Reve Create](https://inference.sh/apps/reve/create.md): ~$0.024/image, +$0.02/quality level, +~$0.002/MP upscale, +~$0.002/MP background removal
- [Reve Edit](https://inference.sh/apps/reve/edit.md): ~$0.04/image, +$0.032/quality level, +~$0.002/MP upscale, +~$0.002/MP background removal
- [Reve Remix](https://inference.sh/apps/reve/remix.md): ~$0.04/image, +$0.032/quality level, +~$0.002/MP upscale, +~$0.002/MP background removal
- [Runway Gen-4 Image](https://inference.sh/apps/runway/gen-4-image.md): $0.05/image (720p), $0.08/image (1080p)
- [Runway Gen-4 Image Turbo](https://inference.sh/apps/runway/gen-4-image-turbo.md): $0.02/image
- [X Post Card Renderer](https://inference.sh/apps/x/post-render.md): from $0.00000277/sec
- [Grok Imagine](https://inference.sh/apps/xai/grok-imagine-image.md): $0.002/input image, $0.02/output image
- [Grok Imagine Image 2.0](https://inference.sh/apps/xai/grok-imagine-image-2-0.md): $0.04/img low 1k, $0.06/img low 2k, $0.06/img med 1k, $0.08/img med 2k; $0.01/source img (edits)
- [Grok Imagine Pro](https://inference.sh/apps/xai/grok-imagine-image-pro.md): $0.002/input image, $0.07/output image
- [Grok Imagine Quality](https://inference.sh/apps/xai/grok-imagine-image-quality.md): $0.01 per input image, $0.05 per 1K image, $0.07 per 2K image

### video

- [HappyHorse 1.0 Image-to-Video](https://inference.sh/apps/alibaba/happyhorse-1-0-i2v.md): $0.14/sec (720P), $0.24/sec (1080P)
- [HappyHorse 1.0 Reference-to-Video](https://inference.sh/apps/alibaba/happyhorse-1-0-r2v.md): $0.14/sec (720P), $0.24/sec (1080P)
- [HappyHorse 1.0 Text-to-Video](https://inference.sh/apps/alibaba/happyhorse-1-0-t2v.md): $0.14/sec (720P), $0.24/sec (1080P)
- [HappyHorse 1.0 Video Edit](https://inference.sh/apps/alibaba/happyhorse-1-0-video-edit.md): $0.14/sec 720P, $0.24/sec 1080P, billed on input+output duration
- [Wan 2.7 Image-to-Video](https://inference.sh/apps/alibaba/wan-2-7-i2v.md): $0.10/sec 720P, $0.15/sec 1080P
- [Wan 2.7 Reference-to-Video](https://inference.sh/apps/alibaba/wan-2-7-r2v.md): $0.10/sec (720P) or $0.15/sec (1080P); billed for input + output video duration
- [Wan 2.7 Text-to-Video](https://inference.sh/apps/alibaba/wan-2-7-t2v.md): $0.10/sec (720P), $0.15/sec (1080P)
- [Wan 2.7 Video Edit](https://inference.sh/apps/alibaba/wan-2-7-videoedit.md): 720P: $0.10/s, 1080P: $0.15/s (input + output duration)
- [FLUX 3 Video](https://inference.sh/apps/bfl/flux-3-video.md): From $17/sec (HD)
- [Bria Video Eraser](https://inference.sh/apps/bria/video-eraser.md): $0.02/sec
- [Bria Video Green Screen](https://inference.sh/apps/bria/video-green-screen.md): $0.0033/sec
- [Bria Video Increase Resolution](https://inference.sh/apps/bria/video-increase-resolution.md): $0.02/sec
- [Bria Video Replace Background](https://inference.sh/apps/bria/video-replace-background.md): $0.0033/sec
- [Bria Video Background Removal](https://inference.sh/apps/bria/video-rmbg.md): $0.0033/sec
- [OmniHuman 1.0](https://inference.sh/apps/bytedance/omnihuman-1-0.md): $0.12/sec
- [OmniHuman 1.5](https://inference.sh/apps/bytedance/omnihuman-1-5.md): $0.12/sec
- [Seedance 1.0 Pro](https://inference.sh/apps/bytedance/seedance-1-0-pro.md): $2.50/M tokens (w*h*fps*s/1024)
- [Seedance 1.0 Pro Fast](https://inference.sh/apps/bytedance/seedance-1-0-pro-fast.md): $1.00/M video tokens (w×h×fps×sec÷1024)
- [Seedance 1.5 Pro](https://inference.sh/apps/bytedance/seedance-1-5-pro.md): $2.40/M tokens w/audio, $1.20/M no-audio; draft 0.6x/0.7x
- [Seedance 2.0](https://inference.sh/apps/bytedance/seedance-2-0.md): $2.40-$7.70/M tokens by resolution and visual input
- [Seedance 2.0 Fast](https://inference.sh/apps/bytedance/seedance-2-0-fast.md): $0.0033/1K tokens (with visual input), $0.0056/1K tokens (text-only). Tokens = (w*h*fps*(input_s+output_s))/1024
- [Seedance 2.0 Mini](https://inference.sh/apps/bytedance/seedance-2-0-mini.md): $0.0035/K tokens (text-only), $0.0021/K tokens (visual input)
- [Seedance 2.0 Studio](https://inference.sh/apps/bytedance/seedance-2-0-studio.md): Token-based: $2.40-$7.70/M tokens (varies by resolution and input type)
- [Seedance 2.0 Studio Fast](https://inference.sh/apps/bytedance/seedance-2-0-studio-fast.md): $0.0033/1K tokens (with visual input), $0.0056/1K tokens (text-only). Tokens = (w*h*fps*(input_s+output_s))/1024
- [Seedance 2.0 Studio Mini](https://inference.sh/apps/bytedance/seedance-2-0-studio-mini.md): from $0.00000277/sec
- [Seedance 2.5](https://inference.sh/apps/bytedance/seedance-2-5.md): $6.40–$11.70/M tokens, varies by output resolution and visual input
- [Seedance 2.5 Studio](https://inference.sh/apps/bytedance/seedance-2-5-studio.md): $6.40–$11.70/M tokens, varies by output resolution and visual input
- [Fabric 1.0](https://inference.sh/apps/falai/fabric-1-0.md): 480p: $0.08/sec, 720p: $0.15/sec
- [MiniMax H3 Max](https://inference.sh/apps/falai/minimax-h3-max.md): $0.08/sec (768P), $0.05/sec (480P)
- [Wan 2.5](https://inference.sh/apps/falai/wan-2-5.md): $0.05/sec (480p), $0.10/sec (720p), $0.15/sec (1080p)
- [Wan 2.5 Image-to-Video](https://inference.sh/apps/falai/wan-2-5-i2v.md): $0.05-$0.15/sec, 480p: $0.05/sec, 720p: $0.10/sec, 1080p: $0.15/sec
- [Gemini Omni Flash](https://inference.sh/apps/google/gemini-omni-flash.md): $1.00/video
- [Veo 3.1](https://inference.sh/apps/google/veo-3-1.md): $0.20-$0.60/sec, 720p/1080p: $0.20 no audio, $0.40 with audio; 4K: $0.40 no audio, $0.60 with audio
- [Veo 3.1 Fast](https://inference.sh/apps/google/veo-3-1-fast.md): $0.08-$0.30/sec; no audio: 720p $0.08, 1080p $0.10, 4K $0.25; audio: 720p $0.10, 1080p $0.12, 4K $0.30
- [Veo 3.1 Lite](https://inference.sh/apps/google/veo-3-1-lite.md): $0.03–$0.05/sec (720p), $0.05–$0.08/sec (1080p)
- [HeyGen Avatar Video](https://inference.sh/apps/heygen/avatar-video.md): $0.05/sec
- [HeyGen Create Avatar](https://inference.sh/apps/heygen/create-avatar.md): $1.00/call
- [HeyGen Lip Sync](https://inference.sh/apps/heygen/lipsync.md): $0.033/sec speed, $0.067/sec precision
- [HeyGen Photo Video](https://inference.sh/apps/heygen/photo-video.md): $0.05/sec (720p/1080p), $0.067/sec (4K)
- [HeyGen Video Agent](https://inference.sh/apps/heygen/video-agent.md): $0.033/sec
- [HeyGen Video Translate](https://inference.sh/apps/heygen/video-translate.md): $0.033/sec (speed), $0.067/sec (precision), $0.033/sec (audio-only)
- [Inference Shell Extract Last Frame](https://inference.sh/apps/infsh/extract-last-frame.md): from $0.00000277/sec
- [HTML to Video](https://inference.sh/apps/infsh/html-to-video.md): from $0.00000277/sec
- [HeyGen Hyperframes Render](https://inference.sh/apps/infsh/hyperframes-render.md): from $0.00000277/sec
- [Inference Shell Media Merger](https://inference.sh/apps/infsh/media-merger.md): from $0.00000277/sec
- [Remotion Render](https://inference.sh/apps/infsh/remotion-render.md): from $0.00000277/sec
- [RIFE Video Interpolation](https://inference.sh/apps/infsh/rife-video-interpolation.md): GPU time, billed per millisecond
- [VideoSeal Watermarking](https://inference.sh/apps/infsh/videoseal.md): GPU time, billed per millisecond
- [Kling Avatar](https://inference.sh/apps/klingai/avatar.md): $0.056/sec (std) or $0.112/sec (pro)
- [Kling Lip Sync](https://inference.sh/apps/klingai/lip-sync.md): $0.014/sec, 5sec minimum
- [Kling Video O1](https://inference.sh/apps/klingai/video-o1.md): $0.084-$0.168/sec, std: $0.084-$0.126, pro: $0.112-$0.168, +50% with video input
- [Kling Video V2.5 Turbo](https://inference.sh/apps/klingai/video-v2-5.md): std: $0.21 (5s), $0.42 (10s) | pro: $0.35 (5s), $0.70 (10s)
- [Kling Video V2.6](https://inference.sh/apps/klingai/video-v2-6.md): $0.21–$1.68/video
- [Kling Video V3](https://inference.sh/apps/klingai/video-v3.md): $0.084-$0.42 per second (std $0.084/s, pro $0.112/s, 4K $0.42/s; +50% with audio)
- [MiniMax H3](https://inference.sh/apps/minimax/h3.md): $0.08/sec (768P), $0.13/sec (2K), first 5 images free, +$0.04/extra image
- [Mirage Avatar X](https://inference.sh/apps/mirage/avatar-x.md): $0.175/sec
- [Mirage Text Overlays](https://inference.sh/apps/mirage/text-overlays.md): from $0.00000277/sec
- [Mirage Video 1](https://inference.sh/apps/mirage/video-1.md): $0.175/sec
- [Mirage Video Captions](https://inference.sh/apps/mirage/video-captions.md): from $0.00000277/sec
- [PixVerse Avatar](https://inference.sh/apps/pixverse/avatar.md): $0.025–$0.10/sec (360p–1080p), ~$1.80/24sec 720p
- [PixVerse C1](https://inference.sh/apps/pixverse/c1.md): from $0.00000277/sec
- [PixVerse Extend](https://inference.sh/apps/pixverse/extend.md): $0.025–$0.115/video (360p–1080p, no audio/audio)
- [PixVerse Fusion](https://inference.sh/apps/pixverse/fusion.md): $0.12/sec
- [PixVerse Lip Sync](https://inference.sh/apps/pixverse/lip-sync.md): $0.02/sec (external audio), $0.02/15 bytes (TTS)
- [PixVerse Modify](https://inference.sh/apps/pixverse/modify.md): $0.04/sec (360p), $0.05/sec (540p), $0.06/sec (720p)
- [PixVerse V6](https://inference.sh/apps/pixverse/v6.md): $0.025–$0.115/sec, varies by resolution and audio
- [P-Video](https://inference.sh/apps/pruna/p-video.md): 720p: $0.02/sec ($0.005/sec draft) | 1080p: $0.04/sec ($0.01/sec draft)
- [P-Video-Avatar](https://inference.sh/apps/pruna/p-video-avatar.md): 720p: $0.025/sec | 1080p: $0.045/sec
- [P-Video-Edit](https://inference.sh/apps/pruna/p-video-edit.md): $0.025-$0.045/sec output video; draft: $0.025/sec, standard: $0.045/sec
- [P-Video-Replace](https://inference.sh/apps/pruna/p-video-replace.md): $0.03/sec (720p) or $0.06/sec (1080p)
- [Pruna Wan Image-to-Video](https://inference.sh/apps/pruna/wan-i2v.md): $0.05/video (480p), $0.11/video (720p)
- [Pruna Wan Text-to-Video](https://inference.sh/apps/pruna/wan-t2v.md): 480p: $0.05/video, 720p: $0.10/video
- [Runway Act-Two](https://inference.sh/apps/runway/act-two.md): $0.05/sec
- [Runway Aleph 2.0](https://inference.sh/apps/runway/aleph-2.md): $0.28/sec
- [Runway Gen-4.5](https://inference.sh/apps/runway/gen-4-5.md): $0.12/sec
- [Runway Gen-4 Turbo](https://inference.sh/apps/runway/gen-4-turbo.md): $0.05/sec
- [Topaz Astra](https://inference.sh/apps/topaz/astra.md): $0.0714/credit
- [Topaz Denoise](https://inference.sh/apps/topaz/denoise.md): $0.0714/credit
- [Topaz Frame Interpolation](https://inference.sh/apps/topaz/frame-interpolation.md): $0.0714/credit
- [Topaz Proteus](https://inference.sh/apps/topaz/proteus.md): $0.0714/credit
- [Topaz Starlight](https://inference.sh/apps/topaz/starlight.md): $0.0714/credit
- [Topaz Video Upscale](https://inference.sh/apps/topaz/video-upscale.md): from $0.00000277/sec
- [Topaz Video Utilities](https://inference.sh/apps/topaz/video-utilities.md): $0.0714/credit
- [VEED Subtitles](https://inference.sh/apps/veed/subtitles.md): $0.05/run (basic), $0.10/run (dynamic)
- [Grok Video Extender](https://inference.sh/apps/xai/grok-extend-video.md): $0.002/input image, $0.01/sec of input video, $0.05/sec output
- [Grok Imagine Video](https://inference.sh/apps/xai/grok-imagine-video.md): $0.002/input image, $0.01/sec input video; output: $0.05/sec (480p), $0.07/sec (720p)
- [Grok Imagine Video 1.5](https://inference.sh/apps/xai/grok-imagine-video-1-5.md): $0.08/sec 480p, $0.14/sec 720p, $0.25/sec 1080p; $0.01/input image
- [Grok Reference Video](https://inference.sh/apps/xai/grok-reference-video.md): $0.002/image, $0.01/video, $0.05/sec

### audio

- [ElevenLabs Dubbing](https://inference.sh/apps/elevenlabs/dubbing.md): $0.33/min (watermark), $0.50/min (no watermark)
- [Eleven Flash v2.5](https://inference.sh/apps/elevenlabs/eleven-flash-v2-5.md): $0.04/1K characters
- [Eleven Multilingual v2](https://inference.sh/apps/elevenlabs/eleven-multilingual-v2.md): $0.08/1K characters
- [Eleven v3](https://inference.sh/apps/elevenlabs/eleven-v3.md): $0.08/1K characters
- [Eleven v4](https://inference.sh/apps/elevenlabs/eleven-v4.md): $0.08/1K characters
- [Eleven v4 Turbo](https://inference.sh/apps/elevenlabs/eleven-v4-turbo.md): $0.04/1K characters
- [ElevenLabs Forced Alignment](https://inference.sh/apps/elevenlabs/forced-alignment.md): $0.48/hr audio
- [ElevenLabs Music](https://inference.sh/apps/elevenlabs/music.md): $0.15/min
- [ElevenLabs Sound Effects](https://inference.sh/apps/elevenlabs/sound-effects.md): $0.12/min
- [ElevenLabs Speech to Text](https://inference.sh/apps/elevenlabs/stt.md): $0.22-$0.39/hr (Scribe v2: $0.22/hr, Realtime: $0.39/hr)
- [ElevenLabs Text to Dialogue](https://inference.sh/apps/elevenlabs/text-to-dialogue.md): $0.05/1K chars (Flash/Turbo), $0.10/1K chars (Multilingual v2/v3)
- [ElevenLabs Text to Speech](https://inference.sh/apps/elevenlabs/tts.md): $0.10/1K chars (v2), $0.08/1K chars (v4), $0.04/1K chars (v4 Turbo), $0.05/1K chars (Flash/Turbo)
- [ElevenLabs Voice Changer](https://inference.sh/apps/elevenlabs/voice-changer.md): $0.12/min
- [ElevenLabs Voice Clone](https://inference.sh/apps/elevenlabs/voice-clone.md): $0.10/clone
- [ElevenLabs Voice Design](https://inference.sh/apps/elevenlabs/voice-design.md): $0.10/design
- [ElevenLabs Voice Isolator](https://inference.sh/apps/elevenlabs/voice-isolator.md): $0.12/min
- [ElevenLabs Voice Remix](https://inference.sh/apps/elevenlabs/voice-remix.md): $0.10/remix
- [Dia TTS](https://inference.sh/apps/falai/dia-tts.md): $0.04/K chars
- [Kokoro TTS](https://inference.sh/apps/falai/kokoro-tts.md): $0.02/1K chars
- [Fish Audio Drama 3](https://inference.sh/apps/fish-audio/drama-3.md): $50.00/1M UTF-8 bytes
- [HeyGen Text to Speech](https://inference.sh/apps/heygen/text-to-speech.md): $0.0007/sec
- [HeyGen Instant Voice Clone](https://inference.sh/apps/heygen/voice-clone.md): $0.0007/sec audio (clone-only runs: free)
- [Audio-X Generator](https://inference.sh/apps/infsh/audio-x.md): GPU time, billed per millisecond
- [Chatterbox TTS](https://inference.sh/apps/infsh/chatterbox.md): GPU time, billed per millisecond
- [Dia TTS](https://inference.sh/apps/infsh/dia-tts.md): from $0.00000277/sec
- [DiffRhythm Song Generator](https://inference.sh/apps/infsh/diffrythm.md): GPU time, billed per millisecond
- [DramaBox Text-to-Speech](https://inference.sh/apps/infsh/dramabox.md): GPU time, billed per millisecond
- [Higgs Audio](https://inference.sh/apps/infsh/higgs-audio.md): GPU time, billed per millisecond
- [Kokoro TTS](https://inference.sh/apps/infsh/kokoro-tts.md): from $0.00055833/sec
- [OmniVoice TTS](https://inference.sh/apps/infsh/omnivoice.md): GPU time, billed per millisecond
- [Inworld Speech to Text](https://inference.sh/apps/inworld/speech-to-text.md): $0.35/hr of audio
- [Inworld TTS 1.5 Max](https://inference.sh/apps/inworld/text-to-speech-1-5-max.md): $35.00/M chars
- [Inworld TTS 1.5 Mini](https://inference.sh/apps/inworld/text-to-speech-1-5-mini.md): $25.00/M chars
- [Inworld TTS-2](https://inference.sh/apps/inworld/text-to-speech-2.md): $35.00/M chars
- [Inworld Voice Cloning](https://inference.sh/apps/inworld/voice-cloning.md): from $0.00000277/sec
- [Inworld Voice Design](https://inference.sh/apps/inworld/voice-design.md): from $0.00000277/sec
- [Kling Video to Audio](https://inference.sh/apps/klingai/video-to-audio.md): $0.0088/video
- [MiniMax Music 3.0](https://inference.sh/apps/minimax/music-3-0.md): $0.15/track
- [MiniMax Music Cover](https://inference.sh/apps/minimax/music-cover.md): $0.15/cover
- [MiniMax Speech 2.8 HD](https://inference.sh/apps/minimax/speech-2-8-hd.md): $0.0001/char
- [MiniMax Speech 2.8 Turbo](https://inference.sh/apps/minimax/speech-2-8-turbo.md): $60.00/M chars
- [GPT Transcribe](https://inference.sh/apps/openai/gpt-transcribe.md): $0.0045/min of audio for files, $0.017/min for realtime
- [Grok Speech to Text](https://inference.sh/apps/xai/grok-stt.md): $0.10/hr of audio for files, $0.20/hr for realtime
- [Grok TTS](https://inference.sh/apps/xai/grok-tts.md): $15.00/M chars
- [Grok Voice](https://inference.sh/apps/xai/grok-voice.md): $0.08/min session audio + $0.004/text input

### 3d

- [HunyuanImage-to-3D](https://inference.sh/apps/infsh/hunyuan-image-to-3d.md): GPU time, billed per millisecond
- [Rodin 3D Generator](https://inference.sh/apps/infsh/rodin-3d-generator.md): from $0.00000277/sec

### text

- [Archive Download](https://inference.sh/apps/archive/download.md): from $0.00000277/sec
- [Archive Metadata](https://inference.sh/apps/archive/metadata.md): from $0.00000277/sec
- [Archive Search](https://inference.sh/apps/archive/search.md): from $0.00000277/sec
- [Wayback Machine Availability Check](https://inference.sh/apps/archive/wayback.md): from $0.00000277/sec
- [arXiv Paper](https://inference.sh/apps/arxiv/paper.md): from $0.00000277/sec
- [arXiv Search](https://inference.sh/apps/arxiv/search.md): from $0.00000277/sec
- [bioRxiv Paper](https://inference.sh/apps/biorxiv/paper.md): from $0.00000277/sec
- [bioRxiv Search](https://inference.sh/apps/biorxiv/search.md): from $0.00000277/sec
- [Bria Structured Prompt](https://inference.sh/apps/bria/structured-prompt.md): $0.02/image
- [Ceramic AI Search](https://inference.sh/apps/ceramic/search.md): $0.00005/query
- [ChemRxiv Paper](https://inference.sh/apps/chemrxiv/paper.md): from $0.00000277/sec
- [ChemRxiv Search](https://inference.sh/apps/chemrxiv/search.md): from $0.00000277/sec
- [Exa Answer](https://inference.sh/apps/exa/answer.md): $0.005/query (≤10 results), $0.001/extra result, $0.001/page summary
- [Exa Extract](https://inference.sh/apps/exa/extract.md): $0.001/page; +$0.001/page with summary
- [Exa Search](https://inference.sh/apps/exa/search.md): $0.007/search (includes up to 10 results), $0.001/additional result beyond 10, $0.001/AI page summary when enabled
- [Fastly Domain Search](https://inference.sh/apps/fastly/domain-search.md): suggest/run: $0.00001 per call; status: $0.001/domain (precise) or $0.0005/domain (estimated)
- [DeepSeek OCR](https://inference.sh/apps/infsh/deepseek-ocr.md): GPU time, billed per millisecond
- [DeepSeek OCR 2](https://inference.sh/apps/infsh/deepseek-ocr-2.md): GPU time, billed per millisecond
- [Harrier OSS v1 Text Embeddings](https://inference.sh/apps/infsh/harrier-oss-v1.md): GPU time, billed per millisecond
- [Markdown to Word Converter](https://inference.sh/apps/infsh/markdown-to-word.md): from $0.00000277/sec
- [Inference Shell Python Executor](https://inference.sh/apps/infsh/python-executor.md): from $0.00000277/sec
- [Tavily Extract](https://inference.sh/apps/tavily/extract.md): $0.0016/URL basic, $0.0032/URL advanced
- [Tavily Search Assistant](https://inference.sh/apps/tavily/search-assistant.md): $0.008/search basic, $0.016/search advanced
- [You.com Contents](https://inference.sh/apps/you/contents.md): Pass-through at upstream cost
- [You.com Finance Research](https://inference.sh/apps/you/finance-research.md): $0.11/request
- [You.com Deep Research](https://inference.sh/apps/you/research.md): $0.001–$0.15/call (pass-through)
- [You.com Web Search](https://inference.sh/apps/you/search.md): $0.005/call

### chat

- [Claude Fable 5](https://inference.sh/apps/anthropic/claude-fable-5.md): $10.00/M input, $50.00/M output
- [Claude Fable 5.1](https://inference.sh/apps/anthropic/claude-fable-5-1.md): $10.00/M input, $50.00/M output, $0.25/M cache read, $12.50/M cache write
- [Claude Haiku 4.5](https://inference.sh/apps/anthropic/claude-haiku-4-5.md): $1.00/M input, $5.00/M output
- [Claude Haiku 5.5](https://inference.sh/apps/anthropic/claude-haiku-5-5.md): $0.10/M input, $0.50/M output (<=100K tokens); $0.50/M input, $2.50/M output (>100K)
- [Claude Mythos 5](https://inference.sh/apps/anthropic/claude-mythos-5.md): $10.00/M input, $50.00/M output, $1.00/M cache read, $12.50/M cache write
- [Claude Opus 4.6](https://inference.sh/apps/anthropic/claude-opus-4-6.md): $5.00/M input, $25.00/M output
- [Claude Opus 4.7](https://inference.sh/apps/anthropic/claude-opus-4-7.md): $5.00/M input, $25.00/M output
- [Claude Opus 4.8](https://inference.sh/apps/anthropic/claude-opus-4-8.md): $5.00/M input, $25.00/M output
- [Claude Opus 5](https://inference.sh/apps/anthropic/claude-opus-5.md): $5.00/M input, $25.00/M output
- [Claude Opus 5.5](https://inference.sh/apps/anthropic/claude-opus-5-5.md): $4.00/M input, $20.00/M output, $0.20/M cache read, $5.00/M cache write
- [Claude Sonnet 4.5](https://inference.sh/apps/anthropic/claude-sonnet-4-5.md): $3.00/M input, $15.00/M output
- [Claude Sonnet 4.6](https://inference.sh/apps/anthropic/claude-sonnet-4-6.md): $3.00/M input, $15.00/M output, $0.30/M cache read, $3.75/M cache write
- [Claude Sonnet 5](https://inference.sh/apps/anthropic/claude-sonnet-5.md): $2.00/M input, $10.00/M output
- [Claude Sonnet 5.5](https://inference.sh/apps/anthropic/claude-sonnet-5-5.md): $2.00/M input, $10.00/M output, $0.20/M cache read, $2.50/M cache write
- [Gemini 2.5 Flash](https://inference.sh/apps/google/gemini-2-5-flash.md): $0.30/M input, $2.50/M output
- [Gemini 2.5 Flash-Lite](https://inference.sh/apps/google/gemini-2-5-flash-lite.md): $0.10/M input, $0.40/M output
- [Gemini 2.5 Pro](https://inference.sh/apps/google/gemini-2-5-pro.md): $1.25/M input, $10.00/M output
- [Gemini 3.5 Flash-Lite](https://inference.sh/apps/google/gemini-3-5-flash-lite.md): $0.30/M input, $2.50/M output
- [Gemini 3.6 Flash](https://inference.sh/apps/google/gemini-3-6-flash.md): $1.50/M input, $7.50/M output
- [Gemini 3.7 Flash](https://inference.sh/apps/google/gemini-3-7-flash.md): $1.50/M input, $7.50/M output
- [Gemini 3.8 Flash](https://inference.sh/apps/google/gemini-3-8-flash.md): $1.50/M input, $7.50/M output
- [Gemini 4 Argon](https://inference.sh/apps/google/gemini-4-argon.md): $2.00/M input, $10.00/M output
- [Gemma 3n E4B Instruct](https://inference.sh/apps/infsh/gemma-3n-e4b-it.md): GPU time, billed per millisecond
- [Magistral Small 2506](https://inference.sh/apps/infsh/magistral-small-2506.md): GPU time, billed per millisecond
- [Mistral Small 3.2 24B Instruct](https://inference.sh/apps/infsh/mistral-small-3-2-24b-it-2506.md): GPU time, billed per millisecond
- [Qwen3 30B A3B](https://inference.sh/apps/infsh/qwen3-30b-a3b.md): GPU time, billed per millisecond
- [DeepSeek V4.1 Flash](https://inference.sh/apps/melious/deepseek-v4-1-flash.md): $0.2273/M input, $0.0114/M cached input, $1.1367/M output
- [DeepSeek V4.1 Flash 1017](https://inference.sh/apps/melious/deepseek-v4-1-flash-1017.md): $0.341/M input, $0.0341/M cached input, $1.364/M output
- [DeepSeek V4 Flash 0731](https://inference.sh/apps/melious/deepseek-v4-flash-0731.md): $0.1137/M input, $0.0227/M cached input, $0.2842/M output
- [GLM 5.2](https://inference.sh/apps/melious/glm-5-2.md): $1.1367/M input, $0.2842/M cached input, $4.5468/M output
- [GLM 5.3](https://inference.sh/apps/melious/glm-5-3.md): $1.1367/M input, $0.2273/M cached input, $3.4101/M output
- [GLM 5.3 Flash](https://inference.sh/apps/melious/glm-5-3-flash.md): $0.1137/M input, $0.0227/M cached input, $0.4547/M output
- [Kimi K3](https://inference.sh/apps/melious/kimi-k3.md): $3.1828/M input, $0.7957/M cached input, $15.9138/M output
- [MiniMax M3](https://inference.sh/apps/melious/minimax-m3.md): $0.4547/M input, $0.1137/M cached input, $2.2734/M output
- [Qwen 3.6 27B](https://inference.sh/apps/melious/qwen3-6-27b.md): $0.2273/M input, $1.364/M output
- [Muse Wonder 1.0](https://inference.sh/apps/meta/muse-wonder-1-0.md): $4.00/M input, $0.20/M cached, $20.00/M output
- [MiniMax M2.7](https://inference.sh/apps/minimax/m-2-7.md): $0.30/M input, $1.20/M output
- [MiniMax M2.7 Highspeed](https://inference.sh/apps/minimax/m-2-7-highspeed.md): $0.30/M input, $1.20/M output
- [MiniMax M3](https://inference.sh/apps/minimax/m3.md): $0.30/M input, $1.20/M output
- [GPT-5.6 Luna](https://inference.sh/apps/openai/gpt-5-6-luna.md): $0.20/M input, $0.02/M cached input, $1.20/M output
- [GPT-5.6 Sol](https://inference.sh/apps/openai/gpt-5-6-sol.md): $4.00/M input, $0.40/M cached input, $20.00/M output
- [GPT-5.6 Terra](https://inference.sh/apps/openai/gpt-5-6-terra.md): $2.00/M input, $0.20/M cached input, $12.00/M output
- [GPT-6.1 Sol](https://inference.sh/apps/openai/gpt-6-1-sol.md): $2.00/M input, $0.10/M cached, $10.00/M output
- [GPT-6 Astra](https://inference.sh/apps/openai/gpt-6-astra.md): $10.00/M input, $1.00/M cached, $50.00/M output
- [GPT-6 Luna](https://inference.sh/apps/openai/gpt-6-luna.md): $0.10/M input, $0.01/M cached, $0.50/M output
- [GPT-6 Sol](https://inference.sh/apps/openai/gpt-6-sol.md): $2.00/M input, $0.20/M cached input, $10.00/M output
- [Claude Haiku 4.5](https://inference.sh/apps/openrouter/claude-haiku-45.md): $1.00/M input ($0.10/M cached, $1.25/M cache write), $5.00/M output (min $0.002)
- [Claude Opus 4.5](https://inference.sh/apps/openrouter/claude-opus-45.md): $5.00/M input ($0.50/M cached, $6.25/M cache write), $25.00/M output
- [Claude Opus 4.6](https://inference.sh/apps/openrouter/claude-opus-46.md): $5.00/M input ($0.50/M cached, $6.25/M cache write), $25.00/M output
- [Claude Opus 4.7](https://inference.sh/apps/openrouter/claude-opus-47.md): $5.00/M input ($0.50/M cached, $6.25/M write), $25.00/M output
- [Claude Sonnet 4.5](https://inference.sh/apps/openrouter/claude-sonnet-45.md): Priced at $3/M input ($0.3/M cached read, $3.75/M cache write), $15/M output tokens
- [Claude Sonnet 4.6](https://inference.sh/apps/openrouter/claude-sonnet-46.md): $3.00/M input ($0.30/M cached, $3.75/M write), $15.00/M output
- [DeepSeek V3.2](https://inference.sh/apps/openrouter/deepseek-v32.md): $0.252/M input tokens, $0.378/M output tokens
- [Gemini 3.1 Pro Preview](https://inference.sh/apps/openrouter/gemini-3-1-pro-preview.md): $2.00/M input ($0.20/M cached read, $0.375/M cache write), $12.00/M output; >200K: $4.00/$0.40/$0.75/M in, $18.00/M out
- [Gemini 3 Flash Preview](https://inference.sh/apps/openrouter/gemini-3-flash-preview.md): $0.50/M input ($0.05/M cached, $0.0833/M write), $3.00/M output
- [Gemini 3 Pro Preview](https://inference.sh/apps/openrouter/gemini-3-pro-preview.md): $2.00/M input tokens, $12.00/M output tokens
- [GLM-4.6](https://inference.sh/apps/openrouter/glm-46.md): $0.43/M input tokens, $1.74/M output tokens
- [GLM 5.2](https://inference.sh/apps/openrouter/glm-5-2.md): $1.00/M input, $4.00/M output
- [GPT-OSS Safeguard 20B](https://inference.sh/apps/openrouter/gpt-oss-safeguard-20b.md): $0.075/M input ($0.0375/M cached), $0.30/M output
- [Hunyuan Turbos Hy3 Preview](https://inference.sh/apps/openrouter/hy3-preview.md): $0.18/M input ($0.06/M cached), $0.60/M output
- [Kimi K2](https://inference.sh/apps/openrouter/kimi-k2.md): $0.60/M input ($0.60/M cached), $2.50/M output
- [Kimi K2 Thinking](https://inference.sh/apps/openrouter/kimi-k2-thinking.md): $0.60/M input ($0.15/M cached), $2.50/M output
- [Kimi K2.5](https://inference.sh/apps/openrouter/kimi-k25.md): $0.4/M input tokens, $1.9/M output tokens
- [Kimi K2.6](https://inference.sh/apps/openrouter/kimi-k26.md): $0.75/M input, $3.50/M output
- [Qwen3 32B](https://inference.sh/apps/openrouter/qwen3-32b.md): $0.08/M input, $0.28/M output
- [Grok 4.3](https://inference.sh/apps/xai/grok-4-3.md): $1.25/M input, $0.20/M cached, $2.50/M output (2x at 200k+ prompt tokens)
- [Grok 4.7](https://inference.sh/apps/xai/grok-4-7.md): $2.00/M input, $0.50/M cached, $6.00/M output (2x at 200k+ prompt tokens)
- [Grok Build 0.1](https://inference.sh/apps/xai/grok-build-0-1.md): $1.00/M input, $0.20/M cached, $2.00/M output (2x at 200k+ prompt tokens)

### decision

- [JEV-27B-VL](https://inference.sh/apps/autotrust/jev-27b-vl.md): free for a limited time
- [d1-3B](https://inference.sh/apps/liquid/d1-3b.md): GPU time, billed per second
- [d1-omni-600M](https://inference.sh/apps/liquid/d1-omni-600m.md): GPU time, billed per second
- [OpenAI Decisions](https://inference.sh/apps/openai/decisions.md): $0.10/M input, output free
- [Perplexity Decider v1.1 27B](https://inference.sh/apps/perplexity/decider-v1-1-27b.md): GPU time, billed per second
- [Jev](https://inference.sh/apps/typesafe/jev.md): $0.042/M input, output free
- [Decision 3.0 d3 27B](https://inference.sh/apps/vllm-sr/d3.md): GPU time, billed per second
- [Decision 3.0 d3-edge 0.6B](https://inference.sh/apps/vllm-sr/d3-edge.md): GPU time, billed per second
- [Decision 3.0 d3-flash 9B](https://inference.sh/apps/vllm-sr/d3-flash.md): GPU time, billed per second
- [Decision 3.0 d3-lite 0.8B](https://inference.sh/apps/vllm-sr/d3-lite.md): GPU time, billed per second
- [Decision 3.0 d3-mini 4B](https://inference.sh/apps/vllm-sr/d3-mini.md): GPU time, billed per second
- [Decision 3.0 d3-nano 2B](https://inference.sh/apps/vllm-sr/d3-nano.md): GPU time, billed per second
- [Decision 2.0 Eos 0.8B](https://inference.sh/apps/vllm-sr/decision-2-0-eos-0-8b.md): GPU time, billed per second
- [Decision 2.0 Kai 0.6B](https://inference.sh/apps/vllm-sr/decision-2-0-kai-0-6b.md): GPU time, billed per second
- [Decision 2.0 Lux 9B](https://inference.sh/apps/vllm-sr/decision-2-0-lux-9b.md): GPU time, billed per second
- [Decision 2.0 Nox 4B](https://inference.sh/apps/vllm-sr/decision-2-0-nox-4b.md): GPU time, billed per second
- [Decision 2.0 Sol 2B](https://inference.sh/apps/vllm-sr/decision-2-0-sol-2b.md): GPU time, billed per second
- [Decision 2.0 Vega 27B](https://inference.sh/apps/vllm-sr/decision-2-0-vega-27b.md): GPU time, billed per second

### social

- [X Article Publisher](https://inference.sh/apps/x/article-publish.md): $0.15-$0.30/task, 1 call (draft only) or 2 calls (draft + publish)
- [X Add Bookmark](https://inference.sh/apps/x/bookmark-add.md): $0.15/call
- [X Remove Bookmark](https://inference.sh/apps/x/bookmark-remove.md): $0.15/call
- [X Bookmarks](https://inference.sh/apps/x/bookmarks-list.md): $0.15/call
- [X Direct Messages](https://inference.sh/apps/x/dm-list.md): $0.15/call
- [X Direct Message Send](https://inference.sh/apps/x/dm-send.md): $0.15/call
- [X Followers List](https://inference.sh/apps/x/followers-list.md): $0.15/call
- [X Following List](https://inference.sh/apps/x/following-list.md): $0.15/call
- [X Post Analytics](https://inference.sh/apps/x/post-analytics.md): $0.15/call
- [X Post Create](https://inference.sh/apps/x/post-create.md): $0.15/call
- [X Post Delete](https://inference.sh/apps/x/post-delete.md): $0.15/call
- [X Post Lookup](https://inference.sh/apps/x/post-get.md): $0.15/call
- [X Post Like](https://inference.sh/apps/x/post-like.md): $0.15/call
- [X Post Likers](https://inference.sh/apps/x/post-likers.md): $0.15/call
- [X Post Quotes](https://inference.sh/apps/x/post-quotes.md): $0.15/call
- [X Post Retweet](https://inference.sh/apps/x/post-retweet.md): $0.15/call
- [X Post Search](https://inference.sh/apps/x/post-search.md): $0.15/call
- [X Thread Composer](https://inference.sh/apps/x/post-thread.md): $0.15/call
- [X Timeline Probe](https://inference.sh/apps/x/probe-timeline.md): $0.15/call
- [X Trending Topics](https://inference.sh/apps/x/trends.md): $0.15/call
- [X User Follow](https://inference.sh/apps/x/user-follow.md): $0.15/call
- [X User Profile](https://inference.sh/apps/x/user-get.md): $0.15/call
- [X Mentions](https://inference.sh/apps/x/user-mentions.md): $0.15/call
- [X User Posts](https://inference.sh/apps/x/user-posts.md): $0.15/call
- [X Home Timeline](https://inference.sh/apps/x/user-timeline.md): $0.15/call

### utilities

- [Inference Shell](https://inference.sh/apps/infsh/shell.md): from $0.00000277/sec

### other

- [ArcFace Identity Similarity](https://inference.sh/apps/eval/arcface.md): from $0.00055833/sec
- [CLIPScore](https://inference.sh/apps/eval/clipscore.md): from $0.00055833/sec
- [FID Score](https://inference.sh/apps/eval/fid-score.md): from $0.00055833/sec
- [PickScore](https://inference.sh/apps/eval/pickscore.md): from $0.00055833/sec
- [Google Analytics](https://inference.sh/apps/google/analytics.md): from $0.00000277/sec
- [Google Calendar](https://inference.sh/apps/google/calendar.md): from $0.00000277/sec
- [Google Docs](https://inference.sh/apps/google/docs.md): from $0.00000277/sec
- [Google Drive](https://inference.sh/apps/google/drive.md): from $0.00000277/sec
- [Gmail](https://inference.sh/apps/google/gmail.md): from $0.00000277/sec
- [Google Search Console](https://inference.sh/apps/google/search-console.md): from $0.00000277/sec
- [Google Sheets](https://inference.sh/apps/google/sheets.md): from $0.00000277/sec
- [Google Slides](https://inference.sh/apps/google/slides.md): from $0.00000277/sec
- [Agent Browser](https://inference.sh/apps/infsh/agent-browser.md): from $0.00000277/sec
- [FLUX.2 [klein]](https://inference.sh/apps/infsh/flux-2-klein.md): GPU time, billed per millisecond
- [Get Item in List](https://inference.sh/apps/infsh/get-item-in-list.md): from $0.00000277/sec
- [HTML to Image](https://inference.sh/apps/infsh/html-to-image.md): from $0.00000277/sec
- [HTTP Request](https://inference.sh/apps/infsh/http.md): from $0.00000277/sec
- [Text Templating](https://inference.sh/apps/infsh/text-templating.md): from $0.00000277/sec
- [Inference Shell Video Audio Merger](https://inference.sh/apps/infsh/video-audio-merger.md): from $0.00000277/sec
- [Phota Identity Training](https://inference.sh/apps/phota/train.md): $2.90/profile

cloud gpus are billed by the hour: https://inference.sh/gpus

## faq

### how does pricing work?

subscribe for monthly credits and higher limits, or pay as you go. each app call costs based on compute time + app fee.

### what happens when i run out of included credits?

you can keep running tasks on a pay-as-you-go basis. add credits anytime — no surprises, you set spending limits.

### can i change plans later?

yes, upgrade or downgrade anytime. changes are prorated — you only pay for what you use.

### do credits roll over?

included credits are deposited each billing period and carry forward. credits expire one year from when they were added.

### what is BYOK?

bring your own keys. connect your own API keys for OpenAI, Anthropic, Google, etc. route through your existing cloud credits while using inference shell for orchestration.

### what payment methods do you accept?

we accept credit/debit cards, bank transfers, and stablecoins — all processed securely via Stripe. enterprise customers can also pay by invoice.