AI Model Leaderboard
Every model you can run on Railwail right now, by category: quality from the public Arena leaderboard, the live price of a default call, the context window and run times measured on our own jobs. Scores only where the arena rates exactly the model we run.
Arena scores published Sep 22, 2026Run times from Railwail jobs, last 90 days
- Models you can run
- 274
- Labs
- 34
- Categories
- 9
Today’s record holders
Best models by category
Quality from the public Arena, prices from our pricing rules. Open a category to sort by quality, price or value.
Text & chat
16 of 30 rated- Best quality
- Gemini 3.1 ProArena 1,487
- Cheapest
- Granite Code 8B$0.12 / 1M tokens
- Best value
- Gemini 3.1 Pro8 pts/$
Image generation
22 of 66 rated- Best quality
- Qwen Image 3 ProArena 1,255
- Cheapest
- Stable Diffusion XL≈ $0.0015/run
- Best value
- Nano Banana 2 Lite3,828 pts/$
Image editing
7 of 7 rated- Best quality
- Grok Imagine ImageArena 1,329
- Cheapest
- Grok Imagine Image$0.024/image
- Best value
- Grok Imagine Image3,679 pts/$
Video generation
13 of 27 rated- Best quality
- Google Veo 3.1Arena 1,362
- Cheapest
- LTX-Video (Lightricks)≈ $0.0229/run
- Best value
- Grok Imagine Video504 pts/$
Image to video
14 of 14 rated- Best quality
- Grok Imagine VideoArena 1,415
- Cheapest
- Seedance Lite$0.0432/s
- Best value
- Grok Imagine Video556 pts/$
9 models
Filter by labTap a lab to filter every board.
Language models
30Chat, reasoning and code models billed per token. Sorted by Arena score, highest first; models without a rating follow by price.
| Actions | ||||||
|---|---|---|---|---|---|---|
Claude Opus 4.7 Arena 1494 · $30.00/1M out · 1M ctx | 1494 | $6.00/1M in$6.00 | $30.00 | 1M | · | Try |
Gemini 3.1 Pro Arena 1487 · $14.40/1M out · 1M ctx | 1487 | $2.40/1M in$2.40 | $14.40 | 1M | · | Try |
GPT-5.5 Arena 1476 · $36.00/1M out · 400K ctx | 1476 | $6.00/1M in$6.00 | $36.00 | 400K | · | Try |
Gemini 3 Flash Arena 1474 · $3.60/1M out · 1M ctx | 1474 | $0.60/1M in$0.60 | $3.60 | 1M | · | Try |
Claude Opus 4.8 Arena 1473 · $30.00/1M out · 1M ctx · median 3.2 s | 1473 | $6.00/1M in$6.00 | $30.00 | 1M | 3.2 s198 runs | Try |
Claude Sonnet 4.6 Arena 1473 · $18.00/1M out · 1M ctx | 1473 | $3.60/1M in$3.60 | $18.00 | 1M | · | Try |
GPT-5.4 Arena 1466 · $18.00/1M out · 1.1M ctx | 1466 | $3.00/1M in$3.00 | $18.00 | 1.1M | · | Try |
Gemini 2.5 Pro Arena 1446 · $12.00/1M out · 1M ctx | 1446 | $1.50/1M in$1.50 | $12.00 | 1M | · | Try |
GPT-5.1 Arena 1439 · $12.00/1M out · 400K ctx | 1439 | $1.50/1M in$1.50 | $12.00 | 400K | · | Try |
OpenAI o3 Arena 1432 · $9.60/1M out · 200K ctx | 1432 | $2.40/1M in$2.40 | $9.60 | 200K | · | Try |
| Claude Haiku 4.5 Anthropic | $1.20/1M in | |||||
| GPT-4.1 OpenAI | $2.40/1M in | |||||
| OpenAI o4-mini OpenAI | $1.32/1M in | |||||
| o3-mini OpenAI | $1.32/1M in | |||||
| GPT-4o OpenAI | $3.00/1M in | |||||
| GPT-4o Mini OpenAI | $0.18/1M in | |||||
| Granite Code 8B IBM | $0.060/1M in | |||||
| GPT-6 Luna OpenAI | $0.12/1M in | |||||
| Granite Code 20B IBM | $0.12/1M in | |||||
| GPT-5.4 Nano OpenAI | $0.24/1M in | |||||
| GPT-5 Mini OpenAI | $0.30/1M in | |||||
| DeepSeek V4 Flash DeepSeek | $0.36/1M in | |||||
| DeepSeek V4.1 Flash DeepSeek | $0.36/1M in | |||||
| GPT-5.4 Mini OpenAI | $0.90/1M in | |||||
| DeepSeek V4 Pro DeepSeek | $1.584/1M in | |||||
| Claude Sonnet 5 Anthropic | $2.40/1M in | |||||
| GPT-6 Sol OpenAI | $2.40/1M in | |||||
| Claude Opus 5.5 Anthropic | $4.80/1M in | |||||
| Claude Fable 5.1 Anthropic | $12.00/1M in | |||||
| GPT-6 Astra OpenAI | $12.00/1M in |
Arena scores: Text Arena leaderboard by LMArena, published Sep 13, 2026, CC BY 4.0.Ranked by quality, price and value →
A usage column appears once 5 models have runs from 3 or more different accounts in 30 days.
Image generation & editing
83/134Text-to-image, editing, upscaling and background removal. Sorted by Arena score, highest first; models without a rating follow by price.
| Actions | ||||
|---|---|---|---|---|
Qwen Image 3 Pro Arena 1255 | 1255 | $0.048/image | · | Try |
Nano Banana 2 Lite Arena 1250 | 1250 | $0.0408/image | · | Try |
Ideogram V4 Quality Arena 1204 | 1204 | $0.12/image | · | Try |
Grok Imagine Image Arena 1171 | 1171 | $0.024/image | · | Try |
Recraft V4.1 Utility Pro Arena 1169 | 1169 | $0.30/image | · | Try |
Hunyuan Image 3 Arena 1151 | 1151 | $0.096/image | · | Try |
Nano Banana Arena 1150 | 1150 | $0.0468/image | · | Try |
Recraft V4.1 Pro Arena 1131 | 1131 | $0.30/image | · | Try |
Google Imagen 4 Arena 1129 | 1129 | $0.048/image | · | Try |
Qwen Image 2512 Arena 1125 | 1125 | $0.024/image | · | Try |
| Recraft V4 Recraft | $0.048/image | |||
| Flux Kontext Max Black Forest Labs | $0.096/image | |||
| Flux Kontext Pro Black Forest Labs | $0.048/image | |||
| Qwen Image Alibaba (Qwen) | $0.030/image | |||
| Ideogram v3 Quality Ideogram | $0.108/image | |||
| Photon Luma AI | $0.036/image | |||
| P Image Pruna AI | $0.0060/image | |||
| Gen4 Image Runway | $0.096/image | |||
| Recraft V3 Recraft | $0.048/image | |||
| FLUX 1.1 Pro Black Forest Labs | $0.048/image | |||
| Ideogram v2 Ideogram | $0.096/image | |||
| Stable Diffusion 3.5 Large Stability AI | $0.078/image | |||
| 851-Labs Background Remover Community | ≈ $0.00050/run | |||
| Remove Background (lucataco) Community | ≈ $0.00060/run | |||
| Remove Object (LaMa) Community | ≈ $0.00090/run | |||
| DDColor Community | ≈ $0.0012/run | |||
| Html To Image Community | $0.0012/image | |||
| Stable Diffusion XL Stability AI | ≈ $0.0015/run | |||
| Vectorizer (VTracer) Community | ≈ $0.0022/run | |||
| Real-ESRGAN 4x Community | $0.0024/image | |||
| SDXL Inpainting Community | ≈ $0.0026/run | |||
| GFPGAN v1.4 Tencent ARC | ≈ $0.0027/run | |||
| BiRefNet Background Removal Community | ≈ $0.0036/run | |||
| FLUX.1 [schnell] Black Forest Labs | $0.0036/image | |||
| FLUX.1 Redux Black Forest Labs | $0.0036/image | |||
| Consistent Character Community | ≈ $0.0038/run | |||
| InstructPix2Pix Community | ≈ $0.0039/run | |||
| CodeFormer Community | ≈ $0.0041/run | |||
| Rembg Community | ≈ $0.0047/run | |||
| Real-ESRGAN Anime 4x Community | ≈ $0.0051/run | |||
| Sticker Maker Community | ≈ $0.0055/run | |||
| Flux Fast Community | $0.0060/image | |||
| Hidream L1 Fast Community | $0.0060/image | |||
| PhotoMaker Tencent ARC | ≈ $0.0080/run | |||
| Swin2SR Community | ≈ $0.0088/run | |||
| Icons (SDXL Flat Pop) Community | ≈ $0.0094/run | |||
| Bringing Old Photos Back to Life Microsoft | ≈ $0.010/run | |||
| Face to Many Community | ≈ $0.0105/run | |||
| Image 01 MiniMax | $0.012/image | |||
| Photon Flash Luma AI | $0.012/image | |||
| Recraft Vectorize Recraft | $0.012/image | |||
| ControlNet Depth Community | ≈ $0.0144/run | |||
| SDXL Emoji Community | ≈ $0.0156/run | |||
| Janus Pro 7B DeepSeek | ≈ $0.0169/run | |||
| FLUX PuLID Community | ≈ $0.018/run | |||
| Lucid Origin Community | $0.0201/image | |||
| BRIA Remove Background Bria AI | $0.0216/image | |||
| Clarity Upscaler Community | ≈ $0.024/run | |||
| Hunyuan Image 2.1 Tencent | $0.024/image | |||
| Wan 2.2 Image Community | $0.024/image | |||
| Recraft 20B Recraft | $0.0264/image | |||
| IDM-VTON (Virtual Try-On) Community | ≈ $0.0277/run | |||
| IP-Adapter FaceID Plus v2 Community | ≈ $0.0277/run | |||
| Face to Sticker Community | ≈ $0.0289/run | |||
| Flux Krea Dev Black Forest Labs | $0.030/image | |||
| FLUX.1 [dev] Black Forest Labs | $0.030/image | |||
| FLUX.1 Canny [dev] Black Forest Labs | $0.030/image | |||
| FLUX.1 Depth [dev] Black Forest Labs | $0.030/image | |||
| FLUX.1 Kontext [dev] Black Forest Labs | $0.030/image | |||
| Ideogram V2A Turbo Ideogram | $0.030/image | |||
| Ideogram v3 Turbo Ideogram | $0.036/image | |||
| Qwen Image 3 Alibaba (Qwen) | $0.036/image | |||
| Qwen-Image-Edit Alibaba (Qwen) | $0.036/image | |||
| Seedream 4 ByteDance | $0.036/image | |||
| Wan 2.7 Image Alibaba (Wan) | $0.036/image | |||
| Wan 2.7 Image Pro Alibaba (Wan) | $0.036/image | |||
| LogoAI (SDXL Logo Generator) Community | ≈ $0.0372/run | |||
| Flux Dev Black Forest Labs | $0.0384/image | |||
| Qwen Image 2 Alibaba (Qwen) | $0.042/image | |||
| Seedream 5 Lite ByteDance | $0.042/image | |||
| Stable Diffusion 3 Stability AI | $0.042/image | |||
| Stable Diffusion 3.5 Medium Stability AI | $0.042/image | |||
| TRELLIS (3D) Community | ≈ $0.042/run | |||
| ESRGAN Classic Community | ≈ $0.0468/run | |||
| Fibo Bria AI | $0.048/image | |||
| FLUX.1 Fill [dev] Black Forest Labs | $0.048/image | |||
| Grok Imagine Image 2 xAI | $0.048/image | |||
| Ideogram V2A Ideogram | $0.048/image | |||
| Image 3.2 Bria AI | $0.048/image | |||
| Professional Headshot (FLUX Kontext) Black Forest Labs | $0.048/image | |||
| Recraft V4.1 Recraft | $0.048/image | |||
| Recraft V4.1 Utility Recraft | $0.048/image | |||
| Seedream 4.5 ByteDance | $0.048/image | |||
| Stable Diffusion 3.5 Large Turbo Stability AI | $0.048/image | |||
| Recraft 20B SVG Recraft | $0.0528/image | |||
| Magnific-Style Upscaler Community | ≈ $0.0589/run | |||
| FLUX.1 Canny Black Forest Labs | $0.060/image | |||
| FLUX.1 Depth Black Forest Labs | $0.060/image | |||
| FLUX.1 Fill Black Forest Labs | $0.060/image | |||
| Ideogram V2 Turbo Ideogram | $0.060/image | |||
| AuraFlow v0.3 Community | ≈ $0.0648/run | |||
| Flux Pro Black Forest Labs | $0.066/image | |||
| Ad Inpaint (Product Photo) Community | ≈ $0.0672/run | |||
| ControlNet Canny Community | ≈ $0.0697/run | |||
| Point-E Community | ≈ $0.0708/run | |||
| Flux 1.1 Pro Ultra Black Forest Labs | $0.072/image | |||
| Ideogram V3 Balanced Ideogram | $0.072/image | |||
| Ideogram V4 Balanced Ideogram | $0.072/image | |||
| Playground v2.5 (1024px Aesthetic) Playground AI | ≈ $0.0732/run | |||
| IC-Light (Product Relighting) Community | ≈ $0.0781/run | |||
| Nano Banana 2 Google DeepMind | $0.0804/image | |||
| InstantID Community | ≈ $0.084/run | |||
| Rd Animation Community | $0.084/image | |||
| Kuaishou Kolors Community | ≈ $0.0889/run | |||
| FLUX.1-dev Inpainting Community | ≈ $0.090/run | |||
| Qwen Image 2 Pro Alibaba (Qwen) | $0.090/image | |||
| Cartoonify Community | ≈ $0.096/run | |||
| Recraft v3 SVG Recraft | $0.096/image | |||
| Recraft V4 SVG Recraft | $0.096/image | |||
| Shap-E (OpenAI) Community | ≈ $0.1116/run | |||
| Gpt Image 2 OpenAI | $0.1536/image | |||
| Hunyuan3D 2.0 Tencent | ≈ $0.156/run | |||
| Gpt Image 1.5 OpenAI | $0.1632/image | |||
| Nano Banana Pro Google DeepMind | $0.18/image | |||
| OOTDiffusion (Try-On) Community | ≈ $0.1801/run | |||
| Hunyuan3D 2.1 Community | ≈ $0.264/run | |||
| CCSR (Content-Consistent SR) Community | ≈ $0.2761/run | |||
| Gpt Image 2.5 Flare OpenAI | $0.30/image | |||
| Gpt Image 2.5 Sunburst OpenAI | $0.30/image | |||
| Recraft V4 Pro Recraft | $0.30/image | |||
| SUPIR Upscaler Community | ≈ $0.30/run | |||
| SUPIR Community | ≈ $0.4921/run | |||
| StarVector 8B (image-to-SVG) Community | $0.00117/GPU s | |||
| DreamGaussian Community | $0.00168/GPU s |
Arena scores: Text-to-Image Arena leaderboard by LMArena, published Sep 22, 2026, CC BY 4.0.Ranked by quality, price and value →
Video generation
31/46Text-to-video and image-to-video. Sorted by Arena score, highest first; models without a rating follow by price.
| Actions | ||||
|---|---|---|---|---|
Google Veo 3.1 Arena 1362 | 1362 | $0.48/s$1.92 for 4 s | · | Try |
Google Veo 3.1 Fast Arena 1358 | 1358 | $0.18/s$0.72 for 4 s | · | Try |
Grok Imagine Video Arena 1342 · median 48 s | 1342 | $0.060/s$0.30 for 5 s | 48 s31 runs | Try |
PixVerse v5.6 Arena 1240 | 1240 | $0.084/s$0.42 for 5 s | · | Try |
Runway Gen 4.5 Arena 1225 | 1225 | $0.144/s$0.72 for 5 s | · | Try |
Hailuo 2.3 Arena 1206 | 1206 | $0.336/video | · | Try |
Seedance Pro Arena 1191 | 1191 | $0.18/s$0.90 for 5 s | · | Try |
MiniMax Hailuo 02 Arena 1181 | 1181 | $0.324/video | · | Try |
Google Veo 2 Arena 1164 | 1164 | $0.60/s$4.80 for 8 s | · | Try |
Kling v2.1 Master Arena 1163 | 1163 | $0.336/s$1.68 for 5 s | · | Try |
| Seedance Lite ByteDance | $0.0432/s | |||
| Luma Ray-2 720p Luma AI | $0.216/s | |||
| Mochi 1 Genmo | ≈ $0.5041/run | |||
| FILM Frame Interpolation Google Research | ≈ $0.0016/run | |||
| Wav2Lip Community | ≈ $0.0067/run | |||
| LTX-Video (Lightricks) Lightricks | ≈ $0.0229/run | |||
| SwinIR Video Community | ≈ $0.0277/run | |||
| Wan 2.2 5B Fast Alibaba (Wan) | $0.030/video | |||
| RIFE Frame Interpolation Community | ≈ $0.0444/run | |||
| Wan 2.2 Image-to-Video Alibaba (Wan) | $0.060/video | |||
| Wan 2.2 Text-to-Video Alibaba (Wan) | $0.060/video | |||
| MuseTalk Community | ≈ $0.0624/run | |||
| ToonCrafter Community | ≈ $0.0852/run | |||
| LivePortrait Community | ≈ $0.0949/run | |||
| SadTalker Community | ≈ $0.1165/run | |||
| AnimateDiff Community | ≈ $0.1201/run | |||
| VideoCrafter Community | ≈ $0.1561/run | |||
| Kling v2.1 Kuaishou (Kling) | $0.060/s | |||
| Runway Gen-4 Turbo Runway | $0.060/s | |||
| Luma Ray Flash 2 Luma AI | $0.072/s | |||
| Seedance 1 Pro Fast ByteDance | $0.072/s | |||
| CogVideoX-5B (open) Zhipu AI | ≈ $0.4081/run | |||
| MagicAnimate Community | ≈ $0.4081/run | |||
| Kling V2.5 Turbo Pro Kuaishou (Kling) | $0.084/s | |||
| EchoMimic Community | ≈ $0.48/run | |||
| Mochi 1 Community | ≈ $0.5041/run | |||
| CogVideoX-5B Community | ≈ $0.60/run | |||
| Minimax Video MiniMax | $0.60/video | |||
| Wan 3 Alibaba (Qwen) | $0.12/s | |||
| Google Veo 3 Fast Google DeepMind | $0.18/s | |||
| Kling v3 Kuaishou (Kling) | $0.2688/s | |||
| Kling v3 Omni Kuaishou (Kling) | $0.2688/s | |||
| HunyuanVideo Tencent | ≈ $3.06/run | |||
| Google Veo 3 (Replicate) Google DeepMind | $0.48/s | |||
| AnimateDiff Lightning Community | $0.00117/GPU s | |||
| V-Express Community | $0.00168/GPU s |
Arena scores: Text-to-Video Arena leaderboard by LMArena, published Sep 22, 2026, CC BY 4.0.Ranked by quality, price and value →
Text to speech
7/14Voices from text, including voice cloning. Sorted by the price of one default call, lowest first.
| Actions | ||
|---|---|---|
| $0.018/1k chars | Try | |
| $0.024/1k chars | Try | |
| $0.030/1k chars | Try | |
| $0.036/1k chars | Try | |
| Kokoro TTS 82M Community | ≈ $0.00030/run | |
| StyleTTS 2 Community | ≈ $0.00040/run | |
| Parler-TTS Community | ≈ $0.0024/run | |
| Spark TTS Community | ≈ $0.0035/run | |
| ≈ $0.0157/run | Try | |
| RVC Voice Conversion Community | ≈ $0.0505/run | |
| ≈ $0.0576/run | Try | |
| OpenVoice v2 Community | ≈ $0.0673/run | |
| Tortoise TTS Community | ≈ $0.0816/run | |
| ≈ $0.0972/run | Try |
Speech to text
5Transcription and speaker diarization. Sorted by the price of one default call, lowest first.
Vision & multimodal
30Open models that caption, read or segment images, billed by GPU time. Sorted by the price of one default call, lowest first.
| Actions | ||
|---|---|---|
| ≈ $0.00030/run | Try | |
| ≈ $0.00030/run | Try | |
| ≈ $0.00030/run | Try | |
| ≈ $0.00060/run | Try | |
| ≈ $0.0012/run | Try | |
| ≈ $0.0012/run | Try | |
| ≈ $0.0012/run | Try | |
| ≈ $0.0012/run | Try | |
| ≈ $0.0014/run | Try | |
| ≈ $0.0015/run | Try | |
| MiniCPM-V 2.6 Community | ≈ $0.0015/run | |
| Moondream2 Community | ≈ $0.0020/run | |
| Qwen2-VL 7B Instruct Community | ≈ $0.0024/run | |
| Llama 3.2 Vision 11B (Ollama) Community | ≈ $0.0039/run | |
| Depth Anything v2 Community | ≈ $0.0050/run | |
| Llama 3.2 Vision 90B Community | ≈ $0.0070/run | |
| DeepSeek-VL 7B DeepSeek | ≈ $0.0086/run | |
| GLPN Depth Community | ≈ $0.0094/run | |
| CogVLM2 19B Community | ≈ $0.0114/run | |
| Dots OCR Community | ≈ $0.0132/run | |
| SAM 2 (Segment Anything 2) Meta | ≈ $0.018/run | |
| olmOCR Community | ≈ $0.0205/run | |
| PaddleOCR v3 Community | ≈ $0.0216/run | |
| Mask2Former Meta | ≈ $0.0276/run | |
| Lotus-G Community | ≈ $0.0408/run | |
| CLIP Interrogator Community | ≈ $0.0457/run | |
| Molmo 7B Community | ≈ $0.0505/run | |
| Donut Document Community | ≈ $0.0648/run | |
| Marigold Community | ≈ $0.0936/run | |
| LLaVA 1.6 Vicuna 13B Community | ≈ $0.1021/run |
Open-weight text & code
10Open models on dedicated GPUs, billed by GPU time. Sorted by the price of one default call, lowest first.
Music & audio
3Music and sound generation. Sorted by the price of one default call, lowest first.
Embeddings
2Vectors for search and retrieval, billed per token. Sorted by input price per 1M tokens, lowest first.
| Actions | |||
|---|---|---|---|
OpenAI text-embedding-3-small 8.2K ctx | $0.024/1M in | 8.2K | Try |
OpenAI text-embedding-3-large 8.2K ctx | $0.156/1M in | 8.2K | Try |
How this leaderboard works
Every figure comes from our catalog, our pricing rules, our own job records or, for quality, the public Arena leaderboard. What we cannot source, we leave out.
- What is listed
- Only models you can run right now: active and with a verified price. Left out: 130 catalog entries without a price (they cannot run), 0 removed models and 5 duplicate entries of the same provider model. Legacy models stay listed and link their successor.
- Price
- What one call with the model’s default settings costs on Railwail, from the same pricing rules that bill your runs (1 credit = $0.01). Token models show the price per 1M input and output tokens. Prices marked ≈ are billed by GPU time: the figure is a typical run, the charge follows the real run time.
- Median run time
- Measured on completed Railwail jobs: the median of the newest up to 500 runs in the last 90 days, shown from 5 runs. It includes queueing at the provider. For language models it depends on the answer length, so the LLM board is never sorted by speed. Measured today: 5 models.
- Quality
- Arena scores from the public Arena leaderboard (formerly LMArena, CC BY 4.0), where people compare two anonymous models on the same prompt and vote. A model gets a score only when the arena entry is exactly the model and default setting we run (reviewed list, 56 models today). No score is estimated.
- Context window
- The maximum tokens per request as listed in our catalog. Not re-measured by us.
- Usage
- Runs per model are only shown once they say something: at least 5 models with runs from 3 or more different accounts in 30 days. Until then there is no popularity ranking.
- What we don’t show
- No votes of our own and no estimated scores: our own arena has 0 decided battles and 2 model votes, far too few for a rating. Models the public Arena has not rated in the setting we run show “No Arena rating”.
Source:arena.ai leaderboardDatasetCC BY 4.0
Found a wrong price or a missing model? Write to us
Questions about the leaderboard
Which language model is the cheapest on Railwail?
Right now Granite Code 8B by IBM at $0.060/1M in (output $0.30/1M out). The language model board lists all 30 language models by input price.
Which model has the largest context window?
GPT-5.4 by OpenAI with 1.1M tokens per request, as listed in our catalog.
What is the lowest price per image?
FLUX.1 [schnell] by Black Forest Labs at $0.0036/image. Models billed by GPU time can cost less per run; their price, marked ≈, is a typical run and the charge follows the real run time.
Where do the quality scores come from?
From the public Arena leaderboard (formerly LMArena): people compare two anonymous models on the same prompt and vote for the better result; the votes give each model a score. We use the published leaderboards (text: Sep 13, 2026, image and video: Sep 22, 2026) under CC BY 4.0 and show a score only where the arena rates exactly the model and default setting that runs on Railwail.
How current are the prices?
They come from the same pricing rules that bill your runs and were last checked on Sep 24, 2026. The snapshot on this page is refreshed about once an hour.
How do I run one of these models?
Open the model and try it on its page, or create an account, get an API key and call it through the Railwail API at https://railwail.com/api/v1. Your balance is prepaid in USD; runs are billed by the same pricing rules as the prices shown here.
Keep exploring
One key, one balance in USD, every model on this page.
Get an API key