Aggregate token volume routed through AIgateway over the last day, week, and month. Pick a model the market trusts — or pick the underdog it hasn't noticed yet.
| # | Model | Provider | Modality | Tokens | p50 latency | Δ |
|---|---|---|---|---|---|---|
| 1 | GPT-5.5 Pro openai/gpt-5.5-pro | OpenAI | text | 5.97B | 1277ms | -35% |
| 2 | GPT-5.5 openai/gpt-5.5 | OpenAI | text | 3.77B | 1286ms | +47% |
| 3 | Claude Sonnet 4.6 anthropic/claude-sonnet-4.6 | Anthropic | text | 2.69B | 1035ms | +0% |
| 4 | Claude Opus 4.7 anthropic/claude-opus-4.7 | Anthropic | text | 2.46B | 1299ms | -37% |
| 5 | Inworld TTS 2 inworld/tts-2 | Inworld | audio-tts | 2.18B | 1332ms | -25% |
| 6 | Sonar Deep Research perplexity/sonar-deep-research | Perplexity | text | 2.16B | 1209ms | +39% |
| 7 | Kimi-K2.6 moonshot/kimi-k2.6 | Moonshot | text | 2.14B | 1035ms | -47% |
| 8 | Gemini 3.1 Pro google/gemini-3.1-pro | text | 1.87B | 1111ms | +55% | |
| 9 | Qwen 3.5 397B A17B alibaba/qwen3.5-397b-a17b | Alibaba | text | 1.68B | 974ms | -15% |
| 10 | HappyHorse 1.0 T2V alibaba/hh1-t2v | Alibaba | video | 1.36B | 892ms | -40% |
| 11 | Nemotron-3-120b-A12b nvidia/nemotron-3-120b-a12b | Nvidia | text | 1.36B | 1124ms | -36% |
| 12 | ElevenLabs TTS Multilingual v2 elevenlabs/elevenlabs-tts-multilingual-v2 | ElevenLabs | audio-tts | 1.08B | 1148ms | +21% |
| 13 | Bria Text-to-Image HD bria/bria-text-to-image-hd | Bria | image | 1.08B | 281ms | +51% |
| 14 | Flux 2 Lora Gallery Virtual Tryon black-forest-labs/flux-2-lora-gallery-virtual-tryon | Black Forest Labs | image | 1.08B | 477ms | +39% |
| 15 | Ideogram V3 Reframe ideogram/ideogram-v3-reframe | Ideogram | image | 1.08B | 209ms | +39% |
| 16 | Pixverse V4.5 (Image To Video) pixverse/pixverse-v4.5-image-to-video | PixVerse | video | 1.08B | 1207ms | -12% |
| 17 | Ideogram V2a Turbo Remix ideogram/ideogram-v2a-turbo-remix | Ideogram | image | 1.07B | 1340ms | -12% |
| 18 | ResNet-50 microsoft/resnet-50 | Microsoft | image | 1.07B | 201ms | -43% |
| 19 | MiniMax Hailuo 2.3 [Pro] (Text to Video) minimax/minimax-hailuo-2.3-pro-text-to-video | MiniMax | video | 1.07B | 271ms | +50% |
| 20 | Kling O3 Image to Video [Pro] (Standard) kuaishou/kling-video-o3-standard-image-to-video | Kuaishou | video | 1.07B | 1263ms | -13% |
| 21 | Flux 2 Flash black-forest-labs/flux-2-flash | Black Forest Labs | image | 1.07B | 333ms | +19% |
| 22 | Wan Vace 14b Pose alibaba/wan-vace-14b-pose | Alibaba | video | 1.07B | 1132ms | +49% |
| 23 | Gemma-3-12b-IT google/gemma-3-12b-it | text | 1.06B | 198ms | +37% | |
| 24 | Longcat Video Distilled Image To Video 480p meituan/longcat-video-distilled-image-to-video-480p | Meituan | video | 1.06B | 260ms | +19% |
| 25 | Wan-2.1 First-Last-Frame-to-Video alibaba/wan-flf2v | Alibaba | video | 1.06B | 1260ms | -26% |
| 26 | LTX Video-0.9.5 lightricks/ltx-video-v095 | Lightricks | video | 1.06B | 255ms | +48% |
| 27 | Tripo3d H3.1 Multiview To 3d tripo3d/h3.1/multiview-to-3d | Tripo AI | 3d | 1.06B | 1057ms | -14% |
| 28 | Qwen Image Max (Text To Image) alibaba/qwen-image-max-text-to-image | Alibaba | image | 1.05B | 1119ms | +36% |
| 29 | FLUX1.1 [pro] ultra black-forest-labs/flux-pro-v1.1-ultra | Black Forest Labs | image | 1.05B | 319ms | +17% |
| 30 | Pixverse V3.5 Transition pixverse/pixverse-v3.5-transition | PixVerse | video | 1.05B | 1116ms | +17% |
| 31 | Nano Banana Pro google/nano-banana-pro | image | 1.05B | 1379ms | +47% | |
| 32 | Wan V2.7 (Image To Video) alibaba/wan-v2.7-image-to-video | Alibaba | video | 1.05B | 1047ms | +3% |
| 33 | Gpt Image 1 Edit Image openai/gpt-image-1-edit-image | OpenAI | image | 1.05B | 1046ms | -15% |
| 34 | Flux Kontext Lora black-forest-labs/flux-kontext-lora | Black Forest Labs | image | 1.05B | 1046ms | -46% |
| 35 | MiniMax (Hailuo AI) Video 01 Live minimax/minimax-video-01-live | MiniMax | video | 1.05B | 1046ms | +35% |
| 36 | GPT-5.4 Mini openai/gpt-5.4-mini | OpenAI | text | 1.05B | 1374ms | -16% |
| 37 | Flux 2 Lora Gallery Realism black-forest-labs/flux-2-lora-gallery-realism | Black Forest Labs | image | 1.04B | 1040ms | -28% |
| 38 | Qwen Image Edit Plus Lora Gallery Remove Lighting alibaba/qwen-image-edit-plus-lora-gallery-remove-lighting | Alibaba | image | 1.04B | 1303ms | +16% |
| 39 | Glm-4.7-Flash zai-org/glm-4.7-flash | Zai-org | text | 1.04B | 1038ms | +16% |
| 40 | Pika V2 Pikadditions pika-labs/pika-v2-pikadditions | Pika Labs | video | 1.04B | 1104ms | -16% |
| Provider | Models | Tokens |
|---|---|---|
| Alibaba | 128 | 73.86B |
| Black Forest Labs | 84 | 50.18B |
| Kuaishou | 70 | 35.98B |
| Lightricks | 65 | 32.89B |
| OpenAI | 32 | 28.31B |
| 47 | 27.32B | |
| MiniMax | 38 | 21.35B |
| PixVerse | 41 | 21.30B |
| Bria | 36 | 19.38B |
| ByteDance | 35 | 15.86B |
| Tencent | 30 | 14.01B |
| Ideogram | 22 | 13.04B |
Every request through the gateway increments a counter keyed on the routed model. We anonymize before aggregation, publish daily, and never expose a single customer's workload. If you want your app attributed on the leaderboard, opt in from Dashboard → Settings.