The model index
Every (model, provider) pair — text LLMs plus image video audio generators — with price, context and capabilities. Blended $/1M is the effective cost of a typical 3:1 input:output request (what we rank text models by). Image/video/audio models are priced per unit by the provider (per image, per second) — not per token — so their token fields read “—”. Prices are provider-declared (via models.dev); measured evals are a later step. Machine: GET /v1/models (same filters incl. kind) · MCP: find_model.
x402 Call models through jishie. Beyond indexing, jishie delivers moderated AI generation you pay for per call in USDC — no accounts, no keys. Five services live (/v1/services): POST /v1/ai/rewrite · /translate · /summarize · /extract · /classify with an X-PAYMENT header — call unpaid and you get an HTTP 402 quoting the price, then retry paid. Backed by Gemini Flash today; more models & modalities next.
| Model | Provider | Input $/1M | Output $/1M | Blended ▼ | Context | Capabilities |
|---|---|---|---|---|---|---|
| Wan v2.6 Image-to-Video Flash videoalibaba/wan-v2.6-i2v-flash | Vercel AI Gateway | — | — | — | 0 | vision |
| Wan v2.6 Reference-to-Video videoalibaba/wan-v2.6-r2v | Vercel AI Gateway | — | — | — | 0 | vision |
| Wan v2.6 Reference-to-Video Flash videoalibaba/wan-v2.6-r2v-flash | Vercel AI Gateway | — | — | — | 0 | vision |
| Wan v2.6 Text-to-Video videoalibaba/wan-v2.6-t2v | Vercel AI Gateway | — | — | — | 0 | |
| Wan v2.7 Reference-to-Video videoalibaba/wan-v2.7-r2v | Vercel AI Gateway | — | — | — | 0 | vision |
| Wan v2.7 Text-to-Video videoalibaba/wan-v2.7-t2v | Vercel AI Gateway | — | — | — | 0 | |
| Wan v3.0 Video videoalibaba/wan-v3.0-video | Vercel AI Gateway | — | — | — | 0 | vision |
| Wan v3.0 Video Prime videoalibaba/wan-v3.0-video-prime | Vercel AI Gateway | — | — | — | 0 | vision |
| Wan2.2-T2V-A14B videowan2-2-t2v-a14b | DigitalOcean | — | — | — | 100 | |
| Wan2.7 Image imagewan2.7-image | Alibaba Token Plan (China) | — | — | — | 8k | |
| Wan2.7 Image imagewan2.7-image | Alibaba Token Plan | — | — | — | 8k | |
| Wan2.7 Image Pro imagewan2.7-image-pro | Alibaba Token Plan (China) | — | — | — | 8k | |
| Wan2.7 Image Pro imagewan2.7-image-pro | Alibaba Token Plan | — | — | — | 8k | |
| Whisperopenai/whisper-1 | Merge Gateway | — | — | — | 448k | |
| Whisperopenai/whisper-1 | Vercel AI Gateway | — | — | — | 0 | |
| Whisperwhisper-large-v3 | Groq | — | — | — | 448 | |
| Whisper Large v3whisper-large-v3 | Scaleway | — | — | — | 0 | |
| Whisper Large v3 Turbowhisper-large-v3-turbo | Kenari | — | — | — | 448 | |
| Whisper Large V3 Turbowhisper-large-v3-turbo | Groq | — | — | — | 448 | |
| Wonder 3.5 imagetopaz/wonder-3.5 | Vercel AI Gateway | — | — | — | 0 | vision |
| X-Ai/Grok 4.1 Fast Non Reasoningx-ai/grok-4.1-fast-non-reasoning | Qiniu | — | — | — | 2M | tools · vision |
| X-Ai/Grok 4.1 Fast Reasoningx-ai/grok-4.1-fast-reasoning | Qiniu | — | — | — | 20M | tools · reasoning · vision |
| x-AI/Grok-4-Fastx-ai/grok-4-fast | Qiniu | — | — | — | 2M | tools · reasoning · vision |
| X-Ai/Grok-4-Fast-Non-Reasoningx-ai/grok-4-fast-non-reasoning | Qiniu | — | — | — | 2M | tools · vision |
| X-Ai/Grok-4-Fast-Reasoningx-ai/grok-4-fast-reasoning | Qiniu | — | — | — | 2M | tools · reasoning · vision |
| x-AI/Grok-4.1-Fastx-ai/grok-4.1-fast | Qiniu | — | — | — | 2M | tools · reasoning |
| x-AI/Grok-Code-Fast 1x-ai/grok-code-fast-1 | Qiniu | — | — | — | 256k | tools · reasoning |
| Z-Ai/Autoglm Phone 9bz-ai/autoglm-phone-9b | Qiniu | — | — | — | 13k | tools · vision |
| Zero Data Retentiontrustedrouter/zdr | TrustedRouter | — | — | — | 1M | tools · reasoning · vision |
Source: models.dev (loaded 2026-11-15 00:00 UTC) · provider-declared pricing · this exact query as JSON: GET /v1/models?q=… · /v1/models