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 |
|---|---|---|---|---|---|---|
| No models match those filters — clear or widen them. | ||||||
Source: models.dev (loaded 2026-09-26 04:00 UTC) · provider-declared pricing · this exact query as JSON: GET /v1/models?q=… · /v1/models