Extract JSON API
ai.extract
- providers document it
- 14
Providers
14 providers document extract json in their own API docs. None routes it through GridRouter yet. Scores appear as calls are routed.

Claude models via API (also routable through OpenRouter).

Command, Embed, Rerank and Parse model APIs for enterprise.

OpenAI- and Anthropic-compatible API for DeepSeek models with peak/off-peak pricing.
Knowledge graph and structured extraction from any page.
Serverless and on-demand inference and fine-tuning for open models.
Low-latency inference API for open models (OpenAI-compatible).
La Plateforme API for Mistral models: chat, embeddings, OCR and agents.
GPT models for completion, extraction and embeddings.

One endpoint for hundreds of language models.
Search, Extract, Task (deep research), FindAll and Monitor APIs for AI agents.
LLM-powered extract, scrape, search, crawl and monitor API.

Serverless and dedicated inference for open models, plus batch and fine-tuning.
Show all 14 providers

Grok model API with spend-based rate-limit tiers.

Enrichment orchestration; no public data API as a source.
- What counts as a hit:
- A schema-valid object.
API
Same input for every provider. Set provider.sort to route by price, reliability or latency, or provider.only to pin providers; X-Grid-Max-Cost caps what one call can spend.
| Input | Description |
|---|---|
| text* | Source text (required) |
| schema* | JSON Schema for the output (required) |
curl https://api.gridrouter.io/v1/run/ai.extract \
-H "Authorization: Bearer $GRID_API_KEY" \
-H "Content-Type: application/json" \
-H "X-Grid-Max-Cost: 0.05" \
-d '{"input":{"text":"Dana joined Northwind as VP Sales in March.","schema":"person"},"provider":{"sort":"price"}}'Fields
The normalized output every provider maps into. Suppliers come from integrated endpoint mappings (verified) or field names in each provider's API docs (claimed by the provider).