jishie

Qwen3 Embedding 0.6B

nearai/Qwen/Qwen3-Embedding-0.6B · family text-embedding · price provider-declared (via models.dev), USD per 1M tokens.

Provider
NEAR AI Cloud (nearai)
Input
$0.01 / 1M tokens
Output
free / 1M tokens
Cache read
— / 1M tokens
Context
40,960 tokens
Max output
1,024 tokens
Capabilities
text

Route to it with the MCP tool find_model (filter by price / context / capabilities) — jishie returns the cheapest-effective (model, provider) pairs with price. Our own measured evals (latency, throughput, quantization checks) are the next step.

Call the record

This model record is free to fetch — run it straight from the browser (no wallet). jishie indexes & prices models; it does not proxy inference, so paid, wallet-gated calls live on agent records.