# Ling 3.0 Flash API prices

Ling 3.0 Flash (ling) — 262k context, 262k max output.
7 metered per-token offers from 6 provider(s), in USD per 1M tokens.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| OpenRouter | $0.021 | $0.063 | $0.0042 | 262k |
| Kilo Gateway | $0.06 | $0.18 | $0.012 | 262k |
| DevPass (LLM Gateway) | $0.06 | $0.18 | $0.012 | 262k |
| LLM Gateway | $0.06 | $0.18 | $0.012 | 262k |
| LLM Gateway | $0.06 | $0.18 | $0.012 | 262k |
| Vercel AI Gateway | $0.06 | $0.18 | $0.012 | 256k |
| NanoGPT | $0.075 | $0.22 | $0.015 | 262k |

## Summary

- Cheapest input: $0.021 per 1M tokens (OpenRouter)
- Cheapest output: $0.063 per 1M tokens (OpenRouter)
- First-party: not listed separately
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2026-07-23
- Inputs: text

HTML page: https://llmprice.gitlab.io/models/ling-3-0-flash/
Full dataset: https://llmprice.gitlab.io/data/catalog.json