Source: https://telnyx.com/pricing/inference-api

``` Pay as you go

USD Chat completions pricing (per 1M tokens) Model Price ---- Kimi K2.6 — Highest intelligence, voice AI (with thinking disabled) Input: $0.95 / 1M tokens Cached Input: $0.16 / 1M tokens Output: $4.00 / 1M tokens ---- GLM-5.1-FP8 — Most efficient reasoning Input: $1.40 / 1M tokens Cached Input: $0.26 / 1M tokens Output: $4.40 / 1M tokens ---- MiniMax-M2.7 — Cheapest while maintaining high intelligence Input: $0.30 / 1M tokens Cached Input: $0.06 / 1M tokens Output: $1.20 / 1M tokens ```

We need to update both [model_prices_and_context_window.json](https://github.com/BerriAI/litellm/blob/e58a561caa21169fb02174148444c08509ce7028/model_prices_and_context_window.json) and [model_prices_and_context_window_backup.json](https://github.com/BerriAI/litellm/blob/e58a561caa21169fb02174148444c08509ce7028/litellm/model_prices_and_context_window_backup.json) to reflect the new model.