> ## Documentation Index
> Fetch the complete documentation index at: https://docs.vidgo.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Chat Series Overview

> Supported LLM models, compatible protocols, streaming, and token pricing

All Chat Series endpoints use `https://api.vidgo.ai` and a Vidgo API key. Send the key as `Authorization: Bearer YOUR_API_KEY`. Claude clients may also use `x-api-key`; Gemini clients may use `x-goog-api-key`.

## Model protocol support

| Model             | Responses | Chat Completions | Claude Messages | Gemini native |
| ----------------- | :-------: | :--------------: | :-------------: | :-----------: |
| `gpt-5-6-luna`    |    Yes    |         —        |        —        |       —       |
| `gpt-5-6-terra`   |    Yes    |         —        |        —        |       —       |
| `gpt-5-6-sol`     |    Yes    |         —        |        —        |       —       |
| `kimi-k3`         |     —     |        Yes       |        —        |       —       |
| `claude-sonnet-5` |     —     |        Yes       |       Yes       |       —       |
| `claude-opus-5`   |     —     |        Yes       |       Yes       |       —       |

The Gemini-compatible endpoints are available for future Gemini-capable models. None of the six models above currently supports that protocol.

## Pricing

Prices are Vidgo credits per one million tokens. The final charge is calculated from the usage returned by the model, with a minimum positive charge of `0.001` credit.

| Model             | Input | Output | Cache read |        Cache write |
| ----------------- | ----: | -----: | ---------: | -----------------: |
| `gpt-5-6-luna`    |  11.2 |   67.2 |       1.12 |                 14 |
| `gpt-5-6-terra`   |   112 |    672 |       11.2 |                140 |
| `gpt-5-6-sol`     |   280 |   1680 |         28 |                350 |
| `kimi-k3`         |   456 |   2280 |        456 |                456 |
| `claude-sonnet-5` |   170 |    855 |        170 |                170 |
| `claude-opus-5`   |   400 |   2000 |         40 | 500 (5m), 800 (1h) |

Both normal JSON responses and SSE streaming are supported. Vidgo settles credits after the final usage event. If a provider omits usage but produced output, Vidgo estimates token usage and marks the audit record as estimated. Requests with no valid output are not charged.