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

# Models Catalog

> All 52 AI models — slugs, token costs, providers and tier requirements

Every model has a unique `slug` passed in the `model` field. Costs are in **Elumenta tokens**.

## Text (12 models)

| Slug                | Name              | Provider  | Tier    | Tokens |
| ------------------- | ----------------- | --------- | ------- | ------ |
| `gpt-5-nano`        | GPT-5 Nano        | OpenAI    | Starter | 1      |
| `claude-haiku-4.5`  | Claude Haiku 4.5  | Anthropic | Starter | 1      |
| `gemini-2.5-flash`  | Gemini 2.5 Flash  | Google    | Starter | 1      |
| `deepseek-v3`       | DeepSeek V3 Chat  | DeepSeek  | Starter | 1      |
| `grok-4-fast`       | Grok 4.1 Fast     | xAI       | Starter | 1      |
| `gpt-5`             | GPT-5             | OpenAI    | Basic+  | 2      |
| `deepseek-r1`       | DeepSeek R1       | DeepSeek  | Basic+  | 1      |
| `gpt-5.2`           | GPT-5.2           | OpenAI    | Basic+  | 4      |
| `claude-sonnet-4.5` | Claude Sonnet 4.5 | Anthropic | Basic+  | 4      |
| `gemini-3-pro`      | Gemini 3 Pro      | Google    | Basic+  | 3      |
| `claude-opus-4.5`   | Claude Opus 4.5   | Anthropic | Basic+  | 6      |
| `gpt-5.2-pro`       | GPT-5.2 Pro       | OpenAI    | Basic+  | 39     |

## Image (10 models)

| Slug               | Name              | Provider   | Tier    | Tokens |
| ------------------ | ----------------- | ---------- | ------- | ------ |
| `photon-flash`     | Luma Photon Flash | Luma       | Starter | 1      |
| `dall-e-3`         | DALL·E 3          | OpenAI     | Starter | 5–13   |
| `gpt-image-1.5`    | GPT Image 1.5     | OpenAI     | Basic+  | 1–21   |
| `flux-1.1-pro`     | Flux 1.1 Pro      | Replicate  | Basic+  | 4      |
| `flux-kontext-pro` | Flux Kontext      | Replicate  | Basic+  | 3      |
| `sd-3.5-large`     | SD 3.5 Large      | Replicate  | Basic+  | 7      |
| `midjourney`       | MidJourney        | MidJourney | Basic+  | 2–35   |
| `recraft-v3`       | Recraft V3        | Replicate  | Basic+  | 4      |
| `photon`           | Luma Photon       | Luma       | Basic+  | 1–2    |
| `nano-banana-pro`  | Nano Banana Pro   | Google     | Basic+  | 16–32  |

<Note>
  DALL·E 3 and GPT Image 1.5 use dynamic pricing — cost varies by size and quality. Use [Calculate Price](/en/api-reference/models/calculate-price) for an exact figure.
</Note>

## Video (7 models)

| Slug               | Name             | Provider   | Tier    | Tokens |
| ------------------ | ---------------- | ---------- | ------- | ------ |
| `luma-ray2-flash`  | Luma Ray2 Flash  | Luma       | Starter | 15–93  |
| `kling-v2.1`       | Kling v2.1       | Replicate  | Basic+  | 26–94  |
| `minimax-video`    | MiniMax Video    | Replicate  | Basic+  | 88     |
| `luma-ray2`        | Luma Ray2        | Luma       | Basic+  | 42–180 |
| `midjourney-video` | MidJourney Video | MidJourney | Basic+  | 50–320 |
| `sora-2`           | Sora 2           | OpenAI     | Basic+  | 42–125 |
| `veo-3.1`          | Veo 3.1          | Replicate  | Basic+  | 83–334 |

Token cost scales with duration and resolution. Use [Calculate Price](/en/api-reference/models/calculate-price) for an exact figure.

## Music (2 models)

| Slug               | Name     | Provider   | Tier    | Tokens |
| ------------------ | -------- | ---------- | ------- | ------ |
| `musicgen`         | MusicGen | Replicate  | Starter | 9      |
| `elevenlabs-music` | EL Music | ElevenLabs | Basic+  | 58     |

## TTS — Text to Speech (6 models)

| Slug               | Name            | Provider   | Tier   | Tokens |
| ------------------ | --------------- | ---------- | ------ | ------ |
| `minimax-tts`      | MiniMax TTS     | Replicate  | Basic+ | 1      |
| `openai-tts`       | OpenAI TTS      | OpenAI     | Basic+ | 3      |
| `openai-tts-hd`    | OpenAI TTS HD   | OpenAI     | Basic+ | 6      |
| `gpt-4o-mini-tts`  | GPT-4o Mini TTS | OpenAI     | Basic+ | 3      |
| `elevenlabs-flash` | EL Flash        | ElevenLabs | Basic+ | 18     |
| `elevenlabs-v2`    | EL ML v2        | ElevenLabs | Basic+ | 35     |

## STT — Speech to Text (3 models)

| Slug                | Name              | Provider   | Tier    | Tokens |
| ------------------- | ----------------- | ---------- | ------- | ------ |
| `whisper`           | Whisper STT       | OpenAI     | Starter | 2      |
| `gpt-4o-transcribe` | GPT-4o Transcribe | OpenAI     | Starter | 2      |
| `elevenlabs-scribe` | EL Scribe         | ElevenLabs | Starter | 2      |

## ElevenLabs Audio Tools (5 models)

| Slug                | Name              | Tier   | Tokens |
| ------------------- | ----------------- | ------ | ------ |
| `elevenlabs-sfx`    | EL Sound FX       | Basic+ | 12     |
| `el-voice-changer`  | EL Voice Changer  | Basic+ | 15     |
| `el-voice-isolator` | EL Voice Isolator | Basic+ | 12     |
| `el-dubbing`        | EL Dubbing        | Basic+ | 60–600 |
| `el-dialogue`       | EL Dialogue       | Basic+ | 15     |

## Image & Video Tools (7 models)

All tools are available on Starter tier — **1–3 tokens**.

| Slug             | Name           | Tokens |
| ---------------- | -------------- | ------ |
| `upscale`        | Upscale ESRGAN | 1      |
| `face-swap`      | Face Swap      | 1      |
| `remove-bg`      | Remove BG      | 1      |
| `style-transfer` | Style Transfer | 1      |
| `colorize`       | Colorize       | 1      |
| `inpaint`        | InPaint Edit   | 3      |
| `text-ocr`       | Text OCR       | 1      |

<Tip>
  Any paid plan (Basic and above) unlocks all 52 models. Plans differ only in token quantity — not model access.
</Tip>