# Models

Every model the API serves, with its price. The same list as JSON: /docs/models.json

## Chat and reasoning

- [deepseek-v4.1-flash](/docs/models/deepseek-v4.1-flash.md): DeepSeek V4.1 Flash, $0.15 in, $0.60 out / 1M tokens
- [glm-5.2](/docs/models/glm-5.2.md): GLM 5.2, $0.75 in, $3.00 out / 1M tokens
- [glm-5.3](/docs/models/glm-5.3.md): GLM 5.3, $0.75 in, $3.00 out / 1M tokens
- [glm-5.3-flash](/docs/models/glm-5.3-flash.md): GLM 5.3 Flash, $0.10 in, $0.35 out / 1M tokens
- [glm-5.x-menthol](/docs/models/glm-5.x-menthol.md): GLM 5, $0.40 in, $1.75 out / 1M tokens
- [mimo-v2.6-flash-rl](/docs/models/mimo-v2.6-flash-rl.md): MiMo V2.6 Flash RL, $0.10 in, $0.25 out / 1M tokens
- [mimo-v2.6-pro-rl](/docs/models/mimo-v2.6-pro-rl.md): MiMo V2.6 Pro RL, $0.40 in, $0.80 out / 1M tokens
- [minimax-m3](/docs/models/minimax-m3.md): MiniMax M3, $0.20 in, $0.90 out / 1M tokens
- [muse-glimmer-30b](/docs/models/muse-glimmer-30b.md): Muse Glimmer 30B, $0.25 in, $1.00 out / 1M tokens
- [nemotron-3-nano-omni-30b-a3b-reasoning](/docs/models/nemotron-3-nano-omni-30b-a3b-reasoning.md): Nemotron 3 Nano Omni, $0.10 in, $0.25 out / 1M tokens
- [nemotron-3.5-content-safety](/docs/models/nemotron-3.5-content-safety.md): Nemotron 3.5 Content Safety, $0.05 in, $0.15 out / 1M tokens
- [qwen3.8-27b](/docs/models/qwen3.8-27b.md): Qwen 3.8 27B, $0.15 in, $1.00 out / 1M tokens
- [qwen3.8-flash-next](/docs/models/qwen3.8-flash-next.md): Qwen 3.8 Flash Next, $0.10 in, $0.20 out / 1M tokens

## Images

- [z-image-turbo](/docs/models/z-image-turbo.md): Z-Image Turbo, $0.02 / megapixel

## Video

- [minimax-h3](/docs/models/minimax-h3.md): MiniMax H3, $0.06 / second

## Music

- [minimax-music3](/docs/models/minimax-music3.md): MiniMax Music 3, $0.001 / second

## Speech

- [qwen3-tts-12hz-1.7b](/docs/models/qwen3-tts-12hz-1.7b.md): Qwen 3 TTS 12Hz 1.7B, $0.00028 / second

## Transcription

- [whisper-large-v3-turbo](/docs/models/whisper-large-v3-turbo.md): Whisper Large V3 Turbo, $0.0000111 / second

## Embeddings

- [qwen3-embedding-4b](/docs/models/qwen3-embedding-4b.md): Qwen 3 Embedding 4B, $0.05 / 1M tokens

## Rerank

- [bge-reranker-v2-m3](/docs/models/bge-reranker-v2-m3.md): BGE M3, $0.05 / 1M tokens
- [vultron-retriever-core-qwen3.5-4.5b](/docs/models/vultron-retriever-core-qwen3.5-4.5b.md): Vultron Retriever Core 4.5B, $0.10 / 1M tokens
- [vultron-retriever-flash-qwen3.5-0.8b](/docs/models/vultron-retriever-flash-qwen3.5-0.8b.md): Vultron Retriever Flash 0.8B, $0.05 / 1M tokens

## Decisions

- [clef](/docs/models/clef.md): Clef, $0.10 / 1M tokens
- [clef-flash](/docs/models/clef-flash.md): Clef Flash, $0.05 / 1M tokens