---
title: "The model catalogue"
canonical: "https://router.xark.io/models"
description: "All 24 open-weight text, video, image and embedding models catalogued here, with the rate, the licence and whether each is callable today."
section: "core"
updated: "2026-09-02"
source: "https://router.xark.io/models.md"
---

# The model catalogue

All 24 open-weight text, video, image and embedding models catalogued here, with the rate, the licence and whether each is callable today.

**Availability:** 7 of the 24 catalogued models are callable today. The rest are listed at their intended rate but no configured upstream serves them, so a request naming one returns `no available channel`. Every table below marks which is which.

We serve open-weight models only. Their licences permit third-party hosting, so we run the inference and control the price. Closed-weight models are never resold here.

## Text models

| Model | API id | Publisher | Licence | Capacity | Our rate | Callable | Document |
| --- | --- | --- | --- | --- | --- | --- | --- |
| Kimi K2.6 | `moonshotai/kimi-k2.6` | Moonshot AI | Modified MIT | 256K tokens | $0.55/M | Yes | [read](https://router.xark.io/models/kimi-k2-6.md) |
| Kimi K3 | `moonshotai/kimi-k3` | Moonshot AI | Modified MIT | 512K tokens | $1.85/M | Yes | [read](https://router.xark.io/models/kimi-k3.md) |
| GLM-5.2 | `z-ai/glm-5.2` | Z.ai | MIT | 200K tokens | $0.82/M | Yes | [read](https://router.xark.io/models/glm-5-2.md) |
| GLM-5.2 Air | `z-ai/glm-5.2-air` | Z.ai | MIT | 128K tokens | $0.17/M | No | [read](https://router.xark.io/models/glm-5-2-air.md) |
| DeepSeek V4 Pro | `deepseek/deepseek-v4-pro` | DeepSeek | MIT | 160K tokens | $0.28/M | Yes | [read](https://router.xark.io/models/deepseek-v4-pro.md) |
| DeepSeek V4 Flash | `deepseek/deepseek-v4-flash` | DeepSeek | MIT | 160K tokens | $0.090/M | Yes | [read](https://router.xark.io/models/deepseek-v4-flash.md) |
| Qwen3 Max Instruct | `qwen/qwen3-max-instruct` | Alibaba | Apache 2.0 | 256K tokens | $0.49/M | No | [read](https://router.xark.io/models/qwen3-max-instruct.md) |
| Qwen3 235B A22B | `qwen/qwen3-235b-a22b-instruct` | Alibaba | Apache 2.0 | 128K tokens | $0.13/M | No | [read](https://router.xark.io/models/qwen3-235b-a22b.md) |
| MiniMax M2 | `minimax/minimax-m2` | MiniMax | MIT | 200K tokens | $0.19/M | No | [read](https://router.xark.io/models/minimax-m2.md) |
| Llama 4 Maverick | `meta-llama/llama-4-maverick` | Meta | Llama 4 Community | 1M tokens | $0.14/M | No | [read](https://router.xark.io/models/llama-4-maverick.md) |
| Mistral Large 3 | `mistralai/mistral-large-3` | Mistral AI | Apache 2.0 | 256K tokens | $1.20/M | No | [read](https://router.xark.io/models/mistral-large-3.md) |
| GPT-OSS 120B | `openai/gpt-oss-120b` | OpenAI | Apache 2.0 | 128K tokens | $0.090/M | No | [read](https://router.xark.io/models/gpt-oss-120b.md) |

## Video models

| Model | API id | Publisher | Licence | Capacity | Our rate | Callable | Document |
| --- | --- | --- | --- | --- | --- | --- | --- |
| Wan 2.2 T2V A14B | `alibaba/wan-2.2-t2v-a14b` | Alibaba | Apache 2.0 | 10s, 720p / 1080p | $0.029/sec | No | [read](https://router.xark.io/models/wan-2-2-t2v-a14b.md) |
| Wan 2.2 I2V A14B | `alibaba/wan-2.2-i2v-a14b` | Alibaba | Apache 2.0 | 10s, 720p / 1080p | $0.032/sec | No | [read](https://router.xark.io/models/wan-2-2-i2v-a14b.md) |
| LTX-2.5 | `lightricks/ltx-2.5` | Lightricks | LTXV Open Weights | 20s, 768p | $0.024/sec | No | [read](https://router.xark.io/models/ltx-2-5.md) |
| HunyuanVideo 1.5 | `tencent/hunyuanvideo-1.5` | Tencent | Tencent Hunyuan Community | 10s, 720p | $0.027/sec | No | [read](https://router.xark.io/models/hunyuanvideo-1-5.md) |
| CogVideoX-5B | `zhipuai/cogvideox-5b` | Zhipu AI | Apache 2.0 | 6s, 480p / 720p | $0.017/sec | No | [read](https://router.xark.io/models/cogvideox-5b.md) |
| Mochi 1 | `genmo/mochi-1` | Genmo | Apache 2.0 | 5s, 480p | $0.021/sec | No | [read](https://router.xark.io/models/mochi-1.md) |

## Image models

| Model | API id | Publisher | Licence | Capacity | Our rate | Callable | Document |
| --- | --- | --- | --- | --- | --- | --- | --- |
| FLUX.2 [schnell] | `black-forest-labs/flux-2-schnell` | Black Forest Labs | Apache 2.0 | up to 2K | $0.0018/img | No | [read](https://router.xark.io/models/flux-2-schnell.md) |
| Qwen-Image | `qwen/qwen-image` | Alibaba | Apache 2.0 | up to 1.5K | $0.0120/img | Yes | [read](https://router.xark.io/models/qwen-image.md) |
| Stable Diffusion 3.5 Large | `stabilityai/sd-3.5-large` | Stability AI | Stability Community | 1MP | $0.0210/img | No | [read](https://router.xark.io/models/sd-3-5-large.md) |
| HiDream-I1 | `hidream/hidream-i1` | HiDream | MIT | 1MP | $0.0150/img | No | [read](https://router.xark.io/models/hidream-i1.md) |

## Embedding models

| Model | API id | Publisher | Licence | Capacity | Our rate | Callable | Document |
| --- | --- | --- | --- | --- | --- | --- | --- |
| Qwen3 Embedding 8B | `qwen/qwen3-embedding-8b` | Alibaba | Apache 2.0 | 4096 dims, 32K context | $0.030/M | Yes | [read](https://router.xark.io/models/qwen3-embedding-8b.md) |
| BGE-M3 | `baai/bge-m3` | BAAI | MIT | 1024 dims, 8K context | $0.012/M | No | [read](https://router.xark.io/models/bge-m3.md) |