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

# Changelog

<link rel="alternate" hrefLang="en" href="https://mixroute.ai/docs/changelog" />

<link rel="alternate" hrefLang="zh-Hans" href="https://mixroute.ai/docs/zh-hans/changelog" />

<link rel="alternate" hrefLang="zh-Hant" href="https://mixroute.ai/docs/zh-hant/changelog" />

<link rel="alternate" hrefLang="ja" href="https://mixroute.ai/docs/ja/changelog" />

<link rel="alternate" hrefLang="x-default" href="https://mixroute.ai/docs/changelog" />

Welcome to MixRoute's changelog page. Here you can find important information about our latest model launches, pricing adjustments, feature updates, and more.

<Tip>
  Stay updated: press Ctrl+D to bookmark this page and get the latest model launches and promotional information as soon as possible.
</Tip>

## 🔥 Latest Updates

<CardGroup cols={2}>
  <Card title="Gemini 4 Argon" icon="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/google-color.svg" href="/docs/model-api/google/gemini-4-argon">
    Reasoning for complex coding, mathematics, and agent workflows, with a shared 1M-token context window.
  </Card>

  <Card title="GPT 6.1 Sol" icon="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/openai.svg" href="/docs/model-api/openai/gpt-6.1-sol">
    Text and image reasoning for coding and professional work. Function calling uses the Responses API.
  </Card>

  <Card title="Claude Opus 5.5" icon="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/claude-color.svg" href="/docs/model-api/anthropic/claude-opus-5-5">
    Long-running coding agents and knowledge work, with always-on adaptive thinking and up to 128K output.
  </Card>

  <Card title="Claude Haiku 5.5" icon="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/claude-color.svg" href="/docs/model-api/anthropic/claude-haiku-5-5">
    Low-latency classification, extraction, routing, and coding subagents, with adaptive thinking.
  </Card>

  <Card title="Grok 4.7" icon="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/grok.svg" href="/docs/model-api/xai/grok-4.7">
    Text and image input, configurable reasoning, and tool workflows through the Responses API.
  </Card>

  <Card title="DeepSeek V4.1 Flash" icon="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/deepseek-color.svg" href="/docs/model-api/deepseek/deepseek-v4.1-flash">
    Native visual understanding for coding, agents, and multimodal analysis.
  </Card>
</CardGroup>

***

## 🔧 Update Announcements

### <Icon icon="arrows-rotate" size={18} /> 2026-10-15 Model catalog and documentation sync

This update standardizes the displayed model count at 250 and adds changelog entries for models already supported by MixRoute. The date is the documentation update date, not a first-availability or vendor release date.

* <Icon size={18} src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/google-color.svg" className="m-0!" /> **Google**: [Gemini 4 Argon](/docs/model-api/google/gemini-4-argon), [Gemini 3.8 Flash](/docs/model-api/google/gemini-3.8-flash), [Nano Banana 2.1](/docs/model-api/google/gemini-nano-banana-2.1), [Lyria 3.5](/docs/model-api/google/lyria-3.5)
* <Icon size={18} src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/openai.svg" className="m-0!" /> **OpenAI**: [GPT 6 Astra](/docs/model-api/openai/gpt-6-astra), [GPT 6.1 Sol](/docs/model-api/openai/gpt-6.1-sol), [GPT 6 Sol](/docs/model-api/openai/gpt-6-sol), [GPT 6 Luna](/docs/model-api/openai/gpt-6-luna), [GPT Image 2.5 Sunburst](/docs/model-api/openai/gpt-image-2.5-sunburst), [GPT Image 2.5 Flare](/docs/model-api/openai/gpt-image-2.5-flare)
* <Icon size={18} src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/claude-color.svg" className="m-0!" /> **Anthropic**: [Claude Opus 5.5](/docs/model-api/anthropic/claude-opus-5-5), [Claude Sonnet 5.5](/docs/model-api/anthropic/claude-sonnet-5-5), [Claude Haiku 5.5](/docs/model-api/anthropic/claude-haiku-5-5), [Claude Fable 5.1](/docs/model-api/anthropic/claude-fable-5-1)
* <Icon size={18} src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/grok.svg" className="m-0!" /> **xAI**: [Grok 4.7](/docs/model-api/xai/grok-4.7), [Grok Imagine Image 2.0](/docs/model-api/xai/grok-imagine-image-2.0)
* <Icon size={18} src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/deepseek-color.svg" className="m-0!" /> **DeepSeek**: [DeepSeek V4.1 Flash](/docs/model-api/deepseek/deepseek-v4.1-flash)
* <Icon size={18} src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/zhipu-color.svg" className="m-0!" /> **Zhipu**: [GLM-5.3 FlashX](/docs/model-api/zhipu/glm-5.3-flashx)
* <Icon size={18} src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/tencent-color.svg" className="m-0!" /> **Tencent**: [HY4 Preview](/docs/model-api/tencent/hy4-preview)
* <Icon size={18} src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/alibaba-color.svg" className="m-0!" /> **Alibaba**: [Qwen 3.8 Max](/docs/model-api/alibaba/qwen3.8-max), [Wan 3.0 Video Prime](/docs/model-api/alibaba/wan3.0-video-prime)
* <Icon size={18} src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/bytedance-color.svg" className="m-0!" /> **ByteDance**: [Dreamina Seedance 2.5](/docs/model-api/bytedance/dreamina-seedance-2-5), [Doubao Seedance 2.5](/docs/model-api/bytedance/doubao-seedance-2-5)
* <Icon size={18} src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/minimax-color.svg" className="m-0!" /> **MiniMax**: [MiniMax M3](/docs/model-api/minimax/minimax-m3), [MiniMax H3](/docs/model-api/minimax/minimax-h3)

#### Integration notes

* Gemini 4 Argon shares one 1,048,576-token window across input, thinking, and output; long decode is a separate workflow, not a 1M-token single Chat Completions response.
* Use the Responses API for GPT 6.1 Sol function calling. Its lowest reasoning effort is `low`; `none` and `minimal` are not supported.
* Claude Opus 5.5 always uses adaptive thinking. Use `output_config.effort`; forced tool choices `any` and `tool` are not supported.

See [Popular Models](/docs/api-reference/models) for model selection and the [Model Marketplace](https://console.mixroute.ai/models) for current availability and pricing.

***

### <Icon size={18} src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/zhipu-color.svg" className="m-0!" /> 2026-08-26 GLM-5.3 Flash Release

Z.ai released `glm-5.3-flash`, its first natively multimodal GLM-5 model:

* 1M-token context for long coding, document, and agent workflows
* Text, image, video, and file understanding
* Efficient 320B-parameter MoE architecture with 18B active parameters
* Hybrid sparse and linear attention for lower long-context serving cost

Source: [Z.ai GLM-5.3 Flash announcement](https://z.ai/blog/glm-5.3-flash)

***

### <Icon size={18} src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/zhipu-color.svg" className="m-0!" /> 2026-08-14 GLM-5.3 Release

Z.ai released `glm-5.3`, a flagship always-thinking model built for complex coding and long-horizon agents:

* 1M-token context and up to 128K output
* `low`, `high`, and `max` reasoning effort; `max` is recommended for coding
* Stronger coding, autonomous execution, and security analysis than GLM-5.2
* OpenAI-compatible Chat Completions through MixRoute

Source: [Z.ai GLM-5.3 announcement](https://z.ai/blog/glm-5.3)

***

### <Icon size={18} src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/deepseek-color.svg" className="m-0!" /> 2026-08-13 DeepSeek V4 Pro General Availability

DeepSeek released the general-availability version of `deepseek-v4-pro`:

* Stronger production agent and coding performance
* Native OpenAI Responses API support
* `low`, `high`, and `max` reasoning effort
* 1M-token context and up to 384K output

Source: [DeepSeek V4 Pro GA announcement](https://api-docs.deepseek.com/news/news260813/)

***

### <Icon size={18} src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/grok.svg" className="m-0!" /> 2026-08-12 Grok 4.6 Release

xAI released `grok-4.6` for coding, agentic tasks, and knowledge work:

* 500K context window
* Text and image input with text output
* Function calling and structured output
* `low`, `medium`, `high`, and `xhigh` reasoning effort

Source: [xAI release notes](https://docs.x.ai/developers/release-notes)

***

### <Icon size={18} src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/kimi-color.svg" className="m-0!" /> <Icon size={18} src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/google-color.svg" className="m-0!" /> 2026-07-23 Moonshot Kimi K3 & New Gemini Series Launch

* <Icon size={18} src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/kimi-color.svg" className="m-0!" /> **Moonshot**: New flagship model `kimi-k3` is now available, replacing `kimi-k2.6` as the new Kimi series flagship, with upgraded reasoning and multimodal capabilities
* <Icon size={18} src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/google-color.svg" className="m-0!" /> **Google**: Added `gemini-3.6-flash`, `gemini-3.5-flash-lite` and other new models

***

### <Icon size={18} src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/openai.svg" className="m-0!" /> 2026-07-10 GPT 5.6 New Flagship Series Launch

OpenAI's new GPT-5.6 series is now available, introducing a new naming scheme with major breakthroughs in reasoning efficiency, frontend design, and tool calling:

* <Icon size={18} src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/openai.svg" className="m-0!" /> **OpenAI**: New GPT-5.6 series models launched with a new naming scheme:
  * `gpt-5.6-sol` — Flagship reasoning model, supports Pro Mode deep reasoning (`reasoning.mode: "pro"`)
  * `gpt-5.6-terra` — Cost-effective flagship, balancing performance and cost
  * `gpt-5.6-luna` — High-efficiency, high-volume, ideal for production workloads
  * New `reasoning.effort: max` highest reasoning level
  * Supports Programmatic Tool Calling, Multi-agent (beta), explicit Prompt Caching, persisted reasoning (`reasoning.context`)
  * Token efficiency significantly improved, frontier quality with fewer tokens

***

### <Icon size={18} src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/bytedance-color.svg" className="m-0!" /> <Icon size={18} src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/claude-color.svg" className="m-0!" /> 2026-07-01 New Upgrade to the Video and Image Model Library

We have fully introduced ByteDance's latest video and image generation models, giving you a broader range of visual creation capabilities:

* <Icon size={18} src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/bytedance-color.svg" className="m-0!" /> **New Volcano Engine / ByteDance models launched**:
  * Newly launched flagship **SeeDream 5.0** (`seedream-5-0-260128`) and its lightweight version **SeeDream 5.0 Lite** (`seedream-5-0-lite-260128`).
  * Added stable and practical **SeeDream 4.x-level** models, including `seedream-4-0-250828` (version 4.0) and `seedream-4-5-251128` (version 4.5).
  * Added the lightweight flagship video model **Seedance 2.0 Mini** (`dreamina-seedance-2-0-mini-260615`).
  * All newly added models are fully integrated and support high-quality output, making it easy for multilingual developers to call them flexibly across different application scenarios.
* <Icon size={18} src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/claude-color.svg" className="m-0!" /> **Anthropic**: Also launched the flagship model **Claude Sonnet 5** (`claude-sonnet-5`), with a 1M-token ultra-long context, suitable for coding, agents, and enterprise workflows.

***

### <Icon size={18} src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/bytedance-color.svg" className="m-0!" /> 2026-06-05 Major Upgrade to the Video Model Library

Based on the latest progress in the platform's video generation capabilities, we have fully synchronized and updated the Seedance model series:

* <Icon size={18} src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/bytedance-color.svg" className="m-0!" /> **ByteDance (Dreamina/Seedance)**:
  * Newly launched the latest flagship `dreamina-seedance-2-0-260128` (Seedance 2.0) and `dreamina-seedance-2-0-fast-260128` (fast version).
  * Added support for the high-quality professional version `seedance-1-5-pro-251215` (1.5 Pro).
  * Aligned and updated the 1.0 series, including `seedance-1-0-pro-250528` and `seedance-1-0-pro-fast-251015`.
  * Also upgraded the developer documentation for video task submission and querying, and added English and Traditional Chinese code examples and comparison tables to make integration easier for multilingual developers.

***

### <Icon icon="layer-group" size={18} /> 2026-05-27 Full Model Library Synchronization Update

Based on the latest platform API status, we have fully synchronized and updated the models supported by the platform:

* <Icon size={18} src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/openai.svg" className="m-0!" /> **OpenAI**: Launched the `gpt-5.5` flagship series, the `gpt-5.4` series, the reasoning model `o4-mini`, and the image model `gpt-image-2`
* <Icon size={18} src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/claude-color.svg" className="m-0!" /> **Anthropic**: Launched Anthropic model updates, including `claude-opus-4-7`, `claude-sonnet-5`, and `claude-haiku-4-5-20251001`
* <Icon size={18} src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/google-color.svg" className="m-0!" /> **Google**: Launched the Gemini 3.1 and 3.5 series, including `gemini-3.5-flash`, `gemini-3.1-pro-preview`, and more
* <Icon size={18} src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/deepseek-color.svg" className="m-0!" /> **DeepSeek**: Launched the V4 series, including `deepseek-v4-pro` and `deepseek-v4-flash`
* <Icon size={18} src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/grok.svg" className="m-0!" /> **xAI**: Launched the Grok 4 series, including `grok-4.20-beta-0309-reasoning`, and more
* <Icon size={18} src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/alibaba-color.svg" className="m-0!" /> <Icon size={18} src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/zhipu-color.svg" className="m-0!" /> <Icon size={18} src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/kimi-color.svg" className="m-0!" /> **Chinese models**: Launched key flagship models such as `qwen3.7-max`, `glm-4-plus`, and `kimi-k2.6`

***

<Note>
  Update frequency: this page is updated regularly. We recommend bookmarking it and checking back often. All pricing adjustments and model updates will be announced here as soon as possible.
</Note>

<Tip>
  Newly launched models often come with special promotions during the initial launch period, so we recommend trying them early.
</Tip>


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.