From 5a28a2debcd40ccb1b303d1790f935f94dd60010 Mon Sep 17 00:00:00 2001 From: sophia Date: Fri, 14 Aug 2026 18:20:52 +0800 Subject: [PATCH] docs: add GLM-5.3 and Grok 4.6 pricing --- docs/llmservice/models/deepseek-v4-flash.md | 13 +++- docs/llmservice/models/glm-5-2.md | 2 +- docs/llmservice/models/glm-5-3.md | 59 +++++++++++++++++++ docs/llmservice/models/grok-4.6.md | 53 +++++++++++++++++ docs/llmservice/pricing-and-usage.md | 20 ++----- .../promotions-and-pricing-notices.md | 40 +++++++++++++ .../current.json | 4 ++ .../llmservice/models/deepseek-v4-flash.md | 13 +++- .../current/llmservice/models/glm-5-2.md | 2 +- .../current/llmservice/models/glm-5-3.md | 59 +++++++++++++++++++ .../current/llmservice/models/grok-4.6.md | 53 +++++++++++++++++ .../current/llmservice/pricing-and-usage.md | 20 ++----- .../promotions-and-pricing-notices.md | 40 +++++++++++++ package.json | 2 +- sidebars.js | 5 +- 15 files changed, 347 insertions(+), 38 deletions(-) create mode 100644 docs/llmservice/models/glm-5-3.md create mode 100644 docs/llmservice/models/grok-4.6.md create mode 100644 docs/llmservice/promotions-and-pricing-notices.md create mode 100644 i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/glm-5-3.md create mode 100644 i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/grok-4.6.md create mode 100644 i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/promotions-and-pricing-notices.md diff --git a/docs/llmservice/models/deepseek-v4-flash.md b/docs/llmservice/models/deepseek-v4-flash.md index d9e5f8ed..93f5eed5 100644 --- a/docs/llmservice/models/deepseek-v4-flash.md +++ b/docs/llmservice/models/deepseek-v4-flash.md @@ -1,9 +1,18 @@ -# DeepSeek V4 Flash +# DeepSeek-V4-Flash ## Overview DeepSeek-V4-Flash is DeepSeek's high-efficiency open-source language model, released alongside V4-Pro on April 24, 2026 under the MIT License. With 284 billion total parameters and only 13 billion active parameters, it delivers performance within striking distance of V4-Pro at roughly 3.1x lower cost, making it one of the most cost-effective models available. +:::tip 🔥 Limited-Time Free Access +Offer starts August 17, 2026, and applies to DeepSeek-V4-Flash on B.AI Chat and API. + +* **Chat:** Usage is billed at `0 Credits` during the offer. +* **API:** Usage is billed at `0 Credits` during the offer. No per-request, input, cache write, cache read, or output token fees apply. + +After the offer ends, the model will return to standard pricing. Offer end time, eligibility, actual charges, and final billing are subject to the platform display. +::: + ## Key Features * **Ultra-Efficient Architecture**: 284B total parameters with just 13B activated per forward pass, resulting in a compact 160GB download that runs on significantly less hardware than frontier models while maintaining strong performance. @@ -40,7 +49,7 @@ DeepSeek-V4-Flash is DeepSeek's high-efficiency open-source language model, rele | Model | Input (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | Output (Credits/Token) | Web Search (Credits/Use) | Billing Notes | | :--- | --------------------: | --------------------------: | -------------------------: | ---------------------: | -----------------------: | :--- | -| **DeepSeek V4 Flash** | `0.28` | `0.28` | `0.0056` | `0.56` | `-` | - | +| **DeepSeek-V4-Flash** | `0.28` | `0.28` | `0.0056` | `0.56` | `-` | - | :::info Pricing note Prices shown in the documentation are B.AI standard reference prices for base billing purposes. B.AI may provide lower actual usage costs through top-up bonuses and account benefits. Specific prices, bonus Credits, and account benefits are subject to the platform display and final billing records. diff --git a/docs/llmservice/models/glm-5-2.md b/docs/llmservice/models/glm-5-2.md index 1571a8d5..532c94bb 100644 --- a/docs/llmservice/models/glm-5-2.md +++ b/docs/llmservice/models/glm-5-2.md @@ -4,7 +4,7 @@ GLM-5.2 is a GLM-family text foundation model developed by Z.AI and released on June 16, 2026. It is positioned for long-horizon coding and engineering tasks, with a 1M-token context window, 128K maximum output, and a `reasoning_effort` control for adjusting reasoning depth. -:::tip Limited-time offer: GLM-5.2 at 40% off +:::note Limited-time offer: GLM-5.2 at 40% off Offer starts August 12, 2026. **Eligibility:** This offer applies to GLM-5.2 requests made through the B.AI API and B.AI web app. diff --git a/docs/llmservice/models/glm-5-3.md b/docs/llmservice/models/glm-5-3.md new file mode 100644 index 00000000..14283c99 --- /dev/null +++ b/docs/llmservice/models/glm-5-3.md @@ -0,0 +1,59 @@ +# GLM-5.3 + +## Overview + +GLM-5.3 is a text foundation model released by Z.AI on August 14, 2026 for complex coding, long-horizon agent tasks, and cybersecurity work. It uses the same base model as GLM-5.2; Z.AI attributes the update's gains to scaled post-training across more environments, more diverse tasks, and longer trajectories. + +:::note 🎁 Limited-time offer: GLM-5.3 at 10% off +Offer starts August 14, 2026. + +**Eligibility:** This offer applies to GLM-5.3 requests made through the B.AI API and B.AI web app. + +For a limited time, eligible requests are billed at 90% of the standard reference price: Input `1.26`, Cache Write `1.26`, Cache Read `0.234`, and Output `3.96` Credits/Token. + +This page continues to show standard reference prices. Offer end time, eligibility, actual settlement prices, and final billing are subject to the platform display. +::: + +## Key Features + +* **Scaled Post-Training**: Retains the GLM-5.2 base model while expanding reinforcement-learning environments, task diversity, and training compute for long-horizon professional workflows. +* **Configurable Always-On Reasoning**: Supports `low`, `high`, and `max` reasoning effort, with `max` as the default. Native GLM-5.3 requests require thinking to remain enabled. +* **Coding and Agent Performance**: Z.AI reports 28.3 on Terminal-Bench 3.0, 66.9 on DeepSWE v1.1, 78.1 on FrontierSWE, and 48.2 on AutomationBench v1.0.6. +* **Cybersecurity Evaluation**: Z.AI reports 84.5 on CyberGym, 54.4 on ExploitBench, and 105/130 completed ExploitGym tasks under normalized two-hour/six-hour budgets. +* **1M-Token Coding Workflows**: The GLM Coding Plan supports a 1M-token context. Claude Code users enable it with the `glm-5.3[1m]` model name and a 1,000,000-token auto-compaction window. + +## Best Use Cases + +* **Complex Software Engineering**: Repository-scale implementation, debugging, performance optimization, and test-fix-verify loops that require sustained work across many files and tools. +* **Long-Horizon Coding Agents**: ZCode, Claude Code, Codex, OpenCode, Cline, and other configurable agents that can use Z.AI's Anthropic-compatible or OpenAI-compatible Coding Plan endpoints. +* **Authorized Security Research**: Vulnerability discovery, validation, and exploit-chain analysis in systems the operator is permitted to test. +* **Tool-Driven Professional Workflows**: Multi-step engineering and research tasks with executable environments, objective verification, and iterative feedback. + +## Capabilities and Limitations + +| Capability | Description | +| :--- | :--- | +| **Reasoning** | Thinking is always enabled. `reasoning_effort` supports `low`, `high`, and `max`; the default is `max`, which Z.AI recommends for coding tasks. | +| **Creative Writing** | General text generation is available. | +| **Coding** | Z.AI reports Terminal-Bench 2.1: 88.2, Terminal-Bench 3.0: 28.3, DeepSWE v1.1: 66.9, NL2Repo: 58.0, FrontierSWE: 78.1, and SWE-Marathon v1.1: 42.5. | +| **Multimodal** | Text input and text output. | +| **Response Speed** | Not published as a guaranteed API rate. | +| **Context Window** | Up to 1M tokens in GLM Coding Plan workflows. Claude Code requires the `glm-5.3[1m]` suffix to enable the 1M-token mode. | +| **Max Output** | Not published as a general API limit. | +| **Tool Use** | Designed and evaluated in tool-using coding-agent harnesses; available to Coding Plan users through ZCode and configurable Anthropic-compatible or OpenAI-compatible agents. | +| **Multilingual** | Natural-language prompting is supported. | + +### Known Limitations + +* Native GLM-5.3 API requests do not support `thinking.type: "disabled"`; applications must enable thinking and can choose `reasoning_effort: "low"` for lighter reasoning. The Coding Plan compatibility layer may automatically map disabled thinking to `low`. +* The model is text-only; image, audio, and video inputs are not advertised for GLM-5.3. + +## Credits Usage + +| Model | Input (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | Output (Credits/Token) | Web Search (Credits/Use) | Billing Notes | +| :--- | --------------------: | --------------------------: | -------------------------: | ---------------------: | -----------------------: | :--- | +| **GLM-5.3** | `1.40` | `1.40` | `0.26` | `4.40` | `-` | - | + +:::info Pricing note +Prices shown in the documentation are B.AI standard reference prices for base billing purposes. B.AI may provide lower actual usage costs through top-up bonuses and account benefits. Specific prices, bonus Credits, and account benefits are subject to the platform display and final billing records. +::: diff --git a/docs/llmservice/models/grok-4.6.md b/docs/llmservice/models/grok-4.6.md new file mode 100644 index 00000000..20a78fec --- /dev/null +++ b/docs/llmservice/models/grok-4.6.md @@ -0,0 +1,53 @@ +# Grok 4.6 + +## Overview + +Grok 4.6 is a SpaceXAI reasoning model in the Grok 4 family, released on August 12, 2026 for coding, long-running agents, interactive and visual projects, and knowledge work. Available through the API as `grok-4.6`, it supports text and image input, text output, a 500,000-token context window, and four configurable reasoning-effort levels. + +## Key Features + +* **Long-Horizon Agentic Work**: Trained on agentic reinforcement-learning tasks across knowledge work, general coding, kernel optimization, web development, and computer-aided design, with an emphasis on sustaining complex work across many steps. +* **Configurable Reasoning**: Supports `low`, `medium`, `high`, and `xhigh` reasoning effort, with `high` as the default. Reasoning cannot be disabled, and the API can stream summarized reasoning content. +* **Coding and Knowledge-Work Evaluations**: SpaceXAI reports 69.9% on CursorBench v3.2, 65.9% on DeepSWE v1.1, 61.3% on FrontierCode v1.1 Extended, and 57.5% on APEX-Agents. +* **Long Multimodal Context**: Accepts text and image input within a 500,000-token context window and returns text output. Prompts at or above 200,000 tokens use long-context pricing. +* **Structured Agent Workflows**: Supports function calling, parallel tool calls, structured outputs, and built-in tools such as web search and X search. + +## Best Use Cases + +* **Repository-Scale Software Engineering**: Implementing features, debugging, refactoring, and validating changes across large codebases or long-running coding sessions. +* **Interactive Product Prototypes**: Turning a broad product idea into a working application, including its structure, visual language, and core interactions, then iterating from feedback. +* **Tool-Using Research Agents**: Combining reasoning with web or X search, custom functions, structured outputs, and repeated verification steps. +* **Technical Knowledge Work**: Analyzing documents and images or producing technical artifacts across science, engineering, mathematics, and other professional domains. + +## Capabilities and Limitations + +| Capability | Description | +| :--- | :--- | +| **Reasoning** | Supports `low`, `medium`, `high`, and `xhigh` reasoning effort; `high` is the default and reasoning cannot be disabled. Official results include 61 on the AA Intelligence Index and 1,753 on GDPVal-AA v2. | +| **Coding** | Designed for long-running agentic coding and technical workflows. Official results include 69.9% on CursorBench v3.2, 65.9% on DeepSWE v1.1, 61.3% on FrontierCode v1.1 Extended, and 26% on Terminal-Bench v3.0. | +| **Creative Writing** | Supports general text generation and document creation. | +| **Multimodal** | Text and image input with text output. | +| **Response Speed** | SpaceXAI has not published a model-specific latency or tokens-per-second figure. | +| **Context Window** | 500,000 tokens. Prompts at or above 200,000 tokens are billed at the long-context rates for all tokens in the request. | +| **Max Output** | SpaceXAI's release notes state that the model has no text output limit. | +| **Tool Use** | Function calling, parallel tool calls, structured outputs, and built-in tools including web search and X search. The Responses API also supports code execution, file or collections search, and Remote MCP tools. | +| **Multilingual** | Natural-language prompting is supported. | +| **Knowledge Cutoff** | February 1, 2026. | + +### Known Limitations + +* `logprobs` and `top_logprobs` are not supported by Grok 4.20 and newer models. Reasoning requests also reject `presencePenalty`, `frequencyPenalty`, and `stop`. +* SpaceXAI has not published a model-specific throughput figure, multilingual evaluation, or separate numeric output-token ceiling. + +## Credits Usage + +| Model and Context Tier | Input (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | Output (Credits/Token) | +| :--- | --------------------: | --------------------------: | -------------------------: | ---------------------: | +| **Grok 4.6** | `2.00` | `2.00` | `0.50` | `6.00` | +| **Grok 4.6** (>=200K prompt tokens) | `4.00` | `2.00` | `1.00` | `12.00` | + +* Once a prompt reaches 200,000 tokens, long-context rates apply to all input, cached input, reasoning, and output tokens in the request. Reasoning tokens are billed at the output-token rate. + +:::info Pricing note +Prices shown in the documentation are B.AI standard reference prices for base billing purposes. B.AI may provide lower actual usage costs through top-up bonuses and account benefits. Specific prices, bonus Credits, and account benefits are subject to the platform display and final billing records. +::: diff --git a/docs/llmservice/pricing-and-usage.md b/docs/llmservice/pricing-and-usage.md index fedb68a2..3f82e40b 100644 --- a/docs/llmservice/pricing-and-usage.md +++ b/docs/llmservice/pricing-and-usage.md @@ -12,20 +12,8 @@ The platform uses a unified Credits system to measure and settle usage across al **Model pricing:** Different AI models have different pricing based on their capabilities and compute cost. In general, more capable models consume more Credits. Cache-enabled requests may incur separate cache write and cache read usage. Web search incurs an additional per-use charge. Some models do not support web search and are marked with `-`. See the table below for detailed pricing: -:::caution Planned DeepSeek API Pricing Adjustment -Due to a recent pricing adjustment by DeepSeek, B.AI plans to make a corresponding adjustment to pricing for DeepSeek API services. Please plan your usage accordingly. - -The adjustment scope, effective date, and final prices are subject to the formal announcement and platform display. -::: - -:::tip 🎁 Limited-time offer: GLM-5.2 at 40% off -Offer starts August 12, 2026. - -**Eligibility:** This offer applies to GLM-5.2 requests made through the B.AI API and B.AI web app. - -For a limited time, eligible requests are billed at 60% of the standard reference price: Input `0.84`, Cache Write `0.84`, Cache Read `0.168`, and Output `2.64` Credits/Token. - -The table below continues to show standard reference prices. Offer end time, eligibility, actual settlement price, and final billing are subject to the platform display and final billing records. +:::info Current promotions and pricing updates +The table below lists standard reference prices only. For current limited-time offers and pricing updates, see [Promotions and Pricing Updates](./promotions-and-pricing-notices.md). Eligibility, actual settlement prices, and final billing are subject to the platform display. ::: | Model | Input (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | Output (Credits/Token) | Web Search (Credits/Use) | @@ -38,11 +26,13 @@ The table below continues to show standard reference prices. Offer end time, eli | Qwen3.8-Max | 2.00 | 2.00 | 0.25 | 6.00 | - | | Qwen3.7-Max | 1.65 | 1.65 | 0.33 | 4.951 | - | | Qwen3.6-27B | 0.19 | 0.19 | 0.019 | 2.99 | - | +| GLM-5.3 | 1.40 | 1.40 | 0.26 | 4.40 | - | | GLM-5.2 | 1.40 | 1.40 | 0.28 | 4.40 | - | | GLM-5.1 | 1.40 | 1.40 | 0.28 | 4.40 | - | | DeepSeek V3.2 | 0.29 | 0.29 | 0.145 | 0.44 | - | -| DeepSeek V4 Flash | 0.28 | 0.28 | 0.0056 | 0.56 | - | +| DeepSeek-V4-Flash | 0.28 | 0.28 | 0.0056 | 0.56 | - | | DeepSeek V4 Pro | 0.87 | 0.87 | 0.0087 | 1.74 | - | +| Grok 4.6 | 2.00 | 2.00 | 0.50 | 6.00 | - | | Grok 4.5 | 2.00 | 2.00 | 0.30 | 6.00 | - | | GPT-5.6 Sol | 5.00 | 6.25 | 0.50 | 30.00 | 10,000 | | GPT-5.6 Terra | 2.00 | 2.50 | 0.20 | 12.00 | 10,000 | diff --git a/docs/llmservice/promotions-and-pricing-notices.md b/docs/llmservice/promotions-and-pricing-notices.md new file mode 100644 index 00000000..86e64288 --- /dev/null +++ b/docs/llmservice/promotions-and-pricing-notices.md @@ -0,0 +1,40 @@ +# Promotions and Pricing Updates + +This page summarizes current limited-time offers and pricing updates. The [Pricing and Usage](./pricing-and-usage.md) table continues to show standard reference prices. Eligibility, offer periods, actual settlement prices, and final billing are subject to the platform display. + +## Promotions + +:::tip 🔥 Limited-Time Free Access: DeepSeek-V4-Flash +Offer starts August 17, 2026. + +This offer applies to B.AI Chat and API: + +* **Chat:** DeepSeek-V4-Flash usage is billed at `0 Credits` during the offer. +* **API:** Usage is billed at `0 Credits` during the offer. No per-request, input, cache write, cache read, or output token fees apply. + +After the offer ends, DeepSeek-V4-Flash will return to standard pricing. See the [model details](./models/deepseek-v4-flash.md). +::: + +:::note 🎁 Limited-time offer: GLM-5.2 at 40% off +Offer starts August 12, 2026. + +**Eligibility:** This offer applies to GLM-5.2 requests made through the B.AI API and B.AI web app. + +For a limited time, eligible requests are billed at 60% of the standard reference price: Input `0.84`, Cache Write `0.84`, Cache Read `0.168`, and Output `2.64` Credits/Token. See the [model details](./models/glm-5-2.md). +::: + +:::note 🎁 Limited-time offer: GLM-5.3 at 10% off +Offer starts August 14, 2026. + +**Eligibility:** This offer applies to GLM-5.3 requests made through the B.AI API and B.AI web app. + +For a limited time, eligible requests are billed at 90% of the standard reference price: Input `1.26`, Cache Write `1.26`, Cache Read `0.234`, and Output `3.96` Credits/Token. See the [model details](./models/glm-5-3.md). +::: + +## Pricing Updates + +:::caution Planned DeepSeek API Pricing Adjustment +Due to a recent pricing adjustment by DeepSeek, B.AI plans to make a corresponding adjustment to pricing for DeepSeek API services. Please plan your usage accordingly. + +The adjustment scope, effective date, and final prices are subject to the formal announcement and platform display. +::: diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current.json b/i18n/zh-Hans/docusaurus-plugin-content-docs/current.json index 596261f3..6caf54e5 100644 --- a/i18n/zh-Hans/docusaurus-plugin-content-docs/current.json +++ b/i18n/zh-Hans/docusaurus-plugin-content-docs/current.json @@ -71,6 +71,10 @@ "message": "定价与用量", "description": "The label for the doc item Pricing and Usage in sidebar docsSidebar" }, + "sidebar.docsSidebar.doc.Promotions and Pricing Updates": { + "message": "活动与调整公告", + "description": "The label for the doc item Promotions and Pricing Updates in sidebar docsSidebar" + }, "sidebar.docsSidebar.doc.Invitation Rewards": { "message": "邀请返利规则", "description": "The label for the doc item Invitation Rewards in sidebar docsSidebar" diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/deepseek-v4-flash.md b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/deepseek-v4-flash.md index 713e8643..d66541ff 100644 --- a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/deepseek-v4-flash.md +++ b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/deepseek-v4-flash.md @@ -1,9 +1,18 @@ -# DeepSeek V4 Flash +# DeepSeek-V4-Flash ## 概述 DeepSeek-V4-Flash 是 DeepSeek 于 2026 年 4 月 24 日与 V4-Pro 同步发布的高效率开源大语言模型，采用 MIT License。该模型总参数量为 284B，但每次前向仅激活 13B 参数，以仅为 V4-Pro 约 1/3.1 的成本提供接近旗舰模型的性能，是当前极具性价比的模型之一。 +:::tip 🔥 限时免费开放 +活动开始时间：2026 年 8 月 17 日，适用于 B.AI Chat 和 API 中的 DeepSeek-V4-Flash。 + +* **Chat：** 活动期间使用按 `0 Credits` 结算。 +* **API：** 活动期间使用按 `0 Credits` 结算，不收取单次请求、输入、缓存写入、缓存读取或输出的费用。 + +活动结束后，模型将恢复标准价格。活动结束时间、适用规则、实际结算结果及最终账单以平台页面展示为准。 +::: + ## 核心特性 * **超高效率架构**：总参数量 284B，每次前向仅激活 13B 参数，模型下载体积约 160GB，相比前沿模型对硬件要求更低，同时保持出色性能。 @@ -40,7 +49,7 @@ DeepSeek-V4-Flash 是 DeepSeek 于 2026 年 4 月 24 日与 V4-Pro 同步发布 | 模型名称 | 输入 (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | 输出 (Credits/Token) | 网页搜索（Credits/次） | 计费说明 | | :--- | --------------------: | --------------------------: | -------------------------: | -------------------: | ---------------------: | :--- | -| **DeepSeek V4 Flash** | `0.28` | `0.28` | `0.0056` | `0.56` | `-` | - | +| **DeepSeek-V4-Flash** | `0.28` | `0.28` | `0.0056` | `0.56` | `-` | - | :::info 价格说明 文档价格为 B.AI 平台模型标准参考价，仅供基础计费说明使用。B.AI 可能会通过充值赠送及账户权益等方式，为用户提供更低的实际使用成本。具体价格、赠送积分及账户权益请以平台页面展示及最终账单为准。 diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/glm-5-2.md b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/glm-5-2.md index 77993d4f..ae7f5085 100644 --- a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/glm-5-2.md +++ b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/glm-5-2.md @@ -4,7 +4,7 @@ GLM-5.2 是由 Z.AI 开发的 GLM 系列文本基础模型，于 2026 年 6 月 16 日发布。该模型面向长周期代码和工程任务，支持 1M tokens 上下文窗口、128K 最大输出，并提供 `reasoning_effort` 参数用于调整推理深度。 -:::tip 限时活动：GLM-5.2 6 折 +:::note 限时活动：GLM-5.2 6 折 活动开始时间：2026 年 8 月 12 日。 **适用范围：** 本活动适用于通过 B.AI API 和 B.AI 网页端发起的 GLM-5.2 调用。 diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/glm-5-3.md b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/glm-5-3.md new file mode 100644 index 00000000..8f94ac66 --- /dev/null +++ b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/glm-5-3.md @@ -0,0 +1,59 @@ +# GLM-5.3 + +## 概述 + +GLM-5.3 是 Z.AI 于 2026 年 8 月 14 日发布的文本基础模型，面向复杂编码、长周期 Agent 任务和网络安全工作。它与 GLM-5.2 使用相同的基础模型；Z.AI 将本次更新的能力提升归因于在更多环境、更丰富任务和更长轨迹上扩展后训练。 + +:::note 🎁 限时活动：GLM-5.3 9 折 +活动开始时间：2026 年 8 月 14 日。 + +**适用范围：** 本活动适用于通过 B.AI API 和 B.AI 网页端发起的 GLM-5.3 调用。 + +限时活动期间，符合条件的调用按标准参考价的 90% 结算：输入 `1.26`、缓存写入 `1.26`、缓存读取 `0.234`、输出 `3.96` Credits/Token。 + +本页价格表继续展示标准参考价；活动结束时间、适用规则、实际结算价格及最终账单以平台页面展示为准。 +::: + +## 核心特性 + +* **扩展后训练**：保留 GLM-5.2 的基础模型，同时扩展强化学习环境、任务多样性和训练计算量，以提升长周期专业工作流表现。 +* **可配置的始终开启推理**：支持 `low`、`high` 和 `max` 推理强度，默认使用 `max`。原生 GLM-5.3 请求要求保持推理开启。 +* **编程与 Agent 性能**：Z.AI 报告其在 Terminal-Bench 3.0、DeepSWE v1.1、FrontierSWE 和 AutomationBench v1.0.6 上的得分分别为 28.3、66.9、78.1 和 48.2。 +* **网络安全评测**：Z.AI 报告其在 CyberGym 和 ExploitBench 上的得分分别为 84.5 和 54.4；在统一的两小时/六小时预算下完成了 105/130 个 ExploitGym 任务。 +* **1M Token 编程工作流**：GLM Coding Plan 支持 1M token 上下文。Claude Code 用户可使用 `glm-5.3[1m]` 模型名称和 1,000,000 token 自动压缩窗口启用该能力。 + +## 适用场景 + +* **复杂软件工程**：需要跨多个文件和工具持续推进的仓库级实现、调试、性能优化和测试-修复-验证循环。 +* **长周期编程 Agent**：可使用 Z.AI 兼容 Anthropic 或 OpenAI 协议的 Coding Plan 端点的 ZCode、Claude Code、Codex、OpenCode、Cline 及其他可配置 Agent。 +* **经授权的安全研究**：在操作方获准测试的系统中进行漏洞发现、验证和利用链分析。 +* **工具驱动的专业工作流**：具有可执行环境、客观验证和迭代反馈的多步骤工程与研究任务。 + +## 能力与限制 + +| 能力维度 | 说明 | +| :--- | :--- | +| **推理能力** | 推理始终开启。`reasoning_effort` 支持 `low`、`high` 和 `max`；默认值为 `max`，Z.AI 建议将其用于编码任务。 | +| **创意写作** | 支持通用文本生成。 | +| **编程能力** | Z.AI 报告 Terminal-Bench 2.1 得分为 88.2、Terminal-Bench 3.0 得分为 28.3、DeepSWE v1.1 得分为 66.9、NL2Repo 得分为 58.0、FrontierSWE 得分为 78.1、SWE-Marathon v1.1 得分为 42.5。 | +| **多模态能力** | 支持文本输入和文本输出。 | +| **响应速度** | 未公布有保证的 API 速率。 | +| **上下文窗口** | 在 GLM Coding Plan 工作流中最高支持 1M token。Claude Code 需要使用 `glm-5.3[1m]` 后缀启用 1M token 模式。 | +| **最大输出** | 未公布通用 API 最大输出限制。 | +| **工具调用** | 在工具调用型 Coding Agent 评测框架中设计并评估；Coding Plan 用户可通过 ZCode 和可配置的 Anthropic 兼容或 OpenAI 兼容 Agent 使用。 | +| **多语言能力** | 支持自然语言提示。 | + +### 已知限制 + +* 原生 GLM-5.3 API 请求不支持 `thinking.type: "disabled"`；应用必须启用推理，并可选择 `reasoning_effort: "low"` 以降低推理强度。Coding Plan 兼容层可能会自动将关闭推理映射为 `low`。 +* 该模型仅支持文本，未宣称支持图像、音频或视频输入。 + +## 积分消耗 + +| 模型名称 | 输入 (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | 输出 (Credits/Token) | 网页搜索（Credits/次） | 计费说明 | +| :--- | --------------------: | --------------------------: | -------------------------: | -------------------: | ---------------------: | :--- | +| **GLM-5.3** | `1.40` | `1.40` | `0.26` | `4.40` | `-` | - | + +:::info 价格说明 +文档价格为 B.AI 平台模型标准参考价，仅供基础计费说明使用。B.AI 可能会通过充值赠送及账户权益等方式，为用户提供更低的实际使用成本。具体价格、赠送积分及账户权益请以平台页面展示及最终账单为准。 +::: diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/grok-4.6.md b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/grok-4.6.md new file mode 100644 index 00000000..99710bf4 --- /dev/null +++ b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/grok-4.6.md @@ -0,0 +1,53 @@ +# Grok 4.6 + +## 概述 + +Grok 4.6 是 SpaceXAI 推出的 Grok 4 系列推理模型，于 2026 年 8 月 12 日发布，面向编码、长周期 Agent、交互与视觉项目以及知识工作。该模型可通过 API 使用，模型 ID 为 `grok-4.6`；支持文本和图像输入、文本输出、500,000 token 上下文窗口，以及四档可配置的推理强度。 + +## 核心特性 + +* **长周期 Agent 工作**：在知识工作、通用编程、内核优化、Web 开发和计算机辅助设计等 Agent 强化学习任务上训练，重点提升复杂任务在多步骤执行中的持续能力。 +* **可配置推理**：支持 `low`、`medium`、`high` 和 `xhigh` 推理强度，默认使用 `high`。推理无法关闭，API 可流式返回摘要推理内容。 +* **编程与知识工作评测**：SpaceXAI 报告其在 CursorBench v3.2、DeepSWE v1.1、FrontierCode v1.1 Extended 和 APEX-Agents 上的得分分别为 69.9%、65.9%、61.3% 和 57.5%。 +* **长上下文多模态能力**：支持在 500,000 token 上下文窗口内接收文本和图像输入，并输出文本。提示词达到或超过 200,000 token 时使用长上下文价格。 +* **结构化 Agent 工作流**：支持函数调用、并行工具调用、结构化输出，以及网页搜索和 X 搜索等内置工具。 + +## 适用场景 + +* **仓库级软件工程**：跨大型代码库或长周期编程会话实现功能、调试、重构和验证变更。 +* **交互式产品原型**：将宽泛的产品想法转化为可运行应用，包括其结构、视觉语言和核心交互，并根据反馈持续迭代。 +* **工具型研究 Agent**：结合推理、网页或 X 搜索、自定义函数、结构化输出与反复验证步骤。 +* **技术知识工作**：分析文档和图像，或在科学、工程、数学等专业领域产出技术成果。 + +## 能力与限制 + +| 能力维度 | 说明 | +| :--- | :--- | +| **推理能力** | 支持 `low`、`medium`、`high` 和 `xhigh` 推理强度；默认使用 `high`，且推理无法关闭。官方结果包括 AA Intelligence Index 得分 61，以及 GDPVal-AA v2 得分 1,753。 | +| **编程能力** | 面向长周期 Agent 编程和技术工作流设计。官方结果包括 CursorBench v3.2 得分 69.9%、DeepSWE v1.1 得分 65.9%、FrontierCode v1.1 Extended 得分 61.3%，以及 Terminal-Bench v3.0 得分 26%。 | +| **创意写作** | 支持通用文本生成和文档创建。 | +| **多模态能力** | 支持文本和图像输入，输出为文本。 | +| **响应速度** | SpaceXAI 尚未发布模型专属的延迟或每秒 token 数指标。 | +| **上下文窗口** | 500,000 token。提示词达到或超过 200,000 token 时，请求中的所有 token 按长上下文价格计费。 | +| **最大输出** | SpaceXAI 的发布说明表示该模型没有文本输出上限。 | +| **工具调用** | 支持函数调用、并行工具调用、结构化输出，以及网页搜索和 X 搜索等内置工具。Responses API 还支持代码执行、文件或集合搜索，以及 Remote MCP 工具。 | +| **多语言能力** | 支持自然语言提示。 | +| **知识截止日期** | 2026 年 2 月 1 日。 | + +### 已知限制 + +* Grok 4.20 及更新模型不支持 `logprobs` 和 `top_logprobs`。推理请求也不支持 `presencePenalty`、`frequencyPenalty` 和 `stop`。 +* SpaceXAI 尚未发布模型专属吞吐量、多语言评测或单独的数值型输出 token 上限。 + +## 积分消耗 + +| 模型与上下文档位 | 输入 (Credits/Token) | 缓存写入 (Credits/Token) | 缓存读取 (Credits/Token) | 输出 (Credits/Token) | +| :--- | --------------------: | ------------------------: | ------------------------: | --------------------: | +| **Grok 4.6** | `2.00` | `2.00` | `0.50` | `6.00` | +| **Grok 4.6**（提示词 >=200K token） | `4.00` | `2.00` | `1.00` | `12.00` | + +* 当提示词达到 200,000 token 时，请求中的所有输入、缓存输入、推理和输出 token 均按长上下文价格计费。推理 token 按输出 token 价格计费。 + +:::info 价格说明 +文档价格为 B.AI 平台模型标准参考价，仅供基础计费说明使用。B.AI 可能会通过充值赠送及账户权益等方式，为用户提供更低的实际使用成本。具体价格、赠送积分及账户权益请以平台页面展示及最终账单为准。 +::: diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/pricing-and-usage.md b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/pricing-and-usage.md index 56976891..26129667 100644 --- a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/pricing-and-usage.md +++ b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/pricing-and-usage.md @@ -12,20 +12,8 @@ **模型定价：** 不同 AI 模型会根据能力和算力成本采用不同定价。通常能力越强，消耗的 Credits 越多。启用缓存的请求还可能产生单独的缓存写入和缓存读取消耗。网页搜索会按次额外收费。不支持网页搜索的模型会以 `-` 标记。详细定价请见下表： -:::caution DeepSeek API 定价调整预告 -由于 DeepSeek 官方近期调整服务定价，B.AI 计划相应上调 DeepSeek API 服务价格。请根据业务需求合理安排使用。 - -具体调整范围、生效时间及最终价格以正式通知和平台页面展示为准。 -::: - -:::tip 🎁 限时活动：GLM-5.2 6 折 -活动开始时间：2026 年 8 月 12 日。 - -**适用范围：** 本活动适用于通过 B.AI API 和 B.AI 网页端发起的 GLM-5.2 调用。 - -限时活动期间，符合条件的调用按标准参考价的 60% 结算：输入 `0.84`、缓存写入 `0.84`、缓存读取 `0.168`、输出 `2.64` Credits/Token。 - -下表继续展示标准参考价；活动结束时间、适用规则、实际结算价格及最终账单以平台页面展示为准。 +:::info 当前活动与调整公告 +下方价格总表仅展示标准参考价。当前限时活动和定价调整公告请查看[活动与调整公告](./promotions-and-pricing-notices.md)。活动适用规则、实际结算价格及最终账单以平台页面展示为准。 ::: | 模型 | 输入（Credits/Token） | 缓存写入（Credits/Token） | 缓存读取（Credits/Token） | 输出（Credits/Token） | 网页搜索（Credits/次） | @@ -38,11 +26,13 @@ | Qwen3.8-Max | 2.00 | 2.00 | 0.25 | 6.00 | - | | Qwen3.7-Max | 1.65 | 1.65 | 0.33 | 4.951 | - | | Qwen3.6-27B | 0.19 | 0.19 | 0.019 | 2.99 | - | +| GLM-5.3 | 1.40 | 1.40 | 0.26 | 4.40 | - | | GLM-5.2 | 1.40 | 1.40 | 0.28 | 4.40 | - | | GLM-5.1 | 1.40 | 1.40 | 0.28 | 4.40 | - | | DeepSeek V3.2 | 0.29 | 0.29 | 0.145 | 0.44 | - | -| DeepSeek V4 Flash | 0.28 | 0.28 | 0.0056 | 0.56 | - | +| DeepSeek-V4-Flash | 0.28 | 0.28 | 0.0056 | 0.56 | - | | DeepSeek V4 Pro | 0.87 | 0.87 | 0.0087 | 1.74 | - | +| Grok 4.6 | 2.00 | 2.00 | 0.50 | 6.00 | - | | Grok 4.5 | 2.00 | 2.00 | 0.30 | 6.00 | - | | GPT-5.6 Sol | 5.00 | 6.25 | 0.50 | 30.00 | 10,000 | | GPT-5.6 Terra | 2.00 | 2.50 | 0.20 | 12.00 | 10,000 | diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/promotions-and-pricing-notices.md b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/promotions-and-pricing-notices.md new file mode 100644 index 00000000..dbcf009a --- /dev/null +++ b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/promotions-and-pricing-notices.md @@ -0,0 +1,40 @@ +# 活动与调整公告 + +本页汇总当前限时活动和定价调整公告。[定价与用量](./pricing-and-usage.md)页面的价格总表继续展示标准参考价。活动适用规则、活动周期、实际结算价格及最终账单以平台页面展示为准。 + +## 活动 + +:::tip 🔥 限时免费开放：DeepSeek-V4-Flash +活动开始时间：2026 年 8 月 17 日。 + +本活动覆盖 B.AI Chat 和 API： + +* **Chat：** 活动期间使用 DeepSeek-V4-Flash，按 `0 Credits` 结算。 +* **API：** 活动期间使用按 `0 Credits` 结算，不收取单次请求、输入、缓存写入、缓存读取或输出的费用。 + +活动结束后，DeepSeek-V4-Flash 将恢复标准价格。详见[模型详情](./models/deepseek-v4-flash.md)。 +::: + +:::note 🎁 限时活动：GLM-5.2 6 折 +活动开始时间：2026 年 8 月 12 日。 + +**适用范围：** 本活动适用于通过 B.AI API 和 B.AI 网页端发起的 GLM-5.2 调用。 + +限时活动期间，符合条件的调用按标准参考价的 60% 结算：输入 `0.84`、缓存写入 `0.84`、缓存读取 `0.168`、输出 `2.64` Credits/Token。详见[模型详情](./models/glm-5-2.md)。 +::: + +:::note 🎁 限时活动：GLM-5.3 9 折 +活动开始时间：2026 年 8 月 14 日。 + +**适用范围：** 本活动适用于通过 B.AI API 和 B.AI 网页端发起的 GLM-5.3 调用。 + +限时活动期间，符合条件的调用按标准参考价的 90% 结算：输入 `1.26`、缓存写入 `1.26`、缓存读取 `0.234`、输出 `3.96` Credits/Token。详见[模型详情](./models/glm-5-3.md)。 +::: + +## 定价调整公告 + +:::caution DeepSeek API 定价调整预告 +由于 DeepSeek 官方近期调整服务定价，B.AI 计划相应上调 DeepSeek API 服务价格。请根据业务需求合理安排使用。 + +具体调整范围、生效时间及最终价格以正式通知和平台页面展示为准。 +::: diff --git a/package.json b/package.json index 291dc033..1a4c7f2c 100644 --- a/package.json +++ b/package.json @@ -1,6 +1,6 @@ { "name": "@x402-tron/docs", - "version": "1.3.19", + "version": "1.3.20", "description": "x402-tron documentation", "license": "MIT", "resolutions": { diff --git a/sidebars.js b/sidebars.js index e96daa91..cc70830c 100644 --- a/sidebars.js +++ b/sidebars.js @@ -140,6 +140,7 @@ const sidebars = { { type: 'doc', id: 'llmservice/quick-start', label: 'Quick Start' }, { type: 'doc', id: 'llmservice/auto-mode', label: 'Auto Mode' }, { type: 'doc', id: 'llmservice/pricing-and-usage', label: 'Pricing and Usage' }, + { type: 'doc', id: 'llmservice/promotions-and-pricing-notices', label: 'Promotions and Pricing Updates' }, { type: 'doc', id: 'llmservice/invitation-rewards', label: 'Invitation Rewards' }, { type: 'category', @@ -200,7 +201,7 @@ const sidebars = { collapsed: true, items: [ { type: 'doc', id: 'llmservice/models/deepseek-v4-pro', label: 'DeepSeek V4 Pro' }, - { type: 'doc', id: 'llmservice/models/deepseek-v4-flash', label: 'DeepSeek V4 Flash' }, + { type: 'doc', id: 'llmservice/models/deepseek-v4-flash', label: 'DeepSeek-V4-Flash' }, { type: 'doc', id: 'llmservice/models/deepseek-v3.2', label: 'DeepSeek V3.2' }, ], }, @@ -209,6 +210,7 @@ const sidebars = { label: 'SpaceXAI (Grok)', collapsed: true, items: [ + { type: 'doc', id: 'llmservice/models/grok-4.6', label: 'Grok 4.6' }, { type: 'doc', id: 'llmservice/models/grok-4.5', label: 'Grok 4.5' }, ], }, @@ -217,6 +219,7 @@ const sidebars = { label: 'Z.AI (GLM)', collapsed: true, items: [ + { type: 'doc', id: 'llmservice/models/glm-5-3', label: 'GLM-5.3' }, { type: 'doc', id: 'llmservice/models/glm-5-2', label: 'GLM-5.2' }, { type: 'doc', id: 'llmservice/models/glm-5-1', label: 'GLM-5.1' }, ],