From d9c2682b1b4322dd2c9586d71b776f1b034431f5 Mon Sep 17 00:00:00 2001 From: sophia Date: Fri, 10 Jul 2026 16:18:13 +0800 Subject: [PATCH 1/2] Add GPT-5.6 model pricing docs --- docs/llmservice/models/gpt-5-6-luna.md | 52 +++++++++++++++++++ docs/llmservice/models/gpt-5-6-sol.md | 52 +++++++++++++++++++ docs/llmservice/models/gpt-5-6-terra.md | 52 +++++++++++++++++++ docs/llmservice/pricing-and-usage.md | 7 ++- .../current/llmservice/models/gpt-5-6-luna.md | 52 +++++++++++++++++++ .../current/llmservice/models/gpt-5-6-sol.md | 52 +++++++++++++++++++ .../llmservice/models/gpt-5-6-terra.md | 52 +++++++++++++++++++ .../current/llmservice/pricing-and-usage.md | 7 ++- .../current/sidebars.js | 3 ++ sidebars.js | 3 ++ 10 files changed, 328 insertions(+), 4 deletions(-) create mode 100644 docs/llmservice/models/gpt-5-6-luna.md create mode 100644 docs/llmservice/models/gpt-5-6-sol.md create mode 100644 docs/llmservice/models/gpt-5-6-terra.md create mode 100644 i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-6-luna.md create mode 100644 i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-6-sol.md create mode 100644 i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-6-terra.md diff --git a/docs/llmservice/models/gpt-5-6-luna.md b/docs/llmservice/models/gpt-5-6-luna.md new file mode 100644 index 0000000..95d3064 --- /dev/null +++ b/docs/llmservice/models/gpt-5-6-luna.md @@ -0,0 +1,52 @@ +# GPT-5.6 Luna + +## Overview + +GPT-5.6 Luna is OpenAI's cost-oriented GPT-5.6 tier, made generally available on July 9, 2026. In the API, its model ID is `gpt-5.6-luna`, and OpenAI positions it for efficient, high-volume workloads. + +## Key Features + +* **Cost-Oriented GPT-5.6 Tier**: Designed for high-volume workloads where lower token cost and responsiveness are important. +* **Expanded Reasoning Controls**: Supports `none`, `low`, `medium`, `high`, `xhigh`, and `max` reasoning effort; GPT-5.6 also supports Pro mode through `reasoning.mode: "pro"`. +* **Agentic Tooling**: Supports Responses API workflows, functions, web search, file search, computer use, Programmatic Tool Calling, persisted reasoning, and multi-agent beta. +* **Large Working Context**: Supports a 1.05M-token context window and up to 128K output tokens, with a February 16, 2026 knowledge cutoff. + +## Best Use Cases + +* **High-Volume Assistance**: Summarization, rewriting, classification, extraction, routing, and lightweight analysis. +* **Responsive Product Features**: User-facing assistants, workflow copilots, and routine automation with predictable cost constraints. +* **First-Pass Technical Work**: Initial issue triage, draft code review, test-case generation, and document analysis before escalating difficult cases to Terra or Sol. + +## Capabilities and Limitations + +| Capability | Description | +| :------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------- | +| **Reasoning** | Supports `none`, `low`, `medium`, `high`, `xhigh`, and `max`; API Pro mode is enabled with `reasoning.mode: "pro"` rather than a separate Pro model slug. | +| **Coding** | Official benchmark examples include SWE-Bench Pro 62.7%, DeepSWE v1.1 67.2%, and Terminal-Bench 2.1 84.7%. | +| **Creative Writing** | General text generation is supported. | +| **Multimodal** | Text and image input with text output; GPT-5.6 preserves original image dimensions for `original` or `auto` detail. | +| **Response Speed** | Public API latency depends on reasoning effort, tools, and processing tier; Luna is positioned for efficient, high-volume use. | +| **Context Window** | 1.05M tokens. | +| **Max Output** | 128K tokens. | +| **Tool Use** | Functions, web search, file search, computer use, Programmatic Tool Calling, persisted reasoning, and multi-agent beta. | +| **Multilingual** | OpenAI API model documentation lists multilingual support across current models. | + +### Known Limitations + +* Luna is positioned below Terra and Sol for capability, so complex reasoning, sensitive technical work, and quality-first workflows may need escalation. +* Higher reasoning efforts, Pro mode, multi-agent runs, and long-context use can increase latency and cost. +* Cyber and biology safeguards may refuse, block, or pause sensitive requests, including some legitimate dual-use work. +* Prompt cache writes are billed on GPT-5.6 models, so cache breakpoints should be monitored with `cache_write_tokens` and `cached_tokens`. + +## Credits Usage + +| Context | Input (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | Output (Credits/Token) | Web Search (Credits/Use) | Billing Notes | +| :--- | --------------------: | --------------------------: | -------------------------: | ---------------------: | -----------------------: | :--- | +| Short context | `1.00` | `1.25` | `0.10` | `6.00` | `10,000` | Standard GPT-5.6 Luna pricing | +| Long context (>272K input tokens) | `2.00` | `2.50` | `0.20` | `9.00` | `10,000` | Long-context pricing tier | + +:::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. +::: + +* For GPT-5.6 models, cache writes are billed at 1.25x the uncached input rate; cache reads remain discounted at 0.1x input. diff --git a/docs/llmservice/models/gpt-5-6-sol.md b/docs/llmservice/models/gpt-5-6-sol.md new file mode 100644 index 0000000..96610c5 --- /dev/null +++ b/docs/llmservice/models/gpt-5-6-sol.md @@ -0,0 +1,52 @@ +# GPT-5.6 Sol + +## Overview + +GPT-5.6 Sol is OpenAI's flagship GPT-5.6 tier, made generally available on July 9, 2026. In the API, its model ID is `gpt-5.6-sol`, and the `gpt-5.6` alias routes to this tier. It is designed for complex professional work, reasoning, coding, cybersecurity, science, and tool-heavy workflows. + +## Key Features + +* **GPT-5.6 Flagship Tier**: Designed for complex professional work, reasoning, coding, cybersecurity, science, and tool-heavy workflows. +* **Expanded Reasoning Controls**: Supports `none`, `low`, `medium`, `high`, `xhigh`, and `max` reasoning effort; GPT-5.6 also supports Pro mode through `reasoning.mode: "pro"`. +* **Agentic Tooling**: Supports Responses API workflows, functions, web search, file search, computer use, Programmatic Tool Calling, persisted reasoning, and multi-agent beta. +* **Large Working Context**: Supports a 1.05M-token context window and up to 128K output tokens, with a February 16, 2026 knowledge cutoff. + +## Best Use Cases + +* **Complex Software Engineering**: Repository-level debugging, command-line workflows, multi-file implementation, validation, and code review. +* **Long-Horizon Knowledge Work**: Browser, document, spreadsheet, presentation, and computer-use tasks that need sustained context and tool coordination. +* **Defensive Security and Research Support**: Authorized vulnerability review, patch development, threat modeling, biology workflow analysis, and scientific research assistance with human oversight. + +## Capabilities and Limitations + +| Capability | Description | +| :------------------- | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| **Reasoning** | Supports `none`, `low`, `medium`, `high`, `xhigh`, and `max`; API Pro mode is enabled with `reasoning.mode: "pro"` rather than a separate Pro model slug. | +| **Coding** | Official benchmark examples include SWE-Bench Pro 64.6%, DeepSWE v1.1 72.7%, Terminal-Bench 2.1 88.8%, and Terminal-Bench 2.1 Ultra 91.9%. | +| **Creative Writing** | General text generation is supported. | +| **Multimodal** | Text and image input with text output; GPT-5.6 preserves original image dimensions for `original` or `auto` detail. | +| **Response Speed** | Public API latency depends on reasoning effort, tools, and processing tier; OpenAI also announced Cerebras access for Sol at up to 750 tokens per second for select customers. | +| **Context Window** | 1.05M tokens. | +| **Max Output** | 128K tokens. | +| **Tool Use** | Functions, web search, file search, computer use, Programmatic Tool Calling, persisted reasoning, and multi-agent beta. | +| **Multilingual** | OpenAI API model documentation lists multilingual support across current models. | + +### Known Limitations + +* Higher reasoning efforts, Pro mode, multi-agent runs, and long-context use can increase latency and cost. +* Cyber and biology safeguards may refuse, block, or pause sensitive requests, including some legitimate dual-use work. +* OpenAI says GPT-5.6 does not cross the Critical threshold in cybersecurity or biology evaluations, so it should not be treated as an autonomous operator for high-risk work. +* Prompt cache writes are billed on GPT-5.6 models, so cache breakpoints should be monitored with `cache_write_tokens` and `cached_tokens`. + +## Credits Usage + +| Context | Input (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | Output (Credits/Token) | Web Search (Credits/Use) | Billing Notes | +| :--- | --------------------: | --------------------------: | -------------------------: | ---------------------: | -----------------------: | :--- | +| Short context | `5.00` | `6.25` | `0.50` | `30.00` | `10,000` | Standard GPT-5.6 Sol pricing | +| Long context (>272K input tokens) | `10.00` | `12.50` | `1.00` | `45.00` | `10,000` | Long-context pricing tier | + +:::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. +::: + +* For GPT-5.6 models, cache writes are billed at 1.25x the uncached input rate; cache reads remain discounted at 0.1x input. diff --git a/docs/llmservice/models/gpt-5-6-terra.md b/docs/llmservice/models/gpt-5-6-terra.md new file mode 100644 index 0000000..800ce51 --- /dev/null +++ b/docs/llmservice/models/gpt-5-6-terra.md @@ -0,0 +1,52 @@ +# GPT-5.6 Terra + +## Overview + +GPT-5.6 Terra is OpenAI's balanced GPT-5.6 tier, made generally available on July 9, 2026. In the API, its model ID is `gpt-5.6-terra`, and OpenAI positions it for workloads that balance capability and cost. + +## Key Features + +* **Balanced GPT-5.6 Tier**: Positioned between Sol and Luna for production workflows that need strong reasoning at lower cost than Sol. +* **Expanded Reasoning Controls**: Supports `none`, `low`, `medium`, `high`, `xhigh`, and `max` reasoning effort; GPT-5.6 also supports Pro mode through `reasoning.mode: "pro"`. +* **Agentic Tooling**: Supports Responses API workflows, functions, web search, file search, computer use, Programmatic Tool Calling, persisted reasoning, and multi-agent beta. +* **Large Working Context**: Supports a 1.05M-token context window and up to 128K output tokens, with a February 16, 2026 knowledge cutoff. + +## Best Use Cases + +* **Production Knowledge Work**: Drafting, analysis, document processing, structured research, and multi-step business workflows. +* **Software Engineering Assistance**: Debugging, test planning, code review, repository navigation, and implementation support where cost control matters. +* **Scaled Professional Automation**: Tool-heavy workflows that need strong quality but do not require Sol for every request. + +## Capabilities and Limitations + +| Capability | Description | +| :------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------- | +| **Reasoning** | Supports `none`, `low`, `medium`, `high`, `xhigh`, and `max`; API Pro mode is enabled with `reasoning.mode: "pro"` rather than a separate Pro model slug. | +| **Coding** | Official benchmark examples include SWE-Bench Pro 63.4%, DeepSWE v1.1 69.6%, and Terminal-Bench 2.1 87.4%. | +| **Creative Writing** | General text generation is supported. | +| **Multimodal** | Text and image input with text output; GPT-5.6 preserves original image dimensions for `original` or `auto` detail. | +| **Response Speed** | Public API latency depends on reasoning effort, tools, and processing tier; Terra is positioned as the balanced tier for intelligence and cost. | +| **Context Window** | 1.05M tokens. | +| **Max Output** | 128K tokens. | +| **Tool Use** | Functions, web search, file search, computer use, Programmatic Tool Calling, persisted reasoning, and multi-agent beta. | +| **Multilingual** | OpenAI API model documentation lists multilingual support across current models. | + +### Known Limitations + +* Terra is positioned below Sol for capability, so the hardest quality-first workflows may need Sol, Pro mode, or higher reasoning effort. +* Higher reasoning efforts, Pro mode, multi-agent runs, and long-context use can increase latency and cost. +* Cyber and biology safeguards may refuse, block, or pause sensitive requests, including some legitimate dual-use work. +* Prompt cache writes are billed on GPT-5.6 models, so cache breakpoints should be monitored with `cache_write_tokens` and `cached_tokens`. + +## Credits Usage + +| Context | Input (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | Output (Credits/Token) | Web Search (Credits/Use) | Billing Notes | +| :--- | --------------------: | --------------------------: | -------------------------: | ---------------------: | -----------------------: | :--- | +| Short context | `2.50` | `3.125` | `0.25` | `15.00` | `10,000` | Standard GPT-5.6 Terra pricing | +| Long context (>272K input tokens) | `5.00` | `6.25` | `0.50` | `22.50` | `10,000` | Long-context pricing tier | + +:::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. +::: + +* For GPT-5.6 models, cache writes are billed at 1.25x the uncached input rate; cache reads remain discounted at 0.1x input. diff --git a/docs/llmservice/pricing-and-usage.md b/docs/llmservice/pricing-and-usage.md index a0bd6f1..504a517 100644 --- a/docs/llmservice/pricing-and-usage.md +++ b/docs/llmservice/pricing-and-usage.md @@ -24,6 +24,9 @@ The platform uses a unified Credits system to measure and settle usage across al | DeepSeek V3.2 | 0.29 | 0.29 | 0.145 | 0.44 | - | | DeepSeek V4 Flash | 0.28 | 0.28 | 0.0056 | 0.56 | - | | DeepSeek V4 Pro | 0.87 | 0.87 | 0.0087 | 1.74 | - | +| GPT-5.6 Sol | 5.00 | 6.25 | 0.50 | 30.00 | 10,000 | +| GPT-5.6 Terra | 2.50 | 3.125 | 0.25 | 15.00 | 10,000 | +| GPT-5.6 Luna | 1.00 | 1.25 | 0.10 | 6.00 | 10,000 | | GPT-5.4 | 2.50 | 2.50 | 0.25 | 15.00 | 10,000 | | GPT-5.5 | 5.00 | 5.00 | 0.50 | 30.00 | 10,000 | | GPT-5.5 Instant | 5.00 | 5.00 | 0.50 | 30.00 | 10,000 | @@ -47,7 +50,7 @@ The platform uses a unified Credits system to measure and settle usage across al | Gemini 3 Flash | 0.50 | 0.50 | 0.05 | 3.00 | 14,000 | :::caution Main table scope -The main pricing table shows the currently effective standard reference price for each model. The `Cache Write` column represents the billing rate when cache writing occurs; it does not imply a unified cache TTL across all models. Cache behavior, retention time, and extended caching options may vary by model provider. If a model has special caching rules, 1-hour cache write pricing, or time-based pricing, please refer to the corresponding model detail page. +The main pricing table shows the currently effective standard reference price for each model. The `Cache Write` column represents the billing rate when cache writing occurs; it does not imply a unified cache TTL across all models. Cache behavior, retention time, long-context pricing, and extended caching options may vary by model provider. If a model has special caching rules, long-context pricing, 1-hour cache write pricing, or time-based pricing, please refer to the corresponding model detail page. ::: :::info Pricing note @@ -56,7 +59,7 @@ Prices shown in the documentation are B.AI standard reference prices for base bi ### Cache Pricing Notes -- **Cache Write:** The cost when tokens are first written into the prompt cache. Most providers charge no premium and use the same rate as standard input pricing. Claude models apply a 25% premium on cache writes. +- **Cache Write:** The cost when tokens are first written into the prompt cache. Most providers charge no premium and use the same rate as standard input pricing. Claude models and GPT-5.6 models apply a 25% premium on cache writes; GPT-5.6 long-context cache write rates follow the corresponding long-context input tier. - **Cache Read:** The discounted cost when cached tokens are reused in subsequent requests. - **Example with Caching:** If you use Claude Sonnet 4.6 with 1000 tokens cached: - First request (cache write): `1000 × 3.75 = 3,750 credits` diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-6-luna.md b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-6-luna.md new file mode 100644 index 0000000..7e89293 --- /dev/null +++ b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-6-luna.md @@ -0,0 +1,52 @@ +# GPT-5.6 Luna + +## 概述 + +GPT-5.6 Luna 是 OpenAI GPT-5.6 系列的成本友好层级模型，已于 2026 年 7 月 9 日正式可用。在 API 中，模型 ID 为 `gpt-5.6-luna`，OpenAI 将其定位为面向高效、高频工作负载的模型。 + +## 核心特性 + +* **成本友好的 GPT-5.6 层级**：适合 token 成本和响应效率较重要的高频工作负载。 +* **扩展推理控制**：支持 `none`、`low`、`medium`、`high`、`xhigh` 和 `max` 推理强度；GPT-5.6 还支持通过 `reasoning.mode: "pro"` 启用 Pro 模式。 +* **Agent 工具能力**：支持 Responses API 工作流、函数调用、网页搜索、文件搜索、Computer Use、Programmatic Tool Calling、持久化推理和多 Agent beta 能力。 +* **大工作上下文**：支持 1.05M token 上下文窗口和最高 128K 输出 token，知识截止时间为 2026 年 2 月 16 日。 + +## 适用场景 + +* **高频辅助任务**：摘要、改写、分类、信息抽取、路由和轻量分析。 +* **响应型产品功能**：用户侧助手、流程 Copilot 和成本可预测的常规自动化。 +* **第一轮技术处理**：初步问题分流、草拟代码审查、测试用例生成和文档分析，再将困难任务升级到 Terra 或 Sol。 + +## 能力与限制 + +| 能力维度 | 说明 | +| :--- | :--- | +| **推理能力** | 支持 `none`、`low`、`medium`、`high`、`xhigh` 和 `max`；API Pro 模式通过 `reasoning.mode: "pro"` 启用，而不是独立的 Pro 模型 ID。 | +| **编程能力** | 官方示例指标包括 SWE-Bench Pro 62.7%、DeepSWE v1.1 67.2% 和 Terminal-Bench 2.1 84.7%。 | +| **创作能力** | 支持通用文本生成。 | +| **多模态能力** | 支持文本和图像输入、文本输出；当图像 detail 为 `original` 或 `auto` 时，GPT-5.6 会保留原始图像尺寸。 | +| **响应速度** | 公共 API 延迟取决于推理强度、工具使用和处理层级；Luna 定位为高效、高频使用。 | +| **上下文窗口** | 1.05M tokens。 | +| **最大输出** | 128K tokens。 | +| **工具调用** | 函数调用、网页搜索、文件搜索、Computer Use、Programmatic Tool Calling、持久化推理和多 Agent beta。 | +| **多语言能力** | OpenAI API 模型文档列出当前模型支持多语言能力。 | + +### 已知限制 + +* Luna 的能力定位低于 Terra 和 Sol，复杂推理、敏感技术工作和质量优先的工作流可能需要升级处理。 +* 更高推理强度、Pro 模式、多 Agent 运行和长上下文使用会增加延迟和成本。 +* 网络安全和生物相关防护可能会拒绝、阻止或暂停敏感请求，包括部分合法的双用途工作。 +* GPT-5.6 模型的 Prompt Cache 写入会计费，因此建议通过 `cache_write_tokens` 和 `cached_tokens` 监控缓存断点。 + +## 积分消耗 + +| 上下文档位 | 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 | +| :--- | --------------------: | --------------------------: | -------------------------: | -------------------: | ---------------------: | :--- | +| 短上下文 | `1.00` | `1.25` | `0.10` | `6.00` | `10,000` | GPT-5.6 Luna 标准价格 | +| 长上下文（输入 token >272K） | `2.00` | `2.50` | `0.20` | `9.00` | `10,000` | 长上下文价格档位 | + +:::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。 +::: + +* GPT-5.6 模型的缓存写入按未缓存输入价格的 1.25x 计费；缓存读取按输入价格的 0.1x 折扣计费。 diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-6-sol.md b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-6-sol.md new file mode 100644 index 0000000..0eaea51 --- /dev/null +++ b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-6-sol.md @@ -0,0 +1,52 @@ +# GPT-5.6 Sol + +## 概述 + +GPT-5.6 Sol 是 OpenAI GPT-5.6 系列的旗舰层级模型，已于 2026 年 7 月 9 日正式可用。在 API 中，模型 ID 为 `gpt-5.6-sol`，`gpt-5.6` alias 会路由到该层级。它面向复杂专业工作、推理、代码、安全、科学研究和工具密集型工作流。 + +## 核心特性 + +* **GPT-5.6 旗舰层级**：面向复杂专业工作、推理、代码、安全、科学研究和工具密集型工作流。 +* **扩展推理控制**：支持 `none`、`low`、`medium`、`high`、`xhigh` 和 `max` 推理强度；GPT-5.6 还支持通过 `reasoning.mode: "pro"` 启用 Pro 模式。 +* **Agent 工具能力**：支持 Responses API 工作流、函数调用、网页搜索、文件搜索、Computer Use、Programmatic Tool Calling、持久化推理和多 Agent beta 能力。 +* **大工作上下文**：支持 1.05M token 上下文窗口和最高 128K 输出 token，知识截止时间为 2026 年 2 月 16 日。 + +## 适用场景 + +* **复杂软件工程**：代码库级调试、命令行工作流、多文件实现、验证和代码审查。 +* **长周期知识工作**：需要持续上下文和工具协同的浏览器、文档、表格、演示文稿和 Computer Use 任务。 +* **防御性安全与研究支持**：在人工监督下，用于授权漏洞审查、补丁开发、威胁建模、生物工作流分析和科学研究辅助。 + +## 能力与限制 + +| 能力维度 | 说明 | +| :--- | :--- | +| **推理能力** | 支持 `none`、`low`、`medium`、`high`、`xhigh` 和 `max`；API Pro 模式通过 `reasoning.mode: "pro"` 启用，而不是独立的 Pro 模型 ID。 | +| **编程能力** | 官方示例指标包括 SWE-Bench Pro 64.6%、DeepSWE v1.1 72.7%、Terminal-Bench 2.1 88.8% 和 Terminal-Bench 2.1 Ultra 91.9%。 | +| **创作能力** | 支持通用文本生成。 | +| **多模态能力** | 支持文本和图像输入、文本输出；当图像 detail 为 `original` 或 `auto` 时，GPT-5.6 会保留原始图像尺寸。 | +| **响应速度** | 公共 API 延迟取决于推理强度、工具使用和处理层级；OpenAI 也宣布 Sol 可为部分客户通过 Cerebras 提供最高 750 tokens/s 的访问能力。 | +| **上下文窗口** | 1.05M tokens。 | +| **最大输出** | 128K tokens。 | +| **工具调用** | 函数调用、网页搜索、文件搜索、Computer Use、Programmatic Tool Calling、持久化推理和多 Agent beta。 | +| **多语言能力** | OpenAI API 模型文档列出当前模型支持多语言能力。 | + +### 已知限制 + +* 更高推理强度、Pro 模式、多 Agent 运行和长上下文使用会增加延迟和成本。 +* 网络安全和生物相关防护可能会拒绝、阻止或暂停敏感请求，包括部分合法的双用途工作。 +* OpenAI 表示 GPT-5.6 在网络安全或生物评估中未达到 Critical 阈值，因此不应被视为高风险工作的自主操作者。 +* GPT-5.6 模型的 Prompt Cache 写入会计费，因此建议通过 `cache_write_tokens` 和 `cached_tokens` 监控缓存断点。 + +## 积分消耗 + +| 上下文档位 | 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 | +| :--- | --------------------: | --------------------------: | -------------------------: | -------------------: | ---------------------: | :--- | +| 短上下文 | `5.00` | `6.25` | `0.50` | `30.00` | `10,000` | GPT-5.6 Sol 标准价格 | +| 长上下文（输入 token >272K） | `10.00` | `12.50` | `1.00` | `45.00` | `10,000` | 长上下文价格档位 | + +:::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。 +::: + +* GPT-5.6 模型的缓存写入按未缓存输入价格的 1.25x 计费；缓存读取按输入价格的 0.1x 折扣计费。 diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-6-terra.md b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-6-terra.md new file mode 100644 index 0000000..5c61e60 --- /dev/null +++ b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-6-terra.md @@ -0,0 +1,52 @@ +# GPT-5.6 Terra + +## 概述 + +GPT-5.6 Terra 是 OpenAI GPT-5.6 系列的平衡层级模型，已于 2026 年 7 月 9 日正式可用。在 API 中，模型 ID 为 `gpt-5.6-terra`，OpenAI 将其定位为在能力与成本之间取得平衡的工作负载选择。 + +## 核心特性 + +* **平衡型 GPT-5.6 层级**：定位介于 Sol 和 Luna 之间，适合需要强推理能力、但希望成本低于 Sol 的生产工作流。 +* **扩展推理控制**：支持 `none`、`low`、`medium`、`high`、`xhigh` 和 `max` 推理强度；GPT-5.6 还支持通过 `reasoning.mode: "pro"` 启用 Pro 模式。 +* **Agent 工具能力**：支持 Responses API 工作流、函数调用、网页搜索、文件搜索、Computer Use、Programmatic Tool Calling、持久化推理和多 Agent beta 能力。 +* **大工作上下文**：支持 1.05M token 上下文窗口和最高 128K 输出 token，知识截止时间为 2026 年 2 月 16 日。 + +## 适用场景 + +* **生产知识工作**：写作、分析、文档处理、结构化研究和多步骤业务工作流。 +* **软件工程辅助**：调试、测试规划、代码审查、代码库导航和实现支持，同时兼顾成本控制。 +* **规模化专业自动化**：需要较强质量、但并非每次请求都必须使用 Sol 的工具密集型工作流。 + +## 能力与限制 + +| 能力维度 | 说明 | +| :--- | :--- | +| **推理能力** | 支持 `none`、`low`、`medium`、`high`、`xhigh` 和 `max`；API Pro 模式通过 `reasoning.mode: "pro"` 启用，而不是独立的 Pro 模型 ID。 | +| **编程能力** | 官方示例指标包括 SWE-Bench Pro 63.4%、DeepSWE v1.1 69.6% 和 Terminal-Bench 2.1 87.4%。 | +| **创作能力** | 支持通用文本生成。 | +| **多模态能力** | 支持文本和图像输入、文本输出；当图像 detail 为 `original` 或 `auto` 时，GPT-5.6 会保留原始图像尺寸。 | +| **响应速度** | 公共 API 延迟取决于推理强度、工具使用和处理层级；Terra 定位为兼顾智能水平与成本的平衡层级。 | +| **上下文窗口** | 1.05M tokens。 | +| **最大输出** | 128K tokens。 | +| **工具调用** | 函数调用、网页搜索、文件搜索、Computer Use、Programmatic Tool Calling、持久化推理和多 Agent beta。 | +| **多语言能力** | OpenAI API 模型文档列出当前模型支持多语言能力。 | + +### 已知限制 + +* Terra 的能力定位低于 Sol，最困难且质量优先的工作流可能需要 Sol、Pro 模式或更高推理强度。 +* 更高推理强度、Pro 模式、多 Agent 运行和长上下文使用会增加延迟和成本。 +* 网络安全和生物相关防护可能会拒绝、阻止或暂停敏感请求，包括部分合法的双用途工作。 +* GPT-5.6 模型的 Prompt Cache 写入会计费，因此建议通过 `cache_write_tokens` 和 `cached_tokens` 监控缓存断点。 + +## 积分消耗 + +| 上下文档位 | 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 | +| :--- | --------------------: | --------------------------: | -------------------------: | -------------------: | ---------------------: | :--- | +| 短上下文 | `2.50` | `3.125` | `0.25` | `15.00` | `10,000` | GPT-5.6 Terra 标准价格 | +| 长上下文（输入 token >272K） | `5.00` | `6.25` | `0.50` | `22.50` | `10,000` | 长上下文价格档位 | + +:::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。 +::: + +* GPT-5.6 模型的缓存写入按未缓存输入价格的 1.25x 计费；缓存读取按输入价格的 0.1x 折扣计费。 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 ee4add2..cb2867d 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 @@ -24,6 +24,9 @@ | DeepSeek V3.2 | 0.29 | 0.29 | 0.145 | 0.44 | - | | DeepSeek V4 Flash | 0.28 | 0.28 | 0.0056 | 0.56 | - | | DeepSeek V4 Pro | 0.87 | 0.87 | 0.0087 | 1.74 | - | +| GPT-5.6 Sol | 5.00 | 6.25 | 0.50 | 30.00 | 10,000 | +| GPT-5.6 Terra | 2.50 | 3.125 | 0.25 | 15.00 | 10,000 | +| GPT-5.6 Luna | 1.00 | 1.25 | 0.10 | 6.00 | 10,000 | | GPT-5.4 | 2.50 | 2.50 | 0.25 | 15.00 | 10,000 | | GPT-5.5 | 5.00 | 5.00 | 0.50 | 30.00 | 10,000 | | GPT-5.5 Instant | 5.00 | 5.00 | 0.50 | 30.00 | 10,000 | @@ -47,7 +50,7 @@ | Gemini 3 Flash | 0.50 | 0.50 | 0.05 | 3.00 | 14,000 | :::caution 价格总表说明 -价格总表展示每个模型当前生效的标准参考价。表中的“缓存写入（Cache Write）”表示发生缓存写入时的计费价格，不代表所有模型使用统一的缓存有效期。不同模型厂商的缓存策略、缓存有效期和扩展缓存能力可能不同；如模型存在特殊缓存规则、1 小时缓存写入价格或分时间生效的价格，请以对应模型详情页说明为准。 +价格总表展示每个模型当前生效的标准参考价。表中的“缓存写入（Cache Write）”表示发生缓存写入时的计费价格，不代表所有模型使用统一的缓存有效期。不同模型厂商的缓存策略、缓存有效期、长上下文价格和扩展缓存能力可能不同；如模型存在特殊缓存规则、长上下文价格、1 小时缓存写入价格或分时间生效的价格，请以对应模型详情页说明为准。 ::: :::info 价格说明 @@ -56,7 +59,7 @@ ### 缓存定价说明 -- **缓存写入（Cache Write）：** 当 token 首次写入 Prompt Cache 时产生的消耗。大多数提供方不会额外加价，通常与标准输入价格一致。Claude 模型的缓存写入会在标准输入价格基础上增加 25%。 +- **缓存写入（Cache Write）：** 当 token 首次写入 Prompt Cache 时产生的消耗。大多数提供方不会额外加价，通常与标准输入价格一致。Claude 模型和 GPT-5.6 模型的缓存写入会在对应输入价格基础上增加 25%；GPT-5.6 长上下文缓存写入价格按对应长上下文输入档位计算。 - **缓存读取（Cache Read）：** 后续请求复用缓存 token 时产生的折扣消耗。 - **缓存示例：** 如果你使用 Claude Sonnet 4.6，并有 1000 个 token 被缓存： - 首次请求（缓存写入）：`1000 × 3.75 = 3,750 credits` diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/sidebars.js b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/sidebars.js index 0319bf4..8cf5dff 100644 --- a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/sidebars.js +++ b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/sidebars.js @@ -230,6 +230,9 @@ const sidebars = { 'llmservice/models/gpt-5-mini', 'llmservice/models/gpt-5-nano', 'llmservice/models/gpt-5-2', + 'llmservice/models/gpt-5-6-sol', + 'llmservice/models/gpt-5-6-terra', + 'llmservice/models/gpt-5-6-luna', 'llmservice/models/gpt-5-4', 'llmservice/models/gpt-5-5', 'llmservice/models/gpt-5-5-instant', diff --git a/sidebars.js b/sidebars.js index 205fcbf..7260522 100644 --- a/sidebars.js +++ b/sidebars.js @@ -227,6 +227,9 @@ const sidebars = { 'llmservice/models/gpt-5-mini', 'llmservice/models/gpt-5-nano', 'llmservice/models/gpt-5-2', + 'llmservice/models/gpt-5-6-sol', + 'llmservice/models/gpt-5-6-terra', + 'llmservice/models/gpt-5-6-luna', 'llmservice/models/gpt-5-4', 'llmservice/models/gpt-5-5', 'llmservice/models/gpt-5-5-instant', From 838d63e687444bafb8fd908ce3f925bd33f2595b Mon Sep 17 00:00:00 2001 From: jerryji-prog Date: Fri, 10 Jul 2026 17:49:36 +0800 Subject: [PATCH 2/2] update version --- package.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/package.json b/package.json index 0931c5f..a13d51d 100644 --- a/package.json +++ b/package.json @@ -1,6 +1,6 @@ { "name": "@x402-tron/docs", - "version": "1.3.3", + "version": "1.3.4", "description": "x402-tron documentation", "license": "MIT", "scripts": {