已核信息与来源

GPT-6.1 Terra gpt-6.1-terra A fast, efficient model for visual reasoning, precise computer use, and clear, natural writing. A fast, efficient model for visual reasoning, precise computer use, and clear, natural writing. Compare Try in Playground Reasoning Highest Speed Fast Price $1 • $5 Input • Output Input Text, Image Output Text Use GPT-6.1 Terra to match product photos to catalog entries, interpret technical drawings, act on application screens, or draft and revise text. reasoning.effort supports none , low , medium (default), high , xhigh , and max . Tool calling requires the Responses API. See the GPT-6 guide for prompting and migration guidance. 1,050,000 context window 128,000 max output tokens

获取时间 2026-10-27T05:51:39.273Z
原始快照 SHA-256：327989affa53ea9847ea70e4f7919747bf9d128ccf87c13164fe72370c5a2021

Text tokens Per 1M tokens Input $1.00 Cached input $0.05 Cache writes $1.25 Output $5.00 Cached input tokens are priced at 5% of the uncached input token rate. Cache-write prices shown use 30-minute retention. Standard cache writes cost $1.25 per million tokens for 30-minute retention and $2.50 for 12-hour retention, before long-context adjustments. Prompts with more than 272K input tokens are priced at 2x input and cache rates and 1.5x output for the full request. Batch and Flex prices are 50% lower than Standard. Regional processing adds a 10% premium where available. Fast mode prices are 2x Standard.

获取时间 2026-10-27T05:51:39.273Z
原始快照 SHA-256：327989affa53ea9847ea70e4f7919747bf9d128ccf87c13164fe72370c5a2021

ChatGPT Work and Codex are included in your ChatGPT Free, Go, Plus, Pro, Business, Edu, or Enterprise plan ChatGPT Work and Codex share usage. ChatGPT Work usage inside ChatGPT uses the same pricing, credits, and usage limits as Codex. GPT-5.5 retires from Codex with ChatGPT sign-in on October 14, 2026, at noon PDT (19:00 UTC). The OpenAI API and Codex sessions authenticated with an API key aren’t affected. See GPT-5.5 retirement for migration guidance. See token rates for credit-based plans and GPT-6.1 Sol model guidance for model details. API token prices are separate from subscription usage; don’t use them to estimate included tasks. Pricing options Individual Business / Enterprise Free Explore Codex capabilities on quick coding tasks. $0 /month Get Free GPT-6 Luna at Standard speed in the desktop app, subject to rollout Go Use Codex for lightweight coding tasks. $8 /month Get Go GPT-6 Luna at Standard speed in the desktop app, subject to rollout Plus Power a few focused coding sessions each week. $20 /month Get Plus Codex on the web, in the CLI, in the IDE extension, and on iOS Cloud-based integrations like automatic code review and Slack integration GPT-6.1 Sol and GPT-6 Luna Flexibly extend usage with ChatGPT credits Other ChatGPT features as part of the Plus plan Pro Choose the Pro plan that fits your usage. From $100 /month Get Pro Everything in Plus and: Plans at $100, $200, or $500 USD per month Ultrafast mode access on Pro $500 Other ChatGPT features as part of the Pro plan Compare Pro plans and usage limits. API Key Great for automation in shared environments like CI. Learn more Codex in the CLI, SDK, or IDE extension No cloud-based features (GitHub code review, Slack, etc.) Model availability follows the API models available to your key Pay for Codex usage based on API pricing

获取时间 2026-10-27T05:51:39.237Z
原始快照 SHA-256：6c2a7213111487cf0fc11ae801ee689419a9e971fcbe38b1c96f0af94126356e

What are the usage limits for my plan? The number of messages you can send depends on the model used, size and complexity of your tasks, and whether you run them locally or in the cloud. Small scripts or routine functions may consume only a fraction of your allowance, while larger projects, long-running tasks, or extended sessions that require the agent to hold more context will use significantly more per message. Tasks that look similar can consume different amounts of your allowance. Model choice, context, reasoning, tool use, retrieval, and caching all affect usage, so prompt length alone isn’t a reliable estimate. For model recommendations, see Models . The estimates below show local messages per five-hour period for Plus and Standard Business. Pro plans currently have no five-hour limit. Cloud tasks may use more of your allowance than local messages. Usage depends on the model and task. These estimates are not fixed message limits; check your usage dashboard for current limits and reset times. Model Plus Standard Business GPT-6 Astra 5-45 5-45 GPT-6.1 Sol 15-160 15-160 GPT-6.1 Terra 35-285 35-285 GPT-6 Sol 15-150 15-150 GPT-6 Luna 350-3,000 350-3,000 Local messages and cloud chats share your plan’s usage allowance. Weekly limits may also apply.

获取时间 2026-10-27T05:51:39.237Z
原始快照 SHA-256：6c2a7213111487cf0fc11ae801ee689419a9e971fcbe38b1c96f0af94126356e

GPT-5.5 retires from Codex with ChatGPT sign-in on October 14, 2026, at noon PDT (19:00 UTC). The OpenAI API and Codex sessions authenticated with an API key aren’t affected. See GPT-5.5 retirement

获取时间 2026-10-27T05:51:39.237Z
原始快照 SHA-256：6c2a7213111487cf0fc11ae801ee689419a9e971fcbe38b1c96f0af94126356e

If you're unsure which model to use, start with Claude Opus 5.5 for most workloads. Use Claude Fable 5.1 for demanding reasoning and long-horizon agentic work, or when your evals on Claude Opus 5.5 at higher effort still fall short. All current models support text and image input, text output, multilingual capabilities, vision, and tool use. Each model's page lists the platforms it's available on. Feature Claude Fable 5.1 For demanding reasoning and long-horizon agentic work Claude Opus 5.5 For long-running agentic coding and knowledge work Claude Sonnet 5.5 The best combination of speed and intelligence Claude Haiku 5.5 For high-volume, latency-sensitive tasks such as classification, extraction, and routing Comparative latency Slower Moderate Fast Fastest Pricing $10 / input MTok $50 / output MTok $4 / input MTok $20 / output MTok $2 / input MTok $10 / output MTok From $0.10 / input MTok From $0.50 / output MTok Claude API ID claude-fable-5-1 claude-opus-5-5 claude-sonnet-5-5 claude-haiku-5-5 Capabilities Thinking Adaptive (always on) Adaptive (always on) Adaptive Adaptive Default effort high medium high medium Context window 1M tokens 1M tokens 1M tokens 1M tokens Max output 128K tokens 128K tokens 128K tokens 128K tokens

获取时间 2026-10-27T05:51:41.510Z
原始快照 SHA-256：8cbfe26d5d5ebd55a00e96c360bd2ac4ec8e8377dbd14dfba4c885c4d702a328

Eligible plans Max 5x, Max 20x, and Team, including discounted Team plans Monthly amount $100 USD (Max 5x), $200 USD (Max 20x), up to $500 USD (Team, pooled*) Covers Claude API, Claude Managed Agents, the Claude Agent SDK, and playground Doesn't cover Claude Code, extra usage in the Claude apps Refresh Each billing cycle (or monthly for annual plans) Expiry End of each billing cycle (or monthly for annual plans), with no rollover Payment method for Claude Platform Not required API credit amounts  Plan Monthly credit Max 5x $100 USD Max 20x $200 USD Team, Standard seat $20 USD per seat* Team, Premium seat $100 USD per seat* Discounted Team plans (Nonprofit, Scientists) Same as Team: $20 USD per Standard seat, $100 USD per Premium seat* *On Team plans, credits for all seats are pooled into one monthly balance, capped at $500 USD. Each monthly credit, including the first, is based on the seats on your plan at the start of that billing month. For example, a team with three Standard seats and two Premium seats receives $260 USD a month. Adding another Premium seat raises the next month's credit to $360 USD. Eligibility  Your eligible plan must be active and in good standing. New subscribers can claim credits after 7 days on an eligible plan. Plans purchased through Claude for iOS or Claude for Android are eligible. Claim your credits on claude.ai in a web browser. Free, Pro, and Enterprise plans aren't eligible.

获取时间 2026-10-27T05:51:40.979Z
原始快照 SHA-256：6158c09cce052dd16164d0d8f628747b1589f6a169c0bdbd1d4c6b9a5d4b2f2e

Claude Max and Team plans include monthly credits for the Claude API. To claim them, you link a Claude Console organization to your plan. Credits then arrive in that organization each billing cycle (or monthly for annual plans), and you can use them to build and run your own applications and agents. You don't need to add a payment method to Claude Platform.  Claude Platform on AWS, Amazon Bedrock, Google Cloud, and Microsoft Foundry: These credits apply only to the Claude API in the Claude Console. They can't be used on other platforms. Summary  Topic Details Eligible plans Max 5x, Max 20x, and Team, including discounted Team plans Monthly amount $100 USD (Max 5x), $200 USD (Max 20x), up to $500 USD (Team, pooled*) Covers Claude API, Claude Managed Agents, the Claude Agent SDK, and playground Doesn't cover Claude Code, extra usage in the Claude apps Refresh Each billing cycle (or monthly for annual plans) Expiry End of each billing cycle (or monthly for annual plans), with no rollover

How credits are applied  Timing. Credits arrive each billing cycle, shortly after your plan payment is processed. On annual plans, credits arrive monthly. Order. Included credits are spent first, then any credits you've purchased. Auto-reload is based only on your purchased balance. It reloads when that balance reaches your threshold, even if included credits remain. Expiry. Unused credits expire at the end of each billing cycle (or monthly for annual plans) and don't roll over. Sharing. Every API key and workspace in the linked organization draws from the same balance. To cap spending on a project, give it its own workspace and set that workspace's spend limit . Visibility. Your credits appear in the Promotional credits section of the Billing page ( platform.claude.com/settings/billing ) in the Console, with the amount and expiry date. Your Claude plan. Credits don't change your usage limits in Claude or Claude Code.

获取时间 2026-10-27T05:51:40.979Z
原始快照 SHA-256：6158c09cce052dd16164d0d8f628747b1589f6a169c0bdbd1d4c6b9a5d4b2f2e

模型 deepseek-flash (1) deepseek-v4-pro BASE URL (OpenAI 格式) https://api.deepseek.com BASE URL (Anthropic 格式) https://api.deepseek.com/anthropic 模型版本 DeepSeek-V4.1-Flash-1017 DeepSeek-V4-Pro-0813 思考模式 支持非思考与思考模式（默认） 切换方式详见 思考模式 上下文长度 1M 输出长度 最大 384K 功能 Json Output 支持 支持 Tool Calls 支持 支持 Responses API 支持 支持 Anthropic API 支持 支持 对话前缀续写（Beta） 支持 支持 FIM 补全（Beta） 仅非思考模式支持 仅非思考模式支持 图像理解 支持 不支持 价格 (2) 百万tokens输入 （缓存命中） 空闲时段 0.02元 0.15元 高峰时段 0.04元 0.30元 百万tokens输入 （缓存未命中） 空闲时段 1元 4.5元 高峰时段 2元 9.0元 百万tokens输出 空闲时段 4元 13.5元 高峰时段 8元 27.0元 并发限制 (3) 2500 500 (1) 模型名请使用 deepseek-flash 。旧模型名 deepseek-v4-flash 、 deepseek-v4-flash-vision-exp 仍可调用，但对应模型已下线，请求将由 DeepSeek-V4.1-Flash-1017 模型提供服务，并按 Flash 价格计费。

获取时间 2026-10-27T05:51:42.288Z
原始快照 SHA-256：556097caba8adfeeed6455714bffd731c7f60db520fcee06a922eba5840663a3

价格 (2) 百万tokens输入 （缓存命中） 空闲时段 0.02元 0.15元 高峰时段 0.04元 0.30元 百万tokens输入 （缓存未命中） 空闲时段 1元 4.5元 高峰时段 2元 9.0元 百万tokens输出 空闲时段 4元 13.5元 高峰时段 8元 27.0元 并发限制 (3) 2500 500 (1) 模型名请使用 deepseek-flash 。旧模型名 deepseek-v4-flash 、 deepseek-v4-flash-vision-exp 仍可调用，但对应模型已下线，请求将由 DeepSeek-V4.1-Flash-1017 模型提供服务，并按 Flash 价格计费。 (2) 空闲时段价格为高峰时段价格的一半。北京时间周一至周五（不含中国法定节假日）9:00 - 12:00、14:00 - 18:00 为高峰时段；其余时段，包括周末及中国法定节假日全天均为空闲时段。

获取时间 2026-10-27T05:51:42.288Z
原始快照 SHA-256：556097caba8adfeeed6455714bffd731c7f60db520fcee06a922eba5840663a3

网页搜索与抓取价格 ​ Search 和 Fetch 是独立的 API，按请求次数计费。 API 计费单位 价格 Search 每 1,000 次成功请求 5元 Fetch 每 1,000 次成功请求 5元 请注意，当前用户在 DeepSeek Harness/Claude Code/Codex 中使用 DeepSeek API 时，已经会通过 Server 端工具调用访问到 Search/Fetch 接口，这部分 Search/Fetch 接口调用目前未计费，并将于北京时间 2026 年 11 月 1 日 00:00 起按次收取调用费用。 接口用法与完整计费规则详见 网页搜索与抓取 。 扣费规则 ​ 模型调用费用 = token 消耗量 × 模型单价；Search 和 Fetch 按上表中的成功请求次数计费。对应的费用将直接从充值余额或赠送余额中进行扣减。

获取时间 2026-10-27T05:51:42.288Z
原始快照 SHA-256：556097caba8adfeeed6455714bffd731c7f60db520fcee06a922eba5840663a3

Gemini 4 Argon: Built to solve your hardest problems Oct 13, 2026 | x.com Facebook LinkedIn Mail Copy link We’re giving developers, enterprises, scientists, and consumers access to our latest frontier model. Koray Kavukcuoglu SVP, Google DeepMind and Chief AI Architect, Google Share x.com Facebook LinkedIn Mail Copy link In this article Built to solve your hardest problems Solving complex engineering tasks Transforming critical business and professional workflows Accelerating real-world impact with researchers and domain experts Developing Argon responsibly and safely Get started today Gemini 4 Argon is now globally available today for developers and enterprises via the API in AI Studio and Gemini platform , for Google AI Ultra subscribers in Google Antigravity , and Google AI Ultra and Pro subscribers in the Gemini app and AI Mode in Search .

获取时间 2026-10-27T05:51:42.283Z
原始快照 SHA-256：8b666d0c2cbc55a9ec4092279251f779a93610d92579876ca1f59f5f1c00914b

The model launches today at an introductory price 1 of $2 per million input tokens and $10 per million output tokens (with cached input tokens at 95% off).

After the introductory period expires on November 30, 2026, the price of $4 per 1M input tokens and $20 per 1M output tokens will apply. Applies to the Argon model intended for public access only.

获取时间 2026-10-27T05:51:42.283Z
原始快照 SHA-256：8b666d0c2cbc55a9ec4092279251f779a93610d92579876ca1f59f5f1c00914b

所有套餐均支持 GLM-5.3 、GLM-5.3-Flash。 调用历史模型 GLM-5.2、GLM-5.1 都将自动切换至 GLM-5.3，调用 GLM-5-Turbo、GLM-4.7 将自动切换至 GLM-5.3-Flash。 ​ 适用工具 套餐仅限在官方支持的 指定工具与产品环境 中使用。在除规定工具外调用 API，不可享用 Coding 套餐的额度。 套餐支持 OpenClaw 使用，但采用 次级调度 与尽力交付策略，Coding Agent 任务享有资源抢占优先权，高负载下 OpenClaw 任务将自动触发包括动态排队、限流等公平使用策略。 订阅套餐后，在上述工具中调用 GLM 模型，按接入指南配置即可使用套餐额度。当套餐额度耗尽后，需要等待下一个 5 小时周期恢复额度，系统不会继续消耗您的其他资源包/账户余额。

获取时间 2026-10-27T05:51:43.128Z
原始快照 SHA-256：b462ba45e7031cdf0bd4a8cb1d1e61030c147863d26fd40f9c40dea5685c4ca1

套餐同时设有每 5 小时和每周额度上限，您可以在 用量统计 中查看您的额度消耗进展： 套餐类型 5 小时积分 每周积分 Lite 套餐 2,000 10,000 Pro 套餐 12,000 60,000 Max 套餐 28,000 140,000 积分刷新规则 5 小时积分 ：采用动态刷新机制，积分额度在请求消耗 5 小时后刷新重置。 周积分 ：自套餐下单时起，以 7 天为一个周期刷新。 套餐升级与续费 ：已订阅用户升级套餐后，积分额度将按新套餐档位立即刷新；续费不会触发积分额度重置，原有积分刷新周期保持不变。 ​ 积分抵扣计算方式 模型消耗积分数=（输入 Token × Input 抵扣系数 + 缓存命中 Token × Cached Input 抵扣系数 + 输出 Token × Output 抵扣系数） / 10000

获取时间 2026-10-27T05:51:43.128Z
原始快照 SHA-256：b462ba45e7031cdf0bd4a8cb1d1e61030c147863d26fd40f9c40dea5685c4ca1

<details> <summary>NPM / Homebrew</summary> **NPM** (requires [Node.js 22+](https://nodejs.org/)): ```bash npm install -g @qwen-code/qwen-code@latest ``` **Homebrew** (macOS / Linux): ```bash brew install qwen-code ``` </details> ## Quick Start Open a terminal in your project and start Qwen Code: ```bash cd /path/to/your-project qwen ``` Inside the session, run `/auth` to configure your provider and API key. Then try: ```text Explain this repository and show me where to start. ``` See the [Authentication Guide](https://qwenlm.github.io/qwen-code-docs/en/users/configuration/auth/) and [Settings Reference](https://qwenlm.github.io/qwen-code-docs/en/users/configuration/settings/) for detailed setup.

获取时间 2026-10-27T05:51:43.242Z
原始快照 SHA-256：4a0ebab59ff1b820bcc4456fa8c44e1c8593d7fef26a6183c7c18aa36c6b1966

Choose the interface that fits your workflow: | Interface | Get started | | ------------ | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Terminal** | Run `qwen` in your project — see [Quick Start](#quick-start). | | **Desktop** | [Download Qwen Code Desktop](https://github.com/QwenLM/qwen-code/releases/tag/desktop-latest) for macOS, Windows, and Linux. | | **Web** | Run `qwen serve --open` to open the [Web UI](https://qwenlm.github.io/qwen-code-docs/en/users/qwen-serve/) in your browser. _(experimental)_ | | **Editor** | Set up [VS Code](https://qwenlm.github.io/qwen-code-docs/en/users/integration-vscode/), [Zed](https://qwenlm.github.io/qwen-code-docs/en/users/integration-zed/), or [JetBrains](https://qwenlm.github.io/qwen-code-docs/en/users/integration-jetbrains/). | | **Chat** | Connect [Telegram](https://qwenlm.github.io/qwen-code-docs/en/users/features/channels/telegram/), [DingTalk](https://qwenlm.github.io/qwen-code-docs/en/users/features/channels/dingtalk/), [WeChat](https://qwenlm.github.io/qwen-code-docs/en/users/features/channels/weixin/), or [Feishu](https://qwenlm.github.io/qwen-code-docs/en/users/features/channels/feishu/), then run `qwen channel start`. | For automation and custom integrations: - **Headless** — Run `qwen -p "..."` in scripts, CI/CD, or batch jobs. - **SDKs** — Build with [TypeScript](./packages/sdk-typescript/README.md), [Python](./packages/sdk-python/README.md), or [Java](./packages/sdk-java/qwencode/README.md). - **Daemon** — Run `qwen serve` to connect clients over HTTP + SSE (ACP). _(experimental)_ [Daemon guide](https://qwenlm.github.io/qwen-code-docs/en/users/qwen-serve/).

获取时间 2026-10-27T05:51:43.242Z
原始快照 SHA-256：4a0ebab59ff1b820bcc4456fa8c44e1c8593d7fef26a6183c7c18aa36c6b1966

Ollama runs locally. We don’t see your prompts or data when you run locally. When using cloud-hosted models, we process your prompts and responses to provide the service but do not store or log that content and never train on it. We collect basic account info and limited usage metadata to provide the service that does not include prompt or response content. We don’t sell your data. You can delete your account anytime. ​ How do I disable Ollama’s cloud features? Ollama can run in local only mode by disabling Ollama’s cloud features. By turning off Ollama’s cloud features, you will lose the ability to use Ollama’s cloud models and web search. Set disable_ollama_cloud in ~/.ollama/server.json : { "disable_ollama_cloud" : true } You can also set the environment variable: OLLAMA_NO_CLOUD = 1 Restart Ollama after changing configuration. Once disabled, Ollama’s logs will show Ollama cloud disabled: true . ​ How can I expose Ollama on my network? Ollama binds 127.0.0.1 port 11434 by default. Change the bind address with the OLLAMA_HOST environment variable. Refer to the section above for how to set environment variables on your platform. ​ How can I use Ollama with a proxy server? Ollama runs an HTTP server and can be exposed using a proxy server such as Nginx. To do so, configure the proxy to forward requests and optionally set required headers (if not exposing Ollama on the network). For example, with Nginx: server { listen 80 ; server_name example.com; # Replace with your domain or IP location / { proxy_pass http://localhost:11434; proxy_set_header Host localhost:11434; } }

获取时间 2026-10-27T05:51:45.694Z
原始快照 SHA-256：a2d0de62e0e7395356a6839cfc74be0a0feea41257103b76b502c3625f9d804a

Two ways to use local models in GitHub Copilot GitHub Copilot is adding two ways to use local models across the GitHub Copilot CLI, Copilot app, and VS Code. Developers can let Copilot’s intelligent Auto orchestration choose when to use local or cloud inference, or they can explicitly select a local model for workflows that require direct control. Model selection, inference, and tool execution have different boundaries; local inference does not make the session offline. With Auto, developers do not need to decide where each task should be run. Across a multi-turn session, Copilot can consider task context and cache state as it routes work between local and cloud models, preserving useful, cached work as the session evolves. This orchestrated experience complements direct model selection, giving developers a choice between letting Copilot optimize model placement and choosing a specific local model themselves. Explicit local-model selection supports workflows that need a specific provider, model, or endpoint. Developers can select MAI Code 1.1 Flash through the Windows ML provider or connect GitHub Copilot to OpenAI-compatible local endpoints and choose from the models those endpoints expose. How sandboxes help secure tool execution An agent’s shell commands normally inherit the access of the account running them. Moving inference onto the device doesn’t change that. Sandboxing applies a policy to the processes and local services the agent launches, controlling access to files, networks, credentials, system capabilities, and execution paths regardless of which model requested the work. GitHub Copilot uses  Microsoft Execution Containers , or MXC, an open-source library from the Windows team that translates policy into native operating-system controls. On Windows, GitHub Copilot uses the BaseContainer tier of the ProcessContainer backend. On macOS, it uses Seatbelt. On Linux, it uses  bubblewrap . These local backends don’t require a separate virtual machine or container image, but we plan to make them options available through MXC in the future. When sandboxing is enabled, shell commands and, by default, local Model Context Protocol servers and language servers run inside the process boundary. Built-in file tools run inside GitHub Copilot itself: the agent harness checks their requests against the effective policy, but those checks aren’t OS-enforced child-process isolation. Remote MCP servers are also outside the local process sandbox; when MCP sandbox controls apply, GitHub Copilot checks their connection policy in process. Opening the GitHub Copilot CLI and running `/sandbox` slash command allows you to configure your settings at any time.

获取时间 2026-10-27T05:51:44.748Z
原始快照 SHA-256：42d3825d2882f519ac454806287d377d49fae7a025a7b8d57202d49e10064ced

Microsoft Execution Containers (MXC) is a policy-driven execution layer for untrusted code or dynamically generated workloads. In agentic scenarios, developers can use MXC to contain model-generated output, plugins, tools, agent harness, or the entire agent. This limits what the agent workload can access by containing the scope of the impact if something goes wrong.   Developers declare the resources a workload requires, such as files and network destinations, and MXC enforces the resulting boundary with the appropriate container. The policy remains outside the agent workload’s control, so the agent or generated code cannot grant itself additional access.

Observe agent activity without enforcing policy   In Enforcement mode, MXC applies the policy without activity report. Granted operations proceed, and operations outside the boundary are restricted. In Learning mode, MXC continues to enforce the configured boundary. An operation that has not been granted is blocked and recorded in a JSON activity report. This lets developers or IT reproduce containment failures and understand which resources the workload attempted to access. In Permissive mode, MXC records access that the policy would have denied but allows the operation to continue. This is useful during policy authoring because the workload can be completed while developers or IT collect evidence about the resources it uses. Permissive mode does not bypass other applicable operating system or organizational restrictions.

获取时间 2026-10-27T05:51:44.581Z
原始快照 SHA-256：7dff5dc706fc1b8f7fcceb76c1b58bdd46050c7032d4617f83139faf567775f6

Open d1: Edge decision models for text, vision, and audio OCT 7, 2026 On this page Architecture and Training Benchmarks Fast Inference Everywhere Open d1 in Action Get Started Citation Today, we release d1-3B and d1-omni-600M, two open-weight models in our d1 decision model family .  d1-3B scores 48.57 on the Decision Index v0.2.1 (public split), ahead of every model under 10B and on par with Decider 35B-A3B, a decision model 12x its size. It runs the full NVIDIA stack, from DGX in the data center to Jetson at the edge: d1-3B answers a question in 8 ms on an NVIDIA GeForce RTX 4090, 16 ms on a Jetson AGX Thor, and 26 ms on a Jetson AGX Orin. Even the Jetson Orin Nano runs it in 50 ms, fast enough for real-time decisions on the smallest edge hardware. d1-omni-600M is our first experimental checkpoint, handling both text and image, as well as text and audio. It scores 15.95 on the same index. d1-3B and d1-omni-600M models are available today on Hugging Face. Check out our docs on how to run them locally.

获取时间 2026-10-27T05:51:44.819Z
原始快照 SHA-256：39e52aea5182a38e71a7ca0d0548df01aa12dc528c60283eb7b769fe123b579e

Sasha Blumenfeld &middot; 10/7/2026 Which model to use Which model to use Walkthrough: from a first MP3 to a voice agent Tips for your first requests Getting started ElevenLabs is now on OpenRouter with nine Text to Speech models and two Speech to Text models. If your app already talks to a language model through OpenRouter, it can now speak and listen too. Narrate long-form content with direction over tone and delivery with Eleven v4, give your agent faster spoken replies with v4 Turbo, or transcribe conversations with speaker labels with Scribe v2. You don’t need a separate ElevenLabs plan. Just call POST /api/v1/audio/speech and POST /api/v1/audio/transcriptions with your OpenRouter API key. Every ElevenLabs model is 50% off OpenRouter’s list price for all OpenRouter customers through October 19, 8am PT

Scribe v2 elevenlabs/scribe-v2 General transcription with word timestamps, speaker labels, and audio-event tags in 90+ languages Scribe v2 Medical elevenlabs/scribe-v2-medical Medical terms with 35% fewer errors on clinical audio compared to Scribe v2 Both Scribe models use the same request shape and the same per-second price. Realtime Scribe v2 over WebSocket isn’t part of this launch.

获取时间 2026-10-27T05:51:45.054Z
原始快照 SHA-256：16fc769ef2369a98211774648a82747413744749d96a4ccd3a1dc540a003b132

Every ElevenLabs model is 50% off OpenRouter’s list price for all OpenRouter customers through October 19, 8am PT

获取时间 2026-10-27T05:51:45.054Z
原始快照 SHA-256：16fc769ef2369a98211774648a82747413744749d96a4ccd3a1dc540a003b132