[{"data":1,"prerenderedAt":287},["ShallowReactive",2],{"copy:en:site:":3,"copy:en:changelog:":122,"copy:en:site:common":285},{"common":4,"nav":16,"footer":44,"home":51,"error":115},{"skip":5,"menu":6,"language":7,"sections":8,"footer":9,"tool":10,"home":11,"breadcrumbs":12,"copy":13,"copied":14,"download":15},"Skip to content","Menu","Language","Sections","Footer","tool","Home","Breadcrumbs","Copy","Copied","Download",{"groups":17,"items":25},{"build":18,"connect":19,"instruct":20,"run":21,"web":22,"secure":23,"track":24},"Build","Connect","Instruct","Run","Open your site","Secure","Track",{"models":26,"cost":27,"frameworks":28,"mcp":29,"mcpConfig":30,"mcpClients":31,"agentsMd":32,"files":33,"openclaw":34,"agentReady":35,"llmsTxt":36,"robotsTxt":37,"apiCatalog":38,"bots":39,"security":40,"incidents":41,"checklist":42,"changelog":43},"Models and API prices","Agent cost calculator","Frameworks and SDKs","MCP servers","MCP config generator","MCP clients","AGENTS.md generator","Instruction files","Self-host OpenClaw","Agent-ready websites","llms.txt generator","robots.txt for AI bots","API catalog generator","AI bot directory","Agent security","Incident log","Security checklist","Changelog",{"about":45,"privacy":46,"terms":47,"sitemap":48,"disclaimer":49,"checked":50},"About","Privacy","Terms","Sitemap","Independent reference for people who build AI agents. Not affiliated with any vendor named here.","Facts checked {date}",{"seo":52,"eyebrow":55,"title":56,"lead":57,"ctaMcp":58,"ctaCost":59,"ctaAgents":60,"sheetLabel":61,"sheetTitle":62,"sheet":63,"sheetNote":69,"sectionsTitle":70,"sections":71,"latestTitle":98,"allChanges":99,"rulesTitle":100,"rules":101,"aboutLink":114},{"title":53,"description":54},"DotsAgent: reference and tools for building AI agents","LLM API prices, an agent cost calculator, MCP configs for 13 clients, AGENTS.md and llms.txt generators, and agent security notes. Free, in 18 languages.","For developers building AI agents","The agent builder's desk reference","Prices, protocols, config files and security notes for agent work, each checked against the vendor's own docs. Look a fact up, generate the file you need and get back to your code.","Generate an MCP config","Price an agent task","Write AGENTS.md","Current figures","State of the stack",{"mcp":64,"openclaw":65,"cheapest":66,"models":67,"servers":29,"bots":68},"MCP spec","OpenClaw","Cheapest model, $\u002FM in\u002Fout","Models priced","AI bots tracked","Each figure is checked by hand against vendor docs.","What's on the site",{"models":72,"mcp":76,"instructions":79,"frameworks":82,"openclaw":85,"agentReady":88,"security":91,"changelog":94},{"title":73,"body":74,"unit":75},"Models and prices","Input, output and cached token prices per million, side by side, with a calculator for whole agent runs.","models",{"title":29,"body":77,"unit":78},"A catalogue of Model Context Protocol servers and a config generator that writes the right file for each client.","servers",{"title":33,"body":80,"unit":81},"Write an AGENTS.md and see how CLAUDE.md, .cursor\u002Frules and similar files are read by each tool.","file formats",{"title":28,"body":83,"unit":84},"Compare agent frameworks and vendor SDKs by language, licence, MCP support and multi-agent features.","frameworks",{"title":34,"body":86,"unit":87},"Install, configure and update OpenClaw on your own machine or server, step by step.","current release",{"title":35,"body":89,"unit":90},"Generate llms.txt, robots.txt rules for AI crawlers and an api-catalog, and look up any bot by user agent.","bots listed",{"title":40,"body":92,"unit":93},"The OWASP risks for agents, a log of real incidents and a checklist you can tick off before launch.","incidents logged",{"title":95,"body":96,"unit":97},"API changelog","Dated changes to model APIs, SDKs and protocols, each linked to the vendor's announcement.","entries","Latest changes","All changes","How we keep it accurate",[102,105,108,111],{"title":103,"body":104},"Sourced facts.","Every price, version and flag links to the vendor page it came from, so you can check it yourself.",{"title":106,"body":107},"Dated checks.","Each page shows when its facts were last checked, and stale entries are rechecked or removed.",{"title":109,"body":110},"No paid placement.","Nobody pays to be listed, ranked higher or described more kindly.",{"title":112,"body":113},"Tools run in your browser.","Generators and calculators work locally, and what you type is not sent to a server.","About DotsAgent",{"title":116,"body":117,"home":118,"popular":119,"failed":120,"failedBody":121},"Page not found","This address doesn't match any page. It may have moved, or the link may have a typo.","Go to the home page","Popular tools","Something went wrong","The page failed to load on our side. Try again in a minute, or start from the home page.",{"seo":123,"crumb":43,"eyebrow":24,"title":126,"lead":127,"ui":128,"items":143},{"title":124,"description":125},"AI agent API changelog: models, SDKs, MCP, prices","Dated log of what changed for agent builders: model launches and retirements, API and SDK releases, MCP spec updates and price moves, each with sources.","Changelog for agent builders","Model launches, retirements, API and SDK releases, MCP spec changes and price moves that affect code you have already shipped. Newest first, each entry linked to the vendor's own notes.",{"all":129,"allVendors":130,"byKind":131,"byVendor":132,"empty":133,"kinds":134,"vendors":142},"Everything","All vendors","Filter by kind of change","Filter by vendor","Nothing matches these filters.",{"model":135,"api":136,"sdk":137,"mcp":138,"price":139,"deprecation":140,"security":141},"Model","API","SDK","MCP","Price","Retirement","Security",{"openclaw":65,"mcp":138},{"2026-09-30-claude-sonnet-4-5-deprecated":144,"2026-09-29-gpt-6-1-sol-released":147,"2026-09-29-devday-2026-keynote":150,"2026-09-29-computer-use-added-to-the-agents-api":153,"2026-09-29-ultrafast-mode-for-gpt-6-astra":156,"2026-09-28-claude-sonnet-5-5-launched":159,"2026-09-24-billing-resumes-for-some-early-refusals":162,"2026-09-23-openclaw-v2026-9-6":165,"2026-09-22-gpt-6-sol-and-gpt-6-luna-released":168,"2026-09-22-claude-opus-5-5-launched":171,"2026-09-22-inline-tool-definitions-mid-conversation":174,"2026-09-21-grok-4-7-released":177,"2026-09-18-gemini-2-5-access-restricted-to-existing-users":180,"2026-09-18-openclaw-v2026-9-5":183,"2026-09-17-antigravity-agent-09-2026-replaces-05-2026":186,"2026-09-14-on-demand-conversation-compaction":189,"2026-09-10-agents-api-public-beta":192,"2026-09-10-gpt-live-1-generally-available":195,"2026-09-10-deepseek-v4-1-flash-released-with-price-cut":198,"2026-09-10-managed-agents-auto-permission-policy":201,"2026-09-08-gpt-6-astra-released":204,"2026-09-02-gemini-3-8-flash-ga":207,"2026-09-02-muse-spark-1-3-released":210,"2026-09-01-claude-fable-5-1-launched":213,"2026-08-29-mtls-and-x-509-workload-identity-ga":216,"2026-08-26-assistants-api-shut-down":219,"2026-08-21-gpt-5-6-sol-price-cut":222,"2026-08-19-computer-use-ga-new-browser-use-toolset-files-and-skills-apis-ga":225,"2026-08-19-agents-sdk-v0-22-0":228,"2026-08-14-glm-5-3-released":231,"2026-08-13-deepseek-v4-pro-ga-responses-api-support-peak-off-peak-pricing":234,"2026-08-13-gemini-3-7-flash-ga":237,"2026-08-12-claude-agent-sdk-v0-2-137":240,"2026-08-10-claude-sonnet-5-intro-price-made-permanent":243,"2026-08-07-managed-agents-budgets-and-advisor":246,"2026-08-05-inference-hooks-beta-claude-opus-4-1-retired":249,"2026-08-03-qwen3-8-max-launched":252,"2026-07-30-fast-mode-replaces-priority-processing-gpt-5-6-luna-terra-price-cuts":255,"2026-07-28-mcp-spec-2026-07-28":258,"2026-07-24-claude-opus-5-launched":261,"2026-07-24-deepseek-chat-deepseek-reasoner-names-discontinued":264,"2026-07-21-gemini-3-6-flash-and-3-5-flash-lite-ga-sampling-params-deprecated":267,"2026-07-16-kimi-k3-launched":270,"2026-06-30-claude-sonnet-5-launched":273,"2026-06-24-computer-use-tool-preview-in-gemini-3-5-flash":276,"2026-06-15-claude-sonnet-4-and-opus-4-retired":279,"2026-06-01-gemini-2-0-flash-models-shut-down":282},{"title":145,"summary":146},"Claude Sonnet 4.5 deprecated","Anthropic announced deprecation of claude-sonnet-4-5-20250929, with Claude API retirement scheduled for 2026-11-30 and Sonnet 5.5 as the recommended replacement.",{"title":148,"summary":149},"GPT-6.1 Sol released","OpenAI released gpt-6.1-sol for coding and professional work at $2 input \u002F $0.10 cached \u002F $10 output (\u003C=272K prompts), with multi-agent subagent delegation in beta in the Responses API.",{"title":151,"summary":152},"DevDay 2026 keynote","At DevDay 2026 OpenAI announced Dots persistent agents, GPT-6.1 Sol, the Ultrafast speed tier, a Decisions API limited preview, Amazon Bedrock Managed Agents powered by OpenAI, and ChatGPT support for the draft MCP Events spec.",{"title":154,"summary":155},"Computer use added to the Agents API","Agents built on the Agents API can now complete tasks in an OpenAI-hosted browser, while the developer's application handles website access approvals and sign-in.",{"title":157,"summary":158},"Ultrafast mode for GPT-6 Astra","gpt-6-astra can be called with service_tier \"ultrafast\" in the Responses API at $60 input \u002F $300 output per 1M tokens (short context), with global and US data-residency processing only.",{"title":160,"summary":161},"Claude Sonnet 5.5 launched","claude-sonnet-5-5 launched at $2\u002F$10 per MTok with 1M context and 128K output, with five breaking changes vs Sonnet 5, including forced tool_choice returning 400 and computer_20251124 no longer accepted on the Claude API.",{"title":163,"summary":164},"Billing resumes for some early refusals","Refusals that arrive before any output are billed again when stop_details.category is bio, frontier_llm or reasoning_extraction; early refusals in other categories remain free.",{"title":166,"summary":167},"OpenClaw v2026.9.6","OpenClaw 2026.9.6 added managed-update recovery, 30-day usage reporting, remote-workspace Files\u002FMemory\u002FSkills, and chat-model support for Claude Opus 5.5, GPT-6 Sol\u002FLuna and Grok 4.7.",{"title":169,"summary":170},"GPT-6 Sol and GPT-6 Luna released","OpenAI released the reasoning models gpt-6-sol ($2\u002F$0.20\u002F$10) and gpt-6-luna ($0.10\u002F$0.01\u002F$0.50) on the Responses and Chat Completions APIs.",{"title":172,"summary":173},"Claude Opus 5.5 launched","claude-opus-5-5 launched at $4\u002F$20 per MTok (cheaper than Opus 5) with 1M context, 128K output and always-on adaptive thinking; thinking cannot be disabled and computer use requires computer_toolset_20260801.",{"title":175,"summary":176},"Inline tool definitions mid-conversation (beta)","With the inline-tools-2026-09-15 beta header, tools (including MCP toolsets via mcp-client-2026-09-15) can be added or changed in a mid-conversation system message without invalidating the prompt cache.",{"title":178,"summary":179},"Grok 4.7 released","grok-4.7 launched with a 500K context window at $2 input \u002F $0.50 cached \u002F $6 output (doubling for prompts >=200K), function calling and structured outputs; the Batch API is not supported.",{"title":181,"summary":182},"Gemini 2.5 access restricted to existing users","Google limited Gemini 2.5 model access to users who had already used them (not deprecated) and told new projects to use Gemini 3.5 Flash-Lite or 3.8 Flash.",{"title":184,"summary":185},"OpenClaw v2026.9.5","OpenClaw 2026.9.5 introduced Atomic Updates, plugins that install without restarting the Gateway, shareable conversations, GPT Live in meetings and calls, and guided setup for teams of specialist agents.",{"title":187,"summary":188},"Antigravity Agent 09-2026 replaces 05-2026","Google released managed agent antigravity-preview-09-2026 with renamed PascalCase built-in tools and line-range file edits; antigravity-preview-05-2026 shuts down on 2026-10-05.",{"title":190,"summary":191},"On-demand conversation compaction (beta)","The Messages API can compact a conversation on request (compact-2026-09-04 beta header) and returns a signed compaction block that replaces earlier messages in later requests.",{"title":193,"summary":194},"Agents API public beta","OpenAI launched the Agents API in public beta, exposing the open-source Codex harness as a managed service with durable sessions, MCP\u002Ftools, subagents and OpenAI-hosted, self-hosted or partner sandboxes, with no fee beyond tokens and tools.",{"title":196,"summary":197},"GPT-Live 1 generally available","gpt-live-1 full-duplex voice sessions became GA at $0.05 per minute (billed per second), with backend model or agent reasoning delegated via Responses or the client.",{"title":199,"summary":200},"DeepSeek-V4.1-Flash released with price cut","DeepSeek released the multimodal V4.1-Flash under the model name deepseek-flash, retired V4-Flash, and cut prices (peak $0.30 in \u002F $1.20 out, off-peak half).",{"title":202,"summary":203},"Managed Agents 'auto' permission policy","Claude Managed Agents gained an auto permission policy in which the server evaluates each agent or MCP tool call and runs it, denies it, or pauses for approval.",{"title":205,"summary":206},"GPT-6 Astra released","OpenAI released gpt-6-astra ($10\u002F$1\u002F$50) as its most capable model, adding async tool calling, mid-turn steering over WebSockets and mid-conversation reasoning-effort changes; tool calling requires the Responses API.",{"title":208,"summary":209},"Gemini 3.8 Flash GA","Google released gemini-3.8-flash, aimed at long-horizon software engineering and autonomous agents, at an introductory $0.75\u002F$3.75 per 1M tokens through 2026-12-31.",{"title":211,"summary":212},"Muse Spark 1.3 released","Meta released Muse Spark 1.3 with max reasoning on Muse Code and the Meta Model API at $1.25\u002F$4.25 per 1M tokens (contributor tier $0.10\u002F$0.20).",{"title":214,"summary":215},"Claude Fable 5.1 launched","claude-fable-5-1 launched at $10\u002F$50 per MTok with cache reads cut to $0.25 (0.025x), 1M context and 128K output, alongside Claude Mythos 5.1 for Project Glasswing participants; forced tool_choice is unsupported.",{"title":217,"summary":218},"mTLS and X.509 workload identity GA","Mutual TLS and X.509 workload identity federation became generally available for the OpenAI API, configurable in the Platform console.",{"title":220,"summary":221},"Assistants API shut down","The Assistants API shut down; OpenAI also announced that whisper-1 and the gpt-4o transcribe models will shut down on 2027-02-26.",{"title":223,"summary":224},"GPT-5.6 Sol price cut","GPT-5.6 Sol dropped to $4 input \u002F $20 output per 1M tokens (20% lower input, 33% lower output), a promotional price available at least through 2026-11-21.",{"title":226,"summary":227},"Computer use GA, new browser use toolset, Files and Skills APIs GA","Computer use left beta as computer_toolset_20260801 (batch actions, zoom on by default), a browser_toolset_20260801 client toolset launched, and the Files API and Agent Skills\u002FSkills API dropped their beta headers.",{"title":229,"summary":230},"Agents SDK (Python) v0.22.0","openai-agents-python v0.22.0 shipped runtime hardening, guardrail-output redaction, provider-option validation and expanded handoff graph visualization, with breaking changes listed in the release.",{"title":232,"summary":233},"GLM-5.3 released","Z.ai released GLM-5.3 (same base as GLM-5.2, improved via post-training) at $1.40\u002F$4.40 per 1M tokens; thinking can no longer be disabled.",{"title":235,"summary":236},"DeepSeek-V4-Pro GA, Responses API support, peak\u002Foff-peak pricing","DeepSeek shipped V4-Pro GA with stronger agent benchmarks, native OpenAI Responses API format (adapted for Codex) and low\u002Fhigh\u002Fmax effort, and announced peak\u002Foff-peak pricing effective 2026-08-16.",{"title":238,"summary":239},"Gemini 3.7 Flash GA","Google released gemini-3.7-flash for coding and agentic workflows at an introductory price through 2026-12-31.",{"title":241,"summary":242},"Claude Agent SDK (Python) v0.2.137","claude-agent-sdk v0.2.137 added ConversationResetMessage, message origin fields and resume_session_at\u002Fresume_drops_turn options for safely truncating resumed sessions.",{"title":244,"summary":245},"Claude Sonnet 5 intro price made permanent","Anthropic cancelled the scheduled 2026-09-01 increase to $3\u002F$15, keeping Claude Sonnet 5 at $2\u002F$10 per MTok.",{"title":247,"summary":248},"Managed Agents budgets and advisor","Claude Managed Agents sessions gained hard spend budgets (pausing with budget_reached), an advisor model the agent can consult mid-turn, per-agent inference_geo, and auto-loading of skills from mounted GitHub repos.",{"title":250,"summary":251},"Inference hooks beta; Claude Opus 4.1 retired","Claude Enterprise organizations can route governed prompts to their own AI security server for allow\u002Fdeny verdicts before inference, and claude-opus-4-1-20250805 was retired.",{"title":253,"summary":254},"Qwen3.8-Max launched","Alibaba launched Qwen3.8-Max, a 2.4T-parameter MoE with 1M context, on Model Studio, promising open weights the following week.",{"title":256,"summary":257},"Fast mode replaces Priority processing; GPT-5.6 Luna\u002FTerra price cuts","Priority processing was renamed Fast mode (2x price, up to 2.5x speed for GPT-5.6 Sol), and GPT-5.6 Luna became 80% cheaper and GPT-5.6 Terra 20% cheaper.",{"title":259,"summary":260},"MCP spec 2026-07-28 (stateless protocol)","The new MCP revision removes the initialize handshake and protocol sessions, adds a mandatory server\u002Fdiscover RPC and the Multi Round-Trip Request pattern, moves tasks into an extension, and deprecates Roots, Sampling and Logging.",{"title":262,"summary":263},"Claude Opus 5 launched","claude-opus-5 launched at $5\u002F$25 per MTok with 1M context and 128K output, along with mid-conversation tool changes (beta) and a default server-side fallback mode.",{"title":265,"summary":266},"deepseek-chat \u002F deepseek-reasoner names discontinued","The legacy model names deepseek-chat and deepseek-reasoner were scheduled for discontinuation on this date (announced 2026-04-24 with the V4 launch).",{"title":268,"summary":269},"Gemini 3.6 Flash and 3.5 Flash-Lite GA; sampling params deprecated","Google made gemini-3.6-flash and gemini-3.5-flash-lite generally available and deprecated the temperature, top_p and top_k sampling parameters.",{"title":271,"summary":272},"Kimi K3 launched","Moonshot launched Kimi K3, a 2.8T-parameter open-weight MoE with 1M context, on the Kimi API at $3\u002F$15 per 1M tokens, with weights released by 2026-07-27.",{"title":274,"summary":275},"Claude Sonnet 5 launched","claude-sonnet-5 launched with 1M context and a new tokenizer (~30% more tokens); manual extended thinking and non-default sampling parameters now return 400.",{"title":277,"summary":278},"Computer Use tool preview in Gemini 3.5 Flash","Google launched a public preview of the Computer Use tool in Gemini 3.5 Flash, with browser, mobile and desktop environments, configurable safety policies and prompt-injection detection.",{"title":280,"summary":281},"Claude Sonnet 4 and Opus 4 retired","claude-sonnet-4-20250514 and claude-opus-4-20250514 were retired; requests now return errors.",{"title":283,"summary":284},"Gemini 2.0 Flash models shut down","gemini-2.0-flash, gemini-2.0-flash-001, gemini-2.0-flash-lite and gemini-2.0-flash-lite-001 were shut down, with gemini-3.5-flash or gemini-3.1-flash-lite as replacements.",{"common":286},{"skip":5,"menu":6,"language":7,"sections":8,"footer":9,"tool":10,"home":11,"breadcrumbs":12,"copy":13,"copied":14,"download":15},1790863352011]