{"id":2299,"date":"2026-08-23T04:12:42","date_gmt":"2026-08-23T04:12:42","guid":{"rendered":"https:\/\/convly.ai\/?p=2299"},"modified":"2026-08-23T04:12:42","modified_gmt":"2026-08-23T04:12:42","slug":"ollama-claude-code","status":"publish","type":"post","link":"https:\/\/convly.ai\/es\/ollama-claude-code\/","title":{"rendered":"Using Ollama With Claude Code: Local Model Setup Guide"},"content":{"rendered":"<div class=\"convly-tldr\">\n<ul>\n<li>Claude Code does not natively support Ollama \u2014 it expects the Anthropic API. To use local models, you run a translation proxy (e.g. <code>claude-code-router<\/code> or a LiteLLM proxy) that exposes Ollama on an Anthropic-compatible endpoint.<\/li>\n<li>Point Claude Code at the proxy with <code>ANTHROPIC_BASE_URL<\/code> and a dummy <code>ANTHROPIC_API_KEY<\/code>, then map its model names to your Ollama models.<\/li>\n<li>Best local models for coding on Ollama today: <code>qwen3-coder<\/code>, <code>deepseek-coder-v2<\/code>, and <code>llama3.1<\/code>. Expect noticeably lower tool-use reliability than real Claude Sonnet.<\/li>\n<li>Plan for 24\u201348 GB of VRAM for a usable coding experience at meaningful context lengths.<\/li>\n<\/ul>\n<\/div>\n<p>Claude Code is Anthropic&#8217;s official terminal coding agent, and it talks to Anthropic&#8217;s cloud API by default. Ollama is a local model runner that exposes an OpenAI-compatible HTTP API. The two do not speak the same protocol out of the box, so pairing them requires a small proxy layer that translates Anthropic&#8217;s Messages API into Ollama&#8217;s chat API. This guide covers how that works, which models are worth running, and where the setup breaks down.<\/p>\n<div id=\"ez-toc-container\" class=\"ez-toc-v2_0_86 counter-flat ez-toc-counter ez-toc-container-direction\">\n<label for=\"ez-toc-cssicon-toggle-item-6a8a9dd0426c1\" class=\"ez-toc-cssicon-toggle-label\"><span class=\"\"><span class=\"eztoc-hide\" style=\"display:none;\">Toggle<\/span><span class=\"ez-toc-icon-toggle-span\"><svg style=\"fill: #000000;color:#000000\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" class=\"list-377408\" width=\"20px\" height=\"20px\" viewBox=\"0 0 24 24\" fill=\"none\"><path d=\"M6 6H4v2h2V6zm14 0H8v2h12V6zM4 11h2v2H4v-2zm16 0H8v2h12v-2zM4 16h2v2H4v-2zm16 0H8v2h12v-2z\" fill=\"currentColor\"><\/path><\/svg><svg style=\"fill: #000000;color:#000000\" class=\"arrow-unsorted-368013\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" width=\"10px\" height=\"10px\" viewBox=\"0 0 24 24\" version=\"1.2\" baseProfile=\"tiny\"><path d=\"M18.2 9.3l-6.2-6.3-6.2 6.3c-.2.2-.3.4-.3.7s.1.5.3.7c.2.2.4.3.7.3h11c.3 0 .5-.1.7-.3.2-.2.3-.5.3-.7s-.1-.5-.3-.7zM5.8 14.7l6.2 6.3 6.2-6.3c.2-.2.3-.5.3-.7s-.1-.5-.3-.7c-.2-.2-.4-.3-.7-.3h-11c-.3 0-.5.1-.7.3-.2.2-.3.5-.3.7s.1.5.3.7z\"\/><\/svg><\/span><\/span><\/label><input type=\"checkbox\"  id=\"ez-toc-cssicon-toggle-item-6a8a9dd0426c1\"  aria-label=\"Toggle\" \/><nav><ul class='ez-toc-list ez-toc-list-level-1 ' ><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-1\" href=\"https:\/\/convly.ai\/es\/ollama-claude-code\/#Why_Ollama_and_Claude_Code_Dont_Connect_Directly\" >Why Ollama and Claude Code Don&#8217;t Connect Directly<\/a><\/li><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-2\" href=\"https:\/\/convly.ai\/es\/ollama-claude-code\/#Prerequisites\" >Prerequisites<\/a><\/li><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-3\" href=\"https:\/\/convly.ai\/es\/ollama-claude-code\/#Choosing_a_Local_Model\" >Choosing a Local Model<\/a><\/li><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-4\" href=\"https:\/\/convly.ai\/es\/ollama-claude-code\/#Option_1_claude-code-router\" >Option 1: claude-code-router<\/a><\/li><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-5\" href=\"https:\/\/convly.ai\/es\/ollama-claude-code\/#Option_2_LiteLLM_Proxy\" >Option 2: LiteLLM Proxy<\/a><\/li><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-6\" href=\"https:\/\/convly.ai\/es\/ollama-claude-code\/#Pointing_Claude_Code_at_the_Proxy\" >Pointing Claude Code at the Proxy<\/a><\/li><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-7\" href=\"https:\/\/convly.ai\/es\/ollama-claude-code\/#Configuring_Context_and_Timeouts\" >Configuring Context and Timeouts<\/a><\/li><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-8\" href=\"https:\/\/convly.ai\/es\/ollama-claude-code\/#Known_Limitations\" >Known Limitations<\/a><\/li><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-9\" href=\"https:\/\/convly.ai\/es\/ollama-claude-code\/#When_to_Use_This_Setup_vs_the_API\" >When to Use This Setup vs the API<\/a><\/li><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-10\" href=\"https:\/\/convly.ai\/es\/ollama-claude-code\/#Alternatives_to_Ollama_for_This_Workflow\" >Alternatives to Ollama for This Workflow<\/a><\/li><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-11\" href=\"https:\/\/convly.ai\/es\/ollama-claude-code\/#Frequently_Asked_Questions\" >Frequently Asked Questions<\/a><\/li><\/ul><\/nav><\/div>\n<h2><span class=\"ez-toc-section\" id=\"Why_Ollama_and_Claude_Code_Dont_Connect_Directly\"><\/span>Why Ollama and Claude Code Don&#8217;t Connect Directly<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>Claude Code issues requests in Anthropic&#8217;s Messages API format (<code>\/v1\/messages<\/code>), with Anthropic-specific fields for tool use, cache control, and system prompts. Ollama exposes <code>\/api\/chat<\/code> and an OpenAI-compatible <code>\/v1\/chat\/completions<\/code> endpoint. Neither speaks the Anthropic dialect. To bridge them you need a proxy that:<\/p>\n<ul>\n<li>Accepts Anthropic-format requests on an HTTPS endpoint.<\/li>\n<li>Rewrites them into OpenAI-compatible chat completions.<\/li>\n<li>Forwards to Ollama, then translates streaming responses and tool calls back into the Anthropic event stream Claude Code expects.<\/li>\n<\/ul>\n<p>Two projects handle this reliably as of 2026: <strong>claude-code-router<\/strong> (a purpose-built router for Claude Code that supports Ollama, OpenRouter, and other backends) and <strong>LiteLLM<\/strong> (a general-purpose proxy with an <code>anthropic<\/code> pass-through mode). Either works; claude-code-router has fewer moving parts if Ollama is your only backend.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"Prerequisites\"><\/span>Prerequisites<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<ul>\n<li>Ollama installed and running. See <a href=\"https:\/\/convly.ai\/how-to-install-ollama-2026\/\">how to install Ollama<\/a> if you don&#8217;t have it yet.<\/li>\n<li>Claude Code installed (<code>npm install -g @anthropic-ai\/claude-code<\/code>).<\/li>\n<li>At least one coding-capable model pulled locally.<\/li>\n<li>Node.js 18+ for claude-code-router, or Python 3.10+ for LiteLLM.<\/li>\n<\/ul>\n<p>Verify Ollama is reachable:<\/p>\n<pre><code>curl http:\/\/localhost:11434\/api\/tags<\/code><\/pre>\n<h2><span class=\"ez-toc-section\" id=\"Choosing_a_Local_Model\"><\/span>Choosing a Local Model<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>Claude Code leans heavily on tool-use, structured edits, and long-context reasoning. Smaller general-chat models handle these badly. Stick to coder-tuned models or large instruct models.<\/p>\n<table>\n<thead>\n<tr>\n<th>Model (Ollama tag)<\/th>\n<th>Notable sizes<\/th>\n<th>Rough VRAM (Q4)<\/th>\n<th>Notes<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td><code>qwen3-coder<\/code><\/td>\n<td>30B (A3B MoE), 480B (A35B MoE)<\/td>\n<td>~18 GB (30B); the 480B variant is server-class<\/td>\n<td>Qwen team&#8217;s coder line; strong on agentic tool use.<\/td>\n<\/tr>\n<tr>\n<td><code>deepseek-coder-v2<\/code><\/td>\n<td>16B, 236B<\/td>\n<td>~10 GB (16B lite)<\/td>\n<td>Solid completions and refactors; the 236B is server-only.<\/td>\n<\/tr>\n<tr>\n<td><code>llama3.1<\/code><\/td>\n<td>8B, 70B<\/td>\n<td>~5 GB \/ ~40 GB<\/td>\n<td>General instruct; 70B is a reasonable Claude fallback if you have the VRAM.<\/td>\n<\/tr>\n<tr>\n<td><code>qwen2.5-coder<\/code><\/td>\n<td>7B, 14B, 32B<\/td>\n<td>~5 \/ ~9 \/ ~20 GB<\/td>\n<td>Still widely used; predates qwen3-coder but very stable.<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p>Quantization level, context length, and KV cache size all move VRAM requirements. Use the <a href=\"https:\/\/convly.ai\/llm-vram-calculator\/\">VRAM calculator<\/a> to size a specific configuration, and see <a href=\"https:\/\/convly.ai\/best-local-llms-to-run-on-ollama-2026\/\">best local LLMs for Ollama<\/a> for a wider comparison.<\/p>\n<p>Pull one before configuring the proxy:<\/p>\n<pre><code>ollama pull qwen3-coder:30b\nollama pull deepseek-coder-v2:16b<\/code><\/pre>\n<h2><span class=\"ez-toc-section\" id=\"Option_1_claude-code-router\"><\/span>Option 1: claude-code-router<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>claude-code-router is the shortest path. Install it globally:<\/p>\n<pre><code>npm install -g @musistudio\/claude-code-router<\/code><\/pre>\n<p>Create <code>~\/.claude-code-router\/config.json<\/code>:<\/p>\n<pre><code>{\n  \"Providers\": [\n    {\n      \"name\": \"ollama\",\n      \"api_base_url\": \"http:\/\/localhost:11434\/v1\/chat\/completions\",\n      \"api_key\": \"ollama\",\n      \"models\": [\"qwen3-coder:30b\", \"deepseek-coder-v2:16b\"]\n    }\n  ],\n  \"Router\": {\n    \"default\": \"ollama,qwen3-coder:30b\",\n    \"background\": \"ollama,deepseek-coder-v2:16b\"\n  }\n}<\/code><\/pre>\n<p>Start Claude Code through the router:<\/p>\n<pre><code>ccr code<\/code><\/pre>\n<p>The router launches a local Anthropic-compatible endpoint, sets the environment variables for Claude Code automatically, and proxies traffic to Ollama. Exact config field names have shifted between minor versions \u2014 check the project&#8217;s README if a key is rejected.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"Option_2_LiteLLM_Proxy\"><\/span>Option 2: LiteLLM Proxy<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>If you already run LiteLLM for other services, reuse it. Create <code>config.yaml<\/code>:<\/p>\n<pre><code>model_list:\n  - model_name: claude-sonnet-4\n    litellm_params:\n      model: ollama_chat\/qwen3-coder:30b\n      api_base: http:\/\/localhost:11434\n  - model_name: claude-haiku-4\n    litellm_params:\n      model: ollama_chat\/deepseek-coder-v2:16b\n      api_base: http:\/\/localhost:11434<\/code><\/pre>\n<p>Run it:<\/p>\n<pre><code>litellm --config config.yaml --port 4000<\/code><\/pre>\n<p>Then point Claude Code at the proxy (see next section). LiteLLM handles the Anthropic-to-Ollama translation on the <code>\/anthropic<\/code> route.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"Pointing_Claude_Code_at_the_Proxy\"><\/span>Pointing Claude Code at the Proxy<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>Claude Code reads two environment variables to redirect its API traffic. Set them in your shell before running <code>claude<\/code>.<\/p>\n<h3>macOS and Linux<\/h3>\n<pre><code>export ANTHROPIC_BASE_URL=\"http:\/\/localhost:4000\"\nexport ANTHROPIC_API_KEY=\"sk-anything\"\nclaude<\/code><\/pre>\n<p>Add these to <code>~\/.zshrc<\/code> or <code>~\/.bashrc<\/code> to persist. The key value is unused by the local proxy but Claude Code refuses to start without one set.<\/p>\n<h3>Windows (PowerShell)<\/h3>\n<pre><code>$env:ANTHROPIC_BASE_URL=\"http:\/\/localhost:4000\"\n$env:ANTHROPIC_API_KEY=\"sk-anything\"\nclaude<\/code><\/pre>\n<p>To persist across sessions, use <code>[Environment]::SetEnvironmentVariable(\"ANTHROPIC_BASE_URL\", \"http:\/\/localhost:4000\", \"User\")<\/code>. If Claude Code is installed via WSL, configure the variables inside the WSL shell instead \u2014 Ollama running on Windows is reachable from WSL at <code>http:\/\/host.docker.internal:11434<\/code> or the Windows host IP.<\/p>\n<h3>Windows (native, without WSL)<\/h3>\n<p>Claude Code officially targets macOS, Linux, and WSL. Native Windows support has been rough historically; run it under WSL2 unless you have confirmed the current release runs cleanly on your setup.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"Configuring_Context_and_Timeouts\"><\/span>Configuring Context and Timeouts<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>Claude Code assumes 200K-token context and fast time-to-first-token. Local models will not match either. Two tuning points matter:<\/p>\n<ul>\n<li><strong>Ollama context length.<\/strong> Set it explicitly per model via a Modelfile (<code>PARAMETER num_ctx 32768<\/code>) or the <code>OLLAMA_CONTEXT_LENGTH<\/code> environment variable on the Ollama server. Default context is small and will silently truncate long conversations.<\/li>\n<li><strong>KV cache VRAM.<\/strong> A 32K context on a 30B model consumes several GB of KV cache alone. Check total memory usage with <code>ollama ps<\/code>.<\/li>\n<\/ul>\n<p>For a full breakdown of memory needs at various context sizes, see <a href=\"https:\/\/convly.ai\/vram-requirements-every-major-llm-2026\/\">VRAM requirements by model<\/a>.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"Known_Limitations\"><\/span>Known Limitations<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<ul>\n<li><strong>Tool use is fragile.<\/strong> Claude Code&#8217;s file-edit, bash, and search tools depend on strict JSON tool-call output. Local models fail this more often, producing malformed calls or hallucinating file contents. qwen3-coder and deepseek-coder-v2 are among the most reliable, but neither matches Claude Sonnet.<\/li>\n<li><strong>Prompt caching is a no-op.<\/strong> Anthropic&#8217;s <code>cache_control<\/code> fields are ignored by the proxy. Long system prompts get re-sent every turn.<\/li>\n<li><strong>Speed.<\/strong> Even on a 24 GB GPU, a 30B model at 32K context produces 15\u201340 tokens\/sec. Claude Code&#8217;s agentic loop makes many calls per task, so wall-clock time can be 5\u201310\u00d7 slower than the cloud API.<\/li>\n<li><strong>Sub-agents and MCP.<\/strong> Advanced Claude Code features (background agents, MCP servers) generally still work because they route through the same proxy, but any feature relying on Anthropic-specific server behavior can break silently.<\/li>\n<\/ul>\n<h2><span class=\"ez-toc-section\" id=\"When_to_Use_This_Setup_vs_the_API\"><\/span>When to Use This Setup vs the API<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>Local Claude Code makes sense when: code cannot leave your network, you&#8217;re on a metered API budget and doing bulk refactors, or you&#8217;re experimenting with self-hosting. It makes less sense for daily agentic coding where Sonnet-class reasoning is the point.<\/p>\n<p>To decide numerically, run the numbers on both sides. The <a href=\"https:\/\/convly.ai\/ai-api-cost-calculator\/\">API cost calculator<\/a> estimates monthly Anthropic spend, and the <a href=\"https:\/\/convly.ai\/self-hosting-vs-api-calculator\/\">self-hosting vs API break-even calculator<\/a> compares that against GPU amortization. For most solo developers the API wins; for teams hitting the API hard, a shared local box can pay back inside a year. If you&#8217;re spec&#8217;ing that box, the <a href=\"https:\/\/convly.ai\/best-gpus-for-local-llms-2026\/\">best GPUs for local LLMs<\/a> guide covers the current tier.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"Alternatives_to_Ollama_for_This_Workflow\"><\/span>Alternatives to Ollama for This Workflow<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>If Ollama&#8217;s performance is limiting, other runners with OpenAI-compatible APIs work identically behind the same proxy: LM Studio, vLLM, and llama.cpp&#8217;s server all fit. See the <a href=\"https:\/\/convly.ai\/lm-studio-complete-guide-2026\/\">LM Studio guide<\/a> for a GUI-first option, or the <a href=\"https:\/\/convly.ai\/what-is-ollama-complete-guide-2026\/\">Ollama complete guide<\/a> for a deeper look at Ollama itself.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"Frequently_Asked_Questions\"><\/span>Frequently Asked Questions<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<h3>Can Claude Code use Ollama without a proxy?<\/h3>\n<p>No. Claude Code speaks Anthropic&#8217;s Messages API and Ollama does not implement that dialect. You need a translation layer such as claude-code-router or LiteLLM. Setting <code>ANTHROPIC_BASE_URL<\/code> directly to <code>http:\/\/localhost:11434<\/code> will fail on the first request.<\/p>\n<h3>Which local model comes closest to Claude Sonnet for coding?<\/h3>\n<p>At the sizes most people can actually run, qwen3-coder (30B MoE) and deepseek-coder-v2 (16B lite) are the current top choices. Neither matches Sonnet on multi-file agentic tasks, but both are usable for single-file edits, completions, and code review. Compare intelligence scores on the <a href=\"https:\/\/convly.ai\/llm-leaderboard\/\">LLM leaderboard<\/a>.<\/p>\n<h3>Does prompt caching work with Ollama behind Claude Code?<\/h3>\n<p>No. Anthropic&#8217;s prompt caching is a server-side feature of their API. Proxies strip or ignore the <code>cache_control<\/code> fields, so every request re-processes the full system prompt and conversation history. This is one reason local setups feel slower per turn than the cloud API even at similar raw token throughput.<\/p>\n<h3>How much VRAM do I need for a decent experience?<\/h3>\n<p>A single 24 GB GPU (RTX 3090\/4090\/5090 class) runs a 30B coder model at Q4 with roughly 32K context. For 70B-class models or longer contexts, plan on 48 GB (RTX 6000 Ada, dual 3090s) or more. Use the <a href=\"https:\/\/convly.ai\/llm-vram-calculator\/\">VRAM calculator<\/a> for exact numbers per model and quantization.<\/p>\n<h3>Can I mix local and cloud models in the same Claude Code session?<\/h3>\n<p>Yes, via a router. claude-code-router lets you assign different models to different roles \u2014 for example, cloud Sonnet for the main agent and a local model for background tasks or completions. This can cut API costs substantially while keeping quality high on the critical path.<\/p>\n<h3>Is there an official Anthropic-supported way to run Claude Code locally?<\/h3>\n<p>No. Anthropic ships Claude Code as a client for their API and doesn&#8217;t distribute Claude weights. All local setups are community proxies pointing at third-party models. If Anthropic changes the Messages API, proxies may need updates before Claude Code works again against them.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Claude Code does not natively support Ollama \u2014 it expects the Anthropic API. To use local models, you run a [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":2300,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"site-sidebar-layout":"default","site-content-layout":"","ast-site-content-layout":"default","site-content-style":"default","site-sidebar-style":"default","ast-global-header-display":"","ast-banner-title-visibility":"","ast-main-header-display":"","ast-hfb-above-header-display":"","ast-hfb-below-header-display":"","ast-hfb-mobile-header-display":"","site-post-title":"","ast-breadcrumbs-content":"","ast-featured-img":"","footer-sml-layout":"","ast-disable-related-posts":"","theme-transparent-header-meta":"","adv-header-id-meta":"","stick-header-meta":"","header-above-stick-meta":"","header-main-stick-meta":"","header-below-stick-meta":"","astra-migrate-meta-layouts":"default","ast-page-background-enabled":"default","ast-page-background-meta":{"desktop":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}},"ast-content-background-meta":{"desktop":{"background-color":"var(--ast-global-color-4)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"var(--ast-global-color-4)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"var(--ast-global-color-4)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}},"footnotes":""},"categories":[7],"tags":[],"class_list":["post-2299","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-ai-news"],"_links":{"self":[{"href":"https:\/\/convly.ai\/es\/wp-json\/wp\/v2\/posts\/2299","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/convly.ai\/es\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/convly.ai\/es\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/convly.ai\/es\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/convly.ai\/es\/wp-json\/wp\/v2\/comments?post=2299"}],"version-history":[{"count":1,"href":"https:\/\/convly.ai\/es\/wp-json\/wp\/v2\/posts\/2299\/revisions"}],"predecessor-version":[{"id":2301,"href":"https:\/\/convly.ai\/es\/wp-json\/wp\/v2\/posts\/2299\/revisions\/2301"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/convly.ai\/es\/wp-json\/wp\/v2\/media\/2300"}],"wp:attachment":[{"href":"https:\/\/convly.ai\/es\/wp-json\/wp\/v2\/media?parent=2299"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/convly.ai\/es\/wp-json\/wp\/v2\/categories?post=2299"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/convly.ai\/es\/wp-json\/wp\/v2\/tags?post=2299"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}