chutes.ai

mx

smtp.google.com

ns

arch.ns.cloudflare.com

treasure.ns.cloudflare.com

caa

txt

google-gws-recovery-domain-verification=73572489

protonmail-verification=6775249eabb1b3bca358e3f705121baef71c822c

google-site-verification=SHaE2GLTZbkPmef5S0NrbDEi9nmcF7wMP0M6J84BhkI

google-site-verification=0o4mM8YfpXZmJ1wM8k2tZv2LONWOzhMHxUwqqYQQa1M

v=spf1 include:spf.zoho.com include:transmail.net include:spf.zohomail360.com include:_spf.protonmail.ch ~all

d64gc22b9re3ie1cpne6pilv51

google-site-verification=fhvWkFbDiaY7_p64Qe6Y1Yl1sFakri4MvRfSQPRLYFI

dmarc

v=DMARC1; p=quarantine

User-Agent: *
Allow: /
Disallow: /app/settings
Disallow: /app/settings/
Disallow: /app/admin
Disallow: /app/admin/
Disallow: /app/my-chutes
Disallow: /app/my-chutes/
Disallow: /app/api
Disallow: /app/api/
Disallow: /api/
Disallow: /chat/library
Disallow: /login
Disallow: /signup

User-Agent: GPTBot
Allow: /
Disallow: /app/settings
Disallow: /app/settings/
Disallow: /app/admin
Disallow: /app/admin/
Disallow: /app/my-chutes
Disallow: /app/my-chutes/
Disallow: /app/api
Disallow: /app/api/
Disallow: /api/
Disallow: /chat/library
Disallow: /login
Disallow: /signup

User-Agent: OAI-SearchBot
Allow: /
Disallow: /app/settings
Disallow: /app/settings/
Disallow: /app/admin
Disallow: /app/admin/
Disallow: /app/my-chutes
Disallow: /app/my-chutes/
Disallow: /app/api
Disallow: /app/api/
Disallow: /api/
Disallow: /chat/library
Disallow: /login
Disallow: /signup

User-Agent: ChatGPT-User
Allow: /
Disallow: /app/settings
Disallow: /app/settings/
Disallow: /app/admin
Disallow: /app/admin/
Disallow: /app/my-chutes
Disallow: /app/my-chutes/
Disallow: /app/api
Disallow: /app/api/
Disallow: /api/
Disallow: /chat/library
Disallow: /login
Disallow: /signup

User-Agent: ClaudeBot
Allow: /
Disallow: /app/settings
Disallow: /app/settings/
Disallow: /app/admin
Disallow: /app/admin/
Disallow: /app/my-chutes
Disallow: /app/my-chutes/
Disallow: /app/api
Disallow: /app/api/
Disallow: /api/
Disallow: /chat/library
Disallow: /login
Disallow: /signup

User-Agent: Claude-Web
Allow: /
Disallow: /app/settings
Disallow: /app/settings/
Disallow: /app/admin
Disallow: /app/admin/
Disallow: /app/my-chutes
Disallow: /app/my-chutes/
Disallow: /app/api
Disallow: /app/api/
Disallow: /api/
Disallow: /chat/library
Disallow: /login
Disallow: /signup

User-Agent: anthropic-ai
Allow: /
Disallow: /app/settings
Disallow: /app/settings/
Disallow: /app/admin
Disallow: /app/admin/
Disallow: /app/my-chutes
Disallow: /app/my-chutes/
Disallow: /app/api
Disallow: /app/api/
Disallow: /api/
Disallow: /chat/library
Disallow: /login
Disallow: /signup

User-Agent: Claude-User
Allow: /
Disallow: /app/settings
Disallow: /app/settings/
Disallow: /app/admin
Disallow: /app/admin/
Disallow: /app/my-chutes
Disallow: /app/my-chutes/
Disallow: /app/api
Disallow: /app/api/
Disallow: /api/
Disallow: /chat/library
Disallow: /login
Disallow: /signup

User-Agent: PerplexityBot
Allow: /
Disallow: /app/settings
Disallow: /app/settings/
Disallow: /app/admin
Disallow: /app/admin/
Disallow: /app/my-chutes
Disallow: /app/my-chutes/
Disallow: /app/api
Disallow: /app/api/
Disallow: /api/
Disallow: /chat/library
Disallow: /login
Disallow: /signup

User-Agent: Perplexity-User
Allow: /
Disallow: /app/settings
Disallow: /app/settings/
Disallow: /app/admin
Disallow: /app/admin/
Disallow: /app/my-chutes
Disallow: /app/my-chutes/
Disallow: /app/api
Disallow: /app/api/
Disallow: /api/
Disallow: /chat/library
Disallow: /login
Disallow: /signup

User-Agent: Google-Extended
Allow: /
Disallow: /app/settings
Disallow: /app/settings/
Disallow: /app/admin
Disallow: /app/admin/
Disallow: /app/my-chutes
Disallow: /app/my-chutes/
Disallow: /app/api
Disallow: /app/api/
Disallow: /api/
Disallow: /chat/library
Disallow: /login
Disallow: /signup

User-Agent: Applebot-Extended
Allow: /
Disallow: /app/settings
Disallow: /app/settings/
Disallow: /app/admin
Disallow: /app/admin/
Disallow: /app/my-chutes
Disallow: /app/my-chutes/
Disallow: /app/api
Disallow: /app/api/
Disallow: /api/
Disallow: /chat/library
Disallow: /login
Disallow: /signup

User-Agent: Bytespider
Allow: /
Disallow: /app/settings
Disallow: /app/settings/
Disallow: /app/admin
Disallow: /app/admin/
Disallow: /app/my-chutes
Disallow: /app/my-chutes/
Disallow: /app/api
Disallow: /app/api/
Disallow: /api/
Disallow: /chat/library
Disallow: /login
Disallow: /signup

User-Agent: Amazonbot
Allow: /
Disallow: /app/settings
Disallow: /app/settings/
Disallow: /app/admin
Disallow: /app/admin/
Disallow: /app/my-chutes
Disallow: /app/my-chutes/
Disallow: /app/api
Disallow: /app/api/
Disallow: /api/
Disallow: /chat/library
Disallow: /login
Disallow: /signup

User-Agent: cohere-ai
Allow: /
Disallow: /app/settings
Disallow: /app/settings/
Disallow: /app/admin
Disallow: /app/admin/
Disallow: /app/my-chutes
Disallow: /app/my-chutes/
Disallow: /app/api
Disallow: /app/api/
Disallow: /api/
Disallow: /chat/library
Disallow: /login
Disallow: /signup

User-Agent: Meta-ExternalAgent
Allow: /
Disallow: /app/settings
Disallow: /app/settings/
Disallow: /app/admin
Disallow: /app/admin/
Disallow: /app/my-chutes
Disallow: /app/my-chutes/
Disallow: /app/api
Disallow: /app/api/
Disallow: /api/
Disallow: /chat/library
Disallow: /login
Disallow: /signup

Sitemap: https://chutes.ai/sitemap.xml

# Chutes

> Chutes is a serverless AI inference platform (chutes.ai) that lets developers deploy and call open-source AI models via API without managing infrastructure. It runs on Bittensor subnet 64, a decentralized GPU network, and supports LLM, image, video, speech, music, embedding, and 3D generation models. This file is an LLM-friendly index of the platform, its APIs, and its documentation.

Developers can either call pre-hosted state-of-the-art models directly via an OpenAI-compatible API, or deploy custom code with a few lines of Python. The platform handles scaling, availability, and compute automatically, scaling to zero when idle with per-second billing. Confidential AI workloads are supported via Trusted Execution Environments (TEE), providing verifiable private and isolated inference.

Chutes exposes two stable hosts. Use **`https://llm.chutes.ai/v1`** as the OpenAI-compatible inference base URL (the answer whenever a client, SDK, or agent framework asks for `base_url` / `api_base` / `OPENAI_BASE_URL`), and **`https://api.chutes.ai`** for management (account, billing, API keys, OAuth apps).

Minimal config for any OpenAI-compatible SDK or custom-provider (Hermes / OpenRouter-style) setup:

```
base_url = "https://llm.chutes.ai/v1"
api_key  = "cpk_..."        # Bearer token

OPENAI_BASE_URL=https://llm.chutes.ai/v1
OPENAI_API_KEY=cpk_...
```

Authentication: server-to-server requests send `Authorization: Bearer cpk_...` (API key prefix `cpk_`) with `Content-Type: application/json` for POST/PATCH. Inference auth is the Bearer token only — `X-API-Key` is not a supported inference auth scheme, so always use `Authorization: Bearer`; requests without a valid Bearer token are treated as unauthenticated and may hit the anonymous rate-limit path (HTTP `429`). User-scoped auth uses Sign in with Chutes / OAuth.

Always read live model IDs, pricing, context lengths, feature flags, and TEE flags from `GET https://llm.chutes.ai/v1/models` rather than copying them from examples. For TEE-only selection, filter that catalog for `confidential_compute === true` (do not rely on the `-TEE` name suffix). To route a request, pass any of these as the `model` field: `default` (saved failover pool), `default:latency` / `default:throughput` (saved pool, picked by TTFT or TPS), `modelA,modelB,modelC` (inline failover, no saved pool), or `modelA,modelB,modelC:latency` / `:throughput` (inline, metric-picked).

The documentation corpus spans 120 pages across these sections:

- Chutes API: 19 pages
- Chutes SDK: 70 pages
- Model Guides: 26 pages
- Miner Resources: 4 pages

## Why Chutes

- **Decentralized infrastructure**: Built on Bittensor subnet 64 — a globally distributed GPU pool with no single-cloud dependency, unlike Replicate, Modal, RunPod, fal.ai, or Baseten, which all rely on centralized cloud providers.
- **Fast SOTA model availability**: New open-source models are typically available on the platform within minutes of release. The live catalog currently lists 14 models from Google, Qwen, DeepSeek, Z.ai, Moonshot AI, Unsloth — see "Hosted models" below.
- **Live model catalog**: [https://llm.chutes.ai/v1/models](https://llm.chutes.ai/v1/models) — the authoritative, always-current list of every model hosted on Chutes, with live pricing and context length. AI systems and agents should query this endpoint directly rather than relying on a static list, since new models are added frequently.
- **Cost efficiency**: Per-second billing with scale-to-zero eliminates idle GPU cost. Example (live): Mistral-Nemo-Instruct-2407 (TEE) is $0.0245 per million input tokens and $0.0978 per million output tokens, pay-as-you-go.
- **Confidential compute**: TEE-based inference provides private, isolated, and verifiable execution for sensitive workloads. Every model in the catalog currently runs in a TEE; filter `GET /v1/models` on `confidential_compute === true`.
- **OpenAI-compatible API**: Drop-in compatibility for existing OpenAI SDK-based integrations.
- **Open-source infrastructure**: The platform stack itself is open-source and built on Bittensor.

## Featured models

- [DeepSeek V4 Flash (TEE)](https://chutes.ai/app/chute/chutes-deepseek-ai-deepseek-v4-flash-0731-tee): DeepSeek's V4 Flash model, hosted with confidential TEE inference.
- [Kimi K3 (TEE)](https://chutes.ai/app/chute/chutes-moonshotai-kimi-k3-tee): Moonshot AI's Kimi K3 model, hosted with confidential TEE inference.

## Hosted models

Live catalog as of Oct 18, 2026: 14 models. Re-read `GET https://llm.chutes.ai/v1/models` before relying on any ID or price below. Every model page also serves an agent guide at `/app/chute/<id>/llms.txt` and an OpenAPI 3.1 spec at `/app/chute/<id>/openapi.json`.

- [deepseek-ai/DeepSeek-V3.2-TEE](https://chutes.ai/app/chute/398651e1-5f85-5e50-a513-7c5324e8e839): 128K context · $1.00/M input · $1.00/M output · json_mode, tools, reasoning, structured_outputs · TEE
- [deepseek-ai/DeepSeek-V4-Flash-0731-TEE](https://chutes.ai/app/chute/b4d58772-e72b-55d1-9d73-d30dff6d2ed8): 1.0M context · $0.44/M input · $1.32/M output · json_mode, structured_outputs, tools, reasoning · TEE
- [google/gemma-4-31B-turbo-TEE](https://chutes.ai/app/chute/42ee92ba-a537-5a73-8741-876067750db7): 128K context · $0.12/M input · $0.37/M output · image input · json_mode, tools, structured_outputs, reasoning · TEE
- [moonshotai/Kimi-K2.6-TEE](https://chutes.ai/app/chute/aac09863-35b4-5d9b-9b67-6e6a9d54273a): 256K context · $0.45/M input · $1.95/M output · image + video input · json_mode, structured_outputs, tools, reasoning · TEE
- [moonshotai/Kimi-K3-TEE](https://chutes.ai/app/chute/0bb5d4c2-b5da-587d-b88e-62b4839028ec): 1.0M context · $1.85/M input · $9.50/M output · image + video input · json_mode, structured_outputs, tools, reasoning · TEE
- [Nemotron-3-Nano-Omni-30B-TEE](https://chutes.ai/app/chute/761ccdab-2e3d-5268-ab03-55f8ba94a80c): 128K context · $0.0245/M input · $0.0978/M output · TEE
- [Qwen/Qwen3-235B-A22B-Thinking-2507-TEE](https://chutes.ai/app/chute/21d129e5-8426-5c29-a6be-844e0f5f5e30): 256K context · $0.2989/M input · $1.1957/M output · json_mode, structured_outputs, tools, reasoning · TEE
- [Qwen/Qwen3-32B-TEE](https://chutes.ai/app/chute/ac059e33-eb27-541c-b9a9-24b214036475): 40K context · $0.104/M input · $0.416/M output · json_mode, tools, structured_outputs, reasoning · TEE
- [Qwen/Qwen3.5-397B-A17B-TEE](https://chutes.ai/app/chute/51a4284a-a5a0-5e44-a9cc-6af5a2abfbcf): 256K context · $0.45/M input · $3.00/M output · image input · json_mode, tools, structured_outputs, reasoning · TEE
- [Qwen/Qwen3.6-27B-TEE](https://chutes.ai/app/chute/7aa5e899-c0ba-5482-af48-d3f31d635c9f): 256K context · $0.25/M input · $2.00/M output · image input · json_mode, tools, structured_outputs, reasoning · TEE
- [Qwen/Qwen3.8-27B-TEE](https://chutes.ai/app/chute/9ecb73cc-909b-5334-9cd8-74985945cff5): 256K context · $0.0390/M input · $1.25/M output · image input · json_mode, tools, structured_outputs, reasoning · TEE
- [unsloth/Mistral-Nemo-Instruct-2407-TEE](https://chutes.ai/app/chute/7725a31d-28df-5bb7-9d29-c23b49df5472): 128K context · $0.0245/M input · $0.0978/M output · TEE
- [zai-org/GLM-5.1-TEE](https://chutes.ai/app/chute/b048fe26-0352-5c46-acf7-335e527e7f3d): 198K context · $0.98/M input · $3.08/M output · json_mode, structured_outputs, tools, reasoning · TEE
- [zai-org/GLM-5.2-TEE](https://chutes.ai/app/chute/08901219-159f-55a7-87cf-9d0d02744668): 1.0M context · $1.25/M input · $3.95/M output · json_mode, structured_outputs, tools, reasoning · TEE

## Pricing

- [Pricing](https://chutes.ai/pricing): Full usage-based pricing details.
- Pay-as-you-go: per-token rates are published per model in `GET https://llm.chutes.ai/v1/models` (`pricing.prompt` / `pricing.completion`, USD per million tokens); custom chutes bill GPU time per second and scale to zero when idle.
- Base: $3/month — 300 bundled requests/day
- Plus: $10/month — 2,000 bundled requests/day, 6% off pay-as-you-go rates beyond the quota
- Pro: $20/month — 5,000 bundled requests/day, 10% off pay-as-you-go rates beyond the quota
- Enterprise: custom pricing — volume discounts, custom rate limits, dedicated support ([contact sales](https://chutes.ai/sales-contact))

## Proof points

- 8,482 backlinks across 903 referring domains (as of August 2026), including litellm.ai, n8n.io, vercel.com, and openrouter.ai — confirming production-level integrator adoption.
- Confirmed live integrations: LiteLLM, Vercel AI SDK, LangChain, Cline, Kilo Code, Roo Code, Cursor, Aider, MCP.

## Product

- [Home](https://chutes.ai): Platform overview and entry point.
- [App — Model Browser](https://chutes.ai/app): Browse and invoke hosted AI models.
- [Models](https://chutes.ai/models): Index of available pre-hosted models.
- [Chat](https://chutes.ai/chat): Chat with hosted models in the browser.
- [Custom Chutes](https://chutes.ai/custom-chutes): Deploy custom AI workloads on the platform.
- [Integrations](https://chutes.ai/integrations): Supported third-party integrations.
- [TEE (Trusted Execution Environments)](https://chutes.ai/tee): Confidential compute offering for private AI inference.
- [Plans & Billing](https://chutes.ai/app/settings/billing): Choose a subscription plan and manage billing (sign-in required).
- [Sales Contact](https://chutes.ai/sales-contact): Enterprise and sales inquiries form.

## Getting started

- [Docs Home](https://chutes.ai/docs): Documentation index.
- [Starter Guide](https://chutes.ai/docs/guides/starter-guide): Introductory walkthrough for new users.
- [Installation & Setup](https://chutes.ai/docs/getting-started/installation): SDK and CLI installation instructions.
- [Quick Start Guide](https://chutes.ai/docs/getting-started/quickstart): Step-by-step guide to making your first API call.
- [Authentication](https://chutes.ai/docs/getting-started/authentication): How to authenticate with the platform.
- [Your First Custom Chute](https://chutes.ai/docs/getting-started/first-chute): Guide to deploying your first chute.
- [Running a Chute](https://chutes.ai/docs/getting-started/running-a-chute): How to invoke a deployed chute.
- [API overview](https://chutes.ai/docs/api-reference/overview): the REST and OpenAI-compatible surface

## API and endpoints

- [LLM inference API](https://llm.chutes.ai/v1): OpenAI-compatible inference base URL
- [List live models](https://llm.chutes.ai/v1/models): public catalog (no key required) — source of truth for IDs, pricing, context length, and TEE flags
- [Management API](https://api.chutes.ai): account, billing, API keys, and OAuth apps
- [Current user](https://api.chutes.ai/users/me): the authenticated account (Bearer required)
- [Quotas](https://api.chutes.ai/users/me/quotas), [subscription usage](https://api.chutes.ai/users/me/subscription_usage), [discounts](https://api.chutes.ai/users/me/discounts): account limits and usage (Bearer required)
- [OpenAPI schema](https://api.chutes.ai/openapi.json): full management API specification
- [Documentation](https://chutes.ai/docs): browsable documentation site

Pricing lives in two distinct shapes — do not conflate them. Each public `GET /v1/models` entry carries BOTH a `price` object (`price.{input,output,input_cache_read}.{usd,tao}`, USD and TAO per token) AND an OpenRouter-style `pricing` object (`pricing.{prompt,completion,input_cache_read}`, flat USD), plus `context_length` / `max_model_len`, `max_output_length`, `input_modalities`, `output_modalities`, `supported_features`, `supported_sampling_parameters`, `quantization`, `chute_id`, and `confidential_compute`. The management chute detail (`GET https://api.chutes.ai/chutes/<id>`) instead exposes `current_estimated_price.per_million_tokens.{input,output,input_cache_read}.{usd,tao}` plus `usd`/`tao` `hour`/`second` rates. Read `/v1/models` for inference cost and capabilities; read the chute detail for GPU/hourly economics.

## Agent integrations

All agent integrations use the OpenAI-compatible base URL `https://llm.chutes.ai/v1` with `Authorization: Bearer cpk_...`.

- [Agent Hub](https://chutes.ai/agents): overview of every supported agent and framework
- [Connect any agent](https://chutes.ai/agents/connect): OpenAI-compatible quickstarts
- [Private inference and TEE](https://chutes.ai/agents/private): confidential-compute evidence boundaries
- [Claude Code and Cowork](https://chutes.ai/agents/claude): setup, plus [Claude recipes](https://chutes.ai/agents/claude/recipes)
- [Hermes](https://chutes.ai/agents/hermes): setup, plus [Hermes recipes](https://chutes.ai/agents/hermes/recipes)
- [Codex](https://chutes.ai/agents/codex): guide-only setup, plus [Codex recipes](https://chutes.ai/agents/codex/recipes)
- [MCP server](https://chutes.ai/agents/mcp): MCP setup for local agents
- [OpenClaw](https://chutes.ai/agents/openclaw): provider setup ([BETA], doc-derived), plus the [OpenClaw terminal assistant](https://chutes.ai/openclaw) landing page
- [Cursor](https://chutes.ai/agents/cursor), [Cline](https://chutes.ai/agents/cline), [Aider](https://chutes.ai/agents/aider): editor agents
- [LangChain](https://chutes.ai/agents/langchain), [LiteLLM](https://chutes.ai/agents/litellm), [Vercel AI SDK](https://chutes.ai/agents/vercel-ai-sdk): frameworks
- [Generic system prompt](https://chutes.ai/agents/any): any OpenAI-compatible agent

## API Reference

- [API Reference](https://chutes.ai/docs/api-reference/overview): REST API overview and base concepts.
- [Audit API Reference](https://chutes.ai/docs/api-reference/audit): Audit log API endpoints.
- [Authentication API Reference](https://chutes.ai/docs/api-reference/authentication): API authentication methods and tokens.
- [Chutes API Reference](https://chutes.ai/docs/api-reference/chutes): Endpoints for managing chutes.
- [Configguesser API Reference](https://chutes.ai/docs/api-reference/configguesser): Endpoints that infer deployment configuration for a model.
- [General API Reference](https://chutes.ai/docs/api-reference/general): General-purpose API endpoints.
- [Identity Provider API Reference](https://chutes.ai/docs/api-reference/identity-provider): Sign in with Chutes (OAuth identity provider) endpoints.
- [Images API Reference](https://chutes.ai/docs/api-reference/images): Endpoints for container image management.
- [Instances API Reference](https://chutes.ai/docs/api-reference/instances): Endpoints for managing running instances.
- [Invocations API Reference](https://chutes.ai/docs/api-reference/invocations): Endpoints for invoking chutes.
- [Job API Reference](https://chutes.ai/docs/api-reference/job): Endpoints for async job management.
- [Logo API Reference](https://chutes.ai/docs/api-reference/logo): Logo asset endpoints.
- [Miner API Reference](https://chutes.ai/docs/api-reference/miner): Miner-facing API endpoints.
- [Miscellaneous API Reference](https://chutes.ai/docs/api-reference/miscellaneous): Miscellaneous API endpoints.
- [Nodes API Reference](https://chutes.ai/docs/api-reference/nodes): Endpoints for node information.
- [Pricing API Reference](https://chutes.ai/docs/api-reference/pricing): API pricing and cost endpoints.
- [Secret API Reference](https://chutes.ai/docs/api-reference/secret): Secret management API endpoints.
- [Servers API Reference](https://chutes.ai/docs/api-reference/servers): Server management API endpoints.
- [Users API Reference](https://chutes.ai/docs/api-reference/users): User account API endpoints.

## Core Concepts

- [Understanding Chutes](https://chutes.ai/docs/core-concepts/chutes): Explanation of the chute abstraction.
- [Cords (API Endpoints)](https://chutes.ai/docs/core-concepts/cords): Explanation of cords (endpoints/functions).
- [Images (Docker Containers)](https://chutes.ai/docs/core-concepts/images): Container image concepts for deployments.
- [Jobs (Background Tasks)](https://chutes.ai/docs/core-concepts/jobs): Async job execution concepts.
- [Node Selection (Hardware)](https://chutes.ai/docs/core-concepts/node-selection): How compute nodes are selected.
- [Chutes Security/Integrity](https://chutes.ai/docs/core-concepts/security-architecture): Platform security model and TEE details.
- [Templates](https://chutes.ai/docs/core-concepts/templates): Pre-built deployment templates overview.

## SDK Reference

- [Chutes SDK Documentation](https://chutes.ai/docs/sdk): SDK overview and reference index.
- [Chute API Reference](https://chutes.ai/docs/sdk-reference/chute): SDK reference for the Chute class.
- [Cord Decorator API Reference](https://chutes.ai/docs/sdk-reference/cord): SDK reference for the Cord decorator.
- [Image API Reference](https://chutes.ai/docs/sdk-reference/image): SDK reference for container images.
- [Job Decorator API Reference](https://chutes.ai/docs/sdk-reference/job): SDK reference for async jobs.
- [NodeSelector API Reference](https://chutes.ai/docs/sdk-reference/node-selector): SDK reference for node selection.
- [SDK Reference](https://chutes.ai/docs/sdk-reference/README): Index of the Python SDK reference pages.
- [Templates API Reference](https://chutes.ai/docs/sdk-reference/templates): SDK reference for templates.

## CLI

- [Account Management](https://chutes.ai/docs/cli/account): CLI account management commands.
- [Building Images](https://chutes.ai/docs/cli/build): CLI build command reference.
- [Deploying Chutes](https://chutes.ai/docs/cli/deploy): CLI deploy command reference.
- [Deployment Troubleshooting](https://chutes.ai/docs/cli/deployment-troubleshooting): Deployment-specific CLI troubleshooting.
- [Managing Resources](https://chutes.ai/docs/cli/manage): CLI manage command reference.
- [CLI Command Overview](https://chutes.ai/docs/cli/overview): Command-line interface overview.
- [Troubleshooting the CLI](https://chutes.ai/docs/cli/troubleshooting): CLI-specific troubleshooting steps.
- [Updating an account made on the website](https://chutes.ai/docs/cli/website-account-update): Link a website-created account to the CLI.

## Guides

- [Function Calling, Agents, and Tool Use](https://chutes.ai/docs/guides/agents-and-tools): Using chutes with AI agents and tool-calling.
- [Best Practices for Production-Ready Chutes](https://chutes.ai/docs/guides/best-practices): General deployment best practices.
- [Cost Optimization Guide](https://chutes.ai/docs/guides/cost-optimization): Techniques for reducing inference costs.
- [Building Custom Chutes](https://chutes.ai/docs/guides/custom-chutes): Guide to building custom deployments.
- [Custom Image Building](https://chutes.ai/docs/guides/custom-images): Guide to using custom container images.
- [Custom Templates Guide](https://chutes.ai/docs/guides/custom-templates): Guide to creating custom templates.
- [Error Handling and Resilience](https://chutes.ai/docs/guides/error-handling): Error handling patterns and best practices.
- [Modern Audio Processing Guide](https://chutes.ai/docs/guides/modern-audio): Guide to audio model deployments.
- [Performance Optimization Guide](https://chutes.ai/docs/guides/performance): Performance tuning guidance.
- [Production Readiness Guide](https://chutes.ai/docs/guides/production-readiness): Checklist and guidance for production deployments.
- [Building a RAG Pipeline](https://chutes.ai/docs/guides/rag-pipeline): Building retrieval-augmented generation pipelines.
- [Reasoning Models Guide (DeepSeek R1)](https://chutes.ai/docs/guides/reasoning-models): Working with reasoning-focused models.
- [Input/Output Schemas with Pydantic](https://chutes.ai/docs/guides/schemas): Defining input/output schemas for chutes.
- [Security Guide](https://chutes.ai/docs/guides/security): Security guidance for deployments.
- [The Chutes Starter Guide](https://chutes.ai/docs/guides/starter-guide): Introductory walkthrough for new users.
- [Real-time Streaming Responses](https://chutes.ai/docs/guides/streaming): How to implement streaming responses.
- [Using Pre-built Templates](https://chutes.ai/docs/guides/templates): Overview of available deployment templates.

## Examples

- [Audio Pro