# Modelflare

> Modelflare is an AI model gateway for stable, lower-cost access to GPT, Claude, Grok, and other leading models. Every request includes a complete record of token usage and cost so individuals and teams can monitor consumption and manage usage in one place.

Modelflare supports compatible API clients, applications, and coding agents. Users choose a model and model group, can configure ordered fallback groups, and can review request status, token usage, latency, and cost in usage logs.

## Product

- [Homepage](https://modelflare.dev/): Product overview, model access, model groups, logs, costs, and quick start.
- [Models and pricing](https://modelflare.dev/pricing): Available models, model-group pricing, official API list-price comparisons, and compatible formats.
- [About Modelflare](https://modelflare.dev/about): Product purpose and service overview.
- [Trust and security](https://modelflare.dev/trust): API data handling, retention, service-provider boundaries, safeguards, reliability, and security reporting.
- [Supported countries and regions](https://modelflare.dev/supported-regions): The 171 countries, regions, and territories where commercial API service is currently available.

## Documentation

The full documentation lives on its own site: https://docs.modelflare.dev

- [Documentation index](https://docs.modelflare.dev/): Setup guides, model contracts, and API reference.
- [Quickstart](https://docs.modelflare.dev/quickstart/): Create an API key and send a first request.
- [Codex setup](https://docs.modelflare.dev/guides/clients/codex/): Connect Codex with the Modelflare setup command and a supported GPT model.
- [Codex interactive quick setup](https://docs.modelflare.dev/guides/clients/codex/start/): Visual first-run rehearsal for connecting Codex to Modelflare. It does not change your computer.
- [Claude Code setup](https://docs.modelflare.dev/guides/clients/claude-code/): Configure Claude Code with the Anthropic-compatible endpoint.
- [Claude Code interactive quick setup](https://docs.modelflare.dev/guides/clients/claude-code/start/): Visual first-run rehearsal for connecting Claude Code to Modelflare. It does not change your computer.
- [Grok Build setup](https://docs.modelflare.dev/guides/clients/grok-build/): Configure the official Grok Build CLI with the Responses API endpoint.
- [OpenCode setup](https://docs.modelflare.dev/guides/clients/opencode/): Configure Modelflare as an OpenAI-compatible provider in OpenCode.
- [CC-Switch setup](https://docs.modelflare.dev/guides/clients/cc-switch/): Save and switch local Modelflare profiles for supported coding tools.
- [Models](https://docs.modelflare.dev/models/): Text, image, and video model pages with the exact request contract for each.
- [API reference](https://docs.modelflare.dev/api/): Base URL, authentication, and endpoint families.

## Technical articles

- [Technical article library](https://modelflare.dev/articles): Browse practical guides by API engineering, protocols, reliability, security, usage, and cost.
- [OpenAI-compatible API guide](https://modelflare.dev/articles/openai-compatible-api-guide): Move an existing client by changing the base URL and verify production compatibility.
- [What is an AI API gateway?](https://modelflare.dev/articles/what-is-ai-api-gateway): Understand authentication, model access, routing, fallback, usage records, and protocol boundaries.
- [Responses API vs Chat Completions](https://modelflare.dev/articles/responses-api-vs-chat-completions): Compare request formats, streaming, tools, and provider compatibility.
- [AI API streaming guide](https://modelflare.dev/articles/ai-api-streaming-guide): Implement SSE parsing, phased timeouts, first-effective-output metrics, and cancellation handling.
- [Reliable AI API routing](https://modelflare.dev/articles/reliable-ai-api-routing): Use ordered fallback groups, RPM behavior, and request timing evidence.
- [AI API error guide](https://modelflare.dev/articles/ai-api-error-troubleshooting): Diagnose 401, 403, 429, 499, and 5xx failures by request layer.
- [AI API cost tracking](https://modelflare.dev/articles/ai-api-cost-tracking): Understand model prices, token usage, group multipliers, and per-request records.
- [AI API key security](https://modelflare.dev/articles/api-key-security-cost-controls): Design key isolation, quotas, expiration, model limits, IP rules, rotation, and cost attribution.

## Policies

- [Terms of Service](https://modelflare.dev/terms)
- [Usage Policy](https://modelflare.dev/usage-policy)
- [Privacy Policy](https://modelflare.dev/privacy-policy)
- [User Agreement](https://modelflare.dev/user-agreement)

## More detail

- [Expanded product reference](https://modelflare.dev/llms-full.txt)

## Programs and integrations

- [Plugins and integrations](https://modelflare.dev/integrations): Installation paths for supported developer tools and applications.
- [Project Plaza](https://modelflare.dev/projects): Published projects and partnerships.
- [Affiliate program](https://modelflare.dev/affiliates): Applications, referral links, and eligible commissions.
- [Project sponsorship](https://modelflare.dev/sponsorship): Eligibility, review, quota plans, and release conditions.
- [Partner Program Terms](https://modelflare.dev/partner-program-terms)
- [Top-up and Refund Policy](https://modelflare.dev/topup-refund-policy)

The website supports multiple interface languages. Available translated versions
are declared by each page's hreflang links; some policies have fewer translations.