Skip to content
Back to search

gomodel

AI gateway / AI control plane / AI proxy written in Go. Unified OpenAI-compatible and Anthropic-compatible API for OpenAI, Anthropic, Gemini, Groq, xAI, Ollama, vLLM and more. A LiteLLM alternative with observability, guardrails, streaming, cost tracking, intelligent routing, sticky sessions, failover, real-time logs and usage tracking. Prod ready.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/enterpilot/gomodel with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/enterpilot/gomodel'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/enterpilot--gomodel/badge.svg)](/listings/enterpilot--gomodel)

HTML

<a href="/listings/enterpilot--gomodel"><img src="/api/listings/enterpilot--gomodel/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

These steps run a script from the network that findsafeskills does not scan.

**Step 1:** Install and start GoModel

**macOS / Linux**

curl -fsSL https://gomodel.enterpilot.io/install.sh | sh
# OPENAI_API_KEY="your-openai-key" # (optional)
gomodel

**Windows (PowerShell)**

irm https://gomodel.enterpilot.io/install.ps1 | iex
# $env:OPENAI_API_KEY = "your-openai-key" # (optional)
gomodel

**Docker**

docker run --rm -p 8080:8080 \
  -e OPENAI_API_KEY="your-openai-key" \
  enterpilot/gomodel

ℹ️ Configure GoModel with `.env`, a `config.yaml` file, or manage the most important settings directly in the dashboard.

ℹ️ See [`.env.template`](./.env.template) for the complete list of environment variables, including all available providers.

**Step 2:** Open the dashboard

http://localhost:8080/admin/dashboard

**Step 3:** Make an API call

curl http://localhost:8080/v1/responses \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5-chat-latest",
    "input": "Hello!"
  }'

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 239 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. <p align="center">
  2. <img alt="GoModel logo" src="docs/logo.svg" width="96">
  3. </p>
  4. <h1 align="center">
  5. GoModel - The last AI gateway you will ever need
  6. </h1>
  7. <p align="center">
  8. <a href="https://github.com/ENTERPILOT/GoModel/actions/workflows/test.yml"><img alt="CI" src="https://github.com/ENTERPILOT/GoModel/actions/workflows/test.yml/badge.svg"></a>
  9. <a href="https://scorecard.dev/viewer/?uri=github.com/ENTERPILOT/GoModel"><img alt="OpenSSF Scorecard" src="https://api.scorecard.dev/projects/github.com/ENTERPILOT/GoModel/badge"></a>
  10. <a href="https://github.com/ENTERPILOT/GoModel/blob/main/go.mod"><img alt="GO Version" src="https://img.shields.io/github/go-mod/go-version/ENTERPILOT/GoModel?label=GO"></a>
  11. <a href="https://hub.docker.com/r/enterpilot/gomodel"><img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/enterpilot/gomodel?label=Docker%20Pulls"></a>
  12. <a href="https://discord.gg/gaEB9BQSPH"><img alt="Discord" src="https://img.shields.io/badge/Discord-Join-5865F2?logo=discord&logoColor=white"></a>
  13. <a href="https://github.com/sponsors/ENTERPILOT"><img alt="Sponsor GoModel" src="https://img.shields.io/badge/Sponsor-%E2%9D%A4-EA4AAA?logo=githubsponsors&logoColor=white"></a>
  14. </p>
  15. <p align="center">
  16. <a href="https://news.ycombinator.com/item?id=47849097"><img alt="Hacker News" src="https://img.shields.io/badge/Hacker%20News-Apr%2021%20%2726%20%7C%20%234-brightgreen?logo=ycombinator&logoColor=white"></a>
  17. <a href="https://gomodel.enterpilot.io/docs?utm_source=readme"><img alt="docs GoModel" src="https://img.shields.io/badge/Docs-GoModel-blue"></a>
  18. </p>
  19. <p align="center">
  20. <a href="https://news.ycombinator.com/item?id=47849097"><img alt="GoModel on Hacker News" src="https://hackerbadge.vercel.app/api?id=47849097"></a>
  21. </p>
  22. <p align="center">
  23. GoModel is the fastest and the most resource-efficient AI Gateway (<a href="https://gomodel.enterpilot.io/docs/about/benchmarks?utm_source=readme">the self-reproducible benchmarks</a>). It's an alternative to LiteLLM (which was hacked recently) and Portkey (which is no longer maintained on GitHub).
  24. </p>
  25. <a href="https://demo.enterpilot.io/admin/dashboard?utm_source=readme">
  26. <img src="docs/2026-07-07_demo.gif" alt="GoModel AI gateway dashboard showing AI usage analytics, observability panel, token and costs tracking, and estimated cost monitoring" width="100%">
  27. </a>
  28. <p align="center">
  29. (click on the animation ↑ to see the live demo)
  30. </p>
  31. <p>
  32. GoModel saves you money and nerves.
  33. </p>
  34. <p>
  35. <strong>Money</strong> - because you can remember the responses on this layer (caching), track your spending and do tricks like prompt compression and intelligent routing.
  36. </p>
  37. <p>
  38. <strong>Nerves</strong> - because we strive to achieve good quality and reliability. Our ambition is to be the last AI gateway you will need - the most reliable, resource-optimal, feature-rich and fast.
  39. </p>
  40. ## Quick Start
  41. **Step 1:** Install and start GoModel
  42. **Docker**
  43. ```bash
  44. docker run --rm -p 8080:8080 \
  45. -v gomodel_data:/app/data \
  46. enterpilot/gomodel
  47. ```
  48. **macOS / Linux**
  49. ```bash
  50. curl -fsSL https://gomodel.enterpilot.io/install.sh | sh
  51. # OPENAI_API_KEY="your-openai-key" # (optional)
  52. gomodel
  53. ```
  54. **Windows (PowerShell)**
  55. ```powershell
  56. irm https://gomodel.enterpilot.io/install.ps1 | iex
  57. # $env:OPENAI_API_KEY = "your-openai-key" # (optional)
  58. gomodel
  59. ```
  60. ℹ️ Configure GoModel with `.env`, a `config.yaml` file, or manage the most important settings directly in the dashboard.
  61. ℹ️ See [`.env.template`](./.env.template) for the complete list of environment variables, including all available providers.
  62. **Step 2:** Open the dashboard and add a provider
  63. ```text
  64. http://localhost:8080/admin/dashboard
  65. ```
  66. **Step 3:** Make an API call
  67. ```bash
  68. curl http://localhost:8080/v1/responses \
  69. -H "Content-Type: application/json" \
  70. -d '{
  71. "model": "gpt-5-chat-latest",
  72. "input": "Hello!"
  73. }'
  74. ```
  75. ## GoModel and official SDKs
  76. GoModel accepts requests in two compatible formats:
  77. - OpenAI-compatible at `/v1`
  78. - Anthropic-compatible at `/v1/messages`
  79. The official SDKs therefore work unchanged. Configure their base URLs as follows:
  80. - OpenAI SDK: `http://localhost:8080/v1`
  81. - Anthropic SDK: `http://localhost:8080` (the SDK appends `/v1/messages`)
  82. ## List of Supported LLM Providers
  83. - OpenAI
  84. - Anthropic
  85. - xAI (Grok)
  86. - Google Gemini
  87. - Cohere
  88. - Vertex AI
  89. - DeepSeek
  90. - Groq
  91. - Fireworks AI
  92. - Together AI
  93. - Meta (Muse Spark)
  94. - OpenRouter
  95. - Z.ai
  96. - Alibaba Cloud Model Studio (Bailian)
  97. - Kilo AI
  98. - Eden AI
  99. - MiniMax
  100. - Mistral AI
  101. - Xiaomi MiMo
  102. - OpenCode Go
  103. - Azure OpenAI
  104. - Oracle
  105. - Ollama
  106. - SGLang
  107. - vLLM
  108. - llm-d
  109. - Amazon Bedrock Runtime and Bedrock Mantle
  110. - ChatGPT (the Codex backend) and Claude
  111. - GitHub Copilot
  112. - ElevenLabs (text-to-speech and speech-to-text)
  113. - Jev (TypeSafe System One decision API) and self-hosted Kev, also behind OpenAI's Decisions API
  114. - All OpenAI-compatible providers
  115. See the [Providers Overview](https://gomodel.enterpilot.io/docs/providers/overview?utm_source=readme) for the full
  116. per-provider feature matrix.
  117. ---
  118. ## Docker Compose
  119. **Infrastructure only** (Redis, PostgreSQL, MongoDB, Adminer - no image build):
  120. ```bash
  121. cp .env.template .env
  122. # Add your API keys to .env
  123. docker compose up -d
  124. # or: make infra
  125. ```
  126. **Full stack** (adds GoModel + Prometheus; builds the app image):
  127. ```bash
  128. docker compose --profile app up -d
  129. # or: make image
  130. ```
  131. ---
  132. ## API docs
  133. - [API Endpoints](https://gomodel.enterpilot.io/docs/advanced/api-endpoints?utm_source=readme)
  134. - [Admin API Endpoints](https://gomodel.enterpilot.io/docs/advanced/admin-endpoints?utm_source=readme)
  135. ---
  136. ## Gateway Configuration
  137. GoModel resolves configuration in the following order, with each source
  138. overriding those to its left:
  139. [Good defaults](https://gomodel.enterpilot.io/docs/about/technical-philosophy#good-defaults) → [`config.yaml`](./config/config.example.yaml) → [`.env`](./.env.template) → exported environment variables
  140. See the [Configuration reference](https://gomodel.enterpilot.io/docs/advanced/configuration?utm_source=readme)
  141. for the full list of settings.
  142. ---
  143. ## Features
  144. - [Caching](https://gomodel.enterpilot.io/docs/features/cache?utm_source=readme) - exact and semantic response caching, so repeated prompts cost nothing
  145. - [Cost tracking](https://gomodel.enterpilot.io/docs/features/cost-tracking?utm_source=readme) - per-request cost estimates, usage analytics, and spending breakdowns in the dashboard
  146. - [Budgets](https://gomodel.enterpilot.io/docs/features/budgets?utm_source=readme) - soft spend limits per user, team, or key: new requests are blocked once a limit is spent, but concurrent and in-flight requests can overshoot it
  147. - [Rate limits](https://gomodel.enterpilot.io/docs/features/rate-limits?utm_source=readme) - requests, tokens, and concurrency caps per user path, provider, or model
  148. - [Usage API](https://gomodel.enterpilot.io/docs/advanced/usage-api?utm_source=readme) - clients check their own usage, remaining budget, and rate-limit headroom with the key they already use for inference
  149. - [Virtual models](https://gomodel.enterpilot.io/docs/features/virtual-models?utm_source=readme) - aliases and load balancing (round-robin or cost-based) behind stable model names
  150. - [Session keeping](https://gomodel.enterpilot.io/docs/features/session-keeping?utm_source=readme) - detect a client session and pin it to one target and provider key, so provider prompt caches stay warm and request logs read as threads
  151. - [Failover](https://gomodel.enterpilot.io/docs/features/failover?utm_source=readme) - automatic rerouting to backup providers, with [retries and circuit breakers](https://gomodel.enterpilot.io/docs/advanced/resilience?utm_source=readme)
  152. - [Labelling](https://gomodel.enterpilot.io/docs/features/labelling?utm_source=readme) - tag requests from HTTP headers or API keys and break down usage by label
  153. - [User paths](https://gomodel.enterpilot.io/docs/features/user-path?utm_source=readme) - hierarchical scoping of keys, model access, budgets, usage, and request logs
  154. - [Model access control](https://gomodel.enterpilot.io/docs/features/users?utm_source=readme) - per-group, per-user, and per-key model allowlists that intersect down the user-path tree
  155. - [MCP gateway](https://gomodel.enterpilot.io/docs/features/mcp-gateway?utm_source=readme) - aggregate your MCP servers behind one authenticated endpoint
  156. - [Passthrough API](https://gomodel.enterpilot.io/docs/features/passthrough-api?utm_source=readme) - provider-native APIs under `/p/{provider}/...`, with GoModel auth and tracking
  157. - [Audio and image APIs](https://gomodel.enterpilot.io/docs/advanced/audio-api?utm_source=readme) - OpenAI-compatible text-to-speech, transcription, and [image generation and editing](https://gomodel.enterpilot.io/docs/advanced/images-api?utm_source=readme) with the same access rules, budgets, and cost tracking as chat
  158. - [Provider replay state](https://gomodel.enterpilot.io/docs/advanced/extra-content?utm_source=readme) - preserves Gemini thought signatures and Anthropic thinking blocks across turns, APIs, and providers
  159. - [Guardrails](https://gomodel.enterpilot.io/docs/advanced/guardrails?utm_source=readme) - request and response policies enforced at the gateway
  160. - [Plugins](https://gomodel.enterpilot.io/docs/advanced/plugins?utm_source=readme) - one contract for guardrails, response and stream filters, header edits, and routing strategies; built in, compiled in, or loaded from a `.so` at startup
  161. - [Workflows](https://gomodel.enterpilot.io/docs/advanced/workflows?utm_source=readme) - versioned per-request policies that scope cache, budgets, request logging, guardrail phases, and failover by user path, provider, or model
  162. - [Provider key rotation](https://gomodel.enterpilot.io/docs/providers/key-rotation?utm_source=readme) - round-robin over multiple API keys to lift per-key rate limits
  163. - [Observability](https://gomodel.enterpilot.io/docs/guides/prometheus-metrics?utm_source=readme) - Prometheus metrics, [OpenTelemetry](https://gomodel.enterpilot.io/docs/guides/opentelemetry?utm_source=readme) traces, request logs, and live request streaming in the dashboard
  164. - [Playground](https://gomodel.enterpilot.io/docs/features/playground?utm_source=readme) - try any model or virtual model from the dashboard and inspect the exact request and response JSON
  165. ## GoModel Pro
  166. [GoModel Pro](https://gomodel.enterpilot.io/docs/pro/overview?utm_source=readme) is the commercial build: the same gateway, configuration, and dashboard, with licensed extensions.
  167. - [Prompt compression](https://gomodel.enterpilot.io/docs/pro/compression?utm_source=readme) - remove repeated and structural context before it reaches the provider, without changing the request shape
  168. - [Intelligent routing](https://gomodel.enterpilot.io/docs/pro/intelligent-routing?utm_source=readme) - classify each request as easy or hard, then pick the healthiest and cheapest provider in that tier
  169. - [OIDC single sign-on](https://gomodel.enterpilot.io/docs/pro/sso?utm_source=readme) - protect the dashboard with your identity provider using Authorization Code flow with PKCE
  170. More in the documentation...
  171. Not ready for Pro? [Sponsor GoModel](https://github.com/sponsors/ENTERPILOT) to keep the open-source gateway moving.
  172. ## Roadmap
  173. See the [roadmap](https://gomodel.enterpilot.io/docs/about/roadmap?utm_source=readme) for GoModel Pro and the upcoming 0.3.0 release.
  174. ## Featured Sponsors
  175. <a href="https://github.com/Neiko2002"><img src="https://github.com/Neiko2002.png" alt="Neiko2002" width="64"></a>
  176. <a href="https://github.com/ajboainain"><img src="https://github.com/ajboainain.png" alt="ajboainain" width="64"></a>
  177. **Goal: $1K/month** - [~15% achieved!](https://github.com/sponsors/ENTERPILOT)
  178. If GoModel saves you money or time, [become a sponsor](https://github.com/sponsors/ENTERPILOT) or try [GoModel Pro](https://gomodel.enterpilot.io/docs/pro/overview?utm_source=readme).
  179. ## Community
  180. We are on [Discord](https://discord.gg/gaEB9BQSPH). Feel free to stop by and tell us what you think about GoModel.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.