Popular: Data updated October 26, 2026

Categories

Internet1,355
Communication321
Audio & video898
Graphics & design539
Office & productivity1,120
Developer tools3,132
AI tools527
Security & privacy385
System tools3,113
Games523
Education & science239
Network & IT284

CLI Proxy API 7.3.0 download

Wrap Gemini CLI, ChatGPT Codex as an OpenAI/Gemini/Claude compatible API service, allowing you to enjoy the free Gemini 2.5 Pro, GPT 5 model through API

Luis Pater AI assistants & LLMs #42 AI assistants & LLMs
This is an older version. The current version is 8.0.43. CLI Proxy API 8.0.43 · Released:

Installer files 7.3.0

ArchitectureTypeScopeFile sizeDownloadSHA256
64-bit ZIP → Portable — — github.com VirusTotal

Link and SHA256 come from the Windows Package Manager community manifest. Compare the hash of the downloaded file before running it.

Release notes

Linux release assets
- CLIProxyAPI_<version>_linux_<arch>.tar.gz is the default Linux build. It supports dynamic library plugins and is built against a GLIBC 2.17 baseline.
- CLIProxyAPI_<version>_linux_<arch>_no-plugin.tar.gz is the portable Linux build for musl-based or older systems such as OpenWrt. It does not support dynamic library plugins.
FreeBSD release assets
- CLIProxyAPI_<version>_freebsd_aarch64_no-plugin.tar.gz is the FreeBSD arm64 build. It is built without CGO and does not support dynamic library plugins.
Changelog
- feat(codex): forward X-Codex-Turn-State header in executor requests (e696ea47)
- feat(codex): preserve native fidelity for responses-lite requests (f702bc1a)
- feat(cooldowns): add cooldown snapshot feature for management auth files (1ca975df)
- docs(config): document payload filter examples for codex tools (94d6eb53)
- Merge pull request #5795 from router-for-me/feat/management-auth-cooldowns (d23ba5ee)
- feat(devin): add Devin/Cognition provider integration and CLI OAuth (f9475276)
- feat(devin): bind upstream session_id and cascade_id to CPA canonical session (cbe800aa)
- feat(devin): prefix all Devin model IDs with devin/ namespace (eed24907)
- feat(devin): restrict glm-5-2 to free tier, remove static swe-1-7-lightning, and harden cloak (02fd1bde)
- fix(devin): restrict sensitive word obfuscation strictly to system prompt only (f5247e49)
- feat(devin): support sensitive-words in auth json metadata and attributes (1b694851)
- refactor(devin): align sensitive-words with antigravity to config.yaml only (d115fe2c)
- fix(devin): sanitize claude subagent identity and emoji directives to prevent content policy 403 (c0b86059)
- refactor(devin): keep sensitive words strictly external in config.yaml without hardcoding (c0b76c2d)
- feat(devin): support credential quota and seat status query via GetUserStatus (7b5741c6)
- fix(devin): strip system prompt lines matching configured sensitive words to evade unicode normalization bypass (5b8e3821)
- feat(devin): add devin/gemini-3-8-flash and devin/grok-4-6 model definitions and signature recognition (ea2f29fe)
- feat(devin): enhance request-log with intermediate interactions and decoded upstream body (2caab7db)
- docs(devin): document cloud-side system instructions baseline in DevinExecutor (8a377071)
- feat(devin): add deepseek-v4-flash and deepseek-v4-1-flash models (308e5ad3)
- feat(devin): support none thinking level for glm-5-2 (0c2351bb)
- docs(devin): update DevinExecutor comment with verbatim reconstructed cloud system prompt (59df75d2)
- feat(devin): add standalone devin_models.json catalog and remote updater (982cd124)
- feat(devin): auto-namespace model IDs from clean devin_models.json (61741744)
- feat(devin): add symmetric decoded upstream response in request log (16cb6c0b)
- feat(devin): parse protobuf timestamp and harden partial failure logging (469aa367)
- feat(cmd): add fetch_devin_models CLI tool for dynamic model catalog extraction (2683ec20)
- feat(devin): clamp maxTokens to model MaxCompletionTokens (ca664c6e)
- feat(devin): map model aliases and swe-1-7/haiku/sonnet/gpt-4-1 UIDs (bf06746d)
- feat(registry): auto-populate Gemini token limits and generation methods for Devin models (0aedd05d)
- fix(devin): calculate total_input_tokens and total_tokens correctly (85ddf3ae)
- feat(registry): transparently resolve un-prefixed devin models in auth selection (fbabc274)
- Revert "feat(registry): transparently resolve un-prefixed devin models in auth selection" (a0ccc3a4)
- fix(util): enforce strict devin/ prefix requirement for devin provider (ca159b30)
- fix(devin): align wire protocol, harden streaming, and resolve multi-turn tool/signature parity (f1f5506c)
- fix(devin): sort streaming tool call stop events and normalize prompt CRLF (a5ea971f)
- fix(devin): guard against reopening thought step on late-arriving signatures (2f2f9b43)
- fix(devin): bound tool call indices against OOM, set Refresh timeout, and check manual callback state (d754298a)
- fix(devin): update streaming tool call step metadata if arriving in subsequent frames (50dd5826)
- fix(devin): enforce Connect-RPC EOS trailer invariant, validate frame flag, and bind OAuth callback to ctx (5d0c77cf)
- perf(devin): cache sensitive word regex matcher, preallocate request bytes and frame decompression buffer (6c7d2d57)
- perf(devin): eliminate O(K^2) tool call argument string allocations using strings.Builder (6df8f322)
- perf(devin): cache Devin HTTP transports per proxy URL to reuse connection pools (86de823d)
- fix(devin): propagate stream chunk errors, fix truncated protobuf infinite loop, respect ctx roundtripper, and limit auth response body reads (6a239f57)
- fix(devin): store transient quota metrics strictly in Quota.Signals and keep Metadata static (98b106f0)
- fix(devin): normalize upstream internal errors to 502 Bad Gateway (1604cb03)
- fix(devin): dynamic catalog-driven chat_model_uid resolution and effort clamping (926450e8)
- fix(devin): transport reuse, interleaved stream steps, strings.Builder panic, and updater URL (fb2c1c1a)
- feat(devin): integrate global signature detector for cross-provider signature detection (9d190f30)
- refactor(devin): deduplicate auth credentials extraction, filter sparse tool calls, and optimize model lookup (30b2ac89)
What's Changed
- feat(cooldowns): add cooldown snapshot feature for management auth files by @LTbinglingfeng in https://github.com/router-for-me/CLIProxyAPI/pull/5795
- feat(devin): add Devin / Cognition Connect-RPC provider integration by @sususu98 in https://github.com/router-for-me/CLIProxyAPI/pull/5789
Full Changelog: https://github.com/router-for-me/CLIProxyAPI/compare/v7.2.159...v7.3.0

https://github.com/router-for-me/CLIProxyAPI/releases/tag/v7.3.0

Most popular in AI assistants & LLMs

See all
  1. Claude CodeUnleash Claude’s raw power directly in your terminal. Search million-line codebases instantly. Turn hours-long workflows into a single command. Your tools. Your workflow. Your codebase, evolving at thought speed.
  2. Codex CLICodex CLI is an open‑source local coding agent that runs in your terminal, letting you write, edit, and understand code without leaving the command line.
  3. ChatGPTChatGPT Desktop Application
  4. GPT4AllGPT4All is a GUI application for loading and interacting with Generative AI models
  5. JanTurn your computer into an AI computer
  6. WSL ManagerA GUI to quickly manage your WSL2 instances.
  7. oh-my-pi⌥ AI Coding agent for the terminal — hash-anchored edits, optimized tool harness, LSP, Python, browser, subagents, and more
  8. T3 CodeT3 Code is a minimal web GUI for coding agents.
  9. CC SwitchA cross-platform desktop All-in-One assistant tool for Claude Code, Codex, OpenCode, openclaw & Gemini CLI.
  10. LobeHubAn open-source, modern-design AI chat framework. Supports Multi AI Providers (OpenAI / Claude 4 / Gemini / Ollama / DeepSeek / Qwen), Knowledge Base (file upload / knowledge management / RAG), Multi-Modals (Plugins/Artifacts) and Thinking.

More from Luis Pater

See all
  • Any AI Proxy APIA Go-based proxy server that provides OpenAI-compatible API endpoints for Any AI website using browser automation.

Tags

Share