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 6.0.0 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 6.0.0

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

Changelog
- c28a5d24f89c1e7821987a80f8ae6490e2d2ed8f Merge pull request #54 from router-for-me/v6-test
- c9ce3a5464a7af485721da41a9de02d87a4bece5 Merge pull request #55 from router-for-me/v6-test
- 45d382f34473a54cdc9fc53868736951e10f4a9a Merge pull request #57 from router-for-me/v6-test
- c159180589d27cd98f03830df8abaefac1bb4432 Merge pull request #58 from router-for-me/v6-test
- 361a69f4defa44de5984970b27b99d92f9023dd5 Merge pull request #59 from router-for-me/gemini-web-v6
- 68be2f023f96d3c42c3f6cc10cbd7854348a9cb2 Merge pull request #60 from router-for-me/v6-test
- e9d2905a82c9779bf3f77f968b2e278895bad780 Merge pull request #61 from router-for-me/gemini-web
- 3c5390a87ef8b8e570fb1c4fd76b5568105d35d2 Merge remote-tracking branch 'origin/v6' into v6
- 4ecc798b1b456ad7256088d1f34deae4eb2e1824 Reduce the size of gemini-web's package files
- d4f5ec2492b77c284e19ed51abdf688ea1251025 Removed the cookie snapshot feature.
- 0db0b03db901fcba09f2ddc4ba42c34ceb9fbbb9 chore(docs): add and refine package-level comments across modules
- c6b391304dcd728d85d71c343f04584d3a03df17 chore(executor): add debug logging for API request errors
- c5df806ad2c500fac4baa8c54d1ab47ea38f4586 chore(executor): add debug logging for API request errors
- 837ae1b1b3af22d59e2ae564bbf39c58337a2647 chore(logging): add debug logs for executor Refresh methods
- 06a3e9792d974fad55ba245e4df24bb7953e2efc chore: Ignore .serena directory
- 3ffd87d8def0334272e0eab2607f9528345b1d0c docs(sdk-access): add SDK usage guides in English and Chinese
- 27246304300900f4a4178b9d468d787fd233e7c9 feat(auth): add Gemini Web token saving endpoint
- 8fc73874de7536b53f90369b6b5f22257ac18a88 feat(auth): centralize token store management and enhance persistence
- e68a6037e24b617ae934d423ebc929af1061ed4e feat(auth): enable model suspension and resumption logic in AuthManager
- 6046a8c95b4c16176db5717a338ff03ae18b45b3 feat(auth): enhance watcher with asynchronous dispatch and buffering
- 792ec49e5b8740ef4d80ca1f03766b06818b2b8a feat(auth): implement incremental auth updates with queue integration
- 4008be19f488ffc0bf3092ac8faa3ec7f7131833 feat(auth): introduce auth.providers for flexible authentication configuration
- ab55373bc58a09482855869cca2b796c8ccdc4bc feat(auth): introduce per-model state tracking and enhanced error handling
- 2e836cee88ec015749dae441f0656a43656f41ed feat(auth): standardize last_refresh metadata handling across executors
- 11b0efc38ff365a43ab2828f372622487d081ee4 feat(claude-executor): add ZSTD decoding support for Claude executor responses
- ac59023abb72d7c6c6931d0854320448cb6cf816 feat(executor): add CountTokens support across all executors
- e313d39be84c4d85eb6c8dddbf1e25cf769a69b4 feat(gemini-executor): implement CountTokens method with request translation and API integration
- 22a69333a074c3ce5e08b583801382b7abb03947 feat(gemini-web): Implement proactive PSIDTS cookie rotation
- 50c8f7f96f38435ee60aee05357a7642b567b573 feat(gemini-web): Inject fallback text for image-only flash model responses
- f1c4caf14ab0a327d7f47882e746c2bff53ad804 feat(logging): integrate logrus with custom Gin middleware for enhanced request logging and recovery
- e41d1277326c5e5b02e6f0f3cc540cd673664a12 feat(openai-compat): enhance provider key handling and model resolution
- 3dd50957923703eb7ccebcc8d921954046b91e04 feat(translators): add token counting support for Claude and Gemini responses
- d41ff2076f95b3c2600a20dd0bcf54d75cf76202 feat(translators): improve system instruction extraction and input handling for OpenAI and Claude responses
- 5090d9853bccf13a8c68ed3eb8010945394abd0f feat(translators): improve system instruction extraction and input handling for OpenAI and Claude responses
- 9df04d71e26fbb8ea2a17043dcc67618481993d1 feat(translators/claude): implement non-streaming response parsing for various translator types
- 19609db13cec1bb1822e48ae3a89b53bba8fbe34 feat(usage): add in-memory usage statistics tracking and API endpoint
- 3ade03f3b3d382ce85586196a16d2cb6e7eda00a feat(usage): implement usage tracking infrastructure across executors
- d5ad5fab8778b4de322e6f4d386311233e8158e3 feat: enhance request logging and account handling in CLI proxy
- 0607e52767c1cf779fd19072f1020c2ef636d736 feat: implement token refresh support for executors
- f81898c906c287e6c75029a70ee6c128b7b30ad0 feat: introduce custom provider example and remove redundant debug logs
- 759bb88a900fb1ba9031d161f82edf88fc049cda fix(auth): Improve file-based auth handling and consistency
- 5bf7a9575c6522a4be996f61b606e014903e1bc1 fix(auth): address index logic bug and remove redundant conditions
- ec08500924517ce3751f83b38e82fd89757333bf fix(auth): resolve drain label for correct loop termination in cliproxy service
- b86ed46845936285b78e56c9ab544daf06e564e5 fix(codex): Remove reasoning.effort for default gpt-5-codex model
- 48bbd9e2143a75a2524f9efeb279865bacc6cbd6 fix(gemini): handle "[DONE]" chunk, trim "data:" prefix, and remove session_id from requests
- b01807291414a877c9d3293e16a2638714dee9c3 fix(gemini): trim "data:" prefix in raw JSON and resolve variable shadowing in stream translation
- 73cf491478595b600e936c43525078bf6c5024ce fix(gemini-web): Correct stream translation and reduce auth refresh lead
- 49232372a7d17abb5f8aa5f8c477673e59c27f3a fix(log): Trim trailing newlines to prevent blank log lines
- 314125e7ecb5a625c76a6fead7b687a0d7e9407b fix(logging): Prevent race conditions in FileStreamingLogWriter
- 84248b6ec282a0847a0c3a36584fa55a430c6384 merge
- f5dc380b636c4fb9dd50a37cb54b52fb6693d3df rebuild branch
- 053134f66ec8f97d730adf581d5b6d1b80ffb5a2 refactor(auth): remove unused Refresh methods from authenticators
- bb8f93146fef872ed3778f5ea087a547f2adef9c refactor(auth): replace FileStore with FileTokenStore for unified token persistence
- 72ffeb73d3084478937d444c74d0be7d656cddf4 refactor(auth): replace NextRefreshAfter with NextRetryAfter for clarity and consistency
- e3be548e8d03b10c2a04d046edf49282b59d9b4c refactor(auth): replace log calls with fmt for improved consistency and standard output usage
- ed87dda0a6959ed8e76536b88f6eac3ac9943164 refactor(client): remove deprecated and unused methods for cleaner session handling and core auth management
- 58f74ebad10bfa64d9793a83d8448fcb34fcd8c5 refactor(config): remove force-gpt-5-codex option and related handlers
- 688547b0635a379edc94232fedfd7e0d4ad7e477 refactor(config, auth): remove allow-localhost-unauthenticated support and related handlers
- 7ea88358f05905f94c354969be235ced9499d384 refactor(executor): centralize header application logic for executors
- a2c5fdaf662039f5b2e0b247834a92cb2414cab3 refactor(executor): remove ClientAdapter and legacy fallback logic
- e9707c2f9ee45c228bb6a2afb594e0df12e06056 refactor(gemini-web): Move provider logic to its own package
- 8e485e58689a6a576afcc0a75d220d1cc8dc3315 refactor(gemini-web): Remove auto-refresh, auto-close, and caching
- c76b8785f8186684e4e108a8340975e2ac6ac920 refactor(gemini-web): Standardize logging with logrus
- d32fc0400e60478ea8f18b0ea36a4baa9a0287f5 refactor(headers): centralize header logic using EnsureHeader utility
- ac93641946f7b8ba4681df18965489ec1e4bd7f4 refactor(logging, mgmt): update timestamp format in logs and remove force-gpt-5-codex handlers
- d6bb1439787f469a5fe2f1ff29903ca67fad02b8 refactor(translator): Remove unused logrus imports
- 582677d067ce0d3cb4b7ed66533ea0e7688e5673 refactor(usage): replace channel-based queue with mutex-protected slice
- e8e00d4cb898e60123b097f0cf3f186639e24f0b refactor(watcher): Remove unnecessary log separator
- d9ad65622a198ed8490aef80874a64f6466ed4a9 refactor: standardize constant naming and improve file-based auth handling
- 3f69254f4363d77d2f41bf445d849f29dcc3180f remove all
- 4999fce7f4341ba740bc71395ee6af0c4d1905d5 v6 version first commit

https://github.com/router-for-me/CLIProxyAPI/releases/tag/v6.0.0

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