# User statistics
- Active users: 335
- Expired users (tokens still in memory): 19
Service info: https://smolproxy.org
Smolproxy is a service that provides API access to multiple LLMs. There are a lot of uses for LLMs, a few examples:
You can use Smolproxy with any application/library/frontend where it is possible to specify a custom endpoint URL. Just to name a few:
For example, if the software that you use supports a custom OpenAI base URL and you want to use Smol, you can simply set the base URL to https://smolproxy.org/proxy/openai/v1 and set the API key to your token. See the full list of available API endpoints.
If you have any questions regarding service usage or payment, feel free to contact me.
If any of the providers below have issues for sustained periods of time, proxy tokens will be extended for the duration of the outage:
Other providers are generally stable as well, but might have more issues.
The proxy supports OpenAI's Chat Completions and Responses API, supports Anthropic API for Deepseek/GLM/Kimi/Qwen, and Gemini API for Gemini/Vertex.
Instructions for some of the popular harnesses:
Codex
Install Codex, don't launch it.
Create the folder ~/.codex, create ~/.codex/config.toml with:
model_provider = "smol"
[model_providers.smol]
name = "OpenAI"
base_url = "https://smolproxy.org/openai/flex/v1"
wire_api = "responses"
supports_websockets = true
experimental_bearer_token = "your token here"
http_headers = { "X-OpenAI-Actor-Authorization" = "smol" }
/flex is the 50% cheaper endpoint at the cost of (sometimes) slower generation or capacity errors. You can remove "/flex/" if you are okay with higher cost.
The IDE extension and the Codex app will also pick up the same config.
Claude Code
Install Claude Code, don't launch it.
Create ~/.claude.json with:
{"hasCompletedOnboarding": true}
~/.claude, create and edit ~/.claude/settings.json with:{
"env": {"ANTHROPIC_BASE_URL": "https://smolproxy.org/anthropic"},
"apiKeyHelper": "echo YOURTOKENHERE"
}
Claude Code endpoints for other models:
https://smolproxy.org/deepseek/anthropichttps://smolproxy.org/glm/anthropichttps://smolproxy.org/kimi/anthropicSeptember 23, 2026 - Added a little bit of stock, but it was bought out instantly, with some people creating 5-7 orders. Fulfilled all of them for now. Expect changes to the price or quota due to demand.
September 22, 2026 - Added GPT-6 Sol, GPT-6 Luna, Claude Opus 5.5. Added /openai/auto endpoint.
September 4, 2026 - Added GPT-6 Astra. Compared to Sol, it costs 2.5x more on the API, so use it lightly.
September 2, 2026 - Added some stock, added pricing for Fable 5.1 and Flash 3.8.
August 28, 2026 - Fixed standalone web search with Responses Lite for Codex on the OpenAI provider.
August 13, 2026 - Added some experimental Anthropic access, do not consider it stable. Also, as an experiment (do not expect it to be permanent yet) removed almost al per-provider quota caps (e.g. OpenAI had $65/day) and instead lowered the overall quota from $100 to $85, this should let you use the models you like more.
August 11, 2026 - Small network outage on the VPS, proxy was down for ~3 hours, added 1 day to all tokens.
August 10, 2026 - Gemini access is stable, restored the existing token prices. No new token purchases yet.
August 7, 2026 - The situation with LLM access is stabilized for now. If everything goes well and the access remains stable, the token renewal price will go back to its normal values. Token purchases are still disabled for now.
August 5, 2026 - Restored Gemini access, will monitor it. Added xAI Grok (no stability guarantee) back. Will monitor the situation, and perhaps will reopen purchases if Gemini stays stable.
August 4, 2026 - No Gemini access left for now; lowered the token renewal price in the store. Added 20% remaining time to all tokens, e.g. if you had 10 days remaining, now you have 12.
July 30, 2026 - Due to some issues, the proxy will be downsized: no new token purchases for now. If some models become more unavailable, the price for existing renewals will probably decrease probably decrease. This might get fixed in the future, but if you want a stable service for months to come, for now Smolproxy will not satisfy you. Also applied API pricing change for Luna and Terra.
July 6, 2026 - The VPS hosting the proxy had a brief outage. Added 1 day to all tokens.
June 26, 2026 - Disabled the old proxy completely, the beta proxy is now the main proxy. Currently both the beta and main proxy resolve to the same running instance, so you don't have to migrate. If you were using the old proxy before, you'll need to change your clients/endpoints, e.g. instead of /proxy/openai you'll now have /openai. The endpoint list is available on the main proxy page.
June 20, 2026 - Some issues with Gemini on the proxy. Added 3 days to all tokens. Gemini API has issues currently, but if you're getting blank responses on /google/vertex, try disabling streaming to see the actual error, most likely PROHIBITED_CONTENT or similar.
June 16, 2026 - Added GLM 5.2.
May 23, 2026 - Added Alibaba with Qwen3.7 Max and some of their other hosted models. They also host Kimi K2.6, Deepseek V4 Pro, GLM 5.1.
May 22, 2026 - The main proxy will be switched to the software currently running on the beta proxy in the start of June.
Apr 24, 2026 - Added Kimi models to the beta proxy, contact me if you have any issues with it.
Apr 24, 2026 - Added Deepseek V4 Flash and Pro to the beta proxy.
Mar 17, 2026 - Added GPT 5.4 mini and nano. Added 4-week token renewal/purchase options.
Mar 5, 2026 - Added GPT 5.4. Use the new beta proxy for best results with the Responses API.
Feb 26, 2026 - Added Gemini 3.1 Flash Image (Nano Banana 2).
Feb 24, 2026 - Added GPT 5.3 Codex.
Feb 19, 2026 - Added Gemini 3.1 Pro.
Feb 12, 2026 - Added GLM 5 explicitly to both proxies (you could already use it on the beta proxy before).
Feb 6, 2026 - Launched the new proxy implementation at https://beta.smolproxy.org/, please test. Has some Claude.
Jan 12, 2026 - Old domain https://smol.services seems to have been disabled, switched to the new domain for now: https://smolproxy.org
Dec 28, 2025 - Proxy was down for ~2 hours due to issues with the new VPS host. Added 1 day to all tokens as compensation.
Dec 22, 2025 - Added GLM 4.7.
Dec 17, 2025 - Added Gemini 3 Flash.
Dec 12, 2025 - Added GPT-5.2.
Nov 21, 2025 - Added https://gen.smol.services - small frontend for Gemini 3 Pro image gen.
Nov 18, 2025 - Added Gemini 3 Pro (preview) to the proxy.
Nov 12, 2025 - Added GPT-5.1 to the proxy.
Oct 3, 2025 - Added GLM (ported from reanon, thanks for the implementation).
Sep 24, 2025 - Added Grok 4 Fast and Grok Code Fast 1.
The live list of endpoints and their API schema docs is available at the main page of https://smolproxy.org/
Small frontend for the Gemini 3 Pro image gen model (also called Nano Banana Pro)
You can use it with your smolproxy.org token or with a Gemini API key. Image handling and API requests are done directly from the browser, there's no backend.
Items might be out of stock because I want to limit the total amount of users.
After the order is done, you will automatically receive a temporary token that will work for the stated duration.
Crypto only. ETH (only through the main Ethereum chain), USDT, LTC, BTC, XMR. Due to small amounts, be careful about high fees, especially for BTC and sometimes ETH. Use LTC and XMR whether possible (longer confirmation but very low fees)
If you break the fair use limits (excessive usage 24/7, token sharing, etc), you will get banned.
Token renewal is completely automatic, click here to proceed
For expired tokens, the new expiration is set to current time plus renewal duration. For active tokens, renewal duration is added to the existing expiration date.
Examples:
You can renew the same token multiple times (e.g. buy the 4-week renewal two times), there's no upper limit. Be aware that there are no special discounts, guarantees or perks for such cases.
$80 API-equivalent credits per day, with cache discounts applied.
Specific per-provider quotas:
A maximum of 10 concurrent and 180 requests per minute are allowed.
How do I make my quota last longer?
If you use any of the big providers, the #1 win is to make sure your requests are cached. Agentic harnesses do this automatically, but some frontends like SillyTavern need special configuration.
For OpenAI specifically: use the /openai/flex/v1 endpoint for a 2x discount at the cost of more instability in terms of timeouts/capacity errors. They can still be easily retried.
Can I renew an expired token?
Yes, but only if it's still in the memory. All tokens that have expired will be purged after roughly 1 week of inactivity. You can check if your token still works by going to https://smolproxy.org/user.
How long does it take you to restore service if some LLM endpoint stops working?
If an LLM endpoint stops working and I'm able to restore it - I will. If it takes me too long, I will compensate for the inconvenience by extending the duration of all tokens (including those that expired during the outage) by at least the outage duration (usually more). For example, if the Deepseek endpoint didn't work (not due to upstream issues) for for 6 hours and I was able to restore it, I will extend all tokens by at least 6 hours.
4chan tripcode: !!ahg+yVFXVZL (old: !!zLqNx4NnbXf)