What OpenRouter's free tier allows
Model variants whose ID ends in :free are capped at 20 requests/minute regardless of account status. The daily cap depends on lifetime credit purchases: under 10 credits gives 50 requests/day, and 10 or more credits raises it to 1,000 requests/day. OpenRouter governs capacity globally, so extra accounts or extra API keys do not raise these limits.
- Published limits
- 20 requests per minute, 50 requests per day
- Free access type
- Free model aggregator
- Credit card
- Not required
- Protocol
- OpenAI-compatible at
https://openrouter.ai/api/v1 - Lifecycle
- Active
- Sources reviewed
- 2026-07-25
A negative account balance can return 402 errors even on free models until the balance is topped back above zero.
Where OpenRouter sits in this catalog
OpenRouter is one of 1 free model aggregator entries among the 25 providers detailed here. It asks for no credit card, which is true of 23 of the 25. It publishes fixed numbers — 20 requests per minute, 50 requests per day — which only 9 of the 25 do.
| Compared with | Published limits | Card | Endpoint |
|---|---|---|---|
| OpenRouter (this page) | 20 requests per minute, 50 requests per day | Not required | openrouter.ai |
| Together AI | Dynamic, no fixed numbers | Not required | api.together.xyz |
| Nebius Token Factory | 60 requests per minute | Not required | api.tokenfactory.nebius.com |
| Perplexity API | 50 requests per minute | Not required | api.perplexity.ai |
Models OpenRouter lists as free
Model IDs ending in :free— not part of any family this catalog tracks across providersopenrouter/free— not part of any family this catalog tracks across providers
The models above do not fall into any of the multi-provider families this catalog tracks, so OpenRouter is the only route to them here.
Checking a OpenRouter key
The CORS preflight allows any origin to send an Authorization header, so a browser can call this endpoint directly. That was measured against https://openrouter.ai on 2026-07-25.
So a key can be checked in the browser checker without installing anything. If you would rather not paste a key into a web page, this does the same thing:
#!/usr/bin/env sh
set -eu
: "${OPENROUTER_API_KEY:?Set OPENROUTER_API_KEY to a key you created yourself at the provider console}"
# Prints the models this key can reach, then the HTTP status on its own line so
# 200, 401, and 429 stay distinguishable.
curl --silent --show-error \
--write-out '\nHTTP %{http_code}\n' \
--header "Authorization: Bearer $OPENROUTER_API_KEY" \
'https://openrouter.ai/api/v1/models'
Using a OpenRouter key
OpenRouter serves the OpenAI chat completions protocol at https://openrouter.ai/api/v1. Point any client that accepts a custom base URL at it, and let the client read the key from OPENROUTER_API_KEY so the value never lands in a config file:
# Merge this snippet into ~/.codex/config.toml.
# Project-level config cannot select a custom model provider.
model = "openrouter/free"
model_provider = "openrouter"
[model_providers.openrouter]
name = "OpenRouter OpenAI-compatible gateway"
base_url = "https://openrouter.ai/api/v1"
env_key = "OPENROUTER_API_KEY"
wire_api = "responses"
Questions about the OpenRouter free tier
Does OpenRouter ask for a credit card?
No. OpenRouter is one of 23 providers here that hand out free access without a card, so the only cost of trying it is the signup.
What are OpenRouter's free-tier rate limits?
OpenRouter publishes 20 requests per minute, 50 requests per day. Those are the numbers in its own documentation as reviewed on 2026-07-25.
What happens when a OpenRouter key hits the limit?
The endpoint answers 429. That is a statement about the request that was refused, not about how much quota is left; only a reset header from the provider tells you when it clears.
Is the OpenRouter free tier going away?
Nothing in OpenRouter's own documentation says so as of 2026-07-25. A negative account balance can return 402 errors even on free models until the balance is topped back above zero.
Can OpenRouter be used with Codex, Cline, or Continue?
Yes. OpenRouter serves the OpenAI chat completions protocol at https://openrouter.ai/api/v1, so any client that accepts a custom base URL can use it. Claude Code is the exception, because it speaks the Anthropic protocol instead.
Official sources
- OpenRouter API rate limitshttps://openrouter.ai/docs/api-reference/limits
- OpenRouter free model variantshttps://openrouter.ai/docs/guides/routing/model-variants/free
- OpenRouter quickstarthttps://openrouter.ai/docs/quickstart
Every figure above was read from those pages on 2026-07-25. Where a provider states a limit only inside a console, this catalog records that fact instead of a number. See the methodology for how an entry gets in and how it gets corrected.