OpenRouter
LLM 5.7/10Best first BYOK option: one API for many free and paid models.
OpenRouter scores 5.7/10 for free value in LLM. The main constraint: 27 zero-price OpenRouter routes; no-top-up free-model limits are request-based (20 RPM, 50 requests/day). Buying credits raises the daily limit.
Free value score
5.7 / 10Show the math
Key metrics
Models
27 free · 340 total| Model | Family | AA | Access |
|---|---|---|---|
| NVIDIA: Nemotron 3 Ultra (free) | NVIDIA | 37.8 | free |
| Google: Gemma 4 26B A4B (free) | 25.7 | free | |
| OpenAI: gpt-oss-120b (free) | OpenAI | 23.8 | free |
| NVIDIA: Nemotron 3 Nano 30B A3B (free) | NVIDIA | 7.4 | free |
| Cohere: North Mini Code (free) | Cohere | — | free |
| Free Models Router | openrouter | — | free |
| Google: Gemma 4 31B (free) | — | free | |
| Google: Lyria 3 Clip Preview | — | free | |
| Google: Lyria 3 Pro Preview | — | free | |
| LiquidAI: LFM2.5-1.2B-Instruct (free) | LiquidAI | — | free |
| LiquidAI: LFM2.5-1.2B-Thinking (free) | LiquidAI | — | free |
| Meta: Llama 3.2 3B Instruct (free) | Meta | — | free |
| Meta: Llama 3.3 70B Instruct (free) | Meta | — | free |
| Nex AGI: Nex-N2-Pro (free) | Nex AGI | — | free |
| Nous: Hermes 3 405B Instruct (free) | Nous | — | free |
| NVIDIA: Nemotron 3 Nano Omni (free) | NVIDIA | — | free |
| NVIDIA: Nemotron 3 Super (free) | NVIDIA | — | free |
| NVIDIA: Nemotron 3.5 Content Safety (free) | NVIDIA | — | free |
| NVIDIA: Nemotron Nano 12B 2 VL (free) | NVIDIA | — | free |
| NVIDIA: Nemotron Nano 9B V2 (free) | NVIDIA | — | free |
| OpenAI: gpt-oss-20b (free) | OpenAI | — | free |
| Owl Alpha | openrouter | — | free |
| Poolside: Laguna M.1 (free) | Poolside | — | free |
| Poolside: Laguna XS.2 (free) | Poolside | — | free |
| Qwen: Qwen3 Coder 480B A35B (free) | Qwen | — | free |
| Qwen: Qwen3 Next 80B A3B Instruct (free) | Qwen | — | free |
| Venice: Uncensored (free) | Venice | — | free |
What you get
27 zero-price routes in OpenRouter models API
20 requests/minute on free models
Higher daily limit after buying credits
OpenAI-compatible API
Sources
-
"you can make up to 20 requests per minute. The following per-day limits apply: If you have purchased less than 10 credits, you're limited to 50 :free model requests per day. Purchasing credits increases the daily limit."
https://openrouter.ai/docs/api/reference/limits -
"DeepSeek V4 Flash (Reasoning, Max Effort) scores 40 on the Artificial Analysis Intelligence Index, placing it well above average among other open weight models of similar size"
https://artificialanalysis.ai/models/deepseek-v4-flash -
"DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek supporting a 1M-token context window. Free Context 1M"
https://openrouter.ai/deepseek/deepseek-v4-flash:free -
"It claims 8 million global users and 100 trillion tokens processed per month... OpenRouter more than doubles valuation to $1.3B in a year"
https://techcrunch.com/2026/05/26/openrouter-more-than-doubles-valuation-to-1-3b-in-a-year/