Open Source Models
Open-weight models — Llama, DeepSeek, Qwen, GLM, Kimi, GPT-OSS, Gemma, and more — served through one API
| Features | |||||
|---|---|---|---|---|---|
| $1.20 | $4.00 | $0.24 | |||
| $1.20 | $4.00 | $0.24 | |||
| $0.04 | $0.40 | $0.00 | |||
| $0.30 | $0.90 | $0.06 | |||
| $0.30 | $0.90 | $0.05 | |||
| $0.10 | $0.10 | $0.00 | |||
| $0.55 | $2.20 | $0.11 | |||
| $0.60 | $2.20 | $0.11 | |||
| $0.07 | $0.40 | $0.01 | |||
| $0.60 | $2.20 | $0.11 | |||
| $2.25 | $2.75 | — | |||
| $0.60 | $2.20 | $0.11 | |||
| $0.45 | $2.00 | — | |||
| $0.60 | $2.20 | $0.11 | |||
| $1.10 | $4.50 | $0.22 | |||
| $2.20 | $8.90 | $0.45 | |||
| $0.20 | $1.10 | $0.03 | |||
| $0.60 | $1.80 | $0.11 | |||
| $0.60 | $1.80 | $0.11 | |||
| $0.60 | $2.20 | $0.11 | |||
| $0.57 | $2.58 | — | |||
| $0.57 | $2.58 | — | |||
| $1.00 | $3.20 | $0.20 | |||
| $1.00 | $3.20 | $0.20 | |||
| $1.00 | $3.20 | $0.20 | |||
| $1.40 | $4.40 | $0.26 | |||
| $1.38 | $4.40 | $0.26 | |||
| $1.40 | $4.40 | $0.26 | |||
| $1.40 | $4.40 | $0.26 | |||
| $1.40 | $4.40 | $0.28 | |||
| $1.40 | $4.40 | $0.28 | |||
| $1.40 | $4.40 | $0.28 | |||
| $1.40 | $4.40 | $0.28 | |||
| $1.40 | $4.40 | $0.28 | |||
| $1.40 | $4.40 | $0.26 | |||
| $1.40 | $4.40 | $0.26 | |||
| $1.40 | $4.40 | $0.26 | |||
| $1.40 | $4.40 | $0.26 | |||
| $1.40 | $4.40 | $0.26 | |||
| $1.40 | $4.40 | $0.26 | |||
| $1.40 | $4.40 | $0.28 | |||
| $1.13 | $3.96 | $0.23 | |||
| $1.13 | $3.96 | $0.23 | |||
| $1.40 | $4.40 | $0.28 | |||
| $1.40 | $4.40 | $0.26 | |||
| $1.40 | $4.40 | $0.26 | |||
| $0.90 | $3.00 | $0.15 | |||
| $1.40 | $4.40 | $0.14 | |||
| $1.40 | $4.40 | $0.26 | |||
| $1.40 | $4.40 | $0.26 |
Open-weight models have closed most of the gap with proprietary frontiers: DeepSeek V4, Qwen3.7, GLM-5, Kimi K2, and MiniMax M3 sit near the top of real-world leaderboards, joined by OpenAI's GPT-OSS and Google's Gemma releases. Their weights are public — but running a 200B+ parameter model yourself means serious GPU infrastructure.
This page lists open-weight models served by hosted providers, so you get the openness — inspectable weights, no lock-in, the option to run the weights yourself later — with API convenience. China OpenRouter provides a hosted API, so you can start without operating any infrastructure.
Frequently asked questions
What is the best open source LLM?
DeepSeek V4, Qwen3.7, GLM-5.2, Kimi K2.6, and MiniMax M3 are the current leaders, each within striking distance of proprietary frontier models. For smaller, hardware-friendly options, GPT-OSS 20B, Gemma 4, and Qwen3.5 9B are the standouts.
What does 'open source' mean for LLMs?
Usually 'open weight': the trained weights are downloadable, but licenses vary — some are Apache 2.0 or MIT, others (like the Llama license) carry usage restrictions, and training data is rarely published. Check the license of a specific model before building on it.
Should I run models myself or use an API?
Running models yourself pays off with steady high volume, strict data-residency needs, or fine-tuned weights. For everything else, per-token APIs are cheaper than idle GPUs. A middle path: develop against hosted open models and keep running them yourself as an exit option, since the weights are public.
Are open models cheaper than proprietary ones?
Dramatically, per token. Competition among hosts drives prices down — DeepSeek V4 Flash and Qwen3 Coder 30B cost 10–50x less than frontier proprietary models. The list above shows every provider's price for each model.