Guides / Cheap API
Best cheap LLM APIs (open models)
Updated November 2026
As of November 2026, the best option is Qwen3.8 27B by Alibaba (Qwen), with a Small LM Index of 77.0, followed by Qwen3.6 35B-A3B (72.2) and Gemma 4 31B (70.1).
Open-weight models served on OpenRouter for at most $0.20 per million tokens (3:1 input:output blend, cheapest provider), ranked by the Small LM Index.
| # | Model | Lab | Small LM Index | Params | Memory (4-bit) | API / 1M | License |
|---|---|---|---|---|---|---|---|
| 1 | Qwen3.8 27B | Alibaba (Qwen) | 77.0 | 27B | ~17.9 GB | $0.13 | Apache-2.0 |
| 2 | Qwen3.6 35B-A3B | Alibaba (Qwen) | 72.2 | 35B (3B active) | ~22.6 GB | $0.031 | Apache-2.0 |
| 3 | Gemma 4 31B | 70.1 | 30.7B | ~21.9 GB | $0.16 | Apache-2.0 | |
| 4 | Gemma 4 26B-A4B | 67.5 | 25.2B (3.8B active) | ~16.8 GB | $0.068 | Apache-2.0 | |
| 5 | GLM-4.7-Flash | Z.ai (GLM) | 66.1 | 31B (3B active) | ~20.4 GB | $0.15 | MIT |
| 6 | gpt-oss-20b | OpenAI | 64.0 | 20.9B (3.6B active) | ~13.8 GB | $0.020 | Apache-2.0 |
| 7 | Qwen3.5 9B | Alibaba (Qwen) | 63.9 | 9B | ~6.4 GB | $0.028 | Apache-2.0 |
| 8 | Nemotron 3.5 Lightning | NVIDIA | 63.6 | 31.6B (3.6B active) | ~22.4 GB | $0.049 | OpenMDW-1.1 |
| 9 | Granite 4.2 8B | IBM (Granite) | 63.5 | 8B | ~6.9 GB | $0.082 | Apache-2.0 |
| 10 | Nemotron 3 Nano 30B-A3B | NVIDIA | 62.6 | 31.6B (3.5B active) | ~20.3 GB | $0.10 | NVIDIA Open Model |
| 11 | Ministral 3 14B | Mistral AI | 60.0 | 14B | ~10.6 GB | $0.20 | Apache-2.0 |
| 12 | Ministral 3 8B | Mistral AI | 55.2 | 8B | ~6.7 GB | $0.15 | Apache-2.0 |
| 13 | Qwen3 32B | Alibaba (Qwen) | 52.4 | 32.8B | ~23.2 GB | $0.13 | Apache-2.0 |
| 14 | Ministral 3 3B | Mistral AI | 49.4 | 3B | ~3.3 GB | $0.10 | Apache-2.0 |
| 15 | Phi-4 | Microsoft (Phi) | 44.7 | 14.7B | ~11.4 GB | $0.070 | MIT |
Memory covers the weights only; long contexts need more. Scores are mostly lab-reported, so gaps of 1–2 points are noise. See the methodology, or filter the full leaderboard yourself.
Head to head
Questions
What is the best cheap LLM API?
As of November 2026, the best option is Qwen3.8 27B by Alibaba (Qwen), with a Small LM Index of 77.0, followed by Qwen3.6 35B-A3B (72.2) and Gemma 4 31B (70.1).
How is this list ranked?
Open-weight models served on OpenRouter for at most $0.20 per million tokens (3:1 input:output blend, cheapest provider), ranked by the Small LM Index.
Which of the top five needs the least memory?
Gemma 4 26B-A4B, at about 16.8 GB with 4-bit quantization.
Which is the cheapest to use through an API?
gpt-oss-20b, at $0.020 per million tokens from the cheapest provider on OpenRouter.
Other guides
- Best small open models for coding
- Best small open models for math
- Best LLMs that run on an 8 GB GPU or laptop
- Best LLMs that run on a 16 GB GPU
- Best LLMs for a 24 GB GPU (RTX 4090, RTX 3090)
- Best tiny LLMs for phones and edge devices
- Best small open vision-language models
- Best open models with an Apache 2.0 or MIT license
- Best European open language models
- Best American open models under 100B
- Best fully open models (open data and code)