Cheapest LLM APIs right now (Nov 2026)
The lowest-priced language models you can call through an API today, limited to models that support tool calling and read at least 128,000 tokens - the minimum for real agent and document work.
Cheapest today: GLM 5.3 Flash from Z.ai at $0.0399 per million input tokens and $0.0784 per million output tokens. The spread to #20 (GPT-6 Luna Pro) is 4x on a blended basis.
Data updated 2026-11-11 - 20 models - source: public OpenRouter model list, refreshed daily. Prices in USD per million tokens.
| # | Model | Vendor | Input | Output | Blended | Context | Max out | Features | 30-day range (out) |
|---|---|---|---|---|---|---|---|---|---|
| 1 | GLM 5.3 Flash | Z.ai | $0.0399 | $0.0784 | $0.0495 | 1.05M | 131K | reasoning, tools, vision, video | $0.0701 - $0.9 * |
| 2 | Qwen3.7 Flash | Alibaba (Qwen) | $0.03 | $0.13 | $0.055 | 1M | 66K | reasoning, tools, vision, video | stable |
| 3 | Gemma 4 26B A4B | $0.08 | $0.1 | $0.085 | 262K | 128K | reasoning, tools, vision, video | $0.094 - $0.255 * | |
| 4 | Ministral 3 3B 2512 | Mistral AI | $0.1 | $0.1 | $0.1 | 131K | 105K | tools, vision | stable |
| 5 | Nemotron 3.5 Lightning | NVIDIA | $0.07 | $0.2 | $0.103 | 262K | 236K | reasoning, tools | stable |
| 6 | Nemotron 3 Nano 30B A3B | NVIDIA | $0.06 | $0.24 | $0.105 | 262K | 236K | reasoning, tools | stable |
| 7 | Granite 4.2 8B | IBM | $0.06 | $0.25 | $0.108 | 131K | 118K | reasoning, tools | $0.15 - $0.25 * |
| 8 | DeepSeek V4 Flash 0731 | DeepSeek | $0.0434 | $0.3 | $0.108 | 1.05M | 944K | reasoning, tools | $0.133 - $1.32 * |
| 9 | DeepSeek V4 Flash 0423 | DeepSeek | $0.09 | $0.18 | $0.113 | 1.05M | 393K | reasoning, tools | $0.18 - $1.28 * |
| 10 | Qwen3.5-Flash | Alibaba (Qwen) | $0.065 | $0.26 | $0.114 | 1M | 66K | reasoning, tools, vision, video | stable |
| 11 | Muse Spark 1.3 Contributor | Meta | $0.1 | $0.2 | $0.125 | 1.05M | 944K | reasoning, tools, vision, video | stable |
| 12 | Muse Spark 1.2 Contributor | Meta | $0.1 | $0.2 | $0.125 | 1.05M | 944K | reasoning, tools, vision, video | stable |
| 13 | DeepSeek V4.1 Flash 1017 | DeepSeek | $0.006 | $0.5 | $0.13 | 1.05M | 944K | reasoning, tools, vision | $0.5 - $1.2 * |
| 14 | GLM 4.7 Flash | Z.ai | $0.0605 | $0.4 | $0.145 | 200K | 118K | reasoning, tools | stable |
| 15 | Ministral 3 8B 2512 | Mistral AI | $0.15 | $0.15 | $0.15 | 262K | 210K | tools, vision | stable |
| 16 | Nemotron 3 Super | NVIDIA | $0.075 | $0.4 | $0.156 | 1.05M | 16K | reasoning, tools | $0.4 - $2.4 * |
| 17 | MiMo-V2.6-Flash | Xiaomi | $0.14 | $0.28 | $0.175 | 1.05M | 131K | reasoning, tools, vision, audio, video | stable |
| 18 | DeepSeek V4.1 Flash | DeepSeek | $0.051 | $0.567 | $0.18 | 1.05M | 944K | reasoning, tools, vision | $0.0112 - $1.2 * |
| 19 | Qwen3.5-9B | Alibaba (Qwen) | $0.17 | $0.25 | $0.19 | 262K | 236K | reasoning, tools, vision, video | $0.13 - $0.25 * |
| 20 | GPT-6 Luna Pro | OpenAI | $0.1 | $0.5 | $0.2 | 1.05M | 128K | reasoning, tools, vision | stable |
Blended = (3 x input + output) / 4. Context and max output in tokens (K = thousand, M = million). * Volatile: the output price moved by 30% or more in the last 30 days, usually because OpenRouter routes the model to a different provider.
Head-to-head comparisons for models in this list
Other lists
- Cheapest 1M-context models
- Cheapest reasoning models
- Cheapest vision models
- Largest context windows
- Free LLM APIs
- OpenAI models by price
- Claude models by price
- Gemini models by price
- DeepSeek models by price
- Grok models by price
- Qwen models by price
How we rank
The list includes text models from established vendors that OpenRouter added in the last 12 months, with at least a 32,000-token window. Batch, preview, experimental and image or audio generation variants are left out; batch prices appear in their own column on vendor pages. Prices are the current per-token list rates; for open-weight models served by several hosts, OpenRouter shows the price of the provider it currently routes to, which is why some of them move often. Need a full cost estimate? Use the AI cost calculator or browse the full model atlas.
Frequently asked questions
What is the cheapest LLM API right now?
As of 11 Nov 2026, GLM 5.3 Flash from Z.ai is the cheapest in this list at $0.0399 per million input tokens and $0.0784 per million output tokens (a blended $0.0495). Next is Qwen3.7 Flash at $0.03 / $0.13.
How is the ranking calculated?
Models are sorted by a blended price that assumes three input tokens for every output token, the same convention Artificial Analysis uses. If your workload writes more than it reads, look at the output column instead.
How often is this list updated?
Every day. Prices, context windows and features come from the public OpenRouter model list, refreshed each morning; the date at the top of the page shows the last update.
// follow
New tests and price changes, straight to your feed reader
Free RSS, no account and no email needed.
Follow Quantslant →