AI price index · October 2026
The cheapest LLM APIs, ranked
Price is only half of it: a model that needs three tries costs more than one that gets it right. Start here, then test the top few on your own prompts.
Prices from OpenRouter’s models API, updated October 29, 2026
Cheapest overall
Paid models released this year, by blended price (3 parts input to 1 part output).
| Model | Provider | Input /1M | Output /1M | Cache read /1M | Context | Chatbot, per month* |
|---|---|---|---|---|---|---|
| Extract | scaledown | $0.04 | $0 | – | 1M | $1.80 |
| Summarize | scaledown | $0.04 | $0 | – | 1M | $1.80 |
| Ling 3.0 Flash | inclusionai | $0.021 | $0.063 | $0.0042 | 262K | $1.70 |
| Nex-N2.5-Mini | nex-agi | $0.025 | $0.10 | $0.0025 | 262K | $2.33 |
| GLM 5.3 Flash | Z.ai | $0.046 | $0.074 | $0.03 | 1.05M | $2.95 |
| Qwen3.7 Flash | Alibaba Qwen | $0.03 | $0.13 | $0.006 | 1M | $2.91 |
| Schematron V2 Turbo | inference-net | $0.03 | $0.15 | $0.03 | 128K | $3.15 |
| Mercury 2.5 | inception | $0.04 | $0.15 | $0.004 | 260K | $3.60 |
| Laguna XS 2.1 free variant | poolside | $0.06 | $0.12 | $0.03 | 262K | $4.14 |
| Hy-MT2-1.8B | tencent | $0.044 | $0.177 | – | 8K | $4.10 |
* Support chatbot: 1,000 chats a day, 1,500 tokens in, 400 out, 30 days, no caching. Prices in US dollars per 1M tokens.
Cheapest with tool calling and 128K+ context
For agents and apps that call functions over long documents.
| Model | Provider | Input /1M | Output /1M | Cache read /1M | Context | Chatbot, per month* |
|---|---|---|---|---|---|---|
| Ling 3.0 Flash | inclusionai | $0.021 | $0.063 | $0.0042 | 262K | $1.70 |
| GLM 5.3 Flash | Z.ai | $0.046 | $0.074 | $0.03 | 1.05M | $2.95 |
| Qwen3.7 Flash | Alibaba Qwen | $0.03 | $0.13 | $0.006 | 1M | $2.91 |
| Mercury 2.5 | inception | $0.04 | $0.15 | $0.004 | 260K | $3.60 |
| Laguna XS 2.1 free variant | poolside | $0.06 | $0.12 | $0.03 | 262K | $4.14 |
| Granite 4.2 8B | ibm-granite | $0.06 | $0.15 | $0.015 | 131K | $4.50 |
| Solar Mini 4 | upstage | $0.05 | $0.20 | $0.005 | 524K | $4.65 |
| Ling 3.0 Flash VL | inclusionai | $0.06 | $0.18 | $0.012 | 131K | $4.86 |
| Ternary Bonsai 2 9B | prism-ml | $0.08 | $0.13 | $0.04 | 262K | $5.16 |
| Nemotron 3.5 Lightning free variant | nvidia | $0.07 | $0.20 | $0.04 | 262K | $5.55 |
* Support chatbot: 1,000 chats a day, 1,500 tokens in, 400 out, 30 days, no caching. Prices in US dollars per 1M tokens.
Cheapest with vision
Models that accept images.
| Model | Provider | Input /1M | Output /1M | Cache read /1M | Context | Chatbot, per month* |
|---|---|---|---|---|---|---|
| Extract | scaledown | $0.04 | $0 | – | 1M | $1.80 |
| Summarize | scaledown | $0.04 | $0 | – | 1M | $1.80 |
| Nex-N2.5-Mini | nex-agi | $0.025 | $0.10 | $0.0025 | 262K | $2.33 |
| GLM 5.3 Flash | Z.ai | $0.046 | $0.074 | $0.03 | 1.05M | $2.95 |
| Qwen3.7 Flash | Alibaba Qwen | $0.03 | $0.13 | $0.006 | 1M | $2.91 |
| Ling 3.0 Flash VL | inclusionai | $0.06 | $0.18 | $0.012 | 131K | $4.86 |
| Ternary Bonsai 2 9B | prism-ml | $0.08 | $0.13 | $0.04 | 262K | $5.16 |
| Reka Edge | rekaai | $0.10 | $0.10 | – | 16K | $5.70 |
| Qwen3.5-Flash | Alibaba Qwen | $0.065 | $0.26 | – | 1M | $6.04 |
| Nex-N2.5-Pro | nex-agi | $0.075 | $0.25 | $0.015 | 262K | $6.38 |
* Support chatbot: 1,000 chats a day, 1,500 tokens in, 400 out, 30 days, no caching. Prices in US dollars per 1M tokens.
Cheapest reasoning models
Models that support a reasoning mode.
| Model | Provider | Input /1M | Output /1M | Cache read /1M | Context | Chatbot, per month* |
|---|---|---|---|---|---|---|
| Ling 3.0 Flash | inclusionai | $0.021 | $0.063 | $0.0042 | 262K | $1.70 |
| Nex-N2.5-Mini | nex-agi | $0.025 | $0.10 | $0.0025 | 262K | $2.33 |
| GLM 5.3 Flash | Z.ai | $0.046 | $0.074 | $0.03 | 1.05M | $2.95 |
| Qwen3.7 Flash | Alibaba Qwen | $0.03 | $0.13 | $0.006 | 1M | $2.91 |
| Mercury 2.5 | inception | $0.04 | $0.15 | $0.004 | 260K | $3.60 |
| Laguna XS 2.1 free variant | poolside | $0.06 | $0.12 | $0.03 | 262K | $4.14 |
| Granite 4.2 8B | ibm-granite | $0.06 | $0.15 | $0.015 | 131K | $4.50 |
| Solar Mini 4 | upstage | $0.05 | $0.20 | $0.005 | 524K | $4.65 |
| Ling 3.0 Flash VL | inclusionai | $0.06 | $0.18 | $0.012 | 131K | $4.86 |
| Ternary Bonsai 2 9B | prism-ml | $0.08 | $0.13 | $0.04 | 262K | $5.16 |
* Support chatbot: 1,000 chats a day, 1,500 tokens in, 400 out, 30 days, no caching. Prices in US dollars per 1M tokens.
Related
Cheaper, at the same quality.
Glow’s nuggets find the swap: which of your prompts could run on a cheaper model with the same GlowBench score, and what it saves a month.
- Read-only keys
- Never shown again
- 2FA + Face ID
- 7-day trial