Free tool
LLM cost calculator
Put in your tokens and traffic, see the monthly bill on every model, with prompt caching and batch discounts.
Prices from OpenRouter’s models API, updated October 29, 2026
| Model | Input /1M | Output /1M | Per request | Per month |
|---|---|---|---|---|
| Qwen3.7 Flash | $0.03 | $0.13 | $0.0001 | $3.75 |
| GLM 5.3 Flash | $0.048 | $0.10 | $0.0001 | $4.39 |
| Qwen3.5-Flash | $0.065 | $0.26 | $0.0003 | $7.80 |
| DeepSeek V4 Flash 0423 | $0.091 | $0.182 | $0.0003 | $8.19 |
| Gemma 4 26B A4B | $0.076 | $0.255 | $0.0003 | $8.41 |
| Muse Spark 1.3 Contributor | $0.10 | $0.20 | $0.0003 | $9.00 |
| Muse Spark 1.2 Contributor | $0.10 | $0.20 | $0.0003 | $9.00 |
| GLM 4.7 Flash | $0.06 | $0.40 | $0.0003 | $9.63 |
| DeepSeek V4.1 Flash | $0.045 | $0.50 | $0.0003 | $10.20 |
| DeepSeek V4 Flash 0731 | $0.119 | $0.238 | $0.0004 | $10.71 |
| Claude Haiku 5.5 | $0.10 | $0.50 | $0.0004 | $13.50 |
| GPT-6 Luna | $0.10 | $0.50 | $0.0004 | $13.50 |
| 103 models in between. Type in the filter to find one. | ||||
| GPT Chat Latest | $5 | $30 | $0.025 | $750 |
| GPT-5.5 | $5 | $30 | $0.025 | $750 |
| GPT-6 Astra | $10 | $50 | $0.045 | $1,350 |
| GPT-6 Astra Pro | $10 | $50 | $0.045 | $1,350 |
| Claude Fable 5.1 | $10 | $50 | $0.045 | $1,350 |
| Claude Fable 5 | $10 | $50 | $0.045 | $1,350 |
| GPT-5.5 Pro | $30 | $180 | $0.150 | $4,500 |
| GPT-5.4 Pro | $30 | $180 | $0.150 | $4,500 |
Showing the 12 cheapest and 8 most expensive of 123 current models.
Related
Calculator questions
How is the monthly cost calculated?
(input tokens × input price + output tokens × output price) × requests per day × 30. With caching on, the cached share of input is billed at the model’s cache-read price. With batch on, models that have a batch price use it.
How many tokens is my prompt?
Roughly 4 characters or ¾ of a word per token in English. A page of text is about 500–700 tokens; a typical chat turn with history is 1,000–3,000.
Why does my real bill differ?
Retries, tool calls, reasoning tokens, cache writes and long-context surcharges all add up. Connect OpenRouter to Glow to see your actual spend per model and key, next to this estimate.
Now see your real numbers.
Glow reads your OpenRouter activity and shows actual spend by model, key and product, with the cheaper swap that keeps quality.
- Read-only keys
- Never shown again
- 2FA + Face ID
- 7-day trial