# LLM API pricing statistics, October 2026

338 models, 49 providers, recomputed every morning from the prices on this site. Every figure is free to quote with a link.

Prices checked 12 October 2026 at 06.00 UTC . Source OpenRouter public model list . US dollars per million tokens

## Key figures

- On 12 October 2026, 338 AI models from 49 providers have a public API price per token.
- The median model costs $0.45 per million input tokens and $1.60 per million output tokens.
- The cheapest paid model is Llama 3.1 8B Instruct from Meta, served by DeepInfra, at $0.02 in and $0.04 out per million tokens.
- The most expensive is o1-pro from OpenAI, at $150.00 in and $600.00 out per million tokens.
- Output tokens cost 4.0 times as much as input tokens on the median model.
- 65 percent of paid models, 221 of 338, cost under $1 per million input tokens.
- 76 models have a cheaper batch price for jobs that can wait.
- Cached input is 90 percent cheaper than fresh input on the median model that offers it, and 214 models do.
- The largest context window is 2M tokens, on Grok 4.20 Multi-Agent. 107 models accept one million tokens or more.
- 31 models were listed in the last 30 days.

## Models by input price

| Input price per million tokens | Models | Share of paid models |
|---|---|---|
| Under $0.10 | 52 | 15 percent |
| $0.10 to $0.49 | 120 | 36 percent |
| $0.50 to $0.99 | 49 | 14 percent |
| $1 to $2.99 | 78 | 23 percent |
| $3 to $9.99 | 24 | 7 percent |
| $10 or more | 15 | 4 percent |

## By provider

Providers with at least three paid models on the list.

| Provider | Models | Cheapest model | Median input | Median output | Most expensive model |
|---|---|---|---|---|---|
| OpenAI | 65 | gpt-oss-20b, $0.018 in, $0.09 out | $2.00 | $10.00 | o1-pro, $150.00 in, $600.00 out |
| Alibaba | 42 | Qwen3.7 Flash, $0.03 in, $0.13 out | $0.1975 | $1.00 | Qwen3.8 Max Prime, $4.00 in, $12.00 out |
| Google | 27 | Gemma 3 4B, $0.05 in, $0.10 out | $0.50 | $3.00 | Nano Banana Pro (Gemini 3 Pro Image), $2.00 in, $12.00 out |
| Mistral | 20 | Mistral Small 3, $0.05 in, $0.08 out | $0.3255 | $0.75 | Mistral Medium 3.5, $1.50 in, $7.50 out |
| Anthropic | 16 | Claude Haiku 5.5, $0.10 in, $0.50 out | $4.50 | $22.50 | Claude Opus 4.1, $15.00 in, $75.00 out |
| Z.ai | 16 | GLM 4.7 Flash, $0.06 in, $0.40 out | $0.60 | $2.20 | GLM 5.3 Prime, $2.80 in, $8.80 out |
| DeepSeek | 14 | DeepSeek V4 Flash 0731, $0.06 in, $0.18 out | $0.27 | $1.00 | DeepSeek V4 Pro 0423, $0.45 in, $3.48 out |
| Meta | 14 | Llama 3.1 8B Instruct, $0.02 in, $0.04 out | $0.14 | $0.325 | Muse Spark 1.3, $1.25 in, $4.25 out |
| MiniMax | 8 | MiniMax-01, $0.20 in, $1.10 out | $0.30 | $1.20 | MiniMax M1, $0.40 in, $2.20 out |
| Moonshot AI | 7 | Kimi K2.5, $0.50 in, $2.50 out | $0.60 | $2.50 | Kimi K3, $3.00 in, $15.00 out |
| Tencent | 7 | Hy-MT2-1.8B, $0.044 in, $0.177 out | $0.132 | $0.528 | Hy4 preview, $0.834 in, $2.50 out |
| xAI | 7 | Grok Build 0.1, $1.00 in, $2.00 out | $1.25 | $2.50 | Grok 4.7, $2.00 in, $6.00 out |
| Aion Labs | 6 | Aion 3.5 Mini, $0.70 in, $1.40 out | $0.80 | $1.60 | Aion 3.5, $3.00 in, $6.00 out |
| Bytedance Seed | 6 | Seed 1.6 Flash, $0.075 in, $0.30 out | $0.25 | $2.00 | Seed-2.0-Code, $0.50 in, $3.00 out |
| Amazon | 5 | Nova Micro 1.0, $0.035 in, $0.14 out | $0.30 | $2.50 | Nova Premier 1.0, $2.50 in, $12.50 out |
| Cohere | 5 | Command R7B (12-2024), $0.0375 in, $0.15 out | $0.30 | $1.50 | Command A, $2.50 in, $10.00 out |
| Nvidia | 5 | Nemotron 3.5 Lightning, $0.06 in, $0.16 out | $0.085 | $0.20 | Nemotron 3 Ultra, $0.50 in, $2.20 out |
| Perplexity | 5 | Sonar, $1.00 in, $1.00 out | $2.00 | $8.00 | Sonar Pro Search, $3.00 in, $15.00 out |
| Xiaomi | 5 | MiMo-V2.6-Flash, $0.14 in, $0.28 out | $0.435 | $0.87 | MiMo-V2.6-Pro-UltraSpeed, $4.35 in, $8.70 out |
| Inclusionai | 4 | Ling 3.0 Flash VL, $0.06 in, $0.18 out | $0.0675 | $0.20 | Ling 3.0 Flash Sante, $0.075 in, $0.22 out |
| Sakana | 4 | Sakana Namazu, $0.95 in, $4.00 out | $3.50 | $18.00 | Fugu Ultra v2, $5.00 in, $30.00 out |
| Nousresearch | 3 | Hermes 3 70B Instruct, $0.70 in, $0.70 out | $1.00 | $1.00 | Hermes 4 405B, $1.00 in, $3.00 out |
| Sao10K | 3 | Llama 3 8B Lunaris, $0.04 in, $0.05 out | $0.65 | $0.75 | Llama 3.1 Euryale 70B v2.2, $0.85 in, $0.85 out |
| Stepfun | 3 | Step 3.5 Flash, $0.10 in, $0.30 out | $0.20 | $1.15 | Step 5 Preview, $1.00 in, $2.70 out |
| Thedrummer | 3 | Cydonia 24B V4.1, $0.30 in, $0.50 out | $0.40 | $0.50 | Skyfall 36B V2, $0.55 in, $0.80 out |
| Upstage | 3 | Solar Mini 4, $0.05 in, $0.20 out | $0.09 | $0.36 | Solar Pro 3, $0.15 in, $0.60 out |

## How the figures are worked out

Each price is the model maker's own price for its standard service, as OpenRouter lists it. A promotional discount on it counts, since it is what you pay today, and the regular price is noted under the model. Faster or priority tiers cost more and flex tiers less, and both are left out. Where the maker does not serve a model itself, such as most Llama models, the price is the cheapest regular price among the hosts that do, and that host is named under the model. Short-lived discounts from other hosts are left out. Medians are taken across paid models only. Cheapest and most expensive are ranked on a blended price that weights input three to one over output, a typical mix for agent workloads. Every model and its price is in the [full tracker](https://shurco.ai/tools/llm-api-pricing/).

## How to cite

Quote any figure with a link to this page and the date, for example shurco.ai LLM API pricing statistics, 12 October 2026. The figures change every morning, so the date matters.

## For AI agents and developers

The same figures are available as [JSON](https://shurco.ai/tools/llm-api-pricing/statistics/stats.json), and every model's price as [JSON](https://shurco.ai/tools/llm-api-pricing/prices.json). An agent can also call the MCP server at https://shurco.ai/mcp with no key, to look up a price, estimate a bill or find the cheapest model that fits.

## Common questions

### What does an LLM API cost in October 2026?

On 12 October 2026 the median of 338 paid models costs $0.45 per million input tokens and $1.60 per million output tokens. Prices run from $0.02 to $150.00 per million input tokens, so the model you choose matters far more than the average.

### What is the cheapest LLM API?

On 12 October 2026 the cheapest paid model on this list is Llama 3.1 8B Instruct from Meta, served by DeepInfra, at $0.02 per million input tokens and $0.04 per million output tokens.

### How much more do output tokens cost than input tokens?

On the median model, output tokens cost 4.0 times as much as input tokens. Workloads that write long answers are priced mostly by output, and workloads that read long documents mostly by input.

### Which LLM has the largest context window?

Grok 4.20 Multi-Agent from xAI lists 2M tokens, the largest on this list on 12 October 2026. 107 models accept one million tokens or more.

### How often are these statistics updated?

Every morning at about 06.00 UTC, from the same prices as the tracker on this site. The date on the page is the date of the prices.

## More free tools[Free toolAI automation ROI calculatorPut in the hours a task takes, what an hour costs and what the system would cost to build and run. It shows the hours returned to the team and how long the automation takes to pay for itself.](https://shurco.ai/tools/ai-automation-roi-calculator/)[Free toolFlow efficiency and cycle time calculatorTwo numbers that show where time really goes. Flow efficiency shows how much of an item's life is waiting, and Little's Law turns work in progress into the time a new item takes to get through.](https://shurco.ai/tools/flow-efficiency-calculator/)[Free toolWhat to automate first, a scoring toolList up to four tasks your team repeats every week. Answer five questions about each and the tool ranks them, says which to automate first and which to leave alone, and explains why.](https://shurco.ai/tools/what-to-automate-first/)

## Choosing a model for a production agent

Price is one input. Quality on your own cases, latency and the cost of retries decide the rest. [Tell me what you are building.](https://shurco.ai/#contact)

Web version https://shurco.ai/tools/llm-api-pricing/statistics/