---
title: "LLM API price index: providers' own prices analysed | BroadRouter"
description: "Median, cheapest and dearest LLM API prices for 424 models from 41 providers' own pricing pages. Free CSV and JSON, CC BY 4.0."
url: https://broadrouter.com/data/llm-api-price-index/
lang: en
updated: 2026-11-15
publisher: BroadRouter (a BroadNet site); API by BroadNet Inference, https://inference.broadnet.ai
---

# LLM API price index

Updated 2026-11-15

The median text model costs USD 0.658 per 1M tokens (3:1 input to output), across 424 models priced on 41 providers' own pages. The same model's dearest standard price is a median 1.3× its cheapest, and output tokens cost a median 4.0× as much as input. Data: CSV and JSON.

[Download CSV](https://broadrouter.com/data/llm-api-price-index.csv) [Download JSON](https://broadrouter.com/data/llm-api-price-index.json) [Croissant metadata](https://broadrouter.com/data/llm-api-price-index.croissant.json) Compilation CC BY 4.0 · prices credited to each provider · checked 2026-11-15

Every individual price behind this index, with its source URL, check date and quote, is in the [LLM API provider price database](https://broadrouter.com/data/llm-api-provider-prices/).

Source: 1,671 prices read from 41 providers' own pricing pages, each with a link and check date (the JSON lists every one). This is not BroadNet traffic data. BroadRouter is BroadNet's own site, and BroadNet's prices are not in the index.

## Key findings

1.  The median text model costs USD 0.658 per 1M tokens (3 input tokens per output token) across 424 models with a paid standard price, read from 41 providers' own pricing pages (checked 2026-11-14 to 2026-11-15); the middle half costs USD 0.263 to USD 2.85.
2.  Model price levels run from USD 0.0315 (Tev1 4B Experimental) to USD 67.50 (GPT-5.5 Pro) per 1M tokens, a 2,143-fold range.
3.  For the same model, the dearest standard price is a median 1.3× the cheapest, across 197 models with paid standard prices from two or more providers; 61 of them (31%) have a gap of 2× or more.
4.  The widest gap is Llama 3.1 8B Instruct: USD 0.025 at DeepInfra against USD 0.418 at Cloudflare Workers AI, 17× apart (blended, per 1M tokens).
5.  Where both exist, a third-party host undercuts the model's maker on 29 of 98 models; the maker is cheapest or tied on 69. The median cheapest host costs 1.0× the maker's price.
6.  DeepInfra is the cheapest provider for 49 of the 197 multi-provider models (28 without a tie).
7.  Batch prices are a median 50% below the same provider's standard price, across 156 batch prices from 9 providers.
8.  Output tokens cost a median 4.0× as much as input tokens; the most common ratio is 4.0×, used by 67 of 424 models (15.8%).
9.  65.3% of standard prices (791 of 1,212) include a cached-input price, at a median 88% off the normal input price. Only 25.9% state the numeric precision served.
10.  By context window, the median price level is lowest for up to 32K tokens (USD 0.245 per 1M, 20 models) and highest for 256K to under 1M tokens (USD 3.00, 36 models).

## How much does an LLM API cost per million tokens?

Each model's median blended standard price, grouped by the largest context window a provider states. 424 models with a paid standard price; models with no stated context are left out of this table.

| Context window | Models | Median input | Median output | Median blended | Cheapest | Dearest |
| --- | --- | --- | --- | --- | --- | --- |
| Up to 32K | 20 | USD 0.161 | USD 0.51 | USD 0.245 | USD 0.0425 | USD 3.78 |
| 32K to 128K | 53 | USD 0.19 | USD 0.6 | USD 0.28 | USD 0.0607 | USD 1.59 |
| 128K to 256K | 82 | USD 0.244 | USD 1.03 | USD 0.451 | USD 0.09 | USD 3.50 |
| 256K to under 1M | 36 | USD 2.00 | USD 6.00 | USD 3.00 | USD 0.23 | USD 20.00 |
| 1M and more | 56 | USD 0.75 | USD 2.83 | USD 1.36 | USD 0.0875 | USD 20.00 |

## How much do prices vary between providers for the same model?

197 models with paid standard prices from two or more providers. Blended price per 1M tokens, widest spread first.

| Model | Providers | Cheapest | Median | Dearest | Spread | Cheapest provider |
| --- | --- | --- | --- | --- | --- | --- |
| [Llama 3.1 8B Instruct](https://broadrouter.com/llm-api-pricing/llama-3.1-8b-instruct/) | 6 | USD 0.025 | USD 0.22 | USD 0.418 | 17× | DeepInfra |
| [Qwen-MT Plus](https://broadrouter.com/llm-api-pricing/qwen-mt-plus/) | 2 | USD 0.375 | USD 2.03 | USD 3.69 | 9.8× | Novita AI |
| [Llama 3.3 70B](https://broadrouter.com/llm-api-pricing/llama-3.3-70b-instruct/) | 14 | USD 0.155 | USD 0.71 | USD 1.23 | 7.9× | DeepInfra |
| [Mistral-Nemo-Instruct-2407](https://broadrouter.com/llm-api-pricing/mistral-nemo-instruct-2407/) | 2 | USD 0.0293 | USD 0.127 | USD 0.225 | 7.7× | DeepInfra |
| [Hy3](https://broadrouter.com/llm-api-pricing/hy3/) | 4 | USD 0.231 | USD 0.25 | USD 1.75 | 7.6× | SiliconFlow |
| [Llama 3 8B Stheno V3.2](https://broadrouter.com/llm-api-pricing/l3-8b-stheno-v3.2/) | 2 | USD 0.05 | USD 0.211 | USD 0.372 | 7.5× | Novita AI |
| [DeepSeek V4 Flash 0731](https://broadrouter.com/llm-api-pricing/deepseek-v4-flash-0731/) | 15 | USD 0.09 | USD 0.33 | USD 0.66 | 7.3× | DeepInfra, Hyperbolic |
| [DeepSeek R1 Distill Llama 70B](https://broadrouter.com/llm-api-pricing/deepseek-r1-distill-llama-70b/) | 2 | USD 0.375 | USD 1.54 | USD 2.70 | 7.2× | GMI Cloud |
| [OpenAI GPT OSS 120B](https://broadrouter.com/llm-api-pricing/gpt-oss-120b/) | 21 | USD 0.065 | USD 0.263 | USD 0.45 | 6.9× | CoreWeave Forge |
| [GPT OSS 20B](https://broadrouter.com/llm-api-pricing/gpt-oss-20b/) | 10 | USD 0.036 | USD 0.0775 | USD 0.225 | 6.3× | AkashML |
| [Mistral Medium 3](https://broadrouter.com/llm-api-pricing/mistral-medium-3/) | 2 | USD 0.8 | USD 2.78 | USD 4.76 | 6.0× | Google Vertex AI |
| [DeepSeek R1 Distill Qwen 7B](https://broadrouter.com/llm-api-pricing/deepseek-r1-distill-qwen-7b/) | 2 | USD 0.125 | USD 0.417 | USD 0.71 | 5.7× | GMI Cloud |
| [DeepSeek R1 Distill Qwen 32B](https://broadrouter.com/llm-api-pricing/deepseek-r1-distill-qwen-32b/) | 3 | USD 0.6 | USD 1.59 | USD 3.24 | 5.4× | GMI Cloud |
| [Gemma 3 12B](https://broadrouter.com/llm-api-pricing/gemma-3-12b-it/) | 4 | USD 0.075 | USD 0.107 | USD 0.398 | 5.3× | DeepInfra, Featherless |
| [Gemma 4 31B](https://broadrouter.com/llm-api-pricing/gemma-4-31b-it/) | 12 | USD 0.16 | USD 0.205 | USD 0.813 | 5.1× | CoreWeave Forge |
| [DeepSeek V3.1](https://broadrouter.com/llm-api-pricing/deepseek-chat-v3.1/) | 7 | USD 0.425 | USD 0.464 | USD 2.16 | 5.1× | DeepInfra |
| [GPT-5.6 Luna](https://broadrouter.com/llm-api-pricing/gpt-5.6-luna/) | 6 | USD 0.45 | USD 0.45 | USD 2.25 | 5.0× | OpenAI, DigitalOcean, Microsoft Azure, Perplexity |
| [NVIDIA Nemotron 3 Super 120B A12B](https://broadrouter.com/llm-api-pricing/nemotron-3-super-120b-a12b/) | 3 | USD 0.156 | USD 0.275 | USD 0.75 | 4.8× | DeepInfra |
| [Qwen3.8 27B](https://broadrouter.com/llm-api-pricing/qwen3.8-27b/) | 15 | USD 0.342 | USD 1.05 | USD 1.60 | 4.7× | Chutes |
| [MiMo v2.5](https://broadrouter.com/llm-api-pricing/mimo-v2.5/) | 4 | USD 0.175 | USD 0.205 | USD 0.8 | 4.6× | Baidu, Parasail |
| [DeepSeek V3](https://broadrouter.com/llm-api-pricing/deepseek-chat/) | 3 | USD 0.438 | USD 0.463 | USD 2.00 | 4.6× | SiliconFlow |
| [Llama 3 8B Instruct](https://broadrouter.com/llm-api-pricing/llama-3-8b-instruct/) | 3 | USD 0.0931 | USD 0.375 | USD 0.418 | 4.5× | Featherless |
| [DeepSeek V3.2](https://broadrouter.com/llm-api-pricing/deepseek-v3.2/) | 11 | USD 0.234 | USD 0.367 | USD 1.00 | 4.3× | GMI Cloud |
| [Qwen3 Coder 480B A35B](https://broadrouter.com/llm-api-pricing/qwen3-coder/) | 6 | USD 0.438 | USD 0.626 | USD 1.80 | 4.1× | SiliconFlow |
| [GLM 5.3](https://broadrouter.com/llm-api-pricing/glm-5.3/) | 24 | USD 1.05 | USD 2.15 | USD 4.30 | 4.1× | DeepInfra |
| [Llama 3.1 Instruct (70B)](https://broadrouter.com/llm-api-pricing/llama-3.1-70b-instruct/) | 3 | USD 0.72 | USD 0.783 | USD 2.88 | 4.0× | Amazon Bedrock |
| [DeepSeek V3 0324](https://broadrouter.com/llm-api-pricing/deepseek-chat-v3-0324/) | 3 | USD 0.502 | USD 0.695 | USD 2.00 | 4.0× | GMI Cloud |
| [DeepSeek V4.1 Flash 1017](https://broadrouter.com/llm-api-pricing/deepseek-v4.1-flash-1017/) | 16 | USD 0.147 | USD 0.525 | USD 0.525 | 3.6× | DeepInfra |
| [Qwen 2.5 7B](https://broadrouter.com/llm-api-pricing/qwen2.5-7b-instruct/) | 3 | USD 0.05 | USD 0.07 | USD 0.177 | 3.5× | SiliconFlow |
| [Mistral-Small-24B-Instruct-2501](https://broadrouter.com/llm-api-pricing/mistral-small-24b-instruct-2501/) | 2 | USD 0.0575 | USD 0.131 | USD 0.204 | 3.5× | DeepInfra |
| [DeepSeek R1 0528](https://broadrouter.com/llm-api-pricing/deepseek-r1-0528/) | 5 | USD 0.695 | USD 1.00 | USD 2.36 | 3.4× | Featherless |
| [Qwen3-8B](https://broadrouter.com/llm-api-pricing/qwen3-8b/) | 2 | USD 0.06 | USD 0.131 | USD 0.202 | 3.4× | SiliconFlow |
| [DeepSeek R1 Distill Qwen 14B](https://broadrouter.com/llm-api-pricing/deepseek-r1-distill-qwen-14b/) | 2 | USD 0.2 | USD 0.402 | USD 0.603 | 3.0× | GMI Cloud |
| [Qwen3 VL 235B A22B](https://broadrouter.com/llm-api-pricing/qwen3-vl-235b-a22b-instruct/) | 3 | USD 0.37 | USD 0.632 | USD 1.06 | 2.9× | DeepInfra |
| [Command R](https://broadrouter.com/llm-api-pricing/command-r/) | 2 | USD 0.263 | USD 0.506 | USD 0.75 | 2.9× | Cohere |
| [Qwen3.6 35B A3B](https://broadrouter.com/llm-api-pricing/qwen3.6-35b-a3b/) | 10 | USD 0.297 | USD 0.39 | USD 0.844 | 2.8× | CoreWeave Forge |
| [Llama 4 Scout 17B 16E Instruct](https://broadrouter.com/llm-api-pricing/llama-4-scout/) | 6 | USD 0.15 | USD 0.287 | USD 0.415 | 2.8× | DeepInfra |
| [GLM 5.2](https://broadrouter.com/llm-api-pricing/glm-5.2/) | 19 | USD 0.872 | USD 2.15 | USD 2.37 | 2.7× | DeepInfra |
| [Mistral Small 3.1 24B Instruct](https://broadrouter.com/llm-api-pricing/mistral-small-3.1-24b-instruct/) | 4 | USD 0.15 | USD 0.211 | USD 0.402 | 2.7× | Google Vertex AI |
| [Gemma 3 27B](https://broadrouter.com/llm-api-pricing/gemma-3-27b-it/) | 6 | USD 0.1 | USD 0.145 | USD 0.268 | 2.7× | DeepInfra |
| [DeepSeek R1](https://broadrouter.com/llm-api-pricing/deepseek-r1/) | 4 | USD 0.92 | USD 1.64 | USD 2.36 | 2.6× | GMI Cloud, SiliconFlow |
| [Kimi K2.6](https://broadrouter.com/llm-api-pricing/kimi-k2.6/) | 13 | USD 0.743 | USD 1.45 | USD 1.88 | 2.5× | Chutes |
| [Qwen3 235B A22B Instruct 2507 FP8](https://broadrouter.com/llm-api-pricing/qwen3-235b-a22b-2507/) | 5 | USD 0.153 | USD 0.3 | USD 0.385 | 2.5× | GMI Cloud |
| [DeepSeek V4 Pro](https://broadrouter.com/llm-api-pricing/deepseek-v4-pro/) | 11 | USD 1.20 | USD 2.06 | USD 3.00 | 2.5× | GMI Cloud |
| [GLM 5.3 Flash](https://broadrouter.com/llm-api-pricing/glm-5.3-flash/) | 20 | USD 0.119 | USD 0.237 | USD 0.297 | 2.5× | GMI Cloud |
| [DeepSeek V4.1 Flash](https://broadrouter.com/llm-api-pricing/deepseek-v4.1-flash/) | 16 | USD 0.21 | USD 0.525 | USD 0.525 | 2.5× | DeepInfra |
| [Phi-4](https://broadrouter.com/llm-api-pricing/phi-4/) | 3 | USD 0.0875 | USD 0.0875 | USD 0.219 | 2.5× | DeepInfra, Featherless |
| [Mistral Small 3.2 24B Instruct](https://broadrouter.com/llm-api-pricing/mistral-small-3.2-24b-instruct/) | 4 | USD 0.106 | USD 0.138 | USD 0.263 | 2.5× | DeepInfra |
| [DeepSeek V4 Flash](https://broadrouter.com/llm-api-pricing/deepseek-v4-flash/) | 8 | USD 0.113 | USD 0.174 | USD 0.27 | 2.4× | DeepInfra |
| [MiniMax M3](https://broadrouter.com/llm-api-pricing/minimax-m3/) | 10 | USD 0.412 | USD 0.525 | USD 0.963 | 2.3× | CoreWeave Forge |
| [Qwen3 Coder Next](https://broadrouter.com/llm-api-pricing/qwen3-coder-next/) | 3 | USD 0.29 | USD 0.407 | USD 0.675 | 2.3× | Parasail |
| [Llama 3.2 11B Vision Instruct](https://broadrouter.com/llm-api-pricing/llama-3.2-11b-vision-instruct/) | 3 | USD 0.16 | USD 0.206 | USD 0.371 | 2.3× | Amazon Bedrock |
| [NVIDIA Nemotron 3.5 Super VL](https://broadrouter.com/llm-api-pricing/nemotron-3.5-super-vl/) | 6 | USD 0.175 | USD 0.256 | USD 0.388 | 2.2× | Crusoe Cloud |
| [Llama 3.2 3B Instruct](https://broadrouter.com/llm-api-pricing/llama-3.2-3b-instruct/) | 4 | USD 0.122 | USD 0.136 | USD 0.263 | 2.2× | Featherless |
| [Qwen3 Coder 30B A3B](https://broadrouter.com/llm-api-pricing/qwen3-coder-30b-a3b-instruct/) | 3 | USD 0.122 | USD 0.206 | USD 0.263 | 2.1× | SiliconFlow |
| [Qwen3.8 2.4T A95B](https://broadrouter.com/llm-api-pricing/qwen3.8-2.4t-a95b/) | 6 | USD 1.75 | USD 3.00 | USD 3.75 | 2.1× | Featherless |
| [DeepSeek-V4-Flash-Vision-Exp](https://broadrouter.com/llm-api-pricing/deepseek-v4-flash-vision-exp/) | 3 | USD 0.323 | USD 0.66 | USD 0.66 | 2.0× | DeepInfra |
| [Qwen3 32B FP8](https://broadrouter.com/llm-api-pricing/qwen3-32b/) | 5 | USD 0.13 | USD 0.225 | USD 0.263 | 2.0× | DeepInfra |
| [Gemini 3.6 Flash](https://broadrouter.com/llm-api-pricing/gemini-3.6-flash/) | 3 | USD 1.50 | USD 1.50 | USD 3.00 | 2.0× | Google Gemini API, Google Vertex AI |
| [MiniMax M3.1 Flash](https://broadrouter.com/llm-api-pricing/minimax-m3.1-flash/) | 9 | USD 0.263 | USD 0.263 | USD 0.525 | 2.0× | MiniMax, DigitalOcean, Featherless, Fireworks AI, GMI Cloud, Parasail, Together AI |
| [Qwen3.7 Max](https://broadrouter.com/llm-api-pricing/qwen3.7-max/) | 5 | USD 1.88 | USD 3.75 | USD 3.75 | 2.0× | Novita AI |
| [Kimi K3](https://broadrouter.com/llm-api-pricing/kimi-k3/) | 18 | USD 3.76 | USD 6.00 | USD 7.50 | 2.0× | Chutes |
| [Qwen3 235B A22B FP8](https://broadrouter.com/llm-api-pricing/qwen3-235b-a22b/) | 2 | USD 0.4 | USD 0.598 | USD 0.796 | 2.0× | GMI Cloud |
| [Qwen3 VL 30B A3B Instruct](https://broadrouter.com/llm-api-pricing/qwen3-vl-30b-a3b-instruct/) | 4 | USD 0.237 | USD 0.294 | USD 0.468 | 2.0× | Featherless |
| [Qwen3.6 27B](https://broadrouter.com/llm-api-pricing/qwen3.6-27b/) | 7 | USD 0.688 | USD 1.04 | USD 1.35 | 2.0× | Chutes |
| [Qwen3.5 35B A3B](https://broadrouter.com/llm-api-pricing/qwen3.5-35b-a3b/) | 7 | USD 0.355 | USD 0.63 | USD 0.688 | 1.9× | DeepInfra |
| [Gemma 4 26B A4B](https://broadrouter.com/llm-api-pricing/gemma-4-26b-a4b-it/) | 11 | USD 0.138 | USD 0.198 | USD 0.263 | 1.9× | DeepInfra, Featherless |
| [DeepSeek V4 Pro 0813](https://broadrouter.com/llm-api-pricing/deepseek-v4-pro-0813/) | 15 | USD 1.30 | USD 1.98 | USD 2.48 | 1.9× | Chutes |
| [Mistral Large 3](https://broadrouter.com/llm-api-pricing/mistral-large-2512/) | 3 | USD 0.75 | USD 0.954 | USD 1.38 | 1.8× | Amazon Bedrock |
| [MiniMax M2.7](https://broadrouter.com/llm-api-pricing/minimax-m2.7/) | 3 | USD 0.367 | USD 0.525 | USD 0.656 | 1.8× | GMI Cloud |
| [Qwen3 30B A3B (fp8)](https://broadrouter.com/llm-api-pricing/qwen3-30b-a3b/) | 3 | USD 0.122 | USD 0.122 | USD 0.215 | 1.8× | Cloudflare Workers AI |
| [GLM 5.1](https://broadrouter.com/llm-api-pricing/glm-5.1/) | 12 | USD 1.40 | USD 2.15 | USD 2.37 | 1.7× | Chutes |
| [Qwen3.5 9B](https://broadrouter.com/llm-api-pricing/qwen3.5-9b/) | 4 | USD 0.113 | USD 0.151 | USD 0.19 | 1.7× | DeepInfra, SiliconFlow |
| [Llama 4 Maverick 17B 128E Instruct FP8](https://broadrouter.com/llm-api-pricing/llama-4-maverick/) | 7 | USD 0.388 | USD 0.438 | USD 0.649 | 1.7× | GMI Cloud |
| [GLM 5](https://broadrouter.com/llm-api-pricing/glm-5/) | 10 | USD 0.93 | USD 1.55 | USD 1.55 | 1.7× | GMI Cloud |
| [Llama 3 Instruct (70B)](https://broadrouter.com/llm-api-pricing/llama-3-70b-instruct/) | 2 | USD 2.86 | USD 3.78 | USD 4.70 | 1.6× | Amazon Bedrock |
| [Kimi K2.5](https://broadrouter.com/llm-api-pricing/kimi-k2.5/) | 8 | USD 0.9 | USD 1.20 | USD 1.45 | 1.6× | SiliconFlow |
| [Qwen2.5-72B-Instruct](https://broadrouter.com/llm-api-pricing/qwen2.5-72b-instruct/) | 3 | USD 0.37 | USD 0.378 | USD 0.59 | 1.6× | DeepInfra |
| [MiMo V2.6 Flash](https://broadrouter.com/llm-api-pricing/mimo-v2.6-flash/) | 5 | USD 0.14 | USD 0.175 | USD 0.219 | 1.6× | GMI Cloud |
| [Qwen3.5 122B A10B](https://broadrouter.com/llm-api-pricing/qwen3.5-122b-a10b/) | 4 | USD 0.715 | USD 1.10 | USD 1.10 | 1.5× | SiliconFlow |
| [Claude Sonnet 5](https://broadrouter.com/llm-api-pricing/claude-sonnet-5/) | 5 | USD 4.00 | USD 4.00 | USD 6.00 | 1.5× | Anthropic, DigitalOcean, Google Vertex AI |
| [NVIDIA Nemotron 3 Nano 30B A3B](https://broadrouter.com/llm-api-pricing/nemotron-3-nano-30b-a3b/) | 3 | USD 0.0875 | USD 0.105 | USD 0.131 | 1.5× | Novita AI |
| [GLM 4.7](https://broadrouter.com/llm-api-pricing/glm-4.7/) | 8 | USD 0.738 | USD 1.00 | USD 1.07 | 1.5× | DeepInfra |
| [Qwen3-30B-A3B-Instruct-2507](https://broadrouter.com/llm-api-pricing/qwen3-30b-a3b-instruct-2507/) | 2 | USD 0.142 | USD 0.174 | USD 0.206 | 1.4× | SiliconFlow |
| [Qwen3.5 27B](https://broadrouter.com/llm-api-pricing/qwen3.5-27b/) | 7 | USD 0.588 | USD 0.825 | USD 0.845 | 1.4× | Chutes |
| [Kimi K2.7 Code](https://broadrouter.com/llm-api-pricing/kimi-k2.7-code/) | 12 | USD 1.20 | USD 1.65 | USD 1.71 | 1.4× | CoreWeave Forge |
| [Llama 3.2 1B Instruct](https://broadrouter.com/llm-api-pricing/llama-3.2-1b-instruct/) | 3 | USD 0.0705 | USD 0.0705 | USD 0.1 | 1.4× | Cloudflare Workers AI, Featherless |
| [GPT-5.6 Sol](https://broadrouter.com/llm-api-pricing/gpt-5.6-sol/) | 6 | USD 8.00 | USD 8.00 | USD 11.25 | 1.4× | OpenAI, DigitalOcean, Microsoft Azure, Perplexity |
| [GLM 4.5 Air](https://broadrouter.com/llm-api-pricing/glm-4.5-air/) | 4 | USD 0.31 | USD 0.372 | USD 0.425 | 1.4× | Novita AI |
| [NVIDIA Nemotron 3 Ultra](https://broadrouter.com/llm-api-pricing/nemotron-3-ultra-550b-a55b/) | 9 | USD 0.912 | USD 1.05 | USD 1.25 | 1.4× | CoreWeave Forge |
| [MiMo V2.6 Pro](https://broadrouter.com/llm-api-pricing/mimo-v2.6-pro/) | 3 | USD 0.408 | USD 0.486 | USD 0.544 | 1.3× | GMI Cloud |
| [Qwen3.8 Flash](https://broadrouter.com/llm-api-pricing/qwen3.8-flash/) | 5 | USD 0.18 | USD 0.23 | USD 0.237 | 1.3× | DeepInfra |
| [GLM 4.6](https://broadrouter.com/llm-api-pricing/glm-4.6/) | 6 | USD 0.76 | USD 0.956 | USD 1.00 | 1.3× | Venice |
| [IBM Granite 4.2 8B](https://broadrouter.com/llm-api-pricing/granite-4.2-8b/) | 2 | USD 0.0825 | USD 0.095 | USD 0.107 | 1.3× | CoreWeave Forge |
| [GPT OSS Safeguard 20B](https://broadrouter.com/llm-api-pricing/gpt-oss-safeguard-20b/) | 3 | USD 0.102 | USD 0.131 | USD 0.131 | 1.3× | Amazon Bedrock |
| [Muse Glimmer 30B](https://broadrouter.com/llm-api-pricing/muse-glimmer-30b/) | 3 | USD 0.5 | USD 0.525 | USD 0.637 | 1.3× | Featherless |
| [Hy4](https://broadrouter.com/llm-api-pricing/hy4/) | 3 | USD 0.625 | USD 0.625 | USD 0.784 | 1.3× | GMI Cloud, Novita AI |
| [Gemma 3 4B](https://broadrouter.com/llm-api-pricing/gemma-3-4b-it/) | 3 | USD 0.05 | USD 0.0625 | USD 0.0625 | 1.3× | Amazon Bedrock |
| [GPT-5.6 Terra](https://broadrouter.com/llm-api-pricing/gpt-5.6-terra/) | 6 | USD 4.50 | USD 4.50 | USD 5.63 | 1.3× | OpenAI, DigitalOcean, Microsoft Azure, Perplexity |
| [Hy4 Preview](https://broadrouter.com/llm-api-pricing/hy4-preview/) | 6 | USD 1.25 | USD 1.25 | USD 1.56 | 1.3× | DeepInfra, GMI Cloud, Hyperbolic, Novita AI, SiliconFlow |
| [Muse Spark Open](https://broadrouter.com/llm-api-pricing/muse-spark-open/) | 4 | USD 2.00 | USD 2.00 | USD 2.50 | 1.3× | Baseten, Fireworks AI, Together AI |
| [Qwen3.7 Plus](https://broadrouter.com/llm-api-pricing/qwen3.7-plus/) | 2 | USD 0.56 | USD 0.63 | USD 0.7 | 1.3× | Together AI |
| [Qwen3.5 397B A17B](https://broadrouter.com/llm-api-pricing/qwen3.5-397b-a17b/) | 7 | USD 1.09 | USD 1.29 | USD 1.35 | 1.2× | Chutes, DeepInfra |
| [Ling 3.0 Flash VL](https://broadrouter.com/llm-api-pricing/ling-3.0-flash-vl/) | 2 | USD 0.09 | USD 0.101 | USD 0.111 | 1.2× | DeepInfra |
| [Qwen3-VL 8B](https://broadrouter.com/llm-api-pricing/qwen3-vl-8b-instruct/) | 2 | USD 0.305 | USD 0.34 | USD 0.375 | 1.2× | SiliconFlow |
| [Qwen3-14B](https://broadrouter.com/llm-api-pricing/qwen3-14b/) | 3 | USD 0.122 | USD 0.15 | USD 0.15 | 1.2× | SiliconFlow |
| [Qwen3.8 Max](https://broadrouter.com/llm-api-pricing/qwen3.8-max/) | 6 | USD 2.48 | USD 3.00 | USD 3.00 | 1.2× | DeepInfra |
| [Qwen3.8 Max (0902)](https://broadrouter.com/llm-api-pricing/qwen3.8-max-0902/) | 3 | USD 2.48 | USD 3.00 | USD 3.00 | 1.2× | GMI Cloud |
| [NVIDIA Nemotron 3.5 Lightning 30B A3B](https://broadrouter.com/llm-api-pricing/nemotron-3.5-lightning/) | 5 | USD 0.085 | USD 0.0875 | USD 0.102 | 1.2× | DeepInfra |
| [Qwen3 Next 80B A3B Instruct](https://broadrouter.com/llm-api-pricing/qwen3-next-80b-a3b-instruct/) | 5 | USD 0.343 | USD 0.381 | USD 0.412 | 1.2× | DeepInfra |
| [gemma-4-31B-it-turbo](https://broadrouter.com/llm-api-pricing/gemma-4-31b-it-turbo/) | 2 | USD 0.152 | USD 0.168 | USD 0.182 | 1.2× | DeepInfra |
| [Kimi K2 Thinking](https://broadrouter.com/llm-api-pricing/kimi-k2-thinking/) | 6 | USD 0.9 | USD 1.07 | USD 1.07 | 1.2× | GMI Cloud |
| [MiniMax M2.5](https://broadrouter.com/llm-api-pricing/minimax-m2.5/) | 6 | USD 0.44 | USD 0.525 | USD 0.525 | 1.2× | Venice |
| [Qwen3 Next 80B A3B Thinking](https://broadrouter.com/llm-api-pricing/qwen3-next-80b-a3b-thinking/) | 2 | USD 0.412 | USD 0.45 | USD 0.487 | 1.2× | Google Vertex AI |
| [L3.1-70B-Euryale-v2.2](https://broadrouter.com/llm-api-pricing/l3.1-70b-euryale-v2.2/) | 2 | USD 0.72 | USD 0.785 | USD 0.85 | 1.2× | Featherless |
| [DeepSeek R1 Distill Llama 8B](https://broadrouter.com/llm-api-pricing/deepseek-r1-distill-llama-8b/) | 2 | USD 0.203 | USD 0.216 | USD 0.23 | 1.1× | GMI Cloud |
| [Claude Fable 5](https://broadrouter.com/llm-api-pricing/claude-fable-5/) | 5 | USD 20.00 | USD 20.00 | USD 22.00 | 1.1× | Anthropic, DeepInfra, DigitalOcean, Google Vertex AI |
| [Claude Fable 5.1](https://broadrouter.com/llm-api-pricing/claude-fable-5.1/) | 4 | USD 20.00 | USD 20.00 | USD 22.00 | 1.1× | Anthropic, DigitalOcean, Google Vertex AI |
| [Claude Haiku 4.5](https://broadrouter.com/llm-api-pricing/claude-haiku-4.5/) | 5 | USD 2.00 | USD 2.00 | USD 2.20 | 1.1× | Anthropic, DeepInfra, DigitalOcean, Google Vertex AI |
| [Claude Opus 4.5](https://broadrouter.com/llm-api-pricing/claude-opus-4.5/) | 4 | USD 10.00 | USD 10.00 | USD 11.00 | 1.1× | Anthropic, DigitalOcean, Google Vertex AI |
| [Claude Opus 4.6](https://broadrouter.com/llm-api-pricing/claude-opus-4.6/) | 4 | USD 10.00 | USD 10.00 | USD 11.00 | 1.1× | Anthropic, DigitalOcean, Google Vertex AI |
| [Claude Opus 4.7](https://broadrouter.com/llm-api-pricing/claude-opus-4.7/) | 5 | USD 10.00 | USD 10.00 | USD 11.00 | 1.1× | Anthropic, DeepInfra, DigitalOcean, Google Vertex AI |
| [Claude Opus 4.8](https://broadrouter.com/llm-api-pricing/claude-opus-4.8/) | 5 | USD 10.00 | USD 10.00 | USD 11.00 | 1.1× | Anthropic, DeepInfra, DigitalOcean, Google Vertex AI |
| [Claude Opus 5](https://broadrouter.com/llm-api-pricing/claude-opus-5/) | 5 | USD 10.00 | USD 10.00 | USD 11.00 | 1.1× | Anthropic, DeepInfra, DigitalOcean, Google Vertex AI |
| [Claude Opus 5.5](https://broadrouter.com/llm-api-pricing/claude-opus-5.5/) | 6 | USD 8.00 | USD 8.00 | USD 8.80 | 1.1× | Anthropic, DeepInfra, DigitalOcean, Google Vertex AI, Perplexity |
| [Claude Sonnet 4.5](https://broadrouter.com/llm-api-pricing/claude-sonnet-4.5/) | 4 | USD 6.00 | USD 6.00 | USD 6.60 | 1.1× | Anthropic, DigitalOcean, Google Vertex AI |
| [Claude Sonnet 4.6](https://broadrouter.com/llm-api-pricing/claude-sonnet-4.6/) | 5 | USD 6.00 | USD 6.00 | USD 6.60 | 1.1× | Anthropic, DeepInfra, DigitalOcean, Google Vertex AI |
| [Claude Sonnet 5.5](https://broadrouter.com/llm-api-pricing/claude-sonnet-5.5/) | 6 | USD 4.00 | USD 4.00 | USD 4.40 | 1.1× | Anthropic, DeepInfra, DigitalOcean, Google Vertex AI, Perplexity |
| [GPT-5.4](https://broadrouter.com/llm-api-pricing/gpt-5.4/) | 4 | USD 5.63 | USD 5.63 | USD 6.19 | 1.1× | OpenAI, DigitalOcean, Microsoft Azure |
| [GPT-5.5](https://broadrouter.com/llm-api-pricing/gpt-5.5/) | 6 | USD 11.25 | USD 11.25 | USD 12.38 | 1.1× | OpenAI, DigitalOcean, GMI Cloud, Microsoft Azure, Perplexity |
| [GPT-6 Astra](https://broadrouter.com/llm-api-pricing/gpt-6-astra/) | 6 | USD 20.00 | USD 20.00 | USD 22.00 | 1.1× | OpenAI, DigitalOcean, GMI Cloud, Microsoft Azure, Perplexity |
| [GPT-6 Luna](https://broadrouter.com/llm-api-pricing/gpt-6-luna/) | 6 | USD 0.2 | USD 0.2 | USD 0.22 | 1.1× | OpenAI, DigitalOcean, GMI Cloud, Microsoft Azure, Perplexity |
| [GPT-6 Sol](https://broadrouter.com/llm-api-pricing/gpt-6-sol/) | 6 | USD 4.00 | USD 4.00 | USD 4.40 | 1.1× | OpenAI, DigitalOcean, GMI Cloud, Microsoft Azure, Perplexity |
| [GPT-6.1 Sol](https://broadrouter.com/llm-api-pricing/gpt-6.1-sol/) | 6 | USD 4.00 | USD 4.00 | USD 4.40 | 1.1× | OpenAI, DigitalOcean, GMI Cloud, Microsoft Azure, Perplexity |
| [GPT-6.1 Terra](https://broadrouter.com/llm-api-pricing/gpt-6.1-terra/) | 4 | USD 2.00 | USD 2.00 | USD 2.20 | 1.1× | OpenAI, DigitalOcean, Microsoft Azure |
| [Grok 4.6](https://broadrouter.com/llm-api-pricing/grok-4.6/) | 6 | USD 3.00 | USD 3.00 | USD 3.30 | 1.1× | xAI, GMI Cloud, Google Vertex AI, Microsoft Azure, Perplexity |
| [Grok 4.7](https://broadrouter.com/llm-api-pricing/grok-4.7/) | 6 | USD 3.00 | USD 3.00 | USD 3.30 | 1.1× | xAI, GMI Cloud, Google Vertex AI, Microsoft Azure, Perplexity |
| [Qwen2.5 Coder 32B Instruct](https://broadrouter.com/llm-api-pricing/qwen-2.5-coder-32b-instruct/) | 2 | USD 0.745 | USD 0.777 | USD 0.81 | 1.1× | Cloudflare Workers AI |
| [Qwen3 235B A22B Thinking 2507 FP8](https://broadrouter.com/llm-api-pricing/qwen3-235b-a22b-thinking-2507/) | 3 | USD 1.21 | USD 1.21 | USD 1.31 | 1.1× | Featherless, Venice |
| [MiniMax M2](https://broadrouter.com/llm-api-pricing/minimax-m2/) | 4 | USD 0.486 | USD 0.525 | USD 0.525 | 1.1× | Featherless |
| [Kimi K2 Instruct](https://broadrouter.com/llm-api-pricing/kimi-k2/) | 2 | USD 1.00 | USD 1.04 | USD 1.07 | 1.1× | Novita AI |
| [Inkling 2 Small](https://broadrouter.com/llm-api-pricing/inkling-2-small/) | 3 | USD 0.451 | USD 0.475 | USD 0.475 | 1.1× | DeepInfra |
| [Kimi K3.1 Pro](https://broadrouter.com/llm-api-pricing/kimi-k3.1-pro/) | 13 | USD 3.80 | USD 4.00 | USD 4.00 | 1.1× | DeepInfra |
| [GLM 4.7 Flash](https://broadrouter.com/llm-api-pricing/glm-4.7-flash/) | 6 | USD 0.145 | USD 0.152 | USD 0.152 | 1.1× | Cloudflare Workers AI |
| [DeepSeek-V3.1-Terminus](https://broadrouter.com/llm-api-pricing/deepseek-v3.1-terminus/) | 3 | USD 0.453 | USD 0.453 | USD 0.464 | 1.0× | GMI Cloud, SiliconFlow |
| [Beam 1.0 501B A23B](https://broadrouter.com/llm-api-pricing/beam-1.0-501b-a23b/) | 3 | USD 0.6 | USD 0.6 | USD 0.6 | 1.0× | Baseten, DigitalOcean, Together AI |
| [Claude Fable 5.2](https://broadrouter.com/llm-api-pricing/claude-fable-5.2/) | 4 | USD 16.00 | USD 16.00 | USD 16.00 | 1.0× | Anthropic, DigitalOcean, Google Vertex AI, Perplexity |
| [Claude Haiku 5.5](https://broadrouter.com/llm-api-pricing/claude-haiku-5.5/) | 4 | USD 0.2 | USD 0.2 | USD 0.2 | 1.0× | Anthropic, DigitalOcean, Google Vertex AI, Perplexity |
| [DeepSeek-V3.2-Exp](https://broadrouter.com/llm-api-pricing/deepseek-v3.2-exp/) | 2 | USD 0.305 | USD 0.305 | USD 0.305 | 1.0× | GMI Cloud, SiliconFlow |
| [Gemini 2.5 Flash](https://broadrouter.com/llm-api-pricing/gemini-2.5-flash/) | 3 | USD 0.85 | USD 0.85 | USD 0.85 | 1.0× | Google Gemini API, DeepInfra, Google Vertex AI |
| [Gemini 2.5 Flash-Lite](https://broadrouter.com/llm-api-pricing/gemini-2.5-flash-lite/) | 2 | USD 0.175 | USD 0.175 | USD 0.175 | 1.0× | Google Gemini API, Google Vertex AI |
| [Gemini 2.5 Pro](https://broadrouter.com/llm-api-pricing/gemini-2.5-pro/) | 3 | USD 3.44 | USD 3.44 | USD 3.44 | 1.0× | Google Gemini API, DeepInfra, Google Vertex AI |
| [Gemini 3.1 Flash-Lite (gemini-3.1-flash-lite)](https://broadrouter.com/llm-api-pricing/gemini-3.1-flash-lite/) | 3 | USD 0.563 | USD 0.563 | USD 0.563 | 1.0× | Google Gemini API, DeepInfra, Google Vertex AI |
| [Gemini 3.1 Pro Preview](https://broadrouter.com/llm-api-pricing/gemini-3.1-pro-preview/) | 3 | USD 4.50 | USD 4.50 | USD 4.50 | 1.0× | Google Gemini API, GMI Cloud, Google Vertex AI |
| [Gemini 3.5 Flash](https://broadrouter.com/llm-api-pricing/gemini-3.5-flash/) | 3 | USD 3.38 | USD 3.38 | USD 3.38 | 1.0× | DeepInfra, GMI Cloud, Google Vertex AI |
| [Gemini 3.5 Flash-Lite](https://broadrouter.com/llm-api-pricing/gemini-3.5-flash-lite/) | 3 | USD 0.85 | USD 0.85 | USD 0.85 | 1.0× | Google Gemini API, GMI Cloud, Google Vertex AI |
| [Gemini 3.7 Flash](https://broadrouter.com/llm-api-pricing/gemini-3.7-flash/) | 3 | USD 1.50 | USD 1.50 | USD 1.50 | 1.0× | DeepInfra, GMI Cloud, Google Vertex AI |
| [Gemini 3.8 Flash](https://broadrouter.com/llm-api-pricing/gemini-3.8-flash/) | 3 | USD 1.50 | USD 1.50 | USD 1.50 | 1.0× | Google Gemini API, GMI Cloud, Google Vertex AI |
| [Gemini 4 Argon](https://broadrouter.com/llm-api-pricing/gemini-4-argon/) | 4 | USD 4.00 | USD 4.00 | USD 4.00 | 1.0× | Google Gemini API, GMI Cloud, Google Vertex AI, Perplexity |
| [Gemini 4 Carbon](https://broadrouter.com/llm-api-pricing/gemini-4-carbon/) | 4 | USD 4.00 | USD 4.00 | USD 4.00 | 1.0× | Google Gemini API, GMI Cloud, Google Vertex AI, Perplexity |
| [Gemini 4 Hydrogen](https://broadrouter.com/llm-api-pricing/gemini-4-hydrogen/) | 3 | USD 3.00 | USD 3.00 | USD 3.00 | 1.0× | Google Gemini API, Google Vertex AI, Perplexity |
| [GLM 4.5V](https://broadrouter.com/llm-api-pricing/glm-4.5v/) | 2 | USD 0.9 | USD 0.9 | USD 0.9 | 1.0× | Z.ai, Novita AI |
| [GLM 4.6V](https://broadrouter.com/llm-api-pricing/glm-4.6v/) | 2 | USD 0.45 | USD 0.45 | USD 0.45 | 1.0× | Z.ai, Novita AI |
| [GLM 5.3 FlashX](https://broadrouter.com/llm-api-pricing/glm-5.3-flashx/) | 2 | USD 0.59 | USD 0.59 | USD 0.59 | 1.0× | Z.ai, Novita AI |
| [GLM-4.5-FP8](https://broadrouter.com/llm-api-pricing/glm-4.5/) | 2 | USD 1.00 | USD 1.00 | USD 1.00 | 1.0× | Z.ai, GMI Cloud |
| [GPT Chat Latest](https://broadrouter.com/llm-api-pricing/gpt-chat-latest/) | 2 | USD 11.25 | USD 11.25 | USD 11.25 | 1.0× | OpenAI, Microsoft Azure |
| [GPT-4.1 (2025-04-14)](https://broadrouter.com/llm-api-pricing/gpt-4.1/) | 3 | USD 3.50 | USD 3.50 | USD 3.50 | 1.0× | OpenAI, DigitalOcean, Microsoft Azure |
| [GPT-4.1 Mini](https://broadrouter.com/llm-api-pricing/gpt-4.1-mini/) | 2 | USD 0.7 | USD 0.7 | USD 0.7 | 1.0× | OpenAI, Microsoft Azure |
| [GPT-4o](https://broadrouter.com/llm-api-pricing/gpt-4o/) | 2 | USD 4.38 | USD 4.38 | USD 4.38 | 1.0× | OpenAI, DigitalOcean |
| [GPT-4o mini](https://broadrouter.com/llm-api-pricing/gpt-4o-mini/) | 3 | USD 0.263 | USD 0.263 | USD 0.263 | 1.0× | OpenAI, DigitalOcean, Microsoft Azure |
| [GPT-5 (2025-08-07)](https://broadrouter.com/llm-api-pricing/gpt-5/) | 3 | USD 3.44 | USD 3.44 | USD 3.44 | 1.0× | OpenAI, DigitalOcean, Microsoft Azure |
| [GPT-5 Mini](https://broadrouter.com/llm-api-pricing/gpt-5-mini/) | 3 | USD 0.688 | USD 0.688 | USD 0.688 | 1.0× | OpenAI, DigitalOcean, Microsoft Azure |
| [GPT-5 Nano](https://broadrouter.com/llm-api-pricing/gpt-5-nano/) | 3 | USD 0.138 | USD 0.138 | USD 0.138 | 1.0× | OpenAI, DigitalOcean, Microsoft Azure |
| [GPT-5 Pro](https://broadrouter.com/llm-api-pricing/gpt-5-pro/) | 2 | USD 41.25 | USD 41.25 | USD 41.25 | 1.0× | OpenAI, Microsoft Azure |
| [GPT-5.1](https://broadrouter.com/llm-api-pricing/gpt-5.1/) | 2 | USD 3.44 | USD 3.44 | USD 3.44 | 1.0× | OpenAI, Microsoft Azure |
| [GPT-5.2](https://broadrouter.com/llm-api-pricing/gpt-5.2/) | 3 | USD 4.81 | USD 4.81 | USD 4.81 | 1.0× | OpenAI, DigitalOcean, Microsoft Azure |
| [GPT-5.2 Pro](https://broadrouter.com/llm-api-pricing/gpt-5.2-pro/) | 2 | USD 57.75 | USD 57.75 | USD 57.75 | 1.0× | OpenAI, DigitalOcean |
| [GPT-5.3 Codex](https://broadrouter.com/llm-api-pricing/gpt-5.3-codex/) | 3 | USD 4.81 | USD 4.81 | USD 4.81 | 1.0× | OpenAI, DigitalOcean, Microsoft Azure |
| [GPT-5.4 Mini](https://broadrouter.com/llm-api-pricing/gpt-5.4-mini/) | 3 | USD 1.69 | USD 1.69 | USD 1.69 | 1.0× | OpenAI, DigitalOcean, Microsoft Azure |
| [GPT-5.4 Nano](https://broadrouter.com/llm-api-pricing/gpt-5.4-nano/) | 3 | USD 0.463 | USD 0.463 | USD 0.463 | 1.0× | OpenAI, DigitalOcean, Microsoft Azure |
| [GPT-5.4 Pro](https://broadrouter.com/llm-api-pricing/gpt-5.4-pro/) | 3 | USD 67.50 | USD 67.50 | USD 67.50 | 1.0× | OpenAI, DigitalOcean, Microsoft Azure |
| [Grok 4.20 (non-reasoning)](https://broadrouter.com/llm-api-pricing/grok-4.20-non-reasoning/) | 2 | USD 1.56 | USD 1.56 | USD 1.56 | 1.0× | xAI, Google Vertex AI |
| [Grok 4.20 (reasoning)](https://broadrouter.com/llm-api-pricing/grok-4.20/) | 3 | USD 1.56 | USD 1.56 | USD 1.56 | 1.0× | xAI, Google Vertex AI, Microsoft Azure |
| [Grok 4.3](https://broadrouter.com/llm-api-pricing/grok-4.3/) | 4 | USD 1.56 | USD 1.56 | USD 1.56 | 1.0× | xAI, Amazon Bedrock, Google Vertex AI, Microsoft Azure |
| [Grok 4.5](https://broadrouter.com/llm-api-pricing/grok-4.5/) | 3 | USD 3.00 | USD 3.00 | USD 3.00 | 1.0× | xAI, GMI Cloud, Perplexity |
| [Kimi K2 Instruct 0905](https://broadrouter.com/llm-api-pricing/kimi-k2-0905/) | 2 | USD 1.07 | USD 1.07 | USD 1.07 | 1.0× | Featherless, Novita AI |
| [Ling 3.0 Flash](https://broadrouter.com/llm-api-pricing/ling-3.0-flash/) | 2 | USD 0.09 | USD 0.09 | USD 0.09 | 1.0× | DeepInfra, Novita AI |
| [Minimax M2.1](https://broadrouter.com/llm-api-pricing/minimax-m2.1/) | 3 | USD 0.525 | USD 0.525 | USD 0.525 | 1.0× | Amazon Bedrock, Featherless, GMI Cloud |
| [Ministral 3 14B](https://broadrouter.com/llm-api-pricing/ministral-14b-2512/) | 3 | USD 0.2 | USD 0.2 | USD 0.2 | 1.0× | Mistral AI, Amazon Bedrock, DigitalOcean |
| [Ministral 3 3B](https://broadrouter.com/llm-api-pricing/ministral-3b-2512/) | 2 | USD 0.1 | USD 0.1 | USD 0.1 | 1.0× | Mistral AI, Amazon Bedrock |
| [Ministral 3 8B](https://broadrouter.com/llm-api-pricing/ministral-8b-2512/) | 2 | USD 0.15 | USD 0.15 | USD 0.15 | 1.0× | Mistral AI, Amazon Bedrock |
| [o3 (2025-04-16)](https://broadrouter.com/llm-api-pricing/o3/) | 3 | USD 3.50 | USD 3.50 | USD 3.50 | 1.0× | OpenAI, DigitalOcean, Microsoft Azure |
| [Qwen3.6 Plus](https://broadrouter.com/llm-api-pricing/qwen3.6-plus/) | 3 | USD 1.13 | USD 1.13 | USD 1.13 | 1.0× | Alibaba Cloud, GMI Cloud, Together AI |
| [Ripple-65B Preview](https://broadrouter.com/llm-api-pricing/ripple-65b-preview/) | 2 | USD 0.3 | USD 0.3 | USD 0.3 | 1.0× | GMI Cloud, Together AI |
| [Step 3.7 Flash](https://broadrouter.com/llm-api-pricing/step-3.7-flash/) | 3 | USD 0.438 | USD 0.438 | USD 0.438 | 1.0× | Featherless, GMI Cloud, Novita AI |
| [Step 5 Preview](https://broadrouter.com/llm-api-pricing/step-5-preview/) | 4 | USD 1.43 | USD 1.43 | USD 1.43 | 1.0× | Featherless, GMI Cloud, Hyperbolic, Novita AI |
| [Step-3.5-Flash](https://broadrouter.com/llm-api-pricing/step-3.5-flash/) | 2 | USD 0.15 | USD 0.15 | USD 0.15 | 1.0× | Featherless, SiliconFlow |

## Is a model cheaper from its maker or from a host?

98 models with a maker's own price and at least two providers. Host ÷ maker is the cheapest third-party blended price divided by the maker's; under 1× the host is cheaper.

| Model | Maker's price | Cheapest host | Host price | Host ÷ maker |
| --- | --- | --- | --- | --- |
| [Qwen-MT Plus](https://broadrouter.com/llm-api-pricing/qwen-mt-plus/) | USD 3.69 | Novita AI | USD 0.375 | 0.10× |
| [DeepSeek V4.1 Flash 1017](https://broadrouter.com/llm-api-pricing/deepseek-v4.1-flash-1017/) | USD 0.525 | DeepInfra | USD 0.147 | 0.28× |
| [Qwen3.8 27B](https://broadrouter.com/llm-api-pricing/qwen3.8-27b/) | USD 1.13 | Chutes | USD 0.342 | 0.30× |
| [Qwen3.6 35B A3B](https://broadrouter.com/llm-api-pricing/qwen3.6-35b-a3b/) | USD 0.844 | CoreWeave Forge | USD 0.297 | 0.35× |
| [GLM 5.2](https://broadrouter.com/llm-api-pricing/glm-5.2/) | USD 2.15 | DeepInfra | USD 0.872 | 0.41× |
| [Kimi K2.6](https://broadrouter.com/llm-api-pricing/kimi-k2.6/) | USD 1.71 | Chutes | USD 0.743 | 0.43× |
| [GLM 5.3](https://broadrouter.com/llm-api-pricing/glm-5.3/) | USD 2.15 | DeepInfra | USD 1.05 | 0.49× |
| [GLM 5.3 Flash](https://broadrouter.com/llm-api-pricing/glm-5.3-flash/) | USD 0.237 | GMI Cloud | USD 0.119 | 0.50× |
| [Qwen3.7 Max](https://broadrouter.com/llm-api-pricing/qwen3.7-max/) | USD 3.75 | Novita AI | USD 1.88 | 0.50× |
| [Qwen3.6 27B](https://broadrouter.com/llm-api-pricing/qwen3.6-27b/) | USD 1.35 | Chutes | USD 0.688 | 0.51× |
| [Qwen3.5 35B A3B](https://broadrouter.com/llm-api-pricing/qwen3.5-35b-a3b/) | USD 0.688 | DeepInfra | USD 0.355 | 0.52× |
| [Qwen3.8 2.4T A95B](https://broadrouter.com/llm-api-pricing/qwen3.8-2.4t-a95b/) | USD 3.00 | Featherless | USD 1.75 | 0.58× |
| [GLM 5](https://broadrouter.com/llm-api-pricing/glm-5/) | USD 1.55 | GMI Cloud | USD 0.93 | 0.60× |
| [Kimi K3](https://broadrouter.com/llm-api-pricing/kimi-k3/) | USD 6.00 | Chutes | USD 3.76 | 0.63× |
| [Qwen3.5 122B A10B](https://broadrouter.com/llm-api-pricing/qwen3.5-122b-a10b/) | USD 1.10 | SiliconFlow | USD 0.715 | 0.65× |
| [GLM 5.1](https://broadrouter.com/llm-api-pricing/glm-5.1/) | USD 2.15 | Chutes | USD 1.40 | 0.65× |
| [DeepSeek V4 Pro 0813](https://broadrouter.com/llm-api-pricing/deepseek-v4-pro-0813/) | USD 1.98 | Chutes | USD 1.30 | 0.66× |
| [Kimi K2.7 Code](https://broadrouter.com/llm-api-pricing/kimi-k2.7-code/) | USD 1.71 | CoreWeave Forge | USD 1.20 | 0.70× |
| [Qwen3.5 27B](https://broadrouter.com/llm-api-pricing/qwen3.5-27b/) | USD 0.825 | Chutes | USD 0.588 | 0.71× |
| [GLM 4.5 Air](https://broadrouter.com/llm-api-pricing/glm-4.5-air/) | USD 0.425 | Novita AI | USD 0.31 | 0.73× |
| [GLM 4.7](https://broadrouter.com/llm-api-pricing/glm-4.7/) | USD 1.00 | DeepInfra | USD 0.738 | 0.74× |
| [GLM 4.6](https://broadrouter.com/llm-api-pricing/glm-4.6/) | USD 1.00 | Venice | USD 0.76 | 0.76× |
| [Qwen3.8 Flash](https://broadrouter.com/llm-api-pricing/qwen3.8-flash/) | USD 0.23 | DeepInfra | USD 0.18 | 0.78× |
| [MiniMax M3](https://broadrouter.com/llm-api-pricing/minimax-m3/) | USD 0.525 | CoreWeave Forge | USD 0.412 | 0.79× |
| [Qwen3.7 Plus](https://broadrouter.com/llm-api-pricing/qwen3.7-plus/) | USD 0.7 | Together AI | USD 0.56 | 0.80× |
| [Qwen3.5 397B A17B](https://broadrouter.com/llm-api-pricing/qwen3.5-397b-a17b/) | USD 1.35 | Chutes | USD 1.09 | 0.81× |
| [Qwen3.8 Max](https://broadrouter.com/llm-api-pricing/qwen3.8-max/) | USD 3.00 | DeepInfra | USD 2.48 | 0.82× |
| [Qwen3.8 Max (0902)](https://broadrouter.com/llm-api-pricing/qwen3.8-max-0902/) | USD 3.00 | GMI Cloud | USD 2.48 | 0.82× |
| [Kimi K3.1 Pro](https://broadrouter.com/llm-api-pricing/kimi-k3.1-pro/) | USD 4.00 | DeepInfra | USD 3.80 | 0.95× |
| [Claude Fable 5](https://broadrouter.com/llm-api-pricing/claude-fable-5/) | USD 20.00 | DeepInfra | USD 20.00 | 1.00× |
| [Claude Fable 5.1](https://broadrouter.com/llm-api-pricing/claude-fable-5.1/) | USD 20.00 | DigitalOcean | USD 20.00 | 1.00× |
| [Claude Fable 5.2](https://broadrouter.com/llm-api-pricing/claude-fable-5.2/) | USD 16.00 | DigitalOcean | USD 16.00 | 1.00× |
| [Claude Haiku 4.5](https://broadrouter.com/llm-api-pricing/claude-haiku-4.5/) | USD 2.00 | DeepInfra | USD 2.00 | 1.00× |
| [Claude Haiku 5.5](https://broadrouter.com/llm-api-pricing/claude-haiku-5.5/) | USD 0.2 | DigitalOcean | USD 0.2 | 1.00× |
| [Claude Opus 4.5](https://broadrouter.com/llm-api-pricing/claude-opus-4.5/) | USD 10.00 | DigitalOcean | USD 10.00 | 1.00× |
| [Claude Opus 4.6](https://broadrouter.com/llm-api-pricing/claude-opus-4.6/) | USD 10.00 | DigitalOcean | USD 10.00 | 1.00× |
| [Claude Opus 4.7](https://broadrouter.com/llm-api-pricing/claude-opus-4.7/) | USD 10.00 | DeepInfra | USD 10.00 | 1.00× |
| [Claude Opus 4.8](https://broadrouter.com/llm-api-pricing/claude-opus-4.8/) | USD 10.00 | DeepInfra | USD 10.00 | 1.00× |
| [Claude Opus 5](https://broadrouter.com/llm-api-pricing/claude-opus-5/) | USD 10.00 | DeepInfra | USD 10.00 | 1.00× |
| [Claude Opus 5.5](https://broadrouter.com/llm-api-pricing/claude-opus-5.5/) | USD 8.00 | DeepInfra | USD 8.00 | 1.00× |
| [Claude Sonnet 4.5](https://broadrouter.com/llm-api-pricing/claude-sonnet-4.5/) | USD 6.00 | DigitalOcean | USD 6.00 | 1.00× |
| [Claude Sonnet 4.6](https://broadrouter.com/llm-api-pricing/claude-sonnet-4.6/) | USD 6.00 | DeepInfra | USD 6.00 | 1.00× |
| [Claude Sonnet 5](https://broadrouter.com/llm-api-pricing/claude-sonnet-5/) | USD 4.00 | DigitalOcean | USD 4.00 | 1.00× |
| [Claude Sonnet 5.5](https://broadrouter.com/llm-api-pricing/claude-sonnet-5.5/) | USD 4.00 | DeepInfra | USD 4.00 | 1.00× |
| [Gemini 2.5 Flash](https://broadrouter.com/llm-api-pricing/gemini-2.5-flash/) | USD 0.85 | DeepInfra | USD 0.85 | 1.00× |
| [Gemini 2.5 Flash-Lite](https://broadrouter.com/llm-api-pricing/gemini-2.5-flash-lite/) | USD 0.175 | Google Vertex AI | USD 0.175 | 1.00× |
| [Gemini 2.5 Pro](https://broadrouter.com/llm-api-pricing/gemini-2.5-pro/) | USD 3.44 | DeepInfra | USD 3.44 | 1.00× |
| [Gemini 3.1 Flash-Lite (gemini-3.1-flash-lite)](https://broadrouter.com/llm-api-pricing/gemini-3.1-flash-lite/) | USD 0.563 | DeepInfra | USD 0.563 | 1.00× |
| [Gemini 3.1 Pro Preview](https://broadrouter.com/llm-api-pricing/gemini-3.1-pro-preview/) | USD 4.50 | GMI Cloud | USD 4.50 | 1.00× |
| [Gemini 3.5 Flash-Lite](https://broadrouter.com/llm-api-pricing/gemini-3.5-flash-lite/) | USD 0.85 | GMI Cloud | USD 0.85 | 1.00× |
| [Gemini 3.6 Flash](https://broadrouter.com/llm-api-pricing/gemini-3.6-flash/) | USD 1.50 | Google Vertex AI | USD 1.50 | 1.00× |
| [Gemini 3.8 Flash](https://broadrouter.com/llm-api-pricing/gemini-3.8-flash/) | USD 1.50 | GMI Cloud | USD 1.50 | 1.00× |
| [Gemini 4 Argon](https://broadrouter.com/llm-api-pricing/gemini-4-argon/) | USD 4.00 | GMI Cloud | USD 4.00 | 1.00× |
| [Gemini 4 Carbon](https://broadrouter.com/llm-api-pricing/gemini-4-carbon/) | USD 4.00 | GMI Cloud | USD 4.00 | 1.00× |
| [Gemini 4 Hydrogen](https://broadrouter.com/llm-api-pricing/gemini-4-hydrogen/) | USD 3.00 | Google Vertex AI | USD 3.00 | 1.00× |
| [GLM 4.5V](https://broadrouter.com/llm-api-pricing/glm-4.5v/) | USD 0.9 | Novita AI | USD 0.9 | 1.00× |
| [GLM 4.6V](https://broadrouter.com/llm-api-pricing/glm-4.6v/) | USD 0.45 | Novita AI | USD 0.45 | 1.00× |
| [GLM 5.3 FlashX](https://broadrouter.com/llm-api-pricing/glm-5.3-flashx/) | USD 0.59 | Novita AI | USD 0.59 | 1.00× |
| [GLM-4.5-FP8](https://broadrouter.com/llm-api-pricing/glm-4.5/) | USD 1.00 | GMI Cloud | USD 1.00 | 1.00× |
| [GPT Chat Latest](https://broadrouter.com/llm-api-pricing/gpt-chat-latest/) | USD 11.25 | Microsoft Azure | USD 11.25 | 1.00× |
| [GPT-4.1 (2025-04-14)](https://broadrouter.com/llm-api-pricing/gpt-4.1/) | USD 3.50 | DigitalOcean | USD 3.50 | 1.00× |
| [GPT-4.1 Mini](https://broadrouter.com/llm-api-pricing/gpt-4.1-mini/) | USD 0.7 | Microsoft Azure | USD 0.7 | 1.00× |
| [GPT-4o](https://broadrouter.com/llm-api-pricing/gpt-4o/) | USD 4.38 | DigitalOcean | USD 4.38 | 1.00× |
| [GPT-4o mini](https://broadrouter.com/llm-api-pricing/gpt-4o-mini/) | USD 0.263 | DigitalOcean | USD 0.263 | 1.00× |
| [GPT-5 (2025-08-07)](https://broadrouter.com/llm-api-pricing/gpt-5/) | USD 3.44 | DigitalOcean | USD 3.44 | 1.00× |
| [GPT-5 Mini](https://broadrouter.com/llm-api-pricing/gpt-5-mini/) | USD 0.688 | DigitalOcean | USD 0.688 | 1.00× |
| [GPT-5 Nano](https://broadrouter.com/llm-api-pricing/gpt-5-nano/) | USD 0.138 | DigitalOcean | USD 0.138 | 1.00× |
| [GPT-5 Pro](https://broadrouter.com/llm-api-pricing/gpt-5-pro/) | USD 41.25 | Microsoft Azure | USD 41.25 | 1.00× |
| [GPT-5.1](https://broadrouter.com/llm-api-pricing/gpt-5.1/) | USD 3.44 | Microsoft Azure | USD 3.44 | 1.00× |
| [GPT-5.2](https://broadrouter.com/llm-api-pricing/gpt-5.2/) | USD 4.81 | DigitalOcean | USD 4.81 | 1.00× |
| [GPT-5.2 Pro](https://broadrouter.com/llm-api-pricing/gpt-5.2-pro/) | USD 57.75 | DigitalOcean | USD 57.75 | 1.00× |
| [GPT-5.3 Codex](https://broadrouter.com/llm-api-pricing/gpt-5.3-codex/) | USD 4.81 | DigitalOcean | USD 4.81 | 1.00× |
| [GPT-5.4](https://broadrouter.com/llm-api-pricing/gpt-5.4/) | USD 5.63 | DigitalOcean | USD 5.63 | 1.00× |
| [GPT-5.4 Mini](https://broadrouter.com/llm-api-pricing/gpt-5.4-mini/) | USD 1.69 | DigitalOcean | USD 1.69 | 1.00× |
| [GPT-5.4 Nano](https://broadrouter.com/llm-api-pricing/gpt-5.4-nano/) | USD 0.463 | DigitalOcean | USD 0.463 | 1.00× |
| [GPT-5.4 Pro](https://broadrouter.com/llm-api-pricing/gpt-5.4-pro/) | USD 67.50 | DigitalOcean | USD 67.50 | 1.00× |
| [GPT-5.5](https://broadrouter.com/llm-api-pricing/gpt-5.5/) | USD 11.25 | DigitalOcean | USD 11.25 | 1.00× |
| [GPT-5.6 Luna](https://broadrouter.com/llm-api-pricing/gpt-5.6-luna/) | USD 0.45 | DigitalOcean | USD 0.45 | 1.00× |
| [GPT-5.6 Sol](https://broadrouter.com/llm-api-pricing/gpt-5.6-sol/) | USD 8.00 | DigitalOcean | USD 8.00 | 1.00× |
| [GPT-5.6 Terra](https://broadrouter.com/llm-api-pricing/gpt-5.6-terra/) | USD 4.50 | DigitalOcean | USD 4.50 | 1.00× |
| [GPT-6 Astra](https://broadrouter.com/llm-api-pricing/gpt-6-astra/) | USD 20.00 | DigitalOcean | USD 20.00 | 1.00× |
| [GPT-6 Luna](https://broadrouter.com/llm-api-pricing/gpt-6-luna/) | USD 0.2 | DigitalOcean | USD 0.2 | 1.00× |
| [GPT-6 Sol](https://broadrouter.com/llm-api-pricing/gpt-6-sol/) | USD 4.00 | DigitalOcean | USD 4.00 | 1.00× |
| [GPT-6.1 Sol](https://broadrouter.com/llm-api-pricing/gpt-6.1-sol/) | USD 4.00 | DigitalOcean | USD 4.00 | 1.00× |
| [GPT-6.1 Terra](https://broadrouter.com/llm-api-pricing/gpt-6.1-terra/) | USD 2.00 | DigitalOcean | USD 2.00 | 1.00× |
| [Grok 4.20 (non-reasoning)](https://broadrouter.com/llm-api-pricing/grok-4.20-non-reasoning/) | USD 1.56 | Google Vertex AI | USD 1.56 | 1.00× |
| [Grok 4.20 (reasoning)](https://broadrouter.com/llm-api-pricing/grok-4.20/) | USD 1.56 | Google Vertex AI | USD 1.56 | 1.00× |
| [Grok 4.3](https://broadrouter.com/llm-api-pricing/grok-4.3/) | USD 1.56 | Amazon Bedrock | USD 1.56 | 1.00× |
| [Grok 4.5](https://broadrouter.com/llm-api-pricing/grok-4.5/) | USD 3.00 | GMI Cloud | USD 3.00 | 1.00× |
| [Grok 4.6](https://broadrouter.com/llm-api-pricing/grok-4.6/) | USD 3.00 | GMI Cloud | USD 3.00 | 1.00× |
| [Grok 4.7](https://broadrouter.com/llm-api-pricing/grok-4.7/) | USD 3.00 | GMI Cloud | USD 3.00 | 1.00× |
| [MiniMax M3.1 Flash](https://broadrouter.com/llm-api-pricing/minimax-m3.1-flash/) | USD 0.263 | DigitalOcean | USD 0.263 | 1.00× |
| [Ministral 3 14B](https://broadrouter.com/llm-api-pricing/ministral-14b-2512/) | USD 0.2 | Amazon Bedrock | USD 0.2 | 1.00× |
| [Ministral 3 3B](https://broadrouter.com/llm-api-pricing/ministral-3b-2512/) | USD 0.1 | Amazon Bedrock | USD 0.1 | 1.00× |
| [Ministral 3 8B](https://broadrouter.com/llm-api-pricing/ministral-8b-2512/) | USD 0.15 | Amazon Bedrock | USD 0.15 | 1.00× |
| [o3 (2025-04-16)](https://broadrouter.com/llm-api-pricing/o3/) | USD 3.50 | DigitalOcean | USD 3.50 | 1.00× |
| [Qwen3.6 Plus](https://broadrouter.com/llm-api-pricing/qwen3.6-plus/) | USD 1.13 | GMI Cloud | USD 1.13 | 1.00× |
| [Command R](https://broadrouter.com/llm-api-pricing/command-r/) | USD 0.263 | Amazon Bedrock | USD 0.75 | 2.86× |

## Which provider is cheapest most often?

Number of models, of the 197 with paid standard prices from two or more providers, where the provider has the lowest blended price. Ties count for every tied provider.

| Provider | Cheapest for | Without a tie | Models priced | Prices | With cached price |
| --- | --- | --- | --- | --- | --- |
| [DeepInfra](https://deepinfra.com/pricing) | 49 | 28 | 92 | 183 | 50% |
| [GMI Cloud](https://www.gmicloud.ai/en/models/maas) | 45 | 18 | 97 | 97 | 63.9% |
| [DigitalOcean](https://docs.digitalocean.com/products/inference/details/pricing/) | 41 | 0 | 59 | 95 | 94.9% |
| [Google Vertex AI](https://cloud.google.com/model-garden/pricing) | 36 | 3 | 63 | 118 | 79.4% |
| [Microsoft Azure](https://azure.microsoft.com/en-us/pricing/details/azure-openai/) | 29 | 0 | 97 | 124 | 60.8% |
| [OpenAI](https://developers.openai.com/api/docs/pricing) | 27 | 0 | 37 | 107 | 86.5% |
| [Featherless](https://featherless.ai/pricing) | 19 | 8 | 87 | 87 | 59.8% |
| [Perplexity](https://docs.perplexity.ai/docs/getting-started/pricing) | 18 | 0 | 24 | 24 | 100% |
| [SiliconFlow](https://www.siliconflow.com/pricing) | 17 | 11 | 56 | 56 | 48.2% |
| [Novita AI](https://novita.ai/pricing) | 15 | 6 | 67 | 68 | 65.2% |
| [Anthropic](https://platform.claude.com/docs/en/about-claude/pricing) | 15 | 0 | 18 | 41 | 100% |
| [Amazon Bedrock](https://aws.amazon.com/bedrock/pricing/) | 11 | 6 | 108 | 146 | 31.5% |

Widest coverage: Amazon Bedrock (108 models), Microsoft Azure (97 models), GMI Cloud (97 models), DeepInfra (92 models), Featherless (87 models). The full provider list is in the JSON download.

## How much do batch, flex and priority tiers change the price?

Each non-standard price compared with the same provider's standard price for the same model, blended. Under 1× is a discount.

| Tier | Prices | Providers | Median vs standard |
| --- | --- | --- | --- |
| Batch | 157 | 9 | 0.50× |
| Flex or spot | 117 | 8 | 0.54× |
| Priority | 106 | 9 | 1.75× |
| Fast | 70 | 15 | 2.00× |
| Ultrafast | 3 | 2 | 6.00× |

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

Median output price ÷ median input price, for the 424 models with a non-zero input price. Median 4.0×; middle half 3.0× to 5.0×.

| Output ÷ input | Models | Share |
| --- | --- | --- |
| 1× or less | 17 | 4% |
| Over 1× to 2× | 44 | 10.4% |
| Over 2× to 3× | 70 | 16.5% |
| Over 3× to 4× | 117 | 27.6% |
| Over 4× to 5× | 87 | 20.5% |
| Over 5× to 8× | 74 | 17.5% |
| Over 8× | 15 | 3.5% |

## How many providers publish a cached-input price?

65.3% of standard prices (791 of 1,212) include a price for cached input tokens. Where they do, the median cached price is 88% below the normal input price. A published cache price does not tell you the hit rate you will get; see [cached input tokens](https://broadrouter.com/glossary/cached-input-tokens/).

## Method

-   Source: each provider's own pricing page or price documentation, read with AI assistance and a page renderer between 2026-11-14 and 2026-11-15. Every price is stored with its source URL, the date checked and a verbatim quote from the page (src/data/own-prices/ in the site's code). No router, reseller or aggregator feed is used, not even as a cross-check.
-   Scope: 41 providers (16 of them model makers selling their own API), 1671 prices for 428 text and chat models. Image, audio and embedding models are out of scope. BroadNet Inference, which publishes this site, is not in the index.
-   Prices are USD per 1M tokens: the standard on-demand price at the lowest prompt-size tier in the provider's default region, as the page shows it. A provider's page that calls a price promotional or discounted is kept as published and counted (49 standard prices). DeepSeek bills peak and off-peak rates; the index uses its peak price.
-   Service tiers: batch, flex or spot, priority, fast and ultrafast prices are stored as separate rows (453 in all) and kept out of every per-model statistic; the service-tier table compares each with the same provider's standard price. Free rows (0 input and 0 output, 6) are also left out of price statistics.
-   Blended price = (3 × input + 1 × output) ÷ 4, a common 3:1 input-to-output mix. A model's price level is the median blended price across its paid standard prices.
-   Spread = the dearest paid standard price's blended price ÷ the cheapest's, per model, over the 197 models with paid standard prices from 2 or more providers.
-   Cheapest provider: the provider(s) with the lowest blended standard price for a model, counted over the same 197 models. Ties credit every tied provider.
-   Maker versus host: a maker's own price is a row from the model's maker selling it on its own API (for example DeepSeek on DeepSeek's API, not DeepSeek on Alibaba Cloud). Host ÷ maker compares the cheapest third-party standard price with the maker's, on the blend.
-   Cached input: a standard price that includes a cache-read price. Context tiers use the largest context any provider states for the model; models with no stated context are left out of that table.

**Update frequency:** recomputed on every site build from the committed provider price files. A weekly job re-fetches every source page and flags prices or quotes it no longer finds; flagged pages are re-read before any value changes. This version: checks from 2026-11-14 to 2026-11-15.

**Limits:** published list prices, not what any customer paid; no latency, throughput or uptime weighting; one region and the lowest prompt-size tier per provider; providers that publish no token price are absent. Code: `src/lib/dataset-prices.ts`.

## What do the CSV columns mean?

| Column | Meaning |
| --- | --- |
| `model` | Model slug, as in the /llm-api-pricing/<model>/ page address. |
| `name` | Model name. |
| `maker` | Model maker. |
| `context` | Largest context window any provider states, tokens; empty if none states it. |
| `context_tier` | Context bucket used in the tier table. |
| `providers` | Providers with a standard-tier price (free rows included). |
| `standard_prices` | Paid standard-tier prices used in the statistics. |
| `median_input_per_m` | Median input price across standard prices, USD per 1M tokens. |
| `median_output_per_m` | Median output price across standard prices, USD per 1M tokens. |
| `output_input_ratio` | median\_output ÷ median\_input; empty if input is free. |
| `min_blended` | Lowest blended standard price. |
| `median_blended` | Median blended standard price. |
| `max_blended` | Highest blended standard price. |
| `spread` | max\_blended ÷ min\_blended. |
| `cheapest_providers` | Provider(s) at min\_blended, separated by "; ". |
| `priciest_providers` | Provider(s) at max\_blended. |
| `maker_input_per_m` | Maker's own API input price; empty if the maker sells none. |
| `maker_output_per_m` | Maker's own API output price. |
| `maker_blended` | Maker's own blended price. |
| `cheapest_host` | Cheapest third-party (non-maker) standard price, provider name. |
| `host_vs_maker` | Cheapest host blended ÷ maker blended; under 1 means a host is cheaper. |

The JSON adds every individual price (provider, tier, input, cached, output, context, precision, promo and free flags, source URL and check date) and the provider table. For the same rows with quotes, notes and provider model IDs as a flat CSV, use the [provider price database](https://broadrouter.com/data/llm-api-provider-prices/).

## How to cite this dataset

Our compilation (the selection, statistics, rankings, tables and method): [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/). Free to use, share and adapt with attribution and a link to this page.

Each price is a fact published by the provider named in its row, at the source URL given per row; we do not license those pages to you. Credit the provider as the source of each price.

**Plain text**

```
BroadRouter (2026). LLM API price index: prices from providers' own pages, by model, provider and context length (version 2026-11-15) [Data set]. BroadNet Technologies. https://broadrouter.com/data/llm-api-price-index/
```

**BibTeX**

```
@misc{broadrouter_llm_price_index,
  author       = {BroadRouter},
  title        = {LLM API price index: prices from providers' own pages, by model, provider and context length},
  year         = {2026},
  version      = {2026-11-15},
  publisher    = {BroadNet Technologies},
  howpublished = {\url{https://broadrouter.com/data/llm-api-price-index/}},
  note         = {Data set, data as of 2026-11-15},
}
```

## Questions

### What is the average price of an LLM API per million tokens?

The median model costs USD 0.658 per 1M tokens with input and output mixed 3 to 1, across 424 models priced on 41 providers' own pages. Half of models fall between USD 0.263 and USD 2.85.

### Why does the same model have different prices?

Providers run the same open-weight model on different hardware, regions, precision and service tiers, and set their own prices. Across 197 models with two or more providers, the median gap between the cheapest and dearest standard price is 1.3×.

### Is it cheaper to buy a model from its maker or from a host?

More often from the maker: a third-party host is cheaper than the maker's own API on 29 of 98 models where both publish a price, and the median cheapest host costs 1.0× the maker's price. Each model page shows the gap for that model.

### Where do the prices come from?

From each provider's own pricing page, read with AI assistance and a page renderer, with the source URL, check date and a verbatim quote stored for every price. No router, reseller or aggregator feed is used. BroadNet Inference, which publishes this site, is not in the index; its prices are on the [pricing page](https://broadrouter.com/pricing/).

### How often is the index updated?

When the provider price files change. A weekly job re-fetches every source page and flags any price or quote it can no longer find, for re-reading; the page, CSV, JSON and key findings are then recomputed, and each price keeps its own check date.

### Can I use this data?

Yes. Our compilation (the selection, statistics, rankings, tables and method) is CC BY 4.0; cite it as shown under "How to cite". Each price is a fact published by the provider named in its row, at the source URL given; credit that provider as the source of the price.

Try it on your real workload. New accounts start with $5 of credit for Gemma and transcription. DeepSeek, GLM and Qwen3.8 need a top-up.

[Get started](https://inference.broadnet.ai/account/?utm_source=broadrouter&utm_medium=referral&utm_campaign=data-llm-api-price-index&utm_content=page-cta) ·

**Sources**

-   [DeepInfra: pricing (checked 2026-11-14)](https://deepinfra.com/pricing)
-   [GMI Cloud: pricing (checked 2026-11-15)](https://www.gmicloud.ai/en/models/maas)
-   [DigitalOcean: pricing (checked 2026-11-14)](https://docs.digitalocean.com/products/inference/details/pricing/)
-   [Google Vertex AI: pricing (checked 2026-11-14)](https://cloud.google.com/model-garden/pricing)
-   [Microsoft Azure: pricing (checked 2026-11-14)](https://azure.microsoft.com/en-us/pricing/details/azure-openai/)
-   [OpenAI: pricing (checked 2026-11-14)](https://developers.openai.com/api/docs/pricing)
-   [Featherless: pricing (checked 2026-11-15)](https://featherless.ai/pricing)
-   [Perplexity: pricing (checked 2026-11-15)](https://docs.perplexity.ai/docs/getting-started/pricing)
-   [SiliconFlow: pricing (checked 2026-11-14)](https://www.siliconflow.com/pricing)
-   [Novita AI: pricing (checked 2026-11-14)](https://novita.ai/pricing)
-   [Anthropic: pricing (checked 2026-11-14)](https://platform.claude.com/docs/en/about-claude/pricing)
-   [Amazon Bedrock: pricing (checked 2026-11-14)](https://aws.amazon.com/bedrock/pricing/)
-   [Google Gemini API: pricing (checked 2026-11-14)](https://aistudio.google.com/docs/pricing)
-   [Chutes: pricing (checked 2026-11-15)](https://chutes.ai/pricing)
-   [CoreWeave Forge: pricing (checked 2026-11-15)](https://coreweave.com/forge-pricing/inference-agents)
-   [Together AI: pricing (checked 2026-11-14)](https://www.together.ai/pricing)
-   [xAI: pricing (checked 2026-11-14)](https://docs.x.ai/developers/pricing)
-   [Cloudflare Workers AI: pricing (checked 2026-11-14)](https://developers.cloudflare.com/workers-ai/platform/pricing/)
-   [Z.ai: pricing (checked 2026-11-14)](https://docs.z.ai/guides/overview/pricing)
-   [Venice: pricing (checked 2026-11-15)](https://docs.venice.ai/pricing)
-   [Parasail: pricing (checked 2026-11-14)](https://www.parasail.io/pricing)
-   [Hyperbolic: pricing (checked 2026-11-14)](https://www.hyperbolic.ai/inference)
-   [Mistral AI: pricing (checked 2026-11-14)](https://docs.mistral.ai/inference/pricing)
-   [Fireworks AI: pricing (checked 2026-11-14)](https://fireworks.ai/pricing)
-   [Baseten: pricing (checked 2026-11-14)](https://www.baseten.co/pricing/)
-   [Alibaba Cloud: pricing (checked 2026-11-14)](https://www.alibabacloud.com/help/en/model-studio/model-pricing)
-   [Baidu: pricing (checked 2026-11-15)](https://intl.cloud.baidu.com/en/doc/qianfan/s/Jm8r1826a-intl-en)
-   [Crusoe Cloud: pricing (checked 2026-11-15)](https://www.crusoe.ai/cloud/pricing#Serverless-Inference)
-   [AkashML: pricing (checked 2026-11-15)](https://akashml.com/#pricing)
-   [Cohere: pricing (checked 2026-11-14)](https://cohere.com/pricing)
-   [MiniMax: pricing (checked 2026-11-14)](https://platform.minimax.io/docs/pricing/overview)
-   [IBM watsonx.ai: pricing (checked 2026-11-15)](https://www.ibm.com/products/watsonx-ai/pricing)
-   [Amazon (Bedrock): pricing (checked 2026-11-14)](https://aws.amazon.com/bedrock/pricing/)
-   [FriendliAI: pricing (checked 2026-11-15)](https://friendli.ai/pricing)
-   [SambaNova: pricing (checked 2026-11-14)](https://cloud.sambanova.ai/plans/pricing)
-   [Groq: pricing (checked 2026-11-14)](https://console.groq.com/docs/models)
-   [Moonshot AI: pricing (checked 2026-11-14)](https://platform.kimi.ai/docs/pricing/chat)
-   [Nscale: pricing (checked 2026-11-15)](https://docs.nscale.com/docs/ai-services/models)
-   [AI21 Labs: pricing (checked 2026-11-15)](https://www.ai21.com/pricing/)
-   [Cerebras: pricing (checked 2026-11-14)](https://www.cerebras.ai/pricing)
-   [DeepSeek: pricing (checked 2026-11-14)](https://api-docs.deepseek.com/quick_start/pricing)
