---
title: "Baidu API pricing per token: 14 models | BroadRouter"
description: "Baidu API pricing per 1M tokens for 14 models, from USD 0.14 input, with cached and fast rates, cheapest-host checks and maker price comparison."
url: https://broadrouter.com/llm-api-pricing/providers/baidu/
lang: en
updated: 2026-11-15
publisher: BroadRouter (a BroadNet site); API by BroadNet Inference, https://inference.broadnet.ai
---

# Baidu API pricing

Updated 2026-11-15

Baidu lists standard per-token prices on its own pricing page for 14 models. The cheapest is DeepSeek V4 Flash at USD 0.14 input and USD 0.28 output per 1M tokens; the dearest is GLM 5.2 at USD 1.40 / USD 4.40. It publishes cached-input prices for 13 of them, plus fast prices. Checked 2026-11-15.

Baidu is a model maker: 3 of the 14 models here are its own. By maker: DeepSeek 6, Baidu 3, Z.ai 3, Moonshot AI 1, Xiaomi 1. 15 prices, each read from [Baidu's own pricing page](https://intl.cloud.baidu.com/en/doc/qianfan/s/Jm8r1826a-intl-en), checked 2026-11-15. BroadRouter is BroadNet's own site and does not sell Baidu's services. Automated re-check 2026-11-16: 15 of 15 prices still matched the provider's page.

Models with a standard price

14

Median input / output

USD 0.755 / USD 2.865

Cached-input prices

13 of 14

Cheapest host for

1 of 11 shared models

## Which models is Baidu the cheapest provider for?

Of the 11 models that Baidu and at least one other provider both price at the standard tier, Baidu has the lowest price for 1, ranked on a blend of 3 input tokens to 1 output token (a tie with another provider at the same price; the maker's own API is listed first on a tie). It is the dearest for 2. Another 3 models have a standard price from Baidu only.

Models where Baidu is the cheapest provider
| Model | Baidu input / output | Next cheapest | Saving on 3:1 blend | Providers |
| --- | --- | --- | --- | --- |
| [MiMo v2.5](https://broadrouter.com/llm-api-pricing/mimo-v2.5/) | USD 0.14 / USD 0.28 | Parasail USD 0.14 / USD 0.28 | tie | 4 |

## How does Baidu price the most widely hosted models?

The 6 models Baidu sells that the most other providers also sell, with Baidu's rank among them on the 3:1 blend.

Baidu on the most widely hosted models
| Model | Baidu | Rank | Cheapest |
| --- | --- | --- | --- |
| [GLM 5.2](https://broadrouter.com/llm-api-pricing/glm-5.2/) | USD 1.40 / USD 4.40 | 5 of 19 | DeepInfra USD 0.5625 / USD 1.80 |
| [DeepSeek V4.1 Flash 1017](https://broadrouter.com/llm-api-pricing/deepseek-v4.1-flash-1017/) | USD 0.28 / USD 1.13 | 4 of 16 | DeepInfra USD 0.098 / USD 0.294 |
| [DeepSeek V4 Pro 0813](https://broadrouter.com/llm-api-pricing/deepseek-v4-pro-0813/) | USD 1.32 / USD 3.96 | 5 of 15 | Chutes USD 0.85 / USD 2.65 |
| [DeepSeek V4 Flash 0731](https://broadrouter.com/llm-api-pricing/deepseek-v4-flash-0731/) | USD 0.44 / USD 1.32 | 10 of 15 | DeepInfra USD 0.06 / USD 0.18 |
| [Kimi K2.6](https://broadrouter.com/llm-api-pricing/kimi-k2.6/) | USD 0.95 / USD 4 | 9 of 13 | Chutes USD 0.39 / USD 1.80 |
| [GLM 5.1](https://broadrouter.com/llm-api-pricing/glm-5.1/) | USD 1.40 / USD 4.40 | 5 of 12 | Chutes USD 0.90 / USD 2.90 |

## Which model makers does Baidu sell?

Baidu prices models from 5 makers. DeepSeek leads with 6 models. Standard prices, USD per 1M input / output tokens.

Baidu models by maker
| Maker | Models | Cheapest model | Median input / output |
| --- | --- | --- | --- |
| DeepSeek | 6 | DeepSeek V4 Flash USD 0.14 / USD 0.28 | USD 0.36 / USD 1.225 |
| Baidu | 3 | ERNIE-5.5-Flash-Preview USD 0.28 / USD 1.13 | USD 0.56 / USD 2.53 |
| Z.ai | 3 | GLM 5 USD 1 / USD 3.20 | USD 1.40 / USD 4.40 |
| Moonshot AI | 1 | Kimi K2.6 USD 0.95 / USD 4 | — |
| Xiaomi | 1 | MiMo v2.5 USD 0.14 / USD 0.28 | — |

## Baidu price list

USD per 1M tokens: 15 prices for 14 models, one row per model with any other service tiers stacked under the standard price. Sources checked 2026-11-15 unless a row says otherwise. "vs maker" compares a standard price with the model maker's own API on the 3:1 blend; a minus means Baidu is cheaper. Of 7 hosted model prices with a maker price to compare, 1 is below the maker's and 1 above.

Baidu API prices by model
| Model | Tier | Input | Cached | Output | Context | vs maker | Source |
| --- | --- | --- | --- | --- | --- | --- | --- |
| [DeepSeek V3.2](https://broadrouter.com/llm-api-pricing/deepseek-v3.2/) | standard | USD 0.28 | USD 0.028 | USD 0.42 | 131,072 | — | [source](https://intl.cloud.baidu.com/en/doc/qianfan/s/Jm8r1826a-intl-en) |
| [DeepSeek V4 Flash](https://broadrouter.com/llm-api-pricing/deepseek-v4-flash/) | standard | USD 0.14 | USD 0.028 | USD 0.28 | 1,048,576 | — | [source](https://intl.cloud.baidu.com/en/doc/qianfan/s/Jm8r1826a-intl-en) |
| [DeepSeek V4 Flash 0731](https://broadrouter.com/llm-api-pricing/deepseek-v4-flash-0731/) | standard | USD 0.44 | USD 0.044 | USD 1.32 | 1,048,576 | — | [source](https://intl.cloud.baidu.com/en/doc/qianfan/s/Jm8r1826a-intl-en) |
| [DeepSeek V4 Pro](https://broadrouter.com/llm-api-pricing/deepseek-v4-pro/) | standard | USD 1.69 | USD 0.14 | USD 3.38 | 1,048,576 | +7% | [source](https://intl.cloud.baidu.com/en/doc/qianfan/s/Jm8r1826a-intl-en) |
| [DeepSeek V4 Pro 0813](https://broadrouter.com/llm-api-pricing/deepseek-v4-pro-0813/) | standard | USD 1.32 | USD 0.132 | USD 3.96 | 1,048,576 | same | [source](https://intl.cloud.baidu.com/en/doc/qianfan/s/Jm8r1826a-intl-en) |
| [DeepSeek V4.1 Flash 1017](https://broadrouter.com/llm-api-pricing/deepseek-v4.1-flash-1017/) | standard | USD 0.28 | USD 0.006 | USD 1.13 | 1,048,576 | −6% | [source](https://intl.cloud.baidu.com/en/doc/qianfan/s/Jm8r1826a-intl-en) |
| [ERNIE 5.1](https://broadrouter.com/llm-api-pricing/ernie-5.1/) | standard | USD 0.56 | — | USD 2.53 | not stated | own model | [source](https://intl.cloud.baidu.com/en/doc/qianfan/s/Jm8r1826a-intl-en) |
| [ERNIE-5.5-Flash-Preview](https://broadrouter.com/llm-api-pricing/ernie-5.5-flash-preview/) | standard | USD 0.28 | USD 0.028 | USD 1.13 | 1,048,576 | own model | [source](https://intl.cloud.baidu.com/en/doc/qianfan/s/Jm8r1826a-intl-en) |
| [ERNIE-Light-DT-1.0](https://broadrouter.com/llm-api-pricing/ernie-light-dt-1.0-intl/) | standard | USD 1.13 | USD 0.113 | USD 3.94 | 1,048,576 | own model | [source](https://intl.cloud.baidu.com/en/doc/qianfan/s/Jm8r1826a-intl-en) |
| [GLM 5](https://broadrouter.com/llm-api-pricing/glm-5/) | standard | USD 1 | USD 0.20 | USD 3.20 | 198,000 | same | [source](https://intl.cloud.baidu.com/en/doc/qianfan/s/Jm8r1826a-intl-en) |
| [GLM 5.1](https://broadrouter.com/llm-api-pricing/glm-5.1/) | standard | USD 1.40 | USD 0.26 | USD 4.40 | 198,000 | same | [source](https://intl.cloud.baidu.com/en/doc/qianfan/s/Jm8r1826a-intl-en) |
| [GLM 5.2](https://broadrouter.com/llm-api-pricing/glm-5.2/) | standard · fast | USD 1.40 · USD 2.25 | USD 0.26 · USD 0.56 | USD 4.40 · USD 7.88 | 500,000 / 1,048,576 | same | [source](https://intl.cloud.baidu.com/en/doc/qianfan/s/Jm8r1826a-intl-en) |
| [Kimi K2.6](https://broadrouter.com/llm-api-pricing/kimi-k2.6/) | standard | USD 0.95 | USD 0.16 | USD 4 | 262,144 | same | [source](https://intl.cloud.baidu.com/en/doc/qianfan/s/Jm8r1826a-intl-en) |
| [MiMo v2.5](https://broadrouter.com/llm-api-pricing/mimo-v2.5/) | standard | USD 0.14 | USD 0.0028 | USD 0.28 | 1,048,576 | — | [source](https://intl.cloud.baidu.com/en/doc/qianfan/s/Jm8r1826a-intl-en) |

-   **Cached "—"** means Baidu's page shows no cache price for that row; budget cached tokens at the input price.
-   **Context "not stated"**: the source does not give it (14 of 15 rows have one).

[Report a wrong price or number](mailto:info@broadnet.ai?subject=Wrong%20price%20or%20number%20on%20Baidu%20API%20pricing&body=Page%3A%20https%3A%2F%2Fbroadrouter.com%2Fllm-api-pricing%2Fproviders%2Fbaidu%2F%0A%0AWhat%20looks%20wrong%20(model%2C%20figure%20shown%2C%20correct%20figure%20and%20a%20source%20link%20if%20you%20have%20one)%3A%0A) (email to info@broadnet.ai, with this page's link filled in).

## What service tiers does Baidu publish?

-   **fast** (1 row). Across 1 model with both prices, median fast input is 1.61× standard and median output 1.79× standard. Baidu row note: “GLM-5.2-Fast, the fast version of GLM-5.2.”

Cached input: 13 of 14 standard prices include a cache-read price, a median 10% of the input price. [What cached input means](https://broadrouter.com/glossary/cached-input-tokens/).

**What we recorded about Baidu's pricing page:** Pay-as-you-go online inference prices in USD from the Baidu AI Cloud international Qianfan "Price" doc (intl.cloud.baidu.com). Models listed under Text Generation, Visual Understanding and Deep Thinking are merged (same prices repeated across sections). The China-region CNY price list is not used. providerModelId and context come from the Qianfan "Model List" doc (intl.cloud.baidu.com/en/doc/qianfan/s/7m95lyy43-intl-en); ERNIE 5.1 is priced but not in that list.

## Is Baidu cheaper than the model makers' own APIs?

Mostly it charges the same as the maker. Of 7 standard prices for models whose maker sells its own API, 1 is below the maker's price, 1 above and 5 the same, on the 3:1 blend. The median difference is zero. The biggest saving is DeepSeek V4.1 Flash 1017, 6% below DeepSeek. The biggest markup is DeepSeek V4 Pro, 7% above DeepSeek.

## BroadNet Inference and Baidu

BroadRouter is BroadNet's own site, so BroadNet is never ranked on this page. BroadNet Inference serves none of the models Baidu prices. [BroadNet Inference pricing](https://broadrouter.com/pricing/).

## More on Baidu

-   [Baidu's own pricing page](https://intl.cloud.baidu.com/en/doc/qianfan/s/Jm8r1826a-intl-en) (the source; checked 2026-11-15)
-   [All 41 providers compared](https://broadrouter.com/llm-api-pricing/providers/) · [Cheapest LLM APIs right now](https://broadrouter.com/llm-api-pricing/cheapest/) · [Download every price (CSV, JSON)](https://broadrouter.com/data/llm-api-provider-prices/)

## Questions

### How much does the Baidu API cost per token?

Baidu's standard prices run from USD 0.14 input and USD 0.28 output per 1M tokens (DeepSeek V4 Flash) to USD 1.40 / USD 4.40 (GLM 5.2). The median across 14 standard prices is USD 0.755 input and USD 2.865 output per 1M, which is USD 0.000000755 per input token. Input, cached input and output are billed separately.

### What is the cheapest model on Baidu?

DeepSeek V4 Flash, at USD 0.14 input and USD 0.28 output per 1M tokens (USD 0.175 on a 3:1 input-to-output blend). The cheapest from other makers: ERNIE-5.5-Flash-Preview (Baidu) at USD 0.28 / USD 1.13; GLM 5 (Z.ai) at USD 1 / USD 3.20; Kimi K2.6 (Moonshot AI) at USD 0.95 / USD 4.

### Is Baidu cheaper than other providers?

It depends on the model. Of 11 models that other providers also price, Baidu is the cheapest standard price for 1 (all of them tied with another provider), for example MiMo v2.5; another provider is cheaper for 10; and it is the dearest for 2. Its median rank is 5 of a median 12 providers, on a 3:1 input-to-output blend.

### Does Baidu have batch, cached or priority pricing?

Cached input: yes, for 13 of 14 standard prices, at a median 10% of the input price. Other tiers: fast on 1 row (median input 1.61× standard).

### How much does a chatbot cost per month on Baidu?

For 2,000 requests a day, 1,500 input tokens (60% cached), 300 output, over 30 days: USD 10.23 on MiMo v2.5, USD 95.94 on ERNIE 5.1 (the middle of Baidu's list) and USD 143.64 on GLM 5.2. [Try your own numbers](https://broadrouter.com/tools/llm-api-cost-calculator/).

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=llm-api-pricing-providers-baidu&utm_content=page-cta) ·

**Sources**

-   [Baidu: pricing page (checked 2026-11-15)](https://intl.cloud.baidu.com/en/doc/qianfan/s/Jm8r1826a-intl-en)
