Last verified
CHINA FRONTIER128K CONTEXTTEXTON QIANFANCNY SOURCE

ERNIE 5.1 API Pricing

ERNIE 5.1 is Baidu's frontier MoE model on the Qianfan platform - a cheaper refresh of the ERNIE 5 line. The official billing page lists the 0-32K tier at CNY 4/M input and CNY 18/M output, which AI//COST stores as $0.5952/M and $2.6782/M at 1 CNY = $0.1475. Pulled from cloud.baidu.com.

Input - per 1M tokens
$0.595/M
Original CNY 4/M CNY source
Output - per 1M tokens
$2.68/M
Original CNY 18/M CNY source
Cache N/A
$0.595/M
Cache no public row not listed
Effective - agentic blend
$0.762/M
92/8 split - no cache discount
§ 01 / TERMINAL

Run the numbers.

Live calculator pre-loaded with ERNIE 5.1's 0-32K tier. Above 32K input, Baidu charges the higher CNY 6/M input and CNY 22/M output band shown in the FAQ.

$ /mo
Workload split
Prompt cache hit rate
Tokens you can process
—
Words equivalent (English)
—
Effective rate
—
Open full calculator (all models · share URL · CSV) →
§ 02 / SCENARIOS

Real-world presets.

CODING AGENT

Codebase-scale migration

$0.098/task
120k in / 10k out~1,018 tasks/$100
LONG DOC ANALYSIS

Reading 100-page contracts

$0.129/doc
180k in / 8k out~778 docs/$100
RAG - SUPPORT

Ticket triage

$0.00744/ticket
8k in / 1k out~13,441 tickets/$100
ASSISTANT

Research planning turn

$0.016/turn
18k in / 2k out~6,223 turns/$100
§ 03 / TOKENIZER

Paste text. See tokens. See cost.

Estimate · ernie-tokenizer-estimate · ≈3.85 chars/token Auto-counts as you type

This is a chars-per-token approximation, not a real tokenizer. Actual tokens vary by language, code density, and tool-call overhead — counts are typically ±10–20% off for English prose, more for code or non-Latin scripts. For exact billing, use the vendor's official tokenizer.

Characters 505
Words 82
Tokens (estimated) 131 tokens
Cost as input · uncached $0.00008 USD
Cost as output · uncached $0.00035 USD
Cost as cached input $0.00008 USD
§ 04 / SHELF

Up against the shelf.

All models →
Model Input /M Output /M Effective blended Context Best for
ERNIE 5.1 Current $0.595 $2.68 $0.762 agentic 92/8, no cache 128K Frontier Chinese-language work
ERNIE 4.5 Turbo $0.119 cache $0.0298 $0.476 $0.0803 cheaper sibling 128K High-volume cost-sensitive traffic
DeepSeek V4 Pro $1.32 cache $0.044 $3.96 $0.569 cross-vendor reasoning 1M Low-cost reasoning
Qwen 3.5 Plus $0.40 $2.40 $0.56 China peer 256K General Qwen production
GPT-5.4 $2.50 cache $0.25 $15.00 $1.80 Western frontier 1.05M Frontier daily-driver

Frequently asked.

Practical ERNIE 5.1 pricing questions, with Baidu's published CNY rates kept separate from conversion and workload assumptions.

Q · 01 What is ERNIE 5.1 priced at? +
On Qianfan, the 0-32K tier is CNY 4/M input and CNY 18/M output, stored here as $0.5952/M and $2.6782/M at 1 CNY = $0.1475. Above 32K input, the rate rises to CNY 6/M input and CNY 22/M output.
Q · 02 Does ERNIE 5.1 have a cache discount? +
Baidu does not publish a separate cache-read token price for ERNIE 5.1, so this calculator keeps cached input equal to base input ($0.5952/M). ERNIE 4.5 Turbo does have a published CNY 0.2/M cache-hit rate.
Q · 03 How does ERNIE 5.1 compare with ERNIE 5.0? +
ERNIE 5.0 lists CNY 6/24 ($0.885/$3.54) while ERNIE 5.1 is a cheaper refresh at CNY 4/18 ($0.5952/$2.6782). ERNIE 5.1 is newer and lower-priced.
Q · 04 Which API model ID should I use? +
Use ernie-5.1 on the Qianfan platform. Re-verify the current CNY tier prices on the Qianfan billing page before pinning a production integration.
Q · 05 Does this page include tax? +
No. AI//COST stores Baidu's public pre-tax CNY list price and converts to USD for cross-vendor comparison. Enterprise discounts and Baidu AI Cloud resource packages are outside this page.
Y
Reviewed by Yaroslav Vikhariev Founder - AI//COST - ERNIE pricing converted from Qianfan CNY list - Last verified July 11, 2026
Methodology Report a correction More by Y.V.