Last verified
LEGACY BAICHUAN232K CONTEXTTEXT ONLYUNIFIED TOKEN RATENO CACHE DISCOUNT

Baichuan2-Turbo API Pricing

Baichuan2-Turbo remains on Baichuan's public pricing page as a legacy unified-rate row. The live table lists $1.127/M unified, converted from 0.008 yuan per 1K tokens at 7.10 CNY/USD, with the same price billed for input and output. No separate cache-hit discount is published, and Baichuan's older 192K route now points users toward Baichuan3-Turbo-128K. Pulled directly from platform.baichuan-ai.com daily.

Input - per 1M tokens
$1.13/M
Source Baichuan legacy row
Output - per 1M tokens
$1.13/M
Unified same as input same as input
Cached input - no separate discount
$1.13/M
Cache not listed 0%
Effective - agentic blend
$1.13/M
92/8 split - no cache discount
§ 01 / TERMINAL

Run the numbers.

Live calculator pre-loaded with current Baichuan2-Turbo rates. Tweak spend or workload shape, then share the URL to share the estimate.

$ /mo
Workload split
Prompt cache hit rate
Tokens you can process
—
Words equivalent (English)
—
Effective rate
—
§ 02 / SCENARIOS

Real-world presets.

LEGACY APP

Legacy app turn

$0.022/turn
20,000 total tokens~4,437 turns/$100
SUMMARY

Batch summary

$0.068/batch
60,000 total tokens~1,479 batches/$100
FAQ

FAQ answer

$0.004/answer
4,000 total tokens~22,182 answers/$100
MIGRATION

192K route audit

$0.135/review
120,000 total tokens~739 reviews/$100
§ 03 / TAPE

Price history.

Baichuan2-Turbo has held at $1.13/M unified across our verified live snapshots.

Input · $1.1/M
Output · $1.1/M
Cached · $1.1/M
MAY 18 First AI//COST verified snapshot stored the $1.13/M unified rateMAY 23 Live verification kept the same $1.13/M unified rate
§ 04 / TOKENIZER

Paste text. See tokens. See cost.

Estimate · baichuan-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 —
Words —
Tokens (estimated) —
Cost as input · uncached —
Cost as output · uncached —
Cost as cached input —
§ 05 / SHELF

Up against the shelf.

All models →
Model Input /M Output /M Effective blended Context Best for
Baichuan2-Turbo Current $1.13 cache $1.13 $1.13 $1.13 agentic 92/8 32K Legacy Baichuan2 integrations
Baichuan3-Turbo $1.69 cache $1.69 $1.69 $1.69 pricier 32K Balanced legacy production traffic
Baichuan3-Turbo (128K) $3.38 cache $3.38 $3.38 $3.38 pricier 128K Long-context legacy workloads
Baichuan-M2 $0.28 cache $0.28 $2.82 $0.48 cheaper 32K Budget Chinese text workloads
Baichuan4 Air $0.14 cache $0.14 $0.14 $0.14 cheaper 32K Lowest-cost Baichuan API traffic
GLM-5 $1.00 cache $0.20 $3.20 $0.57 cheaper 200K Chinese coding and agent tasks
Gemini 2.5 Flash $0.30 cache $0.03 $2.50 $0.27 cheaper 1M Global multimodal budget workloads

Frequently asked.

Practical pricing questions for Baichuan2-Turbo, especially for legacy teams deciding whether to keep it or migrate.

Q · 01 What is Baichuan2-Turbo priced at? +
Baichuan's official pricing page lists Baichuan2-Turbo at about $1.127/M on a unified basis. That USD figure comes from 0.008 yuan per 1K tokens converted at 7.10 CNY/USD.
Q · 02 Does Baichuan2-Turbo have prompt-cache pricing? +
No separate cache-hit discount is listed for Baichuan2-Turbo on the public pricing page. AI//COST therefore sets cached input equal to the normal token rate instead of inventing a separate billing mode.
Q · 03 What happened to Baichuan2-Turbo-192K? +
Baichuan's current pricing snapshot notes that the older Baichuan2-Turbo-192K route is deprecated and should be treated as a migration path to Baichuan3-Turbo 128K. The public pricing page no longer gives the 192K row its own active price line.
Q · 04 How does it compare with Baichuan3-Turbo? +
Baichuan3-Turbo is pricier at about $1.69/M unified, but it is the newer family still listed as active rather than legacy. Baichuan2-Turbo is cheaper on raw tokens, but the product-age tradeoff matters if you are choosing a net-new integration.
Q · 05 Is there a better budget option today? +
Yes if raw cost is the goal. Baichuan4 Air is about $0.138/M unified, and Baichuan-M2 lands at roughly $0.282/M input and $2.817/M output depending on workload shape.
Q · 06 How accurate is the tokenizer estimate? +
The browser widget uses a baichuan-tokenizer-estimate chars-per-token approximation for English text. Real billing comes from Baichuan's API usage counters and can differ for Chinese, code, or mixed-language prompts.
Y
Reviewed by Yaroslav Vikhariev Founder - AI//COST - Pricing pulled daily from platform.baichuan-ai.com - Last verified May 23, 2026
Methodology Report a correction More by Y.V.