Baichuan3-Turbo API Pricing
Baichuan3-Turbo is still listed as an active 32K row on Baichuan's public pricing page. The live table lists $1.69/M unified, converted from 0.012 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. Pulled directly from platform.baichuan-ai.com daily.
Run the numbers.
Live calculator pre-loaded with current Baichuan3-Turbo rates. Tweak spend or workload shape, then share the URL to share the estimate.
Real-world presets.
Repo implementation
Knowledge-base answer
Customer conversation
Long report summary
Paste text. See tokens. See cost.
Counts use a chars-per-token calibration measured on the vendor's own published tokenizer (baichuan-inc/Baichuan-M2-32B, 2026-06-10). English prose is typically within a few percent; code and non-Latin scripts tokenize heavier. For billing-exact counts use the vendor's count-tokens API.
| Model | Input /M | Output /M | Effective blended | Context | Best for |
|---|---|---|---|---|---|
| Baichuan3-Turbo Current | $1.69 cache $1.69 | $1.69 | $1.69 agentic 92/8 | 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-Plus | $1.41 cache $1.41 | $4.22 | $1.63 slightly cheaper | 32K | Legacy medical copilots |
| Baichuan4 Turbo | $2.11 cache $2.11 | $2.11 | $2.11 pricier | 32K | Balanced Baichuan production traffic |
| 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 Baichuan3-Turbo, separated from workload assumptions and migration paths.
Q · 01 What is Baichuan3-Turbo priced at? +
$1.69/M on a unified basis. That USD figure comes from 0.012 yuan per 1K tokens converted at 7.10 CNY/USD, and the same rate applies to both input and output.Q · 02 Does Baichuan3-Turbo have prompt-cache pricing? +
Q · 03 How does it compare with Baichuan3-Turbo-128K? +
$3.38/M in exchange for a 4x larger context window. If you do not need the longer context, the 32K row is materially cheaper.Q · 04 Is Baichuan3-Turbo cheaper than Baichuan4 Turbo? +
$1.69/M unified, while Baichuan4 Turbo is about $2.11/M unified on the same official table.Q · 05 Is there a separate batch discount? +
Q · 06 How accurate is the tokenizer estimate? +
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.