Last verified
TEXT EMBEDDING1024-D VECTORSSHARED FREE QUOTANO CACHE PRICECNY SOURCE

Hunyuan Embedding API Pricing

Hunyuan Embedding is Tencent Cloud's vectorization endpoint for search, retrieval, and clustering rather than generative chat. The official pricing page lists Y0.70/M on the published row, which AI//COST stores as $0.099/M at Y7.1/USD; Tencent's API doc says the endpoint returns 1024-dimension vectors. Pulled directly from cloud.tencent.com daily.

Input - per 1M tokens
$0.10/M
Original Y0.70/M CNY source
Published output row
$0.10/M
Table is symmetric same row
Cached input
$0.10/M
No cache listed publicly N/A
Effective - agentic blend
$0.10/M
92/8 split - same row
§ 01 / TERMINAL

Run the numbers.

Live calculator pre-loaded with Hunyuan Embedding's published row. Use it for chunking, vector imports, and retrieval budget planning rather than chat-style output estimates.

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

Real-world presets.

RAG

Single chunk embedding

$0.000/chunk
800 input tokens~1,262,626 chunks/$100
SEARCH

Product snippet indexing

$0.000/snippet
2k input tokens~505,051 snippets/$100
MANUALS

100-page doc vectorization

$0.004/manual
45k input tokens~22,447 manuals/$100
CORPUS

1M-token import

$0.099/corpus
1M input tokens~1,010 imports/$100
§ 03 / TAPE

Price history.

Tencent's public embedding row still shows Y0.70/M on the published symmetric table.

Input · $0.10/M
Output · $0.10/M
Cached · $0.10/M
JAN 05 Tencent Hunyuan Embedding launched with 1024-dimension vectorsMAY 23 Verified unchanged on Tencent Cloud at Y0.70/M on the published symmetric row
§ 04 / TOKENIZER

Paste text. See tokens. See cost.

Estimate · tencent-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
Hunyuan Embedding Current $0.10 $0.10 $0.10 published symmetric row documented elsewhere Tencent search and retrieval indexing
text-embedding-3-small $0.02 $0.00 $0.02 cross-vendor budget benchmark 8K Cheap general-purpose embeddings
text-embedding-3-large $0.13 $0.00 $0.12 similar cross-vendor peer 8K Higher-quality OpenAI embeddings
Yi Lightning $0.14 $0.14 $0.14 Chinese routing peer 16K Cheap Chinese text processing
Hunyuan A13B $0.07 $0.28 $0.09 Tencent text baseline 224K Low-cost Tencent text traffic

Frequently asked.

Practical Hunyuan Embedding pricing questions, with Tencent's published row separated from vector-workload assumptions.

Q · 01 What is Hunyuan Embedding priced at today? +
Tencent Cloud's official Hunyuan pricing page lists a published row of Y0.70/M for Hunyuan Embedding. AI//COST stores that as $0.099/M using the queue's Y7.1/USD conversion rate.
Q · 02 Why does this page show the same number for input and output? +
Because Tencent's public pricing table is presented symmetrically for this row. The actual endpoint is an embedding API, so the real workload is generally input text being turned into vectors rather than generative output tokens.
Q · 03 What does Tencent document about the vectors themselves? +
Tencent's official embedding API doc says the endpoint returns 1024-dimension vectors. The same doc describes the endpoint as a text-to-vector API rather than a chat model.
Q · 04 Is there any free quota before the paid rate starts? +
Yes. Tencent's pricing page says Hunyuan Embedding is covered by the shared 1M token activation quota. The price on this page is the standard paid list rate after that shared quota is used.
Q · 05 Does Tencent publish a cache-hit discount for Hunyuan Embedding? +
No. The public embedding row does not show a separate cache-hit or prompt-cache rate. This page therefore treats cached input the same as standard input instead of inventing a discount.
Q · 06 Does this page include tax or enterprise discounts? +
No. AI//COST stores Tencent's public pre-tax list price and converts it to USD for cross-vendor comparison. Contract rebates, private discounts, and region-specific billing are outside this page.
Y
Reviewed by Yaroslav Vikhariev Founder - AI//COST - Pricing pulled daily from cloud.tencent.com - Last verified May 23, 2026
Methodology Report a correction More by Y.V.