Tencent Hunyuan route
hy3
Hy3 API pricing.
One OpenAI-compatible route at a disclosed public reference rate, billed per token from one prepaid balance. No subscription required.
Input / 1M tokens
$0.20
Output / 1M tokens
$0.80
Cached input / 1M tokens
$0.03
Context window
256K
Provider
Tencent Hunyuan
Workload calculator
Put the token rate into context.
These examples apply the published input and output rates directly. Actual cost follows the exact tokens your client sends and the model returns.
This route is the 11th cheapest of 63 comparable text models and cheaper than 52 on the same key. Its context window ranks 58th of 63.
Short request
$0.0028
10K input + 1K output
Agent turn
$0.028
100K input + 10K output
Exact token billing
No request minimum
One model ID change
OpenAI compatible
Cost neighbourhood
Nearby routes, same workload.
Every comparison uses the same 100K-input / 10K-output turn. Changing route is a one-line model ID edit.
Price does not measure task quality. Check Hy3 benchmark evidence before optimizing on cost alone.
First request
Route it in one call.
Use any OpenAI SDK or tool. Keep the request shape, point the base URL at RouterPlex, and set the model ID shown here.
Read the quickstartcurl https://api.routerplex.com/v1/chat/completions \-H "Authorization: Bearer $ROUTERPLEX_API_KEY" \-H "Content-Type: application/json" \-d '{"model": "hy3","messages": [{"role": "user", "content": "Hello!"}]}'
Route notes
Questions before production traffic.
01How much does the Hy3 API cost?+
Through RouterPlex, Hy3 costs $0.20 per 1M input tokens and $0.80 per 1M output tokens — RouterPlex's disclosed public reference rate, billed per token from a prepaid balance you top up from $5. Cached input tokens are billed at $0.03 per 1M instead of the full input rate, which is most of the prompt on a repeated agent or coding loop. Tencent publishes Hy3 as open weights without a first-party hosted API tariff. RouterPlex uses the public market reference of $0.20 input / $0.80 output per 1M tokens.
02What does one Hy3 agent turn cost?+
A 100K-token input with a 10K-token reply costs about $0.028 on Hy3. That makes it the 11th cheapest of 63 comparable text models on RouterPlex, roughly 2.6× the cost of the cheapest option (DeepSeek V4 Flash).
03What is a cheaper alternative to Hy3?+
DeepSeek V4.1 Flash from DeepSeek is the closest cheaper model on RouterPlex — $0.025 per agent turn against $0.028 for Hy3, at $0.18/1M input and $0.73/1M output. Both run on the same key and the same endpoint, so switching is a one-line model ID change.
04Is Hy3 cheaper than DeepSeek V4 Flash Vision?+
Yes. Per agent turn, Hy3 costs about $0.028 against $0.029 for DeepSeek V4 Flash Vision — 2% less.
05What is the context window of Hy3?+
Hy3 supports a 256K token context window on RouterPlex, the 58th largest of the 63 models that publish one.
06Can I use Hy3 with the OpenAI SDK?+
Yes. RouterPlex serves Hy3 through an OpenAI-compatible endpoint at https://api.routerplex.com/v1 — point any OpenAI SDK or tool at that base URL with your RouterPlex key and set model to "hy3".
Provider family
More from Tencent Hunyuan.
Deploy this route
Put Hy3 behind one key.
Top up from $5 with no subscription required.