DeepInfra raises $107M Series B to scale the inference cloud β read the announcement
tencent/
$0.14
in
$0.58
out
$0.035
cached
/ 1M tokens
Hy3 is a 295B-parameter Mixture-of-Experts (MoE) model with 21B active parameters and 3.8B MTP layer parameters, developed by the Tencent Hy Team. Following the Hy3 Preview launch in late April, we gathered feedback from 50+ products and scaled up post-training with higher quality data. Today, we introduce Hy3, which outperforms similar-size models and rivals flagship open-source models with 2-5x parameters. It also shows significant gains in utility across various products and productivity tasks.

You can POST to our OpenAI Chat Completions compatible endpoint.
Given a list of messages from a conversation, the model will return a response.
curl "https://api.deepinfra.com/v1/openai/chat/completions" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $DEEPINFRA_TOKEN" \
-d '{
"model": "tencent/Hy3",
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
}'
To which you'd get something like:
{
"id": "chatcmpl-guMTxWgpFf",
"object": "chat.completion",
"created": 1694623155,
"model": "tencent/Hy3",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": " Hello! It's nice to meet you. Is there something I can help you with or would you like to chat for a bit?"
},
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 15,
"completion_tokens": 16,
"total_tokens": 31,
"estimated_cost": 0.0000268
}
}
To create a longer chat-like conversation you just have to add each response message and each of the user messages to every request. This way the model will have the context and will be able to provide better answers. You can tweak it even further by providing a system message.
curl "https://api.deepinfra.com/v1/openai/chat/completions" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $DEEPINFRA_TOKEN" \
-d '{
"model": "tencent/Hy3",
"messages": [
{
"role": "system",
"content": "Respond like a michelin starred chef."
},
{
"role": "user",
"content": "Can you name at least two different techniques to cook lamb?"
},
{
"role": "assistant",
"content": "Bonjour! Let me tell you, my friend, cooking lamb is an art form, and I'"'"'m more than happy to share with you not two, but three of my favorite techniques to coax out the rich, unctuous flavors and tender textures of this majestic protein. First, we have the classic \"Sous Vide\" method. Next, we have the ancient art of \"Sous le Sable\". And finally, we have the more modern technique of \"Hot Smoking.\""
},
{
"role": "user",
"content": "Tell me more about the second method."
}
]
}'
The conversation above might return something like the following
{
"id": "chatcmpl-b23a3fb60cde42ce8f24bb980b4dee87",
"object": "chat.completion",
"created": 1715688169,
"model": "tencent/Hy3",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "Sous le Sable, my friend! It's an ancient technique that's been used for centuries in the Middle East and North Africa. The name itself..."
},
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 149,
"total_tokens": 487,
"completion_tokens": 338,
"estimated_cost": 0.00035493
}
}
The longer the conversation gets, the more time it takes the model to generate the response. The number of messages that you can have in a conversation is limited by the context size of a model. Larger models also usually take more time to respond.
You can turn any of the requests above into a streaming request by passing "stream": true:
curl "https://api.deepinfra.com/v1/openai/chat/completions" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $DEEPINFRA_TOKEN" \
-d '{
"model": "tencent/Hy3",
"stream": true,
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
}'
to which you'd get a sequence of SSE events, finishing with [DONE].
data: {"id": "Rc5hsIPHOSfMP3rNSFUw9tfR", "object": "chat.completion.chunk", "created": 1694623354, "model": "tencent/Hy3", "choices": [{"index": 0, "delta": {"role": "assistant", "content": " "}, "finish_reason": null}]}
data: {"id": "Rc5hsIPHOSfMP3rNSFUw9tfR", "object": "chat.completion.chunk", "created": 1694623354, "model": "tencent/Hy3", "choices": [{"index": 0, "delta": {"role": "assistant", "content": " Hi"}, "finish_reason": null}]}
data: {"id": "Rc5hsIPHOSfMP3rNSFUw9tfR", "object": "chat.completion.chunk", "created": 1694623354, "model": "tencent/Hy3", "choices": [{"index": 0, "delta": {"role": "assistant", "content": "!"}, "finish_reason": null}]}
data: {"id": "Rc5hsIPHOSfMP3rNSFUw9tfR", "object": "chat.completion.chunk", "created": 1694623354, "model": "tencent/Hy3", "choices": [{"index": 0, "delta": {"role": "assistant", "content": ""}, "finish_reason": null}]}
data: {"id": "Rc5hsIPHOSfMP3rNSFUw9tfR", "object": "chat.completion.chunk", "created": 1694623354, "model": "tencent/Hy3", "choices": [{"index": 0, "delta": {"role": "assistant", "content": "</s>"}, "finish_reason": null}]}
data: {"id": "Rc5hsIPHOSfMP3rNSFUw9tfR", "object": "chat.completion.chunk", "created": 1694623354, "model": "tencent/Hy3", "choices": [{"index": 0, "delta": {}, "finish_reason": "stop"}]}
data: [DONE]
Β© 2026 DeepInfra. All rights reserved.