tencent/hy3
$0.0880 / M input tokens · $0.3530 / M output tokens
HY3 is a Tencent Hunyuan model route on OurToken for developers who want a low-cost chat completions model for application testing, coding support, and production evaluation.
2026-07-09 13:08:26 UTC
Pricing
Pay-per-use
No upfront costs, pay only for what you use
API Usage
API Access Guide
Code examples
Use the OurToken API endpoint for this model. The examples below use direct HTTP requests and the recommended endpoint for the model family.
curl https://api.ourtoken.ai/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "hy3",
"messages": [
{
"role": "user",
"content": "Hello!"
}
],
"max_tokens": 256
}'Chat Completions API Reference
Create a chat response with the OpenAI Chat Completions-compatible endpoint. Use https://api.ourtoken.ai/v1 as the SDK Base URL and POST /chat/completions as the endpoint.
Authorization
| Content-Type | application/json |
| Authorization | Bearer YOUR_API_KEY |
Request Body
| Field | Type | Required | Description |
|---|---|---|---|
| model | string | Required | Model ID to call. |
| messages | array<object> | Required | Conversation messages sent to the model. |
| max_tokens | integer | Optional | Maximum number of output tokens. |
| temperature | number | Optional | Sampling temperature. |
| top_p | number | Optional | Nucleus sampling parameter. |
| stream | boolean | Optional | Whether to return a streaming response. |
| stream_options | object | Optional | Additional options for streaming responses. |
| tools | array<object> | Optional | Tools available to the model. |
| tool_choice | string | object | Optional | Controls how the model selects tools. |
| response_format | object | Optional | Controls structured output, such as JSON object responses. |
Response Body
| Field | Type | Required | Description |
|---|---|---|---|
| id | string | Required | Unique chat completion identifier. |
| object | "chat.completion" | Required | Object type returned by the Chat Completions API. |
| created | integer | Required | Unix timestamp when the response was created. |
| model | string | Required | Model that produced the response. |
| choices | array<object> | Required | Candidate responses returned by the model. |
| choices[].message.role | string | Required | Role of the returned chat message. |
| choices[].message.content | string | Optional | Text content in the returned chat message. |
| choices[].finish_reason | string | Optional | Reason generation stopped. |
| usage | object | Optional | Token usage information for the chat completion. |
| usage.prompt_tokens | integer | Optional | Input token count. |
| usage.completion_tokens | integer | Optional | Output token count. |
| usage.total_tokens | integer | Optional | Total token count. |
| usage.prompt_tokens_details | object | Optional | Breakdown of input token usage. |
| usage.prompt_tokens_details.cached_tokens | integer | Optional | Tokens served from cache. |
Model Introduction
Hunyuan hy3
HY3 is a Tencent Hunyuan model route on OurToken for developers who want a low-cost chat completions model for application testing, coding support, and production evaluation.
Use HY3 when your team wants Tencent Hunyuan model access through the same OurToken API workflow used for other LLM routes. OurToken keeps the hy3 model ID, API examples, availability status, and pricing details close to the implementation workflow.
Why It Looks Great
- Tencent Hunyuan route for cost-sensitive chat and assistant workloads.
- OpenAI-compatible chat completions setup through the OurToken endpoint.
- Dedicated route page for model ID, code examples, status, and pricing review.
- Useful for comparing real prompt quality, latency, token usage, and cost across providers.
- Simple path from Tencent model discovery into API implementation.
Key Features
- Model ID: hy3
- Provider: Tencent Hunyuan
- Input price: $0.0880 per 1M tokens on OurToken
- Output price: $0.3530 per 1M tokens on OurToken
- Cache read price: $0.0220 per 1M tokens on OurToken
- Cache write price: $0 per 1M tokens on OurToken
- API endpoint: chat completions
- Evaluation focus: chat, coding help, multilingual prompts, route comparison, and production fit
Specifications
tencent hy3 api Features for Developers
Use tencent hy3 api to test the hy3 model, compare Hunyuan Hy3 pricing, and evaluate Tencent workflows through one API.
API Access
Call tencent hy3 api through the OurToken unified endpoint with model ID hy3. This keeps API keys, request examples, route status, and model testing in one developer workflow for teams evaluating Tencent Hunyuan access.
Pricing Review
Review Hunyuan Hy3 pricing before production rollout. OurToken lists $0.0880 input, $0.3530 output, $0.0220 cache read, and $0 cache write per 1M tokens, while public official references show higher baseline pricing.
Model Context
Public Tencent Hy3 model card materials describe a 295B-parameter MoE architecture, 21B active parameters, and long-context positioning. Treat those figures as provider or benchmark context, then validate the hy3 model against your own prompts on OurToken.
Benchmark Review
Use tencent hy3 benchmarks as research signals, not production guarantees. Compare coding, agent, reasoning, and long-context claims with your own workload, latency targets, and acceptance criteria before routing traffic to hy3.
Provider Comparison
HY3 is useful when teams compare Tencent with Qwen, GLM, DeepSeek, MiniMax, OpenRouter listings, or Hugging Face references. OurToken focuses on the active hy3 route, current pricing, and a repeatable API workflow.
Production Fit
Before adopting hy3 tencent traffic paths, test expected prompt sizes, output lengths, structured answer needs, error handling, and cost. The right route should reflect workload quality, availability, pricing, and support requirements.
How to Use tencent hy3 api on OurToken
Create an API key, set hy3 as the model, call chat completions, review pricing, compare benchmarks, and monitor route quality.
Create Key
Create an OurToken API key from the dashboard and store it in a secure server-side environment variable. This gives your backend a stable credential for tencent hy3 api calls without exposing secrets in browser code.
01Set Model
Use hy3 as the model value in your request body. Keep the model ID configurable so your team can compare Hunyuan Hy3 API behavior with Qwen, GLM, DeepSeek, MiniMax, or existing production baselines.
02Call Endpoint
Send requests to the OurToken chat completions endpoint with your API key, model ID, and prompt payload. Existing OpenAI-compatible request patterns can usually be reused after changing the base URL, credential, and model value.
03Review Pricing
Before scaling usage, review the configured HY3 prices: $0.0880 input, $0.3530 output, $0.0220 cache read, and $0 cache write per 1M tokens. Compare these rows with prompt size and output length.
04Compare Benchmarks
Collect public hy3 preview, official release, and tencent hy3 benchmarks as background research. Then run the same prompts through OurToken so quality, latency, token use, and failure behavior are measured in your own workflow.
05Monitor Results
After testing, review usage logs, failures, latency patterns, and spend inside OurToken. This helps decide whether tencent hy3 api is ready for production traffic or needs more prompt and routing validation.
06tencent hy3 api FAQ
Answers about Hunyuan Hy3 API access, pricing, hy3 preview, benchmarks, OpenRouter, free access, Hugging Face, and model selection.
