Favicon for tencent

Tencent: Hy3 (free)

Going away July 21, 2026

Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort: a direct no-think mode by default, plus low and high chain-of-thought modes for complex math, coding, and multi-step problems. With a 256K context window, Hy3 targets long-horizon tasks, including improved coreference resolution, multi-turn constraint tracking, and stable tool-calling that generalizes across agent scaffoldings.

Tencent positions it as a reliable, cost-effective option across coding, document processing, financial analysis, game development, and frontend design, with a strong emphasis on grounded, anti-hallucination behavior that answers when grounded and flags when evidence is missing rather than fabricating.

Modalities

Price

Free

Context

262K

Released

Jul 6, 2026

Providers

Different companies host the same model. OpenRouter routes your request to one of them based on the routing mode you pick — Balanced (price + speed), Nitro (fastest), or Exacto (highest tool-calling accuracy).

FreeFree1.98s39 tps
100.00%

Effective Pricing

The chart below shows the average price customers are actually paying after prompt caching. Depending on the amount of repeated context you send, this can be 60–80% cheaper than the provider list price. Shown are rolling averages from the past 30 days.

Weighted Average

Weighted Avg Input Price

$0.0000

/M tokens

Weighted Avg Output Price

$0.0000

/M tokens

$0.0000$0.000090.3%
100.0%

Input Price / 1M tokens (7 days)

Jul 9Jul 11Jul 13Jul 1501234$/1M

Output Price / 1M tokens (7 days)

Jul 9Jul 11Jul 13Jul 1501234$/1M

Performance

Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).

Throughput

39tok/s

best across providers

Latency

1.98s

p50, best provider

Throughput
NovitaAI
Avg45 tok/s
Latency
NovitaAI
Avg2.89 s
E2E Latency
NovitaAI
Avg14.02 s
Tool Call Error Rate
NovitaAI
Avg1.90 %
Structured Output Error Rate
NovitaAI
Avg13.31 %
Cache Hit Rate
NovitaAI
Avg91.33 %

Uptime

Percent of requests that succeeded over the last 30 days. OpenRouter monitors every provider continuously and automatically retries on the next-best provider when one returns an error.

Avg. Provider Uptime (3d)

99.36%

averaged across all endpoints

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access uptime data programmatically through the Endpoints API. Learn more about our load balancing and customization options.

Benchmarks

Scores on standardized evaluations. Higher percentages are better — and rank percentile shows where this model lands among all models on OpenRouter.

Ranking Distribution
1,181 tournaments

In each tournament, 4 models generate outputs for the same prompt. Users vote on which is best. This chart shows how often this model placed 1st, 2nd, 3rd, or 4th.

FirstSecondThirdFourth0150300450600195267409310
Category Performance
3DElo: 1195Code CategoriesElo: 1193Data VisualizationElo: 1173Game DevelopmentElo: 1190UI ComponentElo: 1186WebsiteElo: 1194

Models Arena

3DTop 46%
1195Elo
39.4% Win60.1s AvgTop 46%
Code CategoriesTop 53%
1193Elo
39.5% Win87.4s AvgTop 53%
Data VisualizationTop 60%
1173Elo
39.1% Win49.2s AvgTop 60%
Game DevelopmentTop 55%
1190Elo
38.5% Win88.4s AvgTop 55%
UI ComponentTop 56%
1186Elo
39.4% Win72.5s AvgTop 56%
WebsiteTop 54%
1194Elo
39.9% Win99.0s AvgTop 54%
Metrics sourced from Design Arena

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

1.
Favicon for https://nousresearch.com
Hermes Agent
Hermes Agent is an open-source, self-improving AI agent by Nous Research that runs persistently with memory across sessions, and builds reusable skills from experience. It comes with 40+ built-in tools, including web search, browser automation, and vision, plus scheduled automations and subagents.
2.37Ttokens
2.
Favicon for https://kilocode.ai/
Kilo Code
Kilo Code is an open-source AI coding agent that works across VS Code, JetBrains, and CLI to help developers ship code faster with agentic workflows.
858Btokens
3.
538Btokens
4.
Favicon for https://claude.ai/apple-touch-icon.png
Claude Code
Claude Code is Anthropic's agentic coding tool that reads your entire codebase, plans and executes changes across files, runs tests, and iterates on failures, all from natural language prompts.
198Btokens
5.
143Btokens
Jul 6Jul 8Jul 10Jul 12Jul 14Jul 16

Activity

Token volume and request traffic to this model over time.

Jul 6Jul 8Jul 10Jul 12Jul 14Jul 16500B1T1.5T2T
Prompt
1.58T
Completion
18.7B
Reasoning
13.8B

Prompt tokens measure input size. Reasoning tokens show internal thinking before a response. Completion tokens reflect total output length.

Quick Start

Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.

1

Get your API key

Create an API key from your OpenRouter dashboard and set it as an environment variable:

Create API Key
export OPENROUTER_API_KEY=sk-or-v1-...
2

Make your first request

Use tencent/hy3:free with the OpenRouter API:

OpenRouter supports reasoning-enabled models that can show their step-by-step thinking process. Use the reasoning parameter in your request to enable reasoning, and access the reasoning_details array in the response to see the model's internal reasoning before the final answer. When continuing a conversation, preserve the complete reasoning_details when passing messages back to the model so it can continue reasoning from where it left off. Learn more about reasoning tokens.

In the examples below, the OpenRouter-specific headers are optional. Setting them allows your app to appear on the OpenRouter leaderboards.

import { OpenRouter } from "@openrouter/sdk";
const openrouter = new OpenRouter({
apiKey: "<OPENROUTER_API_KEY>"
});
// Stream the response to get reasoning tokens in usage
const stream = await openrouter.chat.send({
chatRequest: {
model: "tencent/hy3:free",
messages: [
{
role: "user",
content: "How many r's are in the word 'strawberry'?"
}
],
stream: true
}
});
let response = "";
for await (const chunk of stream) {
const content = chunk.choices[0]?.delta?.content;
if (content) {
response += content;
process.stdout.write(content);
}
// Usage information comes in the final chunk
if (chunk.usage) {
console.log("\nReasoning tokens:", chunk.usage.completionTokensDetails?.reasoningTokens);
}
}

Using third-party SDKs

For information about using third-party SDKs and frameworks with OpenRouter, please see our frameworks documentation.

3

Enable streaming

Add "stream": true to your request body to receive responses as server-sent events:

curl -N https://openrouter.ai/api/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-d '{
"model": "tencent/hy3:free",
"stream": true,
"messages": [
{"role": "user", "content": "Hello"}
]
}'

Endpoint

Sends a request for a model response for the given chat conversation. Supports both streaming and non-streaming modes.

POSThttps://openrouter.ai/api/v1/chat/completions
AuthorizationBearer $OPENROUTER_API_KEY
Content-Typeapplication/json
HTTP-Refereroptional — your site URL, for rankings
X-Titleoptional — your site name, for rankings
Modeltencent/hy3:free

Creates a streaming or non-streaming response using the OpenAI Responses API format.

Docs
POSThttps://openrouter.ai/api/v1/responses
AuthorizationBearer $OPENROUTER_API_KEY
Content-Typeapplication/json
HTTP-Refereroptional — your site URL, for rankings
X-Titleoptional — your site name, for rankings
Modeltencent/hy3:free

Creates a message using the Anthropic Messages API format. Supports text, images, PDFs, tools, and extended thinking.

Docs
POSThttps://openrouter.ai/api/v1/messages
AuthorizationBearer $OPENROUTER_API_KEY
Content-Typeapplication/json
HTTP-Refereroptional — your site URL, for rankings
X-Titleoptional — your site name, for rankings
Modeltencent/hy3:free

Parameters

NameTypeDefaultDescription
reasoningmapControls reasoning behavior for models that support thinking tokens, including whether reasoning is enabled, the reasoning effort, maximum reasoning tokens, and whether reasoning is excluded from the response.
max_tokensintegerThis sets the upper limit for the number of tokens the model can generate in response.
temperaturefloat0.9This setting influences the variety in the model's responses.
top_pfloat1This setting limits the model's choices to a percentage of likely tokens: only the top tokens whose probabilities add up to P.
stoparrayStop generation immediately if the model encounter any token specified in the stop array.
frequency_penaltyfloat0This setting aims to control the repetition of tokens based on how often they appear in the input.
presence_penaltyfloat0Adjusts how often the model repeats specific tokens already used in the input.
seedintegerIf specified, the inferencing will sample deterministically, such that repeated requests with the same seed and parameters should return the same result.
top_kinteger0This limits the model's choice of tokens at each step, making it choose from a smaller set.
repetition_penaltyfloat1Helps to reduce the repetition of tokens from the input.
toolsarrayTool calling parameter, following OpenAI's tool calling request shape.
tool_choicestring or objectControls which (if any) tool is called by the model.

More models from tencent

Compare