NewHow we catch a seller listing the wrong model, and refund you if one does.
UberLLM
Tencent logo

Tencent: Hy4 flash API

tencent/hy4-flashText

Call Tencent: Hy4 flash through UberLLM’s OpenAI-compatible API, from $0.0245/M input and $0.0984/M output, served by third-party providers. Made by Tencent. Open weights. 1,048,576 token context. No UberLLM fee on requests. Adding credit by card costs 5.5% + $0.50.

Also sold directly by: OpenRouter. Here, sellers serve it through their own provider accounts. Where the capacity comes from

How much does the Tencent: Hy4 flash API cost?

On November 19, 2026, Tencent: Hy4 flash costs $0.0245 per million input tokens and $0.0984 per million output tokens through UberLLM, 30% below its list price of $0.035 and $0.1405. 30 sellers on the market can serve it. It reads up to 1,048,576 tokens of context. Every request is listed with its cost in the Activity log. UberLLM adds no fee to these prices, and a request that fails is not billed.

What is the cheapest Tencent: Hy4 flash API?

On November 19, 2026, the cheapest Tencent: Hy4 flash API we found is UberLLM, at $0.0245 per million input tokens and $0.0984 per million output tokens. That is at least 30% less on both input and output than the closest other provider we checked, OpenRouter ($0.035 and $0.1405). Vercel AI Gateway, Novita AI and Requesty are higher still. 30 sellers on the UberLLM market can serve it. UberLLM adds no fee to these prices, and a request that fails is not billed.

Prices as of November 19, 2026, 08:00 UTC. This page is rebuilt every hour.

ProviderInput / 1M tokensOutput / 1M tokensUberLLM is lower by
UberLLM$0.0245$0.0984
OpenRouter$0.035$0.140530%
Vercel AI Gateway$0.035$0.140530%
Novita AI$0.035$0.140530%
Requesty$0.07$0.28165%

UberLLM: the best seller’s price now, no fee added. Other prices from each provider's public price list: OpenRouter, Vercel AI Gateway, Novita AI, Requesty

Tencent: Hy4 flash pricing

You save $0.0105 per 1M input tokens and $0.0422 per 1M output tokens against the official price of $0.035 / $0.1405. OpenRouter charges $0.035 / $0.1405 per 1M input / output tokens.

Price now · per 1M tokens
Input
$0.0245
Output
$0.0984
Cached input
$0.00105
% off list
30% off
90% of input served from cache
Official price · per 1M tokens
Input
$0.035
Output
$0.1405
Cached input
$0.0015

Prices as of 08:00 UTC.

Each request is sent to an available third-party provider for this model and retried if the provider fails before it starts answering. No UberLLM fee on requests. Adding credit by card costs 5.5% + $0.50.

How to use Tencent: Hy4 flash with the OpenAI SDK

With the OpenAI SDK, set the base URL to UberLLM and call Tencent: Hy4 flash with your existing code. Anthropic SDKs work against https://api.uberllm.dev/v1/messages.

python
from openai import OpenAI

client = OpenAI(
    base_url="https://api.uberllm.dev/v1",
    api_key="ull_your_key_here",
)

resp = client.chat.completions.create(
    model="tencent/hy4-flash",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)

Use Tencent: Hy4 flash in your apps

By API, Tencent: Hy4 flash answers on three addresses with the same UberLLM key and the model id tencent/hy4-flash: OpenAI chat completions at https://api.uberllm.dev/v1/chat/completions, the OpenAI Responses API at https://api.uberllm.dev/v1/responses and the Anthropic Messages API at https://api.uberllm.dev/v1/messages.

How do I use Tencent: Hy4 flash in Claude Code?

Claude Code reaches Tencent: Hy4 flash through the Anthropic-compatible address of UberLLM. Set ANTHROPIC_BASE_URL to https://api.uberllm.dev (with no /v1 at the end), ANTHROPIC_AUTH_TOKEN to your UberLLM key and ANTHROPIC_MODEL to tencent/hy4-flash[1m], then start claude. Set the opus, sonnet, haiku and subagent model variables to tencent/hy4-flash as well: a slot left unset keeps asking for a Claude model at Claude prices. The [1m] at the end of the id tells Claude Code that Tencent: Hy4 flash has a 1M-token context; without it Claude Code plans for 200,000 tokens.

bash
export ANTHROPIC_BASE_URL=https://api.uberllm.dev
export ANTHROPIC_AUTH_TOKEN=ull_your_key
export ANTHROPIC_MODEL='tencent/hy4-flash[1m]'
export ANTHROPIC_DEFAULT_OPUS_MODEL='tencent/hy4-flash'
export ANTHROPIC_DEFAULT_SONNET_MODEL='tencent/hy4-flash'
export ANTHROPIC_DEFAULT_HAIKU_MODEL='tencent/hy4-flash'
export CLAUDE_CODE_SUBAGENT_MODEL='tencent/hy4-flash'
claude

Claude Code calls: Anthropic Messages API https://api.uberllm.dev/v1/messages · Full Claude Code guide · Tencent: Hy4 flash in Claude Code

How do I use Tencent: Hy4 flash in Codex CLI?

Codex CLI reaches Tencent: Hy4 flash through the Responses API of UberLLM. In ~/.codex/config.toml, add a model provider with base_url set to https://api.uberllm.dev/v1 and wire_api = "responses", put your UberLLM key in the UBERLLM_API_KEY environment variable, and set model to tencent/hy4-flash. model_context_window is set to 1,048,576, the context size of Tencent: Hy4 flash, because Codex assumes 272,000 tokens for models outside the list of OpenAI models it knows.

toml
model = "tencent/hy4-flash"
model_provider = "uberllm"
model_context_window = 1048576
web_search = "disabled"

[model_providers.uberllm]
name = "UberLLM"
base_url = "https://api.uberllm.dev/v1"
env_key = "UBERLLM_API_KEY"
wire_api = "responses"

Codex CLI calls: OpenAI Responses API https://api.uberllm.dev/v1/responses · Full Codex CLI guide · Tencent: Hy4 flash in Codex CLI

How do I use Tencent: Hy4 flash in OpenCode?

OpenCode reaches Tencent: Hy4 flash through the OpenAI-compatible chat address of UberLLM. In ~/.config/opencode/opencode.json, add a provider named uberllm that uses the @ai-sdk/openai-compatible package with baseURL set to https://api.uberllm.dev/v1, list tencent/hy4-flash under its models, put your UberLLM key in the UBERLLM_API_KEY environment variable, then pick uberllm/tencent/hy4-flash with /models. The limit numbers are the context size and the largest reply of Tencent: Hy4 flash; OpenCode uses them to know when to compact a long session.

json
{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "uberllm": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "UberLLM",
      "options": {
        "baseURL": "https://api.uberllm.dev/v1",
        "apiKey": "{env:UBERLLM_API_KEY}"
      },
      "models": {
        "tencent/hy4-flash": {
          "name": "Tencent: Hy4 flash",
          "limit": {
            "context": 1048576,
            "output": 65536
          }
        }
      }
    }
  },
  "model": "uberllm/tencent/hy4-flash"
}

OpenCode calls: OpenAI chat completions https://api.uberllm.dev/v1/chat/completions · Full OpenCode guide · Tencent: Hy4 flash in OpenCode

How do I use Tencent: Hy4 flash in Cursor?

In Cursor Settings → Models, paste your UberLLM key into the OpenAI API Key field, turn on the OpenAI base URL override and enter https://api.uberllm.dev/v1, turn on Use API Key, then add tencent/hy4-flash as a custom model and select it in the chat model picker. This is for chat in Cursor: Tab completion keeps using the models Cursor provides.

OpenAI API Key
ull_your_key
OpenAI base URL override
https://api.uberllm.dev/v1
Custom model
tencent/hy4-flash

Cursor calls: OpenAI chat completions https://api.uberllm.dev/v1/chat/completions · Full Cursor guide · Tencent: Hy4 flash in Cursor

How do I use Tencent: Hy4 flash in Cline?

In the settings of Cline, set API Provider to OpenAI Compatible, Base URL to https://api.uberllm.dev/v1, paste your UberLLM key into OpenAI Compatible API Key and set Model ID to tencent/hy4-flash. Under Model Configuration, set Context Window Size to 1,048,576: Cline does not read the limits of a model on its own. In the same place, set Max Output Tokens to 65,536.

API Provider
OpenAI Compatible
Base URL
https://api.uberllm.dev/v1
OpenAI Compatible API Key
ull_your_key
Model ID
tencent/hy4-flash
Context Window Size
1048576
Max Output Tokens
65536

Cline calls: OpenAI chat completions https://api.uberllm.dev/v1/chat/completions · Full Cline guide · Tencent: Hy4 flash in Cline

How do I use Tencent: Hy4 flash in SillyTavern?

In SillyTavern, open API Connections, set API to Chat Completion and Chat Completion Source to Custom (OpenAI-compatible), enter https://api.uberllm.dev/v1 in Custom Endpoint (Base URL), paste your UberLLM key into Custom API Key, click Connect, then type tencent/hy4-flash in Enter a Model ID.

API
Chat Completion
Chat Completion Source
Custom (OpenAI-compatible)
Custom Endpoint (Base URL)
https://api.uberllm.dev/v1
Custom API Key
ull_your_key
Enter a Model ID
tencent/hy4-flash

SillyTavern calls: OpenAI chat completions https://api.uberllm.dev/v1/chat/completions · Full SillyTavern guide · Tencent: Hy4 flash in SillyTavern

How do I use Tencent: Hy4 flash in Janitor AI?

In Janitor AI, open a chat, click the gear icon and open API Settings. Choose Proxy and add a configuration with Model Name set to tencent/hy4-flash, Proxy URL set to https://api.uberllm.dev/v1/chat/completions and your UberLLM key in API Key. Click Save Settings, then refresh the page.

Config Name
UberLLM
Model Name
tencent/hy4-flash
Proxy URL
https://api.uberllm.dev/v1/chat/completions
API Key
ull_your_key

Janitor AI calls: OpenAI chat completions https://api.uberllm.dev/v1/chat/completions · Full Janitor AI guide · Tencent: Hy4 flash in Janitor AI

How do I use Tencent: Hy4 flash in Open WebUI?

In Open WebUI, go to Settings → Admin → Connections and add an OpenAI API connection with URL set to https://api.uberllm.dev/v1 and your UberLLM key in API Key. Under Advanced, add tencent/hy4-flash to Model IDs, and leave API Type on Chat Completions.

URL
https://api.uberllm.dev/v1
API Key
ull_your_key
Model IDs
tencent/hy4-flash
API Type
Chat Completions

Open WebUI calls: OpenAI chat completions https://api.uberllm.dev/v1/chat/completions · Full Open WebUI guide · Tencent: Hy4 flash in Open WebUI

Tencent: Hy4 flash API FAQ

Can I cap what a Tencent: Hy4 flash request costs?

Yes. A request costs what its provider charged; the listed price is $0.0261 input and $0.1047 output per million tokens, and a request can cost more when the cheaper providers are busy. Send provider.max_price with your most per million tokens: the request only goes to providers at or under it and is never billed above it. Each request is listed with its cost in Activity.

How do I call Tencent: Hy4 flash via API?

Use any OpenAI-compatible SDK: set the base URL to https://api.uberllm.dev/v1, your UberLLM API key, and model "tencent/hy4-flash". Anthropic SDKs work via https://api.uberllm.dev/v1/messages.

Is Tencent: Hy4 flash OpenAI-compatible on UberLLM?

Yes. Every model on UberLLM, including Tencent: Hy4 flash, is served through one OpenAI-compatible endpoint. Set the base URL and key in your existing client.

Why is Tencent: Hy4 flash cheaper on UberLLM?

UberLLM is a market: sellers offer Tencent: Hy4 flash capacity below its list price, and each request goes to a seller that can serve it. A request costs what its seller charged, UberLLM adds no fee to it, and every request is listed with its cost in Activity.

Are there other fees?

UberLLM adds no fee to model prices. A card fee of 5.5% + $0.50 is added when you buy credit. With the 5.5% added, UberLLM's Tencent: Hy4 flash price is still lower than every other provider in the table.

Embed this price

Show these prices on your own site. The table reads the current prices from UberLLM, so it stays up to date.

Script: the table sets its own height

<script async src="https://uberllm.dev/embed.js" data-models="tencent/hy4-flash"></script>

Plain iframe, for sites that allow no scripts

<iframe src="https://uberllm.dev/embed/prices?models=tencent/hy4-flash" title="AI model API prices" width="100%" height="127" loading="lazy" style="border:0;max-width:720px"></iframe>

Price badge for a README (Markdown)

[![Tencent: Hy4 flash API price on UberLLM](https://api.uberllm.dev/api/v1/public/badge/tencent/hy4-flash.svg)](https://uberllm.dev/models/tencent/hy4-flash?utm_source=embed&utm_medium=referral&utm_campaign=price-badge)

Every option is in the embed docs.

Compared with other providers: Best OpenRouter alternatives

More Tencent models