tencent/hy4-flash

Model release OpenRouter 模型 Source language: Chinese

OpenRouter listed this model on 2026-11-16 (the listing date does not equal the model's official release date); context: 1,048,576 tokens; input price: $0.0437/million tokens; output price: $0.1756/million tokens; positioning (source description): Hy4 flash is a cost-efficient variant of [Hy4]( from Tencent, served with roughly a quarter of the…

Full text

Tencent: Hy4 flash

tencent/hy4-flash

Compare

Hy4 flash is a cost-efficient variant of Hy4Opens in new tab from Tencent, served with roughly a quarter of the flagship's parameter count for lower latency and cost. It targets code assistance, agent pipelines, document and chart comprehension, and high-volume routine automation, with the same context and output limits as Hy4.

Modalities

In / out price

50% off

$0.035 / $0.1405per 1M

Context

1.0M

Released

Nov 16, 2026

Compare

Providers

This model is hosted by one provider. OpenRouter forwards every request without routing.

Latency / throughput

50% off

$0.07$0.035$0.281$0.1405$0.003$0.00152.68s79 tok/s

100.00%

Provider50% offInput / Output /M

Input $0.035 / Output $0.140550% off

79 tok/s100.00% uptime

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Weighted average

Input

$0.006795/M tokens

Output

$0.2783/M tokens

Hy4 flash — Price history

Price history

No effective price data for this selection

$0.00679$0.27894.3%100.0%

ProviderInput / Output /M

Token share

Effective in $0.00679 / Effective out $0.278

Token share

100.0%

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

79tok/s

P50, best across providers

Latency

2.68s

P50, best provider

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Uptime (3d)The model was reachable. Request routed to a provider.

100.00%

Availability (3d)The model returned inference from any provider. Errors and empty responses count against it.

99.02%

Availability over the last 3 days

Last 72 hours

Availability 99.02%

3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability

99.05%

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 per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and provider routing options.

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.

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.

91.6Mtokens

2.

DeepSeek Harness

new

32.1Mtokens

3.

omp

new

11.5Mtokens

4.

Codex

A coding agent that helps you build and ship with AI

11.1Mtokens

5.

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.

10.1Mtokens

Rest of OpenRouter

21.8B

Top 5 Apps

156M

Activity

Token volume and request traffic to this model over time.

API

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.

Not currently available through EU in-region routing. In-region routing docs

Frequently asked questions

Hy4 flash is a cost-efficient variant of Hy4 from Tencent, served with roughly a quarter of the flagship's parameter count for lower latency and cost. It targets code assistance, agent pipelines, document and chart comprehension, and high-volume routine automation, with the same context and output limits as Hy4.

Hy4 flash costs $0.035/M input tokens and $0.1405/M output tokens, with separate rates for Cache Read at $0.0015/M tokens.

Hy4 flash has a 1,048,576 token context window. It supports up to 65,536 completion tokens.

Yes. Hy4 flash accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.

Hy4 flash accepts text and images as input and returns text.

Hy4 flash is served by 1 provider on OpenRouter: Tencent Cloud.

Hy4, Hy4 preview, Hy-MT2-1.8B and 4 more are other text models from Tencent.

Hy4 flash was released on November 16, 2026.

Sources

← Back to the daily brief