Tencent Hy4 Flash

tencent/hy4-flash

low-cost Hy4 for coding, reasoning & agentic work.

cmd --model tencent/hy4-flash
Intelligence index
not yet scored
Coding index
not yet scored
Input
$0.07 /M
Output
$0.28 /M
Cache read
$0.003 /M
Agent-loop cost
$0.02 /M in
Context window
1.02M tokens
Released
November 16, 2026
Modalities
→

vs. the lineup

Tencent Hy4 Flash beside its stablemates and nearest rivals. The ◆ marks the best value in each column across every row shown.

pin a rival:
ModelIntelligenceCodingInput $/MOutput $/MBlended $/MContext
Tencent Hy325.358.8$0.14$0.58$0.25262K
Claude Haiku 4.515.4—$1$5$2200K
Tencent Hy4 Flash ◆——$0.07◆$0.28◆$0.12◆1.02M
Tencent Hy4 Preview——$0.83$2.50$1.251.05M◆
DeepSeek V4 Pro (latest)pinned36◆68.8$0.66$1.98$0.991M
DeepSeek V4 Flash (latest)pinned3469.1◆$0.15$0.60$0.261M

usage calculator

How far a month of credits goes on Tencent Hy4 Flash.

Input tokensfresh prompt
800
Output tokensmodel reply
180
Cache read tokensre-read context
50K
cost / request $0.0003 · in $0.07 · out $0.28 · cache $0.003 per M
fresh input 22%output 20%cache reads 58%
Requests / 30 days
23K
$6 credits ÷ $0.0003 per request
~4.7K quick fixes~935 bug fixes~156 feature PRs

what real work costs

Real coding tasks priced end to end on Tencent Hy4 Flash, from a quick lookup to a full-repo agent run.

One agent task
$0.0069
180K in at 75% cache hit, 12K out
What you pay
$0.04 /M
all-in across every token that task touched
Sticker input
$0.07 /M
cache reads bill at $0.003 /M instead
TaskTokens in · outTencent Hy4 FlashClaude Haiku 4.5
Quick lookup / one-liner8K · 1K$0.0004$0.0065
Review a 500-line PR60K · 4K$0.0025$0.04
Fix a bug (agent loop)180K · 12K$0.0069$0.12
Refactor a module320K · 20K$0.01$0.21
Full-repo agent run900K · 45K$0.03$0.49

frequently asked

How much does Tencent Hy4 Flash cost?
$0.07/M input and $0.28/M output, cache reads $0.003/M. In an agent loop most input is cache-read, so the effective input rate is about $0.02/M.
Which plan do I need?
Available on Go and above.
How do I switch to it?
Run cmd --model tencent/hy4-flash, or type /model in a session and pick it. You can switch mid-session without losing context.

Ship code that matches your taste

Command Code is the AI coding agent that continuously learns your taste. Start for $1.

Benchmarks from Artificial Analysis (v4.3)commandcode.ai/models/hy4-flash