LimitDigest
Home / Compare / AI models / Hunyuan Hy4 vs Qwen4-Max

Hunyuan Hy4 vs Qwen4-Max

Official Tencent Hunyuan and Qwen API prices and LMArena scores, checked 2026-11-20. Add up to 2 more models to compare 4.

Verdict

Hunyuan Hy4 costs less; Qwen4-Max wins more LMArena tasks.

Hunyuan Hy4 is 1.8x cheaper on input and output. Qwen4-Max scores 42 points higher for coding. Across 2 shared LMArena tasks, Qwen4-Max leads 2 to 0. A medium month (20M input + 5M output tokens) costs $29.19 on Hunyuan Hy4 and $52.50 on Qwen4-Max.

  • Pick Hunyuan Hy4 if you want the lower bill ($29.19 vs $52.50 for a medium month) or you reuse long prompts (cached input $0.042 vs $0.075).
  • Pick Qwen4-Max if you care most about coding (+42) and agent tasks (+3).
Sample month

Medium: 20M input + 5M output tokens a month at list price (short-context rate, no caching or batch discounts).

Hunyuan Hy4vsQwen4-Max
Price per 1M tokens
Input$0.834 (better)$1.50
Cached input$0.042 (better)$0.075
Output$2.50 (better)$4.50
Sample month, medium$29.19 (better)$52.50
Context
Context window1M1M
Quality (LMArena relative score, out of 100)
Coding2870 (better)
Chatn/an/a
Creative writingn/an/a
Roleplay and charactersn/an/a
Reasoning and mathn/an/a
Visionn/an/a
Long documentsn/an/a
Cheap bulk and agents3538 (better)

Marked side is better: lower for prices, higher for context and scores. Bars are scaled to the larger of the two.

Spec
Hunyuan Hy4
Qwen4-Max
Price per 1M tokens
Input$0.834$1.50
Cached input$0.042$0.075
Output$2.50$4.50
Blend 3:1$1.25$2.25
Sample month, medium$29.19$52.50
Context
Context window1M tokens1M tokens
Quality (LMArena, out of 100)
Coding28/100 #22 of 5870/100 #9 of 58
ChatNot rankedNot ranked
Creative writingNot rankedNot ranked
Roleplay and charactersNot rankedNot ranked
Reasoning and mathNot rankedNot ranked
VisionNot rankedNot ranked
Long documentsNot rankedNot ranked
Cheap bulk and agents35/100 #17 of 4538/100 #14 of 45
Details
ProviderTencent HunyuanQwen
API model idhy4qwen4-max
NotesSingapore region list price. Tencent bills Hy4 at 50% of list ($0.417 in, $1.251 out) through Dec 31, 2026 (Beijing time). Open weights (Hy4, Hy4-FP8 and Hy4 base, 770B total, 49B active) released on Hugging Face Nov 20, 2026 under the Tencent Hy License.International (Singapore), launched Nov 16, 2026. List price for all prompts up to 1M tokens. Cache read $0.075; 5-minute cache write $1.875, 1-hour $3. Closed weights.
Sources
Last checked2026-11-202026-11-20
Official pricingTencent Hunyuan pricingQwen pricing

API prices in USD per 1M tokens from each provider's official pricing page. Blend 3:1 = (3 x input + output) / 4. Sample month = stated input and output tokens at the list price, no caching. Quality: relative score out of 100 on each LMArena leaderboard (100 = top model we price on that board, n/a = not ranked there), data licensed CC BY 4.0. See how we pick.

Where each one ranks on LMArena

Relative score out of 100 on each leaderboard (100 = the top model we price there), with the rank among the models from our API price table that appear on that board.

  • Coding (Code Arena): Hunyuan Hy4 #22 of 58 (28/100), Qwen4-Max #9 of 58 (70/100)
  • Chat (Text Arena): Hunyuan Hy4 not ranked, Qwen4-Max not ranked
  • Creative writing (Text Arena creative writing): Hunyuan Hy4 not ranked, Qwen4-Max not ranked
  • Roleplay and characters (Text Arena multi-turn): Hunyuan Hy4 not ranked, Qwen4-Max not ranked
  • Reasoning and math (Text Arena math): Hunyuan Hy4 not ranked, Qwen4-Max not ranked
  • Vision (Vision Arena): Hunyuan Hy4 not ranked, Qwen4-Max not ranked
  • Long documents (Document Arena): Hunyuan Hy4 not ranked, Qwen4-Max not ranked
  • Cheap bulk and agents (Agent Arena): Hunyuan Hy4 #17 of 45 (35/100), Qwen4-Max #14 of 45 (38/100)

Pricing details from the official pages

Hunyuan Hy4 lists $0.834 input, $2.50 output, $0.042 cached input per 1M tokens on Tencent Hunyuan pricing. Qwen4-Max lists $1.50 input, $4.50 output, $0.075 cached input per 1M tokens on Qwen pricing. Prices checked 2026-11-20.

  • Hunyuan Hy4: Singapore region list price. Tencent bills Hy4 at 50% of list ($0.417 in, $1.251 out) through Dec 31, 2026 (Beijing time). Open weights (Hy4, Hy4-FP8 and Hy4 base, 770B total, 49B active) released on Hugging Face Nov 20, 2026 under the Tencent Hy License.
  • Qwen4-Max: International (Singapore), launched Nov 16, 2026. List price for all prompts up to 1M tokens. Cache read $0.075; 5-minute cache write $1.875, 1-hour $3. Closed weights.

Sample monthly bill at list price, no caching: Light (2M input + 0.5M output tokens): $2.92 vs $5.25. Medium (20M input + 5M output tokens): $29.19 vs $52.50. Heavy (200M input + 50M output tokens): $291.85 vs $525.

FAQ

Is Hunyuan Hy4 cheaper than Qwen4-Max?

Hunyuan Hy4 costs $0.834 input and $2.50 output per 1M tokens; Qwen4-Max costs $1.50 and $4.50. For a medium month (20M input + 5M output tokens) Hunyuan Hy4 is cheaper: $29.19 vs $52.50.

Which is better for coding, Hunyuan Hy4 or Qwen4-Max?

On LMArena's Code Arena Hunyuan Hy4 scores 28/100 (#22 of 58) and Qwen4-Max 70/100 (#9 of 58), so Qwen4-Max is ahead by 42 points.

Which has the bigger context window?

Hunyuan Hy4: 1M tokens. Qwen4-Max: 1M tokens. Both list the same window.

How much do Hunyuan Hy4 and Qwen4-Max cost per month?

Light (2M input + 0.5M output tokens): $2.92 vs $5.25. Medium (20M input + 5M output tokens): $29.19 vs $52.50. Heavy (200M input + 50M output tokens): $291.85 vs $525. Pick your own token counts in the plan vs API calculator.

Where do these numbers come from?

Prices come from each provider's official pricing page, checked daily. Quality is the relative score on the LMArena leaderboard dataset, licensed CC BY 4.0. Where a model is not ranked we show n/a.

Sources

Related