Home / Compare / DeepSeek R1 0528 vs Hy4 Preview DeepSeek R1 0528 vs Hy4 Preview Close to a tie overall. DeepSeek R1 0528 costs 27% less for the same work.
Model AClaude Fable 5 Claude Haiku 4.5 Claude Opus 4.7 Claude Opus 4.8 Claude Opus 5 Claude Opus 5.5 Claude Sonnet 4.6 Claude Sonnet 5 Claude Sonnet 5.5 DeepSeek R1 0528 DeepSeek V3 DeepSeek V3.1 DeepSeek V3.2 DeepSeek V4 Flash DeepSeek V4 Flash 0731 DeepSeek V4 Pro 0813 DeepSeek V4.1 Flash Gemini 2.5 Flash Gemini 2.5 Pro Gemini 3.1 Flash Lite Gemini 3.1 Pro Gemini 3.5 Flash Gemini 3.7 Flash Gemma 3 12B IT Gemma 3 27B IT Gemma 3 4B IT Gemma 4 26B A4B IT Gemma 4 31B IT GLM 4.6 GLM 4.7 GLM 5.2 GLM 5.3 GLM 5.3 Flash GPT OSS 120B GPT OSS 20B Granite 4.2 8B Hy4 Preview Inkling Small Kimi K2.6 Kimi K3 Ling 3.1 Flash Llama 3.3 70B Instruct Turbo Llama 4 Scout 17B 16E Instruct Meta Llama 3.1 70B Instruct Turbo Meta Llama 3.1 8B Instruct Turbo MiMo V2.6 Flash MiMo V2.6 Pro MiniMax M3 Mistral Small 24B Instruct 2501 Mistral Small 3.2 24B Instruct 2506 Muse Glimmer 30B NVIDIA Nemotron 3 Super 120B A12B NVIDIA Nemotron 3 Ultra 550B A55B NVIDIA Nemotron 3.5 Lightning Phi 4 Qwen2.5 72B Instruct Qwen3 235B A22B Instruct 2507 Qwen3 30B A3B Qwen3 32B Qwen3 Coder 480B A35B Instruct Turbo Qwen3 Next 80B A3B Instruct Qwen3 VL 235B A22B Instruct Qwen3.5 27B Qwen3.5 35B A3B Qwen3.5 397B A17B Qwen3.5 9B Qwen3.6 27B Qwen3.6 35B A3B Qwen3.7 Max Qwen3.8 27B Qwen3.8 Flash Qwen3.8 Max Seed 2.0 Pro Step 5 Preview DeepSeek R1 0528
by DeepSeek · #29 of 67 overall
Coming soon · price at launch
Context 160K
Input / 1M $0.50
Output / 1M $2.15 Model BClaude Fable 5 Claude Haiku 4.5 Claude Opus 4.7 Claude Opus 4.8 Claude Opus 5 Claude Opus 5.5 Claude Sonnet 4.6 Claude Sonnet 5 Claude Sonnet 5.5 DeepSeek R1 0528 DeepSeek V3 DeepSeek V3.1 DeepSeek V3.2 DeepSeek V4 Flash DeepSeek V4 Flash 0731 DeepSeek V4 Pro 0813 DeepSeek V4.1 Flash Gemini 2.5 Flash Gemini 2.5 Pro Gemini 3.1 Flash Lite Gemini 3.1 Pro Gemini 3.5 Flash Gemini 3.7 Flash Gemma 3 12B IT Gemma 3 27B IT Gemma 3 4B IT Gemma 4 26B A4B IT Gemma 4 31B IT GLM 4.6 GLM 4.7 GLM 5.2 GLM 5.3 GLM 5.3 Flash GPT OSS 120B GPT OSS 20B Granite 4.2 8B Hy4 Preview Inkling Small Kimi K2.6 Kimi K3 Ling 3.1 Flash Llama 3.3 70B Instruct Turbo Llama 4 Scout 17B 16E Instruct Meta Llama 3.1 70B Instruct Turbo Meta Llama 3.1 8B Instruct Turbo MiMo V2.6 Flash MiMo V2.6 Pro MiniMax M3 Mistral Small 24B Instruct 2501 Mistral Small 3.2 24B Instruct 2506 Muse Glimmer 30B NVIDIA Nemotron 3 Super 120B A12B NVIDIA Nemotron 3 Ultra 550B A55B NVIDIA Nemotron 3.5 Lightning Phi 4 Qwen2.5 72B Instruct Qwen3 235B A22B Instruct 2507 Qwen3 30B A3B Qwen3 32B Qwen3 Coder 480B A35B Instruct Turbo Qwen3 Next 80B A3B Instruct Qwen3 VL 235B A22B Instruct Qwen3.5 27B Qwen3.5 35B A3B Qwen3.5 397B A17B Qwen3.5 9B Qwen3.6 27B Qwen3.6 35B A3B Qwen3.7 Max Qwen3.8 27B Qwen3.8 Flash Qwen3.8 Max Seed 2.0 Pro Step 5 Preview Coming soon · price at launch
Context 1M
Input / 1M $0.83
Output / 1M $2.50 Better overall
About even
Grade 70.6 vs 69.3
Cheaper
DeepSeek R1 0528
27% less, $0.91 vs $1.25 blended
Larger context
Hy4 Preview
160K vs 1M tokens
Head to head Public benchmarks. Longer is better; each value links to its source.
LMArena Text Elo-style rating · LMArena (CC BY 4.0) · Oct 15, 2026 Hy4 Preview Hy4 Preview: —
DeepSeek R1 0528 DeepSeek R1 0528: —
Hy4 Preview Hy4 Preview: —
Aider Polyglot % of exercises solved · Aider (aider.chat) · Jun 6, 2025 Hy4 Preview Hy4 Preview: —
Hy4 Preview Hy4 Preview: —
DeepSeek R1 0528 DeepSeek R1 0528: —
LiveCodeBench pass@1, % · LiveCodeBench · May 29, 2025 · reference Hy4 Preview Hy4 Preview: —
DeepSeek R1 0528 $186 /month
Hy4 Preview $267 /month
DeepSeek R1 0528 saves you $80.84 a month at this usage, $970 a year.
At a glance Attribute DeepSeek R1 0528 Hy4 Preview Made by DeepSeek Availability Coming soon Coming soon Overall grade Excellent · 70.6 Not rated Overall rank #29 of 67 Not ranked Input price $0.50 per 1M $0.83 per 1M Output price $2.15 per 1M $2.50 per 1M Context window 163,840 tokens 1,048,576 tokens Reasoning levels No No Reads images No No Model ID deepseek-r1-0528 hy4-preview
Try both with one key Same endpoint, same key, both hosted in the USA. Change one word to switch models, in Claude Code, Cursor, Cline or your own code.
Get your API key # Ask either model the same thing
curl https://fullsendai.com/v1/chat/completions \
-H "Authorization: Bearer $FULLSEND_API_KEY " \
-d '{"model": "deepseek-r1-0528", "messages": [...]}'
# …then swap one word
-d '{"model": "hy4-preview", "messages": [...]}' Questions Is DeepSeek R1 0528 or Hy4 Preview better? They grade within two points of each other (70.6 and 69.3), so pick on price and the benchmarks that match your work.
Which is cheaper, DeepSeek R1 0528 or Hy4 Preview? DeepSeek R1 0528: $0.50 in and $2.15 out per million tokens, against $0.83 and $2.50 through FullsendAI.
Which has the larger context window? Hy4 Preview, with 1,048,576 tokens.
Can I use both with one API key? Yes, once they launch: both are coming soon, at the prices shown, and both will use the same FullsendAI key.
Scores: LMArena (CC BY 4.0), Aider (aider.chat), SWE-bench, Terminal-Bench, LiveCodeBench, and model makers’ published results where marked v. Prices are FullsendAI’s, per million tokens. Data as of Oct 28, 2026.
