R1 0528
R1 0528Alternatives?
CheaperClaude Haiku 5.5xhigh+49%-71%$0.12Remove sampling parameters+5
BetterGemini 3.1 Flash Litehigh+21%-19%$0.06OpenDeepSeek V4 Pro 0813max+49%+185%$0.67Memory (4-bit): 411 GB → 990 GB+5
CheaperGPT-6 Lunamax+49%-71%$0.068Function calling only with none · Chat Completions+3CheaperGPT-5.6 Lunamax+48%-35%$0.18Claude Haiku 5.5xhigh+49%-71%$0.12Remove sampling parameters+5GPT-6 Lunamax+49%-71%$0.068Function calling only with none · Chat Completions+3GPT-5.6 Lunamax+48%-35%$0.18
GLM 5.3 FlashmaxOpen+41%-66%$0.28Defaults to max · Self-hosted+4
Qwen3.7 Plusunstated+41%-19%$0.32 / $1.28Gemini 3.1 Flash Litehigh+21%-19%$0.06GPT-6 Lunamax+49%-71%$0.068Function calling only with none · Chat Completions+3Claude Haiku 5.5high+46%-71%$0.079Remove sampling parameters+5GPT OSS 120BhighOpen+34%-91%$0.092GPT-5.6 Terralow+34%+547%$0.14Prompts with >272K input tokensDeepSeek V4 Pro 0813maxOpen+49%+185%$0.67Memory (4-bit): 411 GB → 990 GB+5
Kimi K2.6unstatedOpen+45%+146%$0.95 / $4Memory (4-bit): 411 GB → 616 GBKimi K2.7 CodeunstatedOpen+44%+146%$0.95 / $4Memory (4-bit): 411 GB → 616 GB+1GLM 5.3 FlashmaxOpen+41%-66%$0.28Defaults to max · Self-hosted+4GLM 5.1unstatedOpen+41%+209%$1.40 / $4.40Memory (4-bit): 411 GB → 452 GBDeepSeek V4 Pro 0813maxOpen+49%—$0.67Memory (4-bit): 411 GB → 990 GB+5DeepSeek R1 Distill Qwen 32BOpen-16%—$0.27 / $0.27No strict JSONDeepSeek R1 Distill Llama 70BOpen-23%—$0.70 / $0.80DeepSeek V3unstatedOpen-26%—$0.28 / $0.42DeepSeek R1 0528 Qwen3 8BunstatedOpen-34%—$0.06 / $0.09Context: 128K → 33KDeepSeek V3 0324unstatedOpen-43%—$0.24 / $0.90DeepSeek V4.1 Flash 1017maxOpenn/a—$0.26Memory (4-bit): 411 GB → 458 GB+5DeepSeek V3.2 SpecialethinkingOpenn/a——All DeepSeek models →Run it yourself
estimateBenchmarks
in Chat & KnowledgeFAQ
How much does R1 0528 cost?›
$0.39 per 1M input tokens and $1.63 per 1M output tokens (cheapest host: Featherless).
Is R1 0528 free to use?›
There is no free API; the cheapest paid price is $0.39 per 1M input tokens. The weights are open, so you can run it yourself.
How good is R1 0528, and what is it best at?›
#141 of 334 in Chat & Knowledge, #105 of 239 in Coding, #132 of 242 in Agents & Tool Use, #79 of 195 in Writing & Language.
Is R1 0528 better than Qwen3 32B?›
On OTIS Mock AIME 2024 2025, R1 0528 scores 66.4 vs 66.9 — about the same.
How can I use R1 0528?›
Through the API of DeepInfra, Featherless, Novita, SiliconFlow, StreamLake.
What is the context window of R1 0528?›
128K tokens, with up to 33K output tokens.
When was R1 0528 released? Is there a newer version?›
Released 2025-05-28. It is the current version in its line.
Is R1 0528 open source?›
Yes, the weights are open (MIT licence).
Can I run R1 0528 locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can R1 0528 read images?›
No, it accepts text only.
What is R1 0528?›
R1 0528 is an open-weights language model from DeepSeek, released May 2025.
What are the best alternatives to R1 0528?›
Claude Haiku 5.5 (cheaper), Gemini 3.1 Flash Lite (better), DeepSeek V4 Pro 0813 (open weights).