DeepSeek V3
DeepSeek V3Alternatives?
CheaperGPT-6 Lunamedium+2.5-12%$0.017Function calling only with none · Chat Completions+3
OpenGLM 5.3max+41.9+10,054%$2.01Memory (4-bit): 411 GB → 452 GB+4CheaperGPT-5.6 Lunanon-thinking+1-49%$0.01
CheaperLing 3.0 FlashthinkingOpensame-71%$0.06 / $0.18CheaperLing 3.0 Flash VLthinkingOpensame-71%$0.06 / $0.18GPT-6 Lunamedium+2.5-12%$0.017Function calling only with none · Chat Completions+3GPT-5.6 Lunanon-thinking+1-49%$0.01Ling 3.0 FlashthinkingOpensame-71%$0.06 / $0.18Ling 3.0 Flash VLthinkingOpensame-71%$0.06 / $0.18Ling 3.0 Flash FinthinkingOpensame-71%$0.06 / $0.18GPT-6 Lunamedium+2.5-12%$0.017Function calling only with none · Chat Completions+3
Claude Haiku 5.5low+12.6+24%$0.024Remove sampling parameters+5GPT-5.6 Lunahigh+2.5+123%$0.044
MiMo v2.6 FlashthinkingOpen+22.7+216%$0.062Pass back reasoning_content+3GPT-6.1 Sollow+30.8+562%$0.13Remove unsupported parameters+5GLM 5.3maxOpen+41.9+10,054%$2.01Memory (4-bit): 411 GB → 452 GB+4MiMo v2.6 ProthinkingOpen+34.8+574%$0.13Memory (4-bit): 411 GB → 615 GB+4DeepSeek V4.1 Flash 1017maxOpen+33.8+1,227%$0.26Memory (4-bit): 411 GB → 458 GB+5Ling 3.1 FlashOpen+33.3+4,961%$1.00
Step 5 PreviewthinkingOpen+33.3+5,097%$1.03web_search not available · Chat Completions+2DeepSeek V4.1 Flash 1017maxOpen+33.8+1,227%$0.26Memory (4-bit): 411 GB → 458 GB+5DeepSeek V4 Pro 0813non-thinkingOpen+1.5+1,700%$0.36Memory (4-bit): 411 GB → 990 GB+5DeepSeek V3.1 TerminusthinkingOpensame—$0.27 / $0.95DeepSeek V3 0324non-thinkingOpensame+7%$0.021DeepSeek V3.2 SpecialethinkingOpenn/a——DeepSeek V3.1non-thinkingOpenn/a—$0.25 / $0.95DeepSeek R1 0528 Qwen3 8BthinkingOpenn/a—$0.06 / $0.09Context: 128K → 33KR1 0528thinkingOpenn/a—$0.39 / $1.63All DeepSeek models →Run it yourself
estimateHistory
5 versionsBenchmarks
in CodingFAQ
How much does DeepSeek V3 cost?›
$0.28 per 1M input tokens and $0.42 per 1M output tokens; cached input $0.028 per 1M. A typical benchmark task costs about $0.02 at default effort.
Is DeepSeek V3 free to use?›
There is no free API; the cheapest paid price is $0.28 per 1M input tokens. The weights are open, so you can run it yourself.
How good is DeepSeek V3, and what is it best at?›
#329 of 334 in Chat & Knowledge, #75 of 132 in Coding, #117 of 133 in Agents & Tool Use, #102 of 195 in Writing & Language, #122 of 133 in Vision & Documents.
Is DeepSeek V3 better than Claude Sonnet 4.5?›
On Terminal-Bench 4.0, DeepSeek V3 scores 0 vs 0 — about the same. It is 96% cheaper per task.
How can I use DeepSeek V3?›
Through the API of DeepInfra, Novita.
What is the context window of DeepSeek V3?›
128K tokens, with up to 8K output tokens.
When was DeepSeek V3 released? Is there a newer version?›
Released 2024-12-26. It has been superseded by DeepSeek V3.1.
Is DeepSeek V3 open source?›
Yes, the weights are open.
Can I run DeepSeek V3 locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can DeepSeek V3 read images?›
No, it accepts text only.
What is DeepSeek V3?›
DeepSeek V3 is an open-weights language model from DeepSeek, released Dec 2024.
What are the best alternatives to DeepSeek V3?›
GPT-6 Luna (cheaper), GLM 5.3 (open weights).