Iminingwane yemodeli
Malunga
DeepSeek-R1 7B (7B) yi a chat model eyenziwe ngu DeepSeek. Ivuma kuze kube yi 32K izithonjana zesimo ngasinye sombuzo. Onamandla kakhulu ku Reasoning, math, step-by-step thinking. I-self-hosted ku-Free.ai GPUs - isebenza ngokukhululekile ngaphezu kwe-token pool yakho yansuku zonke (100 tokens umlayezo ngamunye). Kukhishwa ngaphansi kwe-MIT — ukusetshenziswa kokuthengiswa kwempahla kuvunyelwe ku-Free.ai.
Sebenzisa nge-API
curl https://api.free.ai/v1/chat/ \
-H "Authorization: Bearer YOUR_KEY" \
-d '{"model":"deepseek-r1-7b"}'
Imibuzo ebuzwa kaningi
DeepSeek-R1 7B (7B) yi a chat model eyenziwe ngu DeepSeek. Ivuma kuze kube yi 32K izithonjana zesimo ngasinye sombuzo. Onamandla kakhulu ku Reasoning, math, step-by-step thinking. I-self-hosted ku-Free.ai GPUs - isebenza ngokukhululekile ngaphezu kwe-token pool yakho yansuku zonk
DeepSeek-R1 7B isebenza kahle ku-Reasoning, math, step-by-step thinking. Zama isibonelo sokubanjwa phezulu ukuze ubone indlela yayo.
Kuyi 100 ama-token umlayezo ngamunye. Ama-akhawunti amahhala athola i-30,000-token pool ngosuku oluhlanganisa ukuxoxa okuhlelwe ngokwezifiso; amamodeli aphezulu akhokhelwa-njengoba-uhamba, nge-token top-ups kusuka ku-$1.
Kuxhomekeka kumsebenzi. /incoko/uthelekiso/ ukuvumela ukuthi uthumele isiphakamiso esifanayo ku DeepSeek-R1 7B nanoma iyiphi enye imodeli ebhekene ne-side-by-side — uthelekiso yindlela ekhawulela kakhulu yokucabanga.
Yebo. Izingeniso ziyokho — Free.ai ayisebenzisi ilungelo nganoma yini oyenzayo.Imodeli engezansi yi MIT-licensed.
Ama-32,768 ama-token.
Iphendula umsuka we-token-by-token ngaphakathi ~1 sekondi. Isikhathi sokubuyiselwa konke sixhomekeke kude futhi kubukhulu bemodeli — amamodeli amancane asakazeka ngokushesha, amamodeli esifunda ahamba ngokushesha nge-deepness.
Yebo. Abasebenzisi abangeniswe babona yonke ingxoxo ku /account/?tab=history. Ungabelana futhi ngekhophi elinkiwe ngayinye yenoma iyiphi ingxoxo nge-Share button.
Free.ai ayiqeqeshi amamodeli emidlalweni yakho. Amamodeli ahlala e-GPUs ethu. Amamodeli aphezulu ahamba ku-upstream provider for inference.
Yebo. POST ku /v1/chat/ ngemodeli "deepseek-r1-7b" kanye nomyalezo we-array. Ukusakazwa kwe-SSE kuxhaswe. Ubufakazi obuphelele: /api/.
DeepSeek-R1 7B is MIT-licensednge 7B amapharamitha. See /models/deepseek-r1-7b/ for setup notes and our open-source repos at github.com/freeaigit.
Ama-akhawunti amahhala athola i-30,000-token ye-pool yansuku zonke. Uma lokhu kudlula, i-token top-ups iqala ku-$ 1, i-pay-as-you-go - akukho ubhaliso odingekayo.