Rincian Model
Ngeunaan
Z.ai: GLM 5.2 (batch) iku a chat model kang dibangun déning Z-Ai. Ing basa Jawa, tembung "kawula" bisa dijupuk saka tembung "kawula" lan "kawula". Routed through external models - ~1,136 tokens per message (50% markup over upstream cost).
Nggunakake API
curl https://api.free.ai/v1/chat/ \
-H "Authorization: Bearer YOUR_KEY" \
-d '{"model":"z-ai/glm-5.2:batch"}'
Ngbandingake
FAQ
Z.ai: GLM 5.2 (batch) iku a chat model kang dibangun déning Z-Ai. Ing basa Jawa, tembung "kawula" bisa dijupuk saka tembung "kawula" lan "kawula". Routed through external models - ~1,136 tokens per message (50% markup over upstream cost).
Z.ai: GLM 5.2 (batch) bisa dianggo saé pikeun pawarta umum, bantuan nulis, brainstorming, bantuan kode, lan analisis. Coba contona di luhur pikeun ningali gayana.
Kira-kira 1,136 token per rata-rata pesen. Akun bébas meunang 30,000-token pool poéan nu ngawengku obrolan self-hosted; model premium mayar-sakumaha-digunakeun, kalawan token top-up ti $1.
It depends on the task. /chat/compare/ lets you send the same prompt to Z.ai: GLM 5.2 (batch) and any other model side-by-side - comparison is the fastest way to decide.
Ya. Output iku awakmu — Free.ai ora nganggep hak apa wae sing sampeyan hasilake.
1,048,576 tokens.
Ngajawab stream token-by-token dina ~1 detik. Total waktos tanggapan gumantung kana panjangna jeung ukuran model - model alit stream gancang, model wates ngaganti laju pikeun jero.
Ya. Pamaké anu geus ngadaptar ningali unggal obrolan dina /account/?tab=history. Anjeun ogé bisa babagi salinan hiji-paling tina sagala obrolan ku tombol Bagikeun.
Free.ai teu ngalatih model dina obrolan anjeun. Model anu dihost sorangan tetep dina GPU urang. Model Premium ngaliwatan panyadia upstream pikeun inference.
Ya. POST ka /v1/chat/ nganggo model="z-ai/glm-5.2:batch" lan array pesen. Streaming SSE didukung. Referensi lengkap: /api/.
Z.ai: GLM 5.2 (batch) nyaéta model premium anu dilayani ku panyadia luar, janten self-hosting henteu sayogi. Free.ai ngaekspos éta ngalangkungan harga anu didasarkeun kana token.
Akun bébas meunang 30,000-token pool poéan. Nalika éta réngsé, token top-ups dimimitian dina $ 1, pay-as-you-go - teu aya subscription diperlukeun.
Chat karo Z.ai: GLM 5.2 (batch)
Apa Z.ai: GLM 5.2 (batch)?
Z.ai: GLM 5.2 (batch) iku a chat model kang dibangun déning Z-Ai. Ing basa Jawa, tembung "kawula" bisa dijupuk saka tembung "kawula" lan "kawula". Routed through external models - ~1,136 tokens per message (50% markup over upstream cost).
Kenapa nggunakake Z.ai: GLM 5.2 (batch) kanggo chatting?
Jawaban streaming
Jawaban stream token-by-token dina ~1 detik ti pencét Kirim. Teu aya tunggu kosong.
Sejarah sing disimpan
Para pangguna sing ngadaptar bisa ndeleng saben obrolan ing /account/?tab=history kanthi link share siji klik.
Ngbandingake sisih-sisih
Diantarana aya 4 jinis, nyaéta: 1.
Commercial use OK
Output milik anjeun. Gunakeunana dina aplikasi, iklan, dokumén, atawa naon waé tanpa aya nu nyebutkeun.
Contoh pitakon
Rencana
Premium chatting. Biaya iku saben pesen — asring ~1136 Chatting self-hosted dijalankeun bébas dina kolam renang 30,000-token sapopoé anjeun; model premium dibayar-sakumaha- anjeun-go, kalayan top-ups ti $ 1.
Ngbandingake karo alternatif
Lihat kabeh model chatting → · Ngbandingake nganti 4 model chatting kang padha-padha →