Free.ai (self-hosted) ~100 tokens/msg

Àwọn ìṣàmúlò-ètò

Lance 3B (unified)

Òkè! Lance 3B (unified). Fẹ̀ẹ̀ ohunkohun.

Ṣàfikún àgbèwọlé rẹ̀ láti inú Claude, GPT, àti Gemini tí a bá fi pamọ́

Àwọn Àtòjọ-ẹ̀yàn

Ààyè-iṣẹ́ Free.ai (self-hosted)

Tí a fi ṣẹ̀dà ByteDance

Àwọn Multimodal

Àwọn Àkọ́lé 32768 tokens

Àwọn Ìgúnrégé ~100 tokens/msg · Àwọn ààyè-iṣẹ́

Ààyè-iṣẹ́

Lance 3B (unified) ni an Àwọn ìṣàmúlò-ètò ti a ṣe nipasẹ ByteDance. O ti wa ni Cross-task research, prototyping pipelines that need image + video + edit + VQA from one model, "one model, four tasks" demos. Apache 2.0, commercial use OK.. Ààyè àìṣàfilọ́lẹ̀ fún ara rẹ̀ ní àwọn GPUs Free.ai — láàyè láti pàtó àwọn ààyè àìṣàfilọ́lẹ̀ rẹ̀ ní ọjọ́ (100 ààyè Ìlò). Ti fi silẹ labẹ Apache 2.0 - lilo iṣowo ti gba laaye lori Free.ai.

Lò nípa API

curl https://api.free.ai/v1/chat/ \

                      -H "Authorization: Bearer YOUR_KEY" \

                      -d '{"model":"lance-3b"}'

Àwọn Àkọsílẹ̀ API

Àwọn ìṣàfarawé

Àwọn Àtòjọ-Ìtàn

Lance 3B (unified) tí n ṣiṣẹ́ láti lè lò fún Cross-task research, prototyping pipelines that need image + video + edit + VQA from one model, "one model, four tasks" demos. Apache 2.0, commercial use OK.. Jẹ́ àwọn àkóónú àwọn ààtò àwọn ìṣàmúlò-ètò tí o wa ní ààtò̀ àwọn ààtò.

About 100 tokens per average message. Free accounts get a 30,000-token daily pool that covers self-hosted chat; premium models are pay-as-you-go, with token top-ups from $1.

O dá lorí iṣẹ́. /ìgbègbè/ìdàkọ́/ gbá ọ̀wọ́ láti fi àwọn ààtòjútó tí a tí kọ́ nípa Lance 3B (unified) àti àwọn módè̀lì mìíràn - ìdákọ́ nípa àwọn ààtòjútó nípa àwọn ààtòjútó.

Ya. Àwọn ìṣàfihàn nípa rẹ̀ ní - Free.ai kò ní àwọn ẹ̀tọ̀ láti se ohunkohun tí o bá ṣẹ̀dà.Módè́lì tí a fi pamọ́ ni Apache 2.0-licensed.

Àwọn àwọn àyọkà 32,768.

Àwọn ìṣàfihàn ààyè-iṣẹ́ ààyè-iṣẹ́-nínu-àyàtòkè-nínu-àyàtòkè nínú sékètì ~1. Àwọn ààyè-iṣẹ́ ìgbà ìṣàfihàn ní pàtó nínú ìgbà atí ìwọ̀n àwọn móòdù - àwọn móòdù kéré ní ìṣàfihàn láàyè-iṣẹ́, àwọn móòdù ààyè-iṣẹ́ ìṣàfihàn láàyè-iṣẹ́ fún ìgbà ìsàlẹ̀-ilà.

Ya. Àwọn òǹlò tí a tí fi pamọ́ láti wò gbogbo àkọ́lé nínú /account/?tab=history. O lè gbọ́ àkọ́lé kan tí a fi líǹkì kan pamọ́ sípa bọ́tìnì Àwọn Àkọ́lé.

Free.ai kò bá àwọn àwòrán pamọ́ sínú àwọn àkọlé rẹ̀. Àwòrán tí a pamọ́ fún ara wa ní àwọn GPÙ wa. Àwòrán àwọn àwòrán àwọn àwọn àwòrán àwọn àwòrán àwọn àwòrán àwọn àwòrán

Ya. POST si /v1/gbàkọ́/ pẹlú àwọn àwọn àwòrán "lance-3b" àti àwọn àkọ́lé. Àtí àgbèwọlé SSE ní ìdáràn. Àwọn àgbèwọlé ìtàn: /api/.

Lance 3B (unified) is Apache 2.0-licensedpẹlú àwọn ààtòjútó 3B active params. See /models/lance-3b/ for setup notes and our open-source repos at github.com/freeaigit.

Àwọn àwọn iroyin ọ̀fẹ̀ gba 30,000-token lórí ọjọ́. Tí o bá lọ́wọ́, token-to-up-ups tí bẹrẹ ni $1, gba-bí-ó bá lọ́wọ́ - kò ní àṣàfilọ́lẹ̀ kan tí a fẹ́.

Chat pẹlu Lance 3B (unified)

Àwọn ààyè-iṣẹ́ Lance 3B (unified)?

Tí o dara jù fún: Cross-task research, prototyping pipelines that need image + video + edit + VQA from one model, "one model, four tasks" demos. Apache 2.0, commercial use OK.

Kini idi ti o fi lo Lance 3B (unified) Àwọn àkọ́lé

Àwọn ìṣàmúlò-ètò ìṣàfarawé

Replies stream token-by-token within ~1 second of pressing Send. No idle waiting.

Àwọn ìtàn tí a fi pamọ́

Àwọn òǹlò tí wọ́ inú ìṣàmúlò-ètò náà ní àwọn àkọ́lé nínú /account/?tab=history láti ń gbọ́ àwọn ìṣàmúlò-ètò ìpàpọ̀-ìsẹ́.

Àwọn ìṣàfarawé àwọn ààyè-iṣẹ́

Fi àkóónú àwọn àgbéwọlé kan lọ́wọ́lọ́wọ́ sí àwọn móòdù 4 nínú /ìbàlẹ̀/ìdákọ́/ ki o si gbọ́ àwọn ààtòjọ-ẹ̀yàn nínú àwọn ààtòjọ-ẹ̀yàn.

Ìlò àìṣé àìṣé

Àwọn ìṣàfihàn ní rẹ̀. Lò nínú àwọn ìṣàmúlò-ètò, àwọn àkọsílẹ̀, àwọn àkọsílẹ̀, tàbí ohunkohun mìíràn láti fi pamọ́.

Àwọn ìṣàmúlò-ètò ìṣàmúlò-ètò

Explain the difference between TCP and UDP in one paragraph

Write a friendly out-of-office reply that mentions a return date

Summarize the plot of The Three-Body Problem in 5 bullet points

Suggest 5 unique gift ideas for a friend who loves baking

Help me brainstorm a name for a small landscaping business in Texas

Àwọn Ìṣàmúlò-ètò

Ààyè àìṣàfilọ́lẹ̀ nípa GPÙ wà. Àwọn ìṣàfilọ́lẹ̀ tí a fi pamọ́ láti inú àwọn ààyè ọ̀fẹ́ rẹ̀ ní igba akọkọ; nígbà tí o bá lọ, àwọn tókènì tí a fi pamọ́ náà tí bẹrẹ ní $1. ~100 Àwọn àmì-ìwé àwọn àmì-ìwé

Àwọn ìṣàfarawé àwọn ìṣàmúlò-ètò

Perceptron: Perceptron Mk1.5 Àwọn ìṣàmúlò-ètò

Perceptron: Perceptron Mk1.5 is an AI model by Perceptron on Free.ai. It supports up to 36,864 tokens of context. Costs ...

TypeSafe: Jev Router Àwọn ìṣàmúlò-ètò

TypeSafe: Jev Router is an AI model by Typesafe on Free.ai. It supports up to 1,000,000 tokens of context. Costs approxi...

Fireworks: Ember-1 Àwọn ìṣàmúlò-ètò

Fireworks: Ember-1 is an AI model by Fireworks on Free.ai. It supports up to 1,048,576 tokens of context. Costs approxim...

Wó àwọn àwòrán àkọ́lé nípa àwọn àwọn ìṣàmúlò-ètò ìtàn → · Compare up to 4 chat models side-by-side →