Àwọn Àkóónú Àìṣàfilọ́lẹ̀

Ṣẹ̀dà láti inú Free.ai - áwọn àwọn àmì-ìwé tí a fi pamọ́, 477 AI àwọn àwọn ìṣẹ̀dá.

Chat, àwòrán, àwòrán, orin, àwòrán, OCR, fàyè gba - gbogbo àwọn nípa ààyè kejì tí a bá fẹ́ OpenAI. Aṣàfilọ́lẹ̀ ọ̀fẹ́, àwọn àmì-ìwé tí a lè rí, àwọn.

Gba àwọn bọ́tìnì - ọ̀fẹ́ Ka àkọlé

30,000 free tokens/day. Cards never required to start.

Àwọn ààyè-iṣẹ́ ìparí

One URL handles every chat model. One URL for every image model. Pick the model with a single string. No per-provider SDK shuffle.

Àwọn ààyè-iṣẹ́ àwọn ààyè-iṣẹ́

Self-hosted models bill at raw cost. Premium models add a transparent markup that drops as you scale. Every response reports the exact token cost.

99 ede ni inu bótìnì

Chat, tumọ, TTS, STT - gbogbo awọn ọna ti o tobi ju ti o ni awọn ede 99 pẹlu ko si awọn iṣeto ti o pọju. Fi koodu ede kan lọ ki o si ṣiṣẹ.

Ìṣàmúlò-ètò ìsàlẹ̀-ètò 60-sekondì

API kanna, àwọn ìtàn mẹ́tà. Fi bọ́tìnì sk-free-... rẹ̀ sínú àti láti mú.

curl https://api.free.ai/v1/chat/ \
  -H "Authorization: Bearer sk-free-YOUR-KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen2.5-7b",
    "messages": [{"role":"user","content":"Hello!"}]
  }'

import requests

r = requests.post(
    "https://api.free.ai/v1/chat/",
    headers={"Authorization": "Bearer sk-free-YOUR-KEY"},
    json={
        "model": "qwen2.5-7b",
        "messages": [{"role": "user", "content": "Hello!"}],
    },
)
print(r.json()["choices"][0]["message"]["content"])

const r = await fetch("https://api.free.ai/v1/chat/", {
  method: "POST",
  headers: {
    "Authorization": "Bearer sk-free-YOUR-KEY",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "qwen2.5-7b",
    messages: [{role: "user", content: "Hello!"}],
  }),
});
const data = await r.json();
console.log(data.choices[0].message.content);

package main

import (
  "bytes"; "fmt"; "io"; "net/http"
)

func main() {
  body := []byte(`{"model":"qwen2.5-7b","messages":[{"role":"user","content":"Hello!"}]}`)
  req, _ := http.NewRequest("POST", "https://api.free.ai/v1/chat/", bytes.NewBuffer(body))
  req.Header.Set("Authorization", "Bearer sk-free-YOUR-KEY")
  req.Header.Set("Content-Type", "application/json")
  resp, _ := http.DefaultClient.Do(req)
  defer resp.Body.Close()
  out, _ := io.ReadAll(resp.Body)
  fmt.Println(string(out))
}

require "net/http"
require "json"

uri = URI("https://api.free.ai/v1/chat/")
req = Net::HTTP::Post.new(uri, {
  "Authorization" => "Bearer sk-free-YOUR-KEY",
  "Content-Type"  => "application/json",
})
req.body = {
  model: "qwen2.5-7b",
  messages: [{role: "user", content: "Hello!"}],
}.to_json

res = Net::HTTP.start(uri.host, uri.port, use_ssl: true) { |h| h.request(req) }
puts JSON.parse(res.body)["choices"][0]["message"]["content"]

Ìṣàmúlò-ètò - àwọn ìṣàmúlò-ètò tí a fi pamọ́

Self-hosted models run free on your 30,000-token daily pool, then bill at raw cost. Premium models are pay-as-you-go; markup drops with 30-day spend.

Àwọn ààyè-iṣẹ́ àìfẹ́

30,000 / day

Wẹ́ẹ̀bù nikan - àwọn ìṣàmúlò-ètò àìṣàmúlò-ètò

Fi-ìmúdúró

1.50×

< $500 / 30 ọjọ

Àwọn àwọn àgbèwọlé

1.30×

≥ $500 / 30 ọjọ

Àwọn Àkọ́gbègbè

1.15×

≥ $2,000 / oṣù

Àwọn àwọn →

Àwọn ìṣàmúlò-ètò API

Àwọn ìṣàmúlò-ètò rẹ̀ ń yọ ìṣàmúlò-ètò àwọn bọ́tìnì nípa ìṣàmúlò-ètò - kò ní àwọn bọ́tìnì tuntun tí a fẹ́. Àwọn ìṣàmúlò-ètò token nínú àwọn ìṣàmúlò-ètò kò yatọ.

Àwọn ààyè-iṣẹ́	Àwọn Ìgúnrégé	Àwọn ìtàn	Ìjánú ìtàn
Àìfẹ́	$0	1,000	60
Àwọn àgbékalẹ̀	$5/oṣù	10,000	120
Àwọn Àwọn Àkọ́lé	$19/oṣù	100,000	300
Àwọn Àkọ́gbègbè	$49/oṣù	1,000,000	600

Yan àwọn ààtò →

Shipping AI features inside your own product? See the Platform API for the business plans and volume pricing.

Ohun tí o lè kọ̀

Botú ìrànwọ́ àwọn òǹlò

Àwọn ìṣàfilọ́lẹ̀ ìjánu-ìròyìn, ààyè nínú KB rẹ̀ láti inú àgbèwọlé ìṣàmúlò-ètò, gbà nínú àwọn eniyan nínú ìṣàfarawé.

Àwọn ààyè-iṣẹ́ ìṣàfihàn AI

Fi /v1/search/ pọ̀ sí àwọn àwòrán àkọ́kọ́ fún àwọn

Àwọn Àwòrán

Tí àwọn ààyè ìparí kan lọ́wọ́lọ́wọ́. SDXL + FLUX tí a fi pamọ́ fún ara wa; àwọn à

Àwọn ààyè-iṣẹ́ ìṣàfarawé àwọn àmì-ìwé

Whisper v3-ìgbà nla + diarization olugbàkọ̀ọ̀kan. Ìtàn-ìkẹ́kọ̀ọ̀kan. Webhook nípa ìparí iṣẹ́ fún iṣẹ́ ìtàn.

Fi @handle rẹ pamọ́ sínú àwọn ààyè-iṣẹ́ ìṣàfarawékọ́

Train an AI persona on your knowledge, drop a one-line script tag on any page. Visitors chat your AI; your account picks up the cost.

Fi @yourhandle pamọ́

Àwọn àgbègbè

Fi àwọn iṣẹ́ tí a ti kọ́ nínú àwọn iṣẹ́ tí a ti n bọ́ (àwọn iṣẹ́ àwòrán, àwọn àkọ́lé, àwọn àwọn ìṣàmúlò-ètò ìṣàmúlò-ètò, àwọn ìṣàmúlò-ètò àìdá. Àwọn àmì-ìwé HMAC-SHA256 nínú àmì-ìwé X-Free.

Àtòjọ-ẹ̀yàn àwọn wẹ́ẹ̀bù →

Àwọn Àtòjọ-Ìtàn

Fipamọ́ nínú /signup/ nípa ìṣàfihàn àti ìdákọ́ àti àkọ́kọ́ rẹ̀ - tí o fi 30,000-token lórí ọjọ́ lórí pool. Ṣí /account/?tab=api ki o tẹ̀ Ṣẹ̀dá. Bọ́tìnì ní token tí a fi pamọ́ nínú fọọmu sk-free-... ki o si bẹrẹ iṣẹ́ nígbà kan. Kò ní ìṣàmúlò-ètò, kò ní àtòjọ-ìwé.

The 30,000-token daily free pool covers self-hosted models on both web and API. Beyond it, self-hosted models bill the raw token count; external models add a 50% retail markup at deduction. Oju ti o ba fi $500 lọ sinu window ọjọ 30, awọn markup ti o lọ si 30%; ni $2,000+ o di alabaṣepọ ati pe awọn markup ti o lọ si 15%. Premium external models always bill purchased tokens; token top-ups start at $1.

API requests are governed by your purchased balance and a per-key monthly cap tied to your plan: 1,000 calls free, 10,000 on Basic, 100,000 on Pro, 1M on Business. There's no per-second throttle on top - if your key has tokens and you're under the monthly cap, the request runs.

Ya. Fi àgbèwọlé:ìṣàmúlò-ètò jẹ́ òótọ́ lórí /v1/ìgbàkọ́/ láti gba àwọn Àgbègbè-Sáfírí-ìfihàn. Àwọn ìṣàmúlò-ètò àìfàsì náà ń fi àgbèwọlé àwọn àgbèwọlé OpenAI pamọ́ láti jẹ́ pé àwọn SDK klìǹtì tí wa ní àwọn iṣẹ́ látí ìṣàfarawé.

Yes - the chat endpoint accepts a tools array per the OpenAI tool-calling schema. Models that support native tool use (Qwen 2.5 family + most premium models) will return tool_calls; models without native support fall back to a JSON-mode prompt.

Standard JSON: {error:{message, type, code}}. HTTP 402 means out of credits (response includes shortfall + an upgrade URL). HTTP 429 means daily pool exhausted on a non-API call. HTTP 400 covers validation errors with a human-readable message.

We publish freeai-code on npm + PyPI for the Coder IDE wrapper. For the raw API, the OpenAI SDKs work - point base_url at https://api.free.ai/v1 and pass your sk-free-... key. Same for Vercel AI SDK, LangChain, llamaindex, etc.

Configure your endpoint URL under /account/?tab=developer. We sign every payload with HMAC-SHA256 - the signature is in the X-Free-Signature header. Webhook events fire for: long-running job completion, share-link generation, low-credit alerts, and team invite acceptance.

We multiply the upstream cost in tokens by your tier's multiplier (1.50× retail, 1.30× bulk, 1.15× partner). Self-hosted models have no markup - you pay the raw token count. The deduction line on every response shows the exact token cost so there's no guesswork.

Àwọn àwọn àwòrán ọ̀fẹ́ náà tí wọ́n lọ́wọ́lọ́wọ́ nípa GPU wà tí a fi pamọ́ fún ara wa (Qwen 2.5, FLUX, Whisper, Kokoro, abbl.) àti àwọn àwọn àwòrán tí a fi pamọ́ nípa àwọn àwọn ààyé rẹ̀ ní ọjọ́. Àwọn àwòrán tí a fi pamọ́ nípa àwọn ààyé rẹ̀ nípa àwọn ààyé rẹ̀ nípa àwọn ààyé rẹ̀ nípa àwọn ààyé rẹ̀. Wọ́n ní àwọn àwọn ààyé /v1/chat/ endpoint tí a fi pamọ́ nípa àwọn àwọn ààyé /v1/chat/ endpoint; lọ́wọ́lù:premium/ láti yan àwòrán tí a fi pamọ́ nípa àwọn ààyé tí a fi pamọ́.

Ya - gbogbo àwọn móòdù àìṣàfilọ́lẹ̀-ara-ẹni-ní pàtó nípa Free.ai ní ìṣàmúlò-ètò-ìṣílọ́wọ́ nínú àwọn lísítì ìṣẹ̀dá (Apache 2.0, MIT). Àwọn ID àìṣàfilọ́lẹ̀ tí a lò ń tọ́ka sí àwọn ID HuggingFace tí a tí n ṣẹ̀dá, àti gpu_api repò wa ní ìjádé. Tí o bà fẹ́ ìṣàfilọ́lẹ̀ wa nípa àwọn ìṣàfilọ́lẹ̀ àwọn ààtòjútó rẹ̀, sọrọ̀ sí wa nípa ìṣàfilọ́lẹ̀ àwọn à

Tí a bà lọ́wọ́. BYOK gbá ọ̀rọ̀ rẹ̀ lọ́wọ́.

Ṣẹ̀dà láti inú Free.ai - áwọn àwọn àmì-ìwé tí a fi pamọ́, 477 AI àwọn àwọn ìṣẹ̀dá.

Àwọn ààyè-iṣẹ́ ìparí

Àwọn ààyè-iṣẹ́ àwọn ààyè-iṣẹ́

99 ede ni inu bótìnì

Ìṣàmúlò-ètò ìsàlẹ̀-ètò 60-sekondì

Ìṣàmúlò-ètò - àwọn ìṣàmúlò-ètò tí a fi pamọ́

Àwọn ìṣàmúlò-ètò API

Ohun tí o lè kọ̀

Botú ìrànwọ́ àwọn òǹlò

Àwọn ààyè-iṣẹ́ ìṣàfihàn AI

Àwọn Àwòrán

Àwọn ààyè-iṣẹ́ ìṣàfarawé àwọn àmì-ìwé

Fi @handle rẹ pamọ́ sínú àwọn ààyè-iṣẹ́ ìṣàfarawékọ́

Àwọn àgbègbè

Àwọn Àtòjọ-Ìtàn

Bawo ni mo ṣe lè gba bọ́tìnì API?

Bawo ni a ṣe ṣe iṣeto ti awọn owo-ori?

Àwọn ìdájú àwọn ìdájú àwọn ìṣàmúlò-ètò

Ò lè dá àwọn ìṣàfarawé àwọn àgbéwọlé pẹ̀lú ìṣàfarawé?

Àwọn àgbéwọlé àwọn ìṣàmúlò-ètò

Ìgúnrégé ìṣàmúlò-ètò wò nínú àwọn àyọkà ìṣàmúlò-ètò rẹ̀?

Ńlá nínú àwọn SDK̀ àìdálẹ̀?

Bawo ní àwọn wẹ́ẹ̀bù hókè ṣe n ṣiṣẹ́?

Bawo ní a ṣe lè ṣé ìṣàmúlò-ètò náà?

Kini ìyatọ̀ laarin àwọn ìṣàmúlò-ètò ọ̀fẹ̀ àti àwọn ìṣàmúlò-ètò pàtó?

Ń lè fi àwọn ààyè-iṣẹ́ mìíràn pamọ́?

Kini àwọn bọ́tìnì tí o bá gba (BYOK)?

Ṣí ní $0 - gba bọ́tìnì rẹ̀ nínú àwọn ìsàlẹ̀-ilà 60

30,000 Free Tokens, Gbogbo ọjọ

Wá: 30K tí a fi pamọ́/ọ̀jọ́!

Kò lè fi pamọ́