Cloudflare Workers AI
INFERENCE40 MODEL · CONTEXT MAKS 262K
GRATIS: 10,000 Neurons/hari
Catatan dari sumber
10,000 Neurons/day free, no credit card required. 60+ models available on the free tier.
Setup dalam 5 menit
Pilih target snippet
OPENAI SDK (NODE.JS)
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/run",
apiKey: process.env.CLOUDFLARE_WORKERS_AI_API_KEY,
});
const response = await client.chat.completions.create({
model: "cf-moonshotai-kimi-k2-7-code",
messages: [{ role: "user", content: "Halo!" }],
});
console.log(response.choices[0].message.content);.ENV
CLOUDFLARE_WORKERS_AI_API_KEY=your-api-key-hereBelum punya API key? Ambil di halaman resmi Cloudflare Workers AI ↗.
Cara claim API key gratis
Langkah umum — detail pastinya ikuti halaman resmi Cloudflare Workers AI.
- 01Buka halaman API key Cloudflare Workers AI ↗
- 02Daftar akun baru, atau login kalau sudah punya.
- 03Generate API key di dashboard / settings.
- 04Pakai API key + Base URL
https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/rundi SDK atau HTTP client.
Model tersedia (40)
| MODEL | MODALITY | CONTEXT | OUTPUT | RATE LIMIT |
|---|---|---|---|---|
| @cf/moonshotai/kimi-k2.7-codecf-moonshotai-kimi-k2-7-code | text + code + image + video + reasoning | 262K | 256K | 10K neurons/day (shared) |
| @cf/google/gemma-4-26b-a4b-it | Text + Vision | 256K | Shared w/ context | 10K neurons/day (shared) |
| @cf/meta/llama-4-scout-17b-16e-instruct | Multimodal | 131K | Shared w/ context | 10K neurons/day (shared) |
| @cf/zai-org/glm-4.7-flash | Text | 131K | Shared w/ context | 10K neurons/day (shared) |
| @cf/mistralai/mistral-small-3.1-24b-instruct | Text + Vision | 128K | Shared w/ context | 10K neurons/day (shared) |
| @cf/openai/gpt-oss-120b | Text | 128K | Shared w/ context | 10K neurons/day (shared) |
| @cf/deepseek-ai/deepseek-r1-distill-qwen-32b | Text (reasoning) | 80K | Shared w/ context | 10K neurons/day (shared) |
| @cf/meta/llama-3.3-70b-instruct-fp8-fast | Text | 24K | Shared w/ context | 10K neurons/day (shared) |
| @cf/aisingapore/gemma-sea-lion-v4-27b-itcf-aisingapore-gemma-sea-lion-v4-27b-it | — | 8K | 128K | — |
| @cf/baai/bge-base-en-v1.5cf-baai-bge-base-en-v1-5 | — | 8K | — | — |
| @cf/baai/bge-large-en-v1.5cf-baai-bge-large-en-v1-5 | — | 8K | — | — |
| @cf/baai/bge-m3cf-baai-bge-m3 | — | 8K | — | — |
| @cf/baai/bge-small-en-v1.5cf-baai-bge-small-en-v1-5 | — | 8K | — | — |
| @cf/daily-co/phonellm-mini-alpha-2cf-daily-co-phonellm-mini-alpha-2 | — | 8K | — | — |
| @cf/deepseek-ai/deepseek-v4-flash-0731cf-deepseek-ai-deepseek-v4-flash-0731 | — | 8K | — | — |
| @cf/deepseek-ai/deepseek-v4-pro-0813cf-deepseek-ai-deepseek-v4-pro-0813 | — | 8K | — | — |
| @cf/deepseek-ai/deepseek-v4.1-flash-1017cf-deepseek-ai-deepseek-v4-1-flash-1017 | — | 8K | — | — |
| @cf/google/gemma-2b-it-loracf-google-gemma-2b-it-lora | — | 8K | — | — |
| @cf/google/gemma-7b-it-loracf-google-gemma-7b-it-lora | — | 8K | — | — |
| @cf/ibm-granite/granite-4.0-h-microcf-ibm-granite-granite-4-0-h-micro | — | 8K | 131K | — |
| @cf/meta-llama/llama-2-7b-chat-hf-loracf-meta-llama-llama-2-7b-chat-hf-lora | — | 8K | — | — |
| @cf/meta/llama-3.1-8b-instruct-fp8cf-meta-llama-3-1-8b-instruct-fp8 | — | 8K | 32K | — |
| @cf/meta/llama-3.2-1b-instructcf-meta-llama-3-2-1b-instruct | — | 8K | 60K | — |
| @cf/meta/llama-3.2-3b-instructcf-meta-llama-3-2-3b-instruct | — | 8K | 80K | — |
| @cf/meta/llama-guard-3-8bcf-meta-llama-guard-3-8b | — | 8K | 128K | — |
| @cf/mistral/mistral-7b-instruct-v0.2-loracf-mistral-mistral-7b-instruct-v0-2-lora | — | 8K | — | — |
| @cf/moondream/moondream3.1-9B-A2Bcf-moondream-moondream3-1-9b-a2b | — | 8K | 4K | — |
| @cf/moonshotai/kimi-k2.6cf-moonshotai-kimi-k2-6 | — | 8K | — | — |
| @cf/nvidia/nemotron-3-120b-a12bcf-nvidia-nemotron-3-120b-a12b | — | 8K | 256K | — |
| @cf/openai/gpt-oss-20bcf-openai-gpt-oss-20b | — | 8K | — | — |
| @cf/qwen/qwen2.5-coder-32b-instructcf-qwen-qwen2-5-coder-32b-instruct | — | 8K | — | — |
| @cf/qwen/qwen3-30b-a3b-fp8cf-qwen-qwen3-30b-a3b-fp8 | — | 8K | — | — |
| @cf/qwen/qwen3.8-27bcf-qwen-qwen3-8-27b | — | 8K | — | — |
| @cf/qwen/qwq-32bcf-qwen-qwq-32b | — | 8K | — | — |
| @cf/zai-org/glm-5.2cf-zai-org-glm-5-2 | — | 8K | 256K | — |
| @cf/zai-org/glm-5.3cf-zai-org-glm-5-3 | — | 8K | 1M | — |
| @cf/zai-org/glm-5.3-flashcf-zai-org-glm-5-3-flash | — | 8K | 1M | — |
| @cf/google/embeddinggemma-300mcf-google-embeddinggemma-300m | embedding | — | — | — |
| @cf/pfnet/plamo-embedding-1bcf-pfnet-plamo-embedding-1b | embedding | — | — | — |
| @cf/qwen/qwen3-embedding-0.6bcf-qwen-qwen3-embedding-0-6b | embedding | — | — | — |
FAQ
Apakah API Cloudflare Workers AI gratis?
Ya — menurut sumber: "10,000 Neurons/day free, no credit card required. 60+ models available on the free tier." Batas gratis yang tercatat: 10,000 Neurons/hari. Data dari mnfst/awesome-free-llm-apis, freellm.net, models.dev, terakhir di-sync 31 Okt 2026 — cek sumber untuk kondisi terbaru.
Ada berapa model gratis di Cloudflare Workers AI?
40 model tercantum per 31 Okt 2026, termasuk @cf/moonshotai/kimi-k2.7-code, @cf/google/gemma-4-26b-a4b-it, @cf/meta/llama-4-scout-17b-16e-instruct.
Berapa rate limit Cloudflare Workers AI?
Beda-beda per model, contoh: @cf/moonshotai/kimi-k2.7-code: 10K neurons/day (shared); @cf/google/gemma-4-26b-a4b-it: 10K neurons/day (shared); @cf/meta/llama-4-scout-17b-16e-instruct: 10K neurons/day (shared). Limit lengkap per model, lihat tabel di atas.
Berapa context window maksimal di Cloudflare Workers AI?
262K (@cf/moonshotai/kimi-k2.7-code).
DISINKRON 31 OKT 2026 · SUMBER: mnfst/awesome-free-llm-apis, freellm.net, models.dev