Kostenlose Modelle und APIs bei Cloudflare 2026
Cloudflare Workers AI betreibt Modelle in seinem globalen Edge-Netzwerk und enthält ein kostenloses tägliches Kontingent.
30 Modellebis zu 10.5M Kontextbeste: Qwen 3.8 27BAktualisiert:

Cloudflare Workers AI
Online bei der letzten Prüfung
10,000 Neurons pro Tag sind sowohl im Workers-Free- als auch im Paid-Tarif kostenlos.
- Base URL
https://api.cloudflare.com/client/v4/accounts/ACCOUNT_ID/ai/v1- Kompatibilität
- OpenAI Chat Completions
- Karte
- Beim Anbieter prüfen
- Limits
- Workers Free: 10,000 Neurons/day shared across eligible models
| # | Modell ↕ | AA Index ↕ | Kontext ↕ | Größe ↕ | Limit | |
|---|---|---|---|---|---|---|
| 1 |
Qwen 3.8 27B
@cf/qwen/qwen3.8-27b |
33.7 | 262K | Mittelgroß | Workers Free: 10,000 Neurons/day shared across eligible models | Öffnen |
| 2 |
Gemma 4 26B A4B
@cf/google/gemma-4-26b-a4b-it |
16.7 | 256K | Mittelgroß | Workers Free: 10,000 Neurons/day shared across eligible models | Öffnen |
| 3 |
GLM 4.7 Flash
@cf/zai-org/glm-4.7-flash |
14.9 | 131K | Mittelgroß | Workers Free: 10,000 Neurons/day shared across eligible models | Öffnen |
| 4 |
Nemotron 3 120B
@cf/nvidia/nemotron-3-120b-a12b |
— | 256K | Sehr groß | Workers Free: 10,000 Neurons/day shared across eligible models | Öffnen |
| 5 |
gpt-oss-120b
@cf/openai/gpt-oss-120b |
11.6 | 128K | Sehr groß | Workers Free: 10,000 Neurons/day shared across eligible models | Öffnen |
| 6 |
gpt-oss-20b
@cf/openai/gpt-oss-20b |
10.0 | 128K | Mittelgroß | Workers Free: 10,000 Neurons/day shared across eligible models | Öffnen |
| 7 |
Llama 3.3 70B Instruct Fp8 Fast
@cf/meta/llama-3.3-70b-instruct-fp8-fast |
— | 24K | Sehr groß | Workers Free: 10,000 Neurons/day shared across eligible models | Öffnen |
| 8 |
Llama 4 Scout
@cf/meta/llama-4-scout-17b-16e-instruct |
8.1 | 131K | Sehr groß | Workers Free: 10,000 Neurons/day shared across eligible models | Öffnen |
| 9 |
Qwen3 30B
@cf/qwen/qwen3-30b-a3b-fp8 |
9.8 | 33K | Mittelgroß | Workers Free: 10,000 Neurons/day shared across eligible models | Öffnen |
| 10 |
QwQ 32B
@cf/qwen/qwq-32b |
9.5 | 24K | Mittelgroß | Workers Free: 10,000 Neurons/day shared across eligible models | Öffnen |
| 11 |
DeepSeek R1 Distill Qwen 32B
@cf/deepseek-ai/deepseek-r1-distill-qwen-32b |
8.4 | 80K | Mittelgroß | Workers Free: 10,000 Neurons/day shared across eligible models | Öffnen |
| 12 |
Llama 3.1 8B
@cf/meta/llama-3.1-8b-instruct-fp8 |
6.9 | 32K | Klein | Workers Free: 10,000 Neurons/day shared across eligible models | Öffnen |
| 13 |
Gemma SEA-LION V4 27B
@cf/aisingapore/gemma-sea-lion-v4-27b-it |
— | 128K | Mittelgroß | Workers Free: 10,000 Neurons/day shared across eligible models | Öffnen |
| 14 |
Mistral Small 3.1 24B
@cf/mistralai/mistral-small-3.1-24b-instruct |
— | 128K | Mittelgroß | Workers Free: 10,000 Neurons/day shared across eligible models | Öffnen |
| 15 |
Llama 3.2 11B Vision
@cf/meta/llama-3.2-11b-vision-instruct |
5.4 | 128K | Mittelgroß | Workers Free: 10,000 Neurons/day shared across eligible models | Öffnen |
| 16 |
Qwen2.5 Coder 32B
@cf/qwen/qwen2.5-coder-32b-instruct |
6.7 | 33K | Mittelgroß | Workers Free: 10,000 Neurons/day shared across eligible models | Öffnen |
| 17 |
Llama 3.2 1B
@cf/meta/llama-3.2-1b-instruct |
4.8 | 60K | Klein | Workers Free: 10,000 Neurons/day shared across eligible models | Öffnen |
| 18 |
apertus-v1.5-8b
@cf/swiss-ai/apertus-v1.5-8b |
— | 262K | Klein | Workers Free: 10,000 Neurons/day shared across eligible models | Öffnen |
| 19 |
phonellm-mini-alpha-2
@cf/daily-co/phonellm-mini-alpha-2 |
— | 262K | Klein | Workers Free: 10,000 Neurons/day shared across eligible models | Öffnen |
| 20 |
Llama 3.2 3B
@cf/meta/llama-3.2-3b-instruct |
5.7 | 80K | Klein | Workers Free: 10,000 Neurons/day shared across eligible models | Öffnen |
| 21 |
eurollm-9b-it
@cf/utter-project/eurollm-9b-it |
— | 32K | Klein | Workers Free: 10,000 Neurons/day shared across eligible models | Öffnen |
| 22 |
clef
@cf/cloudflare/clef |
— | 66K | Klein | Workers Free: 10,000 Neurons/day shared across eligible models | Öffnen |
| 23 |
Granite 4.0 H Micro
@cf/ibm-granite/granite-4.0-h-micro |
— | 131K | Klein | Workers Free: 10,000 Neurons/day shared across eligible models | Öffnen |
| 24 |
clairic
@cf/cloudflare/clairic |
— | 66K | Klein | Workers Free: 10,000 Neurons/day shared across eligible models | Öffnen |
| 25 |
clef-omni
@cf/cloudflare/clef-omni |
— | 66K | Klein | Workers Free: 10,000 Neurons/day shared across eligible models | Öffnen |
| 26 |
Gemma 7B
@cf/google/gemma-7b-it-lora |
— | 4K | Klein | Workers Free: 10,000 Neurons/day shared across eligible models | Öffnen |
| 27 |
clef-flash
@cf/cloudflare/clef-flash |
— | 25K | Klein | Workers Free: 10,000 Neurons/day shared across eligible models | Öffnen |
| 28 |
Mistral 7B
@cf/mistral/mistral-7b-instruct-v0.2-lora |
5.0 | 15K | Klein | Workers Free: 10,000 Neurons/day shared across eligible models | Öffnen |
| 29 |
Gemma 2B
@cf/google/gemma-2b-it-lora |
— | 8K | Klein | Workers Free: 10,000 Neurons/day shared across eligible models | Öffnen |
| 30 |
Llama 2 7B
@cf/meta-llama/llama-2-7b-chat-hf-lora |
— | 8K | Klein | Workers Free: 10,000 Neurons/day shared across eligible models | Öffnen |
Keine Modelle entsprechen Ihren Filtern.
Benchmarks: Artificial Analysis (24. September 2026). Ein Strich bedeutet, dass das Modell nicht in deren Rangliste steht; wir schätzen Werte nie selbst.
FAQ
Ist Cloudflare Workers AI kostenlos?
10,000 Neurons pro Tag sind sowohl im Workers-Free- als auch im Paid-Tarif kostenlos. 30 Modelle sind derzeit kostenlos.
Ist Cloudflare Workers AI mit der OpenAI API kompatibel?
Ja — nutzen Sie die base URL https://api.cloudflare.com/client/v4/accounts/ACCOUNT_ID/ai/v1 mit einem beliebigen OpenAI-kompatiblen Client oder SDK.
Verlangt Cloudflare Workers AI eine Karte?
Das hängt vom Konto ab — prüfen Sie das Dashboard des Anbieters.