O Ollama Cloud
activeOllama's hosted cloud inference — free tier provides shared session/weekly credits across 30+ open models (gpt-oss, DeepSeek V3, Kimi K2, Qwen3, Gemma 3, etc.). Frontier flagships (DeepSeek V4, Kimi K2.6, GLM-5+) require a paid upgrade. OpenAI-compatible API, no credit card required for Free.
https://ollama.com/v1
Avg Latency
—
90-day Uptime
—%
Rate Limits
— RPM / — RPD
Sign-up Required
Yes
Info
Models (30)
deepseek-v4-pro
CTX: 128K
deepseek-v4-flash
CTX: 128K
deepseek-v3.2
CTX: 128K
deepseek-v3.1:671b
CTX: 128K
kimi-k2.6
CTX: 128K
kimi-k2.5
CTX: 128K
kimi-k2-thinking
CTX: 128K
kimi-k2:1t
CTX: 128K
glm-5.1
CTX: 128K
glm-5
CTX: 128K
glm-4.7
CTX: 128K
glm-4.6
CTX: 128K
qwen3-coder:480b
CTX: 256K
qwen3-coder-next
CTX: 256K
qwen3-next:80b
CTX: 128K
qwen3.5:397b
CTX: 128K
qwen3-vl:235b
CTX: 128K
minimax-m2.7
CTX: 128K
minimax-m2.5
CTX: 128K
gpt-oss:120b
CTX: 128K
gpt-oss:20b
CTX: 128K
gemma4:31b
CTX: 128K
gemma3:27b
CTX: 128K
gemma3:12b
CTX: 128K
gemma3:4b
CTX: 128K
gemini-3-flash-preview
CTX: 1M
mistral-large-3:675b
CTX: 128K
devstral-2:123b
CTX: 128K
nemotron-3-super
CTX: 128K
cogito-2.1:671b
CTX: 128K
Quick Start
export API_KEY="your_api_key_here"
curl https://ollama.com/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $API_KEY" \
-d '{
"model": "gpt-oss:120b",
"messages": [
{"role": "user", "content": "Hello! How are you?"}
]
}' 
