Providers

Atlas Cloud

Verified

A GPU inference cloud serving open-weight models through OpenAI-compatible endpoints.

Start building View requests Official status

Models on Atlas Cloud

Open in catalog

14 of 14

GPT-4.1 MiniChatgpt-4.1-mini1M context$0.40 / $1.60per M input / output

GPT-5.4 MiniChatgpt-5.4-miniReleased Mar 17, 2026410K context$0.75 / $4.50per M input / output

GPT-5.4 NanoChatgpt-5.4-nanoReleased Mar 17, 2026410K context$0.20 / $1.25per M input / output

DeepSeek V4 FlashChatdeepseek-v4-flashReleased Apr 24, 20261M contextWeights $0.14 / $0.28per M input / output

DeepSeek V4 ProChatdeepseek-v4-proReleased Apr 24, 20261M contextWeights $1.74 / $3.48per M input / output

Gemini 2.5 Flash-LiteChatgemini-2.5-flash-lite1M context$0.10 / $0.40per M input / output

Gemini 3 FlashChatgemini-3-flashReleased Dec 17, 20251M context$0.50 / $3.00per M input / output

GLM 5.2Chatglm-5.2Released June 20261M contextWeights $1.40 / $4.40per M input / output

GPT-5.6 LunaChatgpt-5.6-lunaReleased Jul 9, 20261.1M context$0.20 / $1.20per M input / output

GPT-5.6 TerraChatgpt-5.6-terraReleased Jul 9, 20261.1M context$2.00 / $12.00per M input / output

Grok 4.3Chatgrok-4.31M context$1.25 / $2.50per M input / output

Kimi K2.6Chatkimi-k2.6262K context$0.95 / $4.00per M input / output

LongCat 2.0Chatlongcat-2.01M context$0.75 / $2.95per M input / output

Qwen 3.8 MaxChatqwen-3.8-maxReleased Aug 3, 2026262K context$2.00 / $6.00per M input / output

Traffic & reliability

First measured traffic day

3 requests and 46 tokens · 2026-09-04

Inspect 3 requests Filter model catalog

Direct routingCall Atlas Cloud explicitly

atlascloud· routing

# pin every request to Atlas Cloud
curl https://www.ninjachat.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $NINJACHAT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-2.5-flash-lite",
    "messages": [{ "role": "user", "content": "Hello!" }],
    "routing": { "providers": { "only": ["atlascloud"] } }
  }'

Create free key