Modelos Ollama Cloud que se pueden usar con el TIER free

Tiempo de lectura: < 1 minuto

Hoy vamos a indicar cuales son los modelos Ollama Cloud que no dan el error de: {«error»:»this model requires a subscription, upgrade for access: https://ollama.com/upgrade (ref: 374c814e-dc9c-4fc1-a898-0bbc57cb0d0a)»}

Para ello y realizando pruebas mediante este script podemos saber que modelos son disponibles para utilizar con cloud y free tier

cat << 'EOF' > /tmp/test_models.sh
#!/bin/bash
TOKEN="TU_TOKEN_OLLAMA"
MODELS=(
  "qwen3-next:80b" "deepseek-v4-flash" "ministral-3:14b" "ministral-3:8b"
  "ministral-3:3b" "gemma3:4b" "gemma3:12b" "gemma3:27b" "gemma4:31b"
  "glm-4.6" "glm-4.7" "glm-5" "glm-5.1" "kimi-k2.5" "kimi-k2.6"
  "minimax-m2" "minimax-m2.1" "minimax-m2.5" "minimax-m2.7"
  "deepseek-v3.1:671b" "deepseek-v3.2" "deepseek-v4-pro"
  "qwen3.5:397b" "qwen3-coder:480b" "nemotron-3-nano:30b"
  "gpt-oss:20b" "gpt-oss:120b" "rnj-1:8b" "cogito-2.1:671b"
)

for MODEL in "${MODELS[@]}"; do
  RESULT=$(curl -s https://ollama.com/v1/chat/completions \
    -H "Content-Type: application/json" \
    -H "Authorization: Bearer $TOKEN" \
    -d "{\"model\": \"${MODEL}:cloud\", \"messages\": [{\"role\": \"user\", \"content\": \"hi\"}], \"max_tokens\": 5}" \
    --max-time 15)
  if echo "$RESULT" | grep -q "error"; then
    echo "❌ ${MODEL}:cloud"
  else
    echo "✅ ${MODEL}:cloud"
  fi
done
EOF
bash /tmp/test_models.sh

En mi prueba ha salido:

✅ qwen3-next:80b:cloud
❌ deepseek-v4-flash:cloud
✅ ministral-3:14b:cloud
✅ ministral-3:8b:cloud
✅ ministral-3:3b:cloud
✅ gemma3:4b:cloud
✅ gemma3:12b:cloud
✅ gemma3:27b:cloud
✅ gemma4:31b:cloud
✅ glm-4.6:cloud
✅ glm-4.7:cloud
❌ glm-5:cloud
❌ glm-5.1:cloud
❌ kimi-k2.5:cloud
❌ kimi-k2.6:cloud
✅ minimax-m2:cloud
✅ minimax-m2.1:cloud
✅ minimax-m2.5:cloud
❌ minimax-m2.7:cloud
✅ deepseek-v3.1:671b:cloud
✅ deepseek-v3.2:cloud
❌ deepseek-v4-pro:cloud
✅ qwen3.5:397b:cloud
✅ qwen3-coder:480b:cloud
✅ nemotron-3-nano:30b:cloud
✅ gpt-oss:20b:cloud
✅ gpt-oss:120b:cloud
✅ rnj-1:8b:cloud
✅ cogito-2.1:671b:cloud

Estos son los gratis accesibles:

qwen3-next:80b, ministral-3:14b, ministral-3:8b, ministral-3:3b, gemma3:4b, gemma3:12b, gemma3:27b, gemma4:31b, glm-4.6, glm-4.7, minimax-m2, minimax-m2.1, minimax-m2.5, deepseek-v3.1:671b, deepseek-v3.2, qwen3.5:397b, qwen3-coder:480b, nemotron-3-nano:30b, gpt-oss:20b, gpt-oss:120b, rnj-1:8b, cogito-2.1:671b

Deja un comentario