Skip to main content

​
Models supported

​
At a glance

ModelModel IDAccess
Gemma 4 31Bgemma-4-31bAvailable
MiniMax M3minimax-m3Available
GLM 5.2-Request access
DeepSeek V4 Pro-Request access
Kimi K2.6-Request access
DeepSeek V4 Flash-Request access
NVIDIA Nemotron 3 Ultra-Request access

​
Available now

Contact the Terminal team to request access.

​
Gemma 4 31B

cURL
curl -sS https://api.terminal.fyi/v1/chat/completions \
  -H "Authorization: Bearer $TERMINAL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemma-4-31b",
    "messages": [
      {
        "role": "user",
        "content": "Extract three action items from these release notes."
      }
    ],
    "max_tokens": 1000
  }' | jq

​
MiniMax M3

cURL
curl -sS https://api.terminal.fyi/v1/chat/completions \
  -H "Authorization: Bearer $TERMINAL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "minimax-m3",
    "messages": [
      {
        "role": "user",
        "content": "Create a concise implementation plan for adding webhook retries."
      }
    ],
    "max_tokens": 1000
  }' | jq

​
Request access

The following models are available by request:
ModelAccess
GLM 5.2Request access
DeepSeek V4 ProRequest access
Kimi K2.6Request access
DeepSeek V4 FlashRequest access
NVIDIA Nemotron 3 UltraRequest access
Contact the Terminal team with the model name, expected input and output token volume, and whether you need Standard, Flex, or both. We will confirm availability before you send production traffic.