Gemma 4 31B Thinking

nano-gpt/google/gemma-4-31b-it:thinking · family gemma · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: reasoningtextimage.

$0.16Blended $/1M (3:1)

$0.1Input $/1M

$0.35Output $/1M

$0.451M in + 1M out

$0.05 −50%Cache read $/1M

#1131 of 5,000Cheapest rank

Provider: NanoGPT (nano-gpt)
Context: 262,144 tokens
Max output: 131,072 tokens
Capabilities: reasoningtextimage

Call it

jishie indexes & prices models; it does not proxy inference. Most providers are OpenAI-compatible — point base_url at NanoGPT and pass this model id:

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"google/gemma-4-31b-it:thinking","messages":[{"role":"user","content":"hello"}]}'

Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):