Gemma 4 31B

wandb/google/gemma-4-31B-it · family gemma · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolsreasoningtextimage.

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

$0.1Input $/1M

$0.34Output $/1M

$0.441M in + 1M out

$0.1Cache read $/1M

#1124 of 5,000Cheapest rank

Provider: Weights & Biases (wandb)
Context: 262,144 tokens
Max output: 262,144 tokens
Capabilities: toolsreasoningtextimage

Same model, other providers

“Gemma 4 31B” is offered by 5 providers — cheapest-effective first. This one (Weights & Biases) is the cheapest.

Provider	Input	Output	Blended	Context
Weights & Biases (this)	$0.1	$0.34	$0.16	262k
NanoGPT	$0.1	$0.35	$0.16	262k
NovitaAI	$0.14	$0.4	$0.21	262k
Neuralwatt	$0.144	$0.42	$0.21	262k
NanoGPT	$0.45	$1	$0.59	262k

Call it

jishie indexes & prices models; it does not proxy inference. Most providers are OpenAI-compatible — point base_url at Weights & Biases 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","messages":[{"role":"user","content":"hello"}]}'

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