Gemma 4 31B IT

cerebras/gemma-4-31b · family gemma · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: toolsreasoningtextimage.

$1.11Blended $/1M (3:1)

$0.99Input $/1M

$1.49Output $/1M

$2.481M in + 1M out

—Cache read $/1M

#3300 of 5,000Cheapest rank

Provider: Cerebras (cerebras)
Kind: text (outputs text)
Context: 131,072 tokens
Max output: 40,960 tokens
Capabilities: toolsreasoningtextimage

Same model, other providers

“Gemma 4 31B IT” is offered by 9 providers — cheapest-effective first. QVAC is the cheapest at $0.00 blended.

Provider	Input	Output	Blended	Context
QVAC	free	free	$0.00	262k
Kenari	free	free	$0.00	262k
UnoRouter	free	free	$0.00	262k
Kilo Gateway	$0.08	$0.35	$0.15	262k
CrofAI	$0.1	$0.3	$0.15	262k
LLM Gateway	$0.102	$0.297	$0.15	262k
OpenRouter	$0.1	$0.34	$0.16	262k
Lilac	$0.11	$0.35	$0.17	262k
Cerebras (this)	$0.99	$1.49	$1.11	131k

Call it

jishie indexes & prices models; it does not proxy inference.

Most providers are OpenAI-compatible — point base_url at Cerebras and pass this model id:

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

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