jishie

Gemma 4 31B IT

deepinfra/google/gemma-4-31B-it · family gemma · in: text, image, video → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image video.

$0.19
Blended $/1M (3:1)
$0.13
Input $/1M
$0.38
Output $/1M
$0.51
1M in + 1M out
—
Cache read $/1M
#1664 of 7,712
Cheapest rank
Provider
Deep Infra (deepinfra)
Kind
text (outputs text)
Context
262,144 tokens
Max output
32,768 tokens
Capabilities
tools reasoning text image video

Same model, other providers

“Gemma 4 31B IT” is offered by 29 providers — cheapest-effective first. UnoRouter is the cheapest at $0.00 blended.

ProviderInputOutputBlendedContext
UnoRouterfreefree$0.00262k
Kenarifreefree$0.00262k
Requestyfreefree$0.00262k
QVACfreefree$0.00262k
DevPass (LLM Gateway)$0.1$0.25$0.14262k
CrofAI$0.1$0.3$0.15262k
Kilo Gateway$0.09$0.34$0.15262k
OpenRouter$0.09$0.34$0.15262k
Lilac$0.11$0.35$0.17262k
Deep Infra (this)$0.13$0.38$0.19262k
FastRouter$0.13$0.38$0.19262k
OrcaRouter$0.13$0.38$0.19262k
SiliconFlow$0.13$0.4$0.20262k

Call it

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

Most providers are OpenAI-compatible — point base_url at Deep Infra 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):

← all Deep Infra models · model index · JSON