jishie

Gemini 3.1 Pro Preview

aimlapi/google/gemini-3.1-pro-preview · family gemini-pro · in: text, image, video, audio, pdf → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image video audio pdf.

$5.85
Blended $/1M (3:1)
$2.6
Input $/1M
$15.6
Output $/1M
$18.20
1M in + 1M out
$0.65 −75%
Cache read $/1M
#7144 of 8,276
Cheapest rank
Provider
AI/ML API (aimlapi)
Kind
text (outputs text)
Context
1,000,000 tokens
Max output
65,536 tokens
Capabilities
tools reasoning text image video audio pdf

Same model, other providers

“Gemini 3.1 Pro Preview” is offered by 31 providers — cheapest-effective first. Kenari is the cheapest at $0.00 blended.

ProviderInputOutputBlendedContext
Kenarifreefree$0.001M
Kilo Gateway$1$6$2.251M
Perplexity Agent$2$12$4.501M
Abacus$2$12$4.501M
302.AI$2$12$4.501M
OpenRouter$2$12$4.501M
Auriko$2$12$4.501M
ZenMux$2$12$4.501M
Impossibl$2$12$4.501M
Google$2$12$4.501M
FrogBot$2$12$4.501M
Vercel AI Gateway$2$12$4.501M
AI/ML API (this)$2.6$15.6$5.851M

Call it

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

Most providers are OpenAI-compatible — point base_url at AI/ML API and pass this model id:

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"google/gemini-3.1-pro-preview","messages":[{"role":"user","content":"hello"}]}'

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

← all AI/ML API models · model index · JSON