theserverless.dev InferenceList

Models / Google

Google: Gemini 3.1 Pro Preview

google/gemini-3.1-pro-preview

audio text image videoContext 1.0M

Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation...

Price

Input$2

per 1M tokens

Output$12

per 1M tokens

Compare this model

Providers

Each row is one seller. Prices are the published rate from that source. A dash means that source did not publish the amount. Sorted by a 3:1 blend of input and output.

ProviderTagQuant InputOutput ContextUptimeStatusSource
Google google-vertex/global/flex — $1/1M $6/1M 1.0M — Live openrouter-endpoints
Google AI Studio google-ai-studio/flex — $1/1M $6/1M 1.0M 100% Live openrouter-endpoints
AtlasCloud — fp8 $2/1M $12/1M 1M — Listed atlascloud
Google google-vertex/global — $2/1M $12/1M 1.0M 100% Live openrouter-endpoints
Google AI Studio google-ai-studio — $2/1M $12/1M 1.0M 100% Live openrouter-endpoints
Inference.net — — $2/1M $12/1M 1.0M — Listed inferencenet
Phala — — $4/1M $18/1M 1.0M — Listed phala
Google google-vertex/global/priority — $3.6/1M $21.6/1M 1.0M — Live openrouter-endpoints
Google AI Studio google-ai-studio/priority — $3.6/1M $21.6/1M 1.0M — Live openrouter-endpoints

Monthly bill

Token models use the token counts. Image, video, and audio models use units times the flat rate.

$14.00 at list price for this workload

Cache

Cache read$0.2

per 1M tokens

Cache write$0.375

per 1M tokens

Tiers

Web search
$0.014 per request
Image input
$2 per 1M tokens
Audio
$2 per 1M tokens
Audio cache
$0.2 per 1M tokens
Reasoning
$12 per 1M tokens
Above 200,000 prompt tokens
in $4 · out $18 · cache read $0.4 · audio $4
Every rate
UnitInputOutputFlatConfidence
token $2/1M $12/1M Not published— official

Price history

Google: Gemini 3.1 Pro Preview
15 0 2026-09-15: $22026-09-16: $22026-09-17: $22026-09-18: $22026-09-19: $22026-09-20: $22026-09-21: $22026-09-22: $22026-09-23: $22026-09-24: $22026-09-25: $22026-09-26: $22026-09-27: $22026-09-28: $22026-09-29: $22026-09-30: $22026-10-01: $22026-10-02: $22026-10-03: $22026-10-04: $22026-10-05: $22026-10-06: $22026-10-07: $22026-10-08: $22026-10-09: $22026-10-10: $22026-10-11: $22026-10-12: $22026-10-13: $22026-10-14: $22026-10-15: $22026-10-16: $22026-10-17: $22026-10-18: $22026-10-19: $22026-10-20: $22026-10-21: $22026-10-22: $22026-10-23: $22026-10-24: $22026-10-25: $22026-10-26: $22026-10-27: $22026-10-28: $22026-10-29: $22026-10-30: $2 2026-09-15 2026-10-30

input or flat output

Daily snapshots
UTC dateUnitInputOutputFlat
2026-09-15 token $2 $12 Not published—
2026-09-16 token $2 $12 Not published—
2026-09-17 token $2 $12 Not published—
2026-09-18 token $2 $12 Not published—
2026-09-19 token $2 $12 Not published—
2026-09-20 token $2 $12 Not published—
2026-09-21 token $2 $12 Not published—
2026-09-22 token $2 $12 Not published—
2026-09-23 token $2 $12 Not published—
2026-09-24 token $2 $12 Not published—
2026-09-25 token $2 $12 Not published—
2026-09-26 token $2 $12 Not published—
2026-09-27 token $2 $12 Not published—
2026-09-28 token $2 $12 Not published—
2026-09-29 token $2 $12 Not published—
2026-09-30 token $2 $12 Not published—
2026-10-01 token $2 $12 Not published—
2026-10-02 token $2 $12 Not published—
2026-10-03 token $2 $12 Not published—
2026-10-04 token $2 $12 Not published—
2026-10-05 token $2 $12 Not published—
2026-10-06 token $2 $12 Not published—
2026-10-07 token $2 $12 Not published—
2026-10-08 token $2 $12 Not published—
2026-10-09 token $2 $12 Not published—
2026-10-10 token $2 $12 Not published—
2026-10-11 token $2 $12 Not published—
2026-10-12 token $2 $12 Not published—
2026-10-13 token $2 $12 Not published—
2026-10-14 token $2 $12 Not published—
2026-10-15 token $2 $12 Not published—
2026-10-16 token $2 $12 Not published—
2026-10-17 token $2 $12 Not published—
2026-10-18 token $2 $12 Not published—
2026-10-19 token $2 $12 Not published—
2026-10-20 token $2 $12 Not published—
2026-10-21 token $2 $12 Not published—
2026-10-22 token $2 $12 Not published—
2026-10-23 token $2 $12 Not published—
2026-10-24 token $2 $12 Not published—
2026-10-25 token $2 $12 Not published—
2026-10-26 token $2 $12 Not published—
2026-10-27 token $2 $12 Not published—
2026-10-28 token $2 $12 Not published—
2026-10-29 token $2 $12 Not published—
2026-10-30 token $2 $12 Not published—

Alternatives

Parameters (12)
include_reasoningmax_tokensreasoningreasoning_effortresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_p
Call this model

OpenRouter id google/gemini-3.1-pro-preview. InferenceList does not send the request.

curl 
curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"google/gemini-3.1-pro-preview","messages":[{"role":"user","content":"Hello"}]}'

JavaScript 
await fetch("https://openrouter.ai/api/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: "Bearer " + process.env.OPENROUTER_API_KEY,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "google/gemini-3.1-pro-preview",
    messages: [{ role: "user", content: "Hello" }],
  }),
});

Python 
import os, json, urllib.request
req = urllib.request.Request(
    "https://openrouter.ai/api/v1/chat/completions",
    data=json.dumps({"model": "google/gemini-3.1-pro-preview", "messages": [{"role": "user", "content": "Hello"}]}).encode(),
    headers={"Authorization": "Bearer " + os.environ["OPENROUTER_API_KEY"], "Content-Type": "application/json"},
)
print(urllib.request.urlopen(req).read().decode())

JSON · History JSON