per 1M tokens
Google: Gemini 2.5 Pro
google/gemini-2.5-pro
Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...
Price
per 1M tokens
Cheaper on Oracle Cloud (−27.3%) versus the lab price
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.
| Provider | Tag | Quant | Input | Output | Context | Uptime | Status | Source |
|---|---|---|---|---|---|---|---|---|
| Oracle Cloud | — | — | $1.25/1M | Not published— | — | — | Listed | oci-pricelist |
| Google AI Studio | google-ai-studio/flex | — | $0.625/1M | $5/1M | 1.0M | — | Live | openrouter-endpoints |
| AtlasCloud | — | fp8 | $1.25/1M | $10/1M | 1M | — | Listed | atlascloud |
| DeepInfra | — | — | $1.25/1M | $10/1M | 1M | — | Listed | deepinfra |
| Google AI Studio | google-ai-studio | — | $1.25/1M | $10/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Inference.net | — | — | $1.25/1M | $10/1M | 1.0M | — | Listed | inferencenet |
| NEAR AI | — | — | $1.25/1M | $10/1M | 1M | — | Listed | nearai |
| Phala | — | — | $2.5/1M | $15/1M | 1.0M | — | Listed | phala |
| Google AI Studio | google-ai-studio/priority | — | $2.25/1M | $18/1M | 1.0M | — | Live | openrouter-endpoints |
| Oracle Cloud | long-context | — | $15/1M | Not published— | — | — | Listed | oci-pricelist |
Monthly bill
Token models use the token counts. Image, video, and audio models use units times the flat rate.
$11.25 at list price for this workload
Cache
per 1M tokens
per 1M tokens
Tiers
- Web search
- $0.014 per request
- Image input
- $1.25 per 1M tokens
- Audio
- $1.25 per 1M tokens
- Audio cache
- $0.125 per 1M tokens
- Reasoning
- $10 per 1M tokens
- Above 200,000 prompt tokens
- in $2.5 · out $15 · cache read $0.25 · audio $2.5
Every rate
| Unit | Input | Output | Flat | Confidence |
|---|---|---|---|---|
| token | $1.25/1M | $10/1M | Not published— | official |
Price history
input or flat output
Daily snapshots
| UTC date | Unit | Input | Output | Flat |
|---|---|---|---|---|
| 2026-09-15 | token | $1.25 | $10 | Not published— |
| 2026-09-16 | token | $1.25 | $10 | Not published— |
| 2026-09-17 | token | $1.25 | $10 | Not published— |
| 2026-09-18 | token | $1.25 | $10 | Not published— |
| 2026-09-19 | token | $1.25 | $10 | Not published— |
| 2026-09-20 | token | $1.25 | $10 | Not published— |
| 2026-09-21 | token | $1.25 | $10 | Not published— |
| 2026-09-22 | token | $1.25 | $10 | Not published— |
| 2026-09-23 | token | $1.25 | $10 | Not published— |
| 2026-09-24 | token | $1.25 | $10 | Not published— |
| 2026-09-25 | token | $1.25 | $10 | Not published— |
| 2026-09-26 | token | $1.25 | $10 | Not published— |
| 2026-09-27 | token | $1.25 | $10 | Not published— |
| 2026-09-28 | token | $1.25 | $10 | Not published— |
| 2026-09-29 | token | $1.25 | $10 | Not published— |
| 2026-09-30 | token | $1.25 | $10 | Not published— |
| 2026-10-01 | token | $1.25 | $10 | Not published— |
| 2026-10-02 | token | $1.25 | $10 | Not published— |
| 2026-10-03 | token | $1.25 | $10 | Not published— |
| 2026-10-04 | token | $1.25 | $10 | Not published— |
| 2026-10-05 | token | $1.25 | $10 | Not published— |
| 2026-10-06 | token | $1.25 | $10 | Not published— |
| 2026-10-07 | token | $1.25 | $10 | Not published— |
| 2026-10-08 | token | $1.25 | $10 | Not published— |
| 2026-10-09 | token | $1.25 | $10 | Not published— |
| 2026-10-10 | token | $1.25 | $10 | Not published— |
| 2026-10-11 | token | $1.25 | $10 | Not published— |
| 2026-10-12 | token | $1.25 | $10 | Not published— |
| 2026-10-13 | token | $1.25 | $10 | Not published— |
| 2026-10-14 | token | $1.25 | $10 | Not published— |
| 2026-10-15 | token | $1.25 | $10 | Not published— |
| 2026-10-16 | token | $1.25 | $10 | Not published— |
| 2026-10-17 | token | $1.25 | $10 | Not published— |
| 2026-10-18 | token | $1.25 | $10 | Not published— |
| 2026-10-19 | token | $1.25 | $10 | Not published— |
| 2026-10-20 | token | $1.25 | $10 | Not published— |
| 2026-10-21 | token | $1.25 | $10 | Not published— |
| 2026-10-22 | token | $1.25 | $10 | Not published— |
| 2026-10-23 | token | $1.25 | $10 | Not published— |
| 2026-10-24 | token | $1.25 | $10 | Not published— |
| 2026-10-25 | token | $1.25 | $10 | Not published— |
| 2026-10-26 | token | $1.25 | $10 | Not published— |
| 2026-10-27 | token | $1.25 | $10 | Not published— |
| 2026-10-28 | token | $1.25 | $10 | Not published— |
| 2026-10-29 | token | $1.25 | $10 | Not published— |
| 2026-10-30 | token | $1.25 | $10 | Not published— |
Alternatives
- abliteration-abliterated-model-large-flash$1.25/1M · Compare
- Gemini 2.5 Pro$1.25/1M · Compare
- Gemini 2.5 Pro$1.25/1M · Compare
- gemini-2.5-pro$1.25/1M · Compare
- google/gemini-2.5-pro$1.25/1M · Compare
- Google: Gemini 2.5 Pro Preview 06-05$1.25/1M · Compare
Parameters (10)
include_reasoningmax_tokensreasoningresponse_formatseedstructured_outputstemperaturetool_choicetoolstop_p
Call this model
OpenRouter id google/gemini-2.5-pro. 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-2.5-pro","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-2.5-pro",
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-2.5-pro", "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())