google/gemini-2.5-pro
Aliases: gemini-pro, 2.5-pro
$1.25
Input / 1M
$10.00
Output / 1M
1.0M
Context
130 t/s
Speed
Public benchmark scores
Sourced from each provider's published numbers. Verify before quoting.
Quality index
80
MMLU
89.2
GPQA
84
HumanEval
92.6
MATH
91.6
SWE-bench
63.8
Arena Elo
1380
Sources: google-deepmind-blog, lmsys-arena
Capabilities
toolsvisionaudio_inputjson_modestructured_outputstreamingthinking
Input modalities: text, image, file, audio, video
Use gemini-2.5-pro via Relay
Configure the model alias in YAML, then call it from Python.
YAML
# models.yaml
version: 1
models:
gemini-pro:
target: google/gemini-2.5-pro
credential: $env.GOOGLE_API_KEYPython
from relay import Hub
async with Hub.from_yaml("models.yaml") as hub:
resp = await hub.chat(
"gemini-pro",
messages=[{"role": "user", "content": "Hello"}],
)
print(resp.text, resp.cost_usd)pip install ai5labs-relay · full docs on GitHub