mistral/mistral-large-latest
Aliases: mistral-large
$2.00
Input / 1M
$6.00
Output / 1M
128K
Context
50 t/s
Speed
Public benchmark scores
Sourced from each provider's published numbers. Verify before quoting.
Quality index
60
MMLU
84
GPQA
48
HumanEval
84
MATH
71.5
SWE-bench
—
Arena Elo
—
Sources: mistral-blog
Capabilities
toolsjson_modestructured_outputstreaming
Use mistral-large-latest via Relay
Configure the model alias in YAML, then call it from Python.
YAML
# models.yaml
version: 1
models:
mistral-large:
target: mistral/mistral-large-latest
credential: $env.MISTRAL_API_KEYPython
from relay import Hub
async with Hub.from_yaml("models.yaml") as hub:
resp = await hub.chat(
"mistral-large",
messages=[{"role": "user", "content": "Hello"}],
)
print(resp.text, resp.cost_usd)pip install ai5labs-relay · full docs on GitHub