Last refreshed 2026-06-16. Next refresh: weekly.
Why use Mistral Large on GCP Vertex AI?
GCP Vertex AI offers Mistral Large with pay-as-you-go pricing at $0.32/1M input tokens. Vertex AI is Google Cloud's managed AI platform, offering access to Gemini models and hundreds of partner models alongside tools for fine-tuning, grounding, vector search, and end-to-end MLOps pipelines.
Compare Mistral Large across 8 providers to find the best fit for your use caseInput / 1M
$0.32
Output / 1M
$0.96
Cache
Not sourced
Batch
Not sourced
Setup recipe
Python + curlInstall
pip install google-cloud-aiplatformAuth
export GOOGLE_CLOUD_PROJECT=...Call
import os
import vertexai
from vertexai.generative_models import GenerativeModel
vertexai.init(project=os.environ["GOOGLE_CLOUD_PROJECT"], location="us-central1")Model ID
mistral-large-1Request example
import os
import vertexai
from vertexai.generative_models import GenerativeModel
# Reads GOOGLE_CLOUD_PROJECT from env; authenticates via Application Default Credentials
vertexai.init(project=os.environ["GOOGLE_CLOUD_PROJECT"], location="us-central1")
model = GenerativeModel("mistral-large-1")
response = model.generate_content("Hello")
print(response.text)Gotchas
- For Google-published models use the model name directly, e.g. "gemini-2.0-flash-001". For third-party publishers (Anthropic, Meta, etc.) use the full publisher path, e.g. "publishers/anthropic/models/claude-3-5-sonnet-v2@20241022".
- The examples expect GOOGLE_CLOUD_PROJECT; rename it only if your application config maps the new variable.
Compare Mistral Large Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| NVIDIA NIM | — | — |
| Microsoft Foundry | $4.00 | $12.00 |
| AWS Bedrock | $2.00 | $6.00 |
| Mistral AI Studio | $2.00 | $6.00 |
| IBM watsonx | $10.00 | $10.00 |
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.32 |
| Output tokens | $0.96 |
Capabilities
VisionJSON / Tool useStructured Outputs
About Mistral Large
Mistral Large is a language model from MistralAI. It is deprecated (originally released 2024-02-08); use it only for reproducing earlier results or evaluating drift over time.
Model Specs
Released2024-02-08
Parameters123B
Context32k
Knowledge cutoff2024-03