Mistral Large 4 on Vercel AI Gateway

Mistral Large · MistralAI

Serverless
Open Weights

Last refreshed 2026-11-20. Next refresh: weekly.

Why use Mistral Large 4 on Vercel AI Gateway?

Vercel AI Gateway offers Mistral Large 4 with pay-as-you-go pricing at $0.70/1M input tokens. Vercel AI Gateway is a unified AI proxy providing a single OpenAI-compatible API endpoint to 275+ models from 25+ providers including Anthropic, OpenAI, Google, Meta, Mistral, DeepSeek, xAI, Alibaba, Amazon, ByteDance, Cohere, MiniMax, MoonshotAI, KwaiPilot, Black Forest Labs, Recraft, Voyage AI, NVIDIA, and more.

Compare Mistral Large 4 across 3 providers to find the best fit for your use case
Input / 1M
$0.70
Output / 1M
$2.10
Cache
read $0.070
Batch
Not sourced

Setup recipe

Python + curl
Install
pip install openai
Auth
export AI_GATEWAY_API_KEY=...
Call
import os
from openai import OpenAI
client = OpenAI(
    api_key=os.environ["AI_GATEWAY_API_KEY"],
Model ID
mistral/mistral-large-4

Request example

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["AI_GATEWAY_API_KEY"],
    base_url="https://ai-gateway.vercel.sh/v1"
)
response = client.chat.completions.create(
    model="mistral/mistral-large-4",
    messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)

Gotchas

  • Use provider model ID "mistral/mistral-large-4", not the LLMReference slug "mistral-large-4".
  • creator/model-name e.g. kwaipilot/kat-coder-pro-v2
  • The examples expect AI_GATEWAY_API_KEY; rename it only if your application config maps the new variable.

Compare Mistral Large 4 Across Providers

ProviderInput (per 1M)Output (per 1M)
Mistral AI Studio$0.70$2.10
OpenRouter$0.70$2.10
Vercel AI Gateway$0.70$2.10

Pricing

TypePrice (per 1M)
Input tokens$0.70
Output tokens$2.10

Capabilities

VisionMultimodalJSON / Tool useStructured OutputsPrompt CachingBatch API

About Mistral Large 4

Mistral Large 4 (API id mistral-large-4-0, public preview launched 6 October 2026) is Mistral AI's multimodal mixture-of-experts model: 1.05T total parameters, 49B active per token (52B including embeddings and output layers), and a 1.6B vision encoder, with a 1M-token context window. On 29 October 2026 Mistral released the weights of an improved version on Hugging Face under the Mistral Ecosystem Open-Weight License (a modified MIT license that requires a separate commercial license to run a Model-as-a-Service business).

Get Started

Model Specs

Released2026-10-06
Parameters1.05T (49B active)
Context1M
ArchitectureMixture of Experts

Related Models on Vercel AI Gateway