Mistral AI via VerticalAPI

Use Mistral Large, Codestral and Pixtral through an OpenAI-compatible endpoint. BYOK with your Mistral key, zero token markup, EU-hosted models for compliance workloads.

Start free with your Mistral AI key → Read the docs

Endpoint: https://api.verticalapi.com/v1/chat/completions · BYOK header: X-Provider-Key: <your-mistral-key>

Supported models

Mistral AI models routed by VerticalAPI

Pass the model ID below as model in any OpenAI-compatible request. New Mistral AI models are typically supported within 24h of release.

Model ID	Name	Context	Pricing (provider)
`mistral-large-latest`	Mistral Large 2	128K	$2 / $6 per 1M tok
`codestral-latest`	Codestral	256K	$0.30 / $0.90 per 1M tok — code-tuned
`pixtral-large-latest`	Pixtral Large	128K	$2 / $6 per 1M tok — multimodal
`ministral-8b-latest`	Ministral 8B	128K	$0.10 / $0.10 per 1M tok — edge

Pricing reflects Mistral AI's rates — you pay Mistral AI directly. VerticalAPI adds zero markup on tokens.

Quickstart

5-line Mistral AI call via VerticalAPI

Drop-in replacement for the OpenAI SDK. Works with the OpenAI Python client, Node, Go, curl — anything that speaks HTTP.

                mistral_quickstart.py
                Python
            
from openai import OpenAI

client = OpenAI(
    base_url="https://api.verticalapi.com/v1",
    api_key="vapi_...",
    default_headers={"X-Provider-Key": "..."}
)

response = client.chat.completions.create(
    model="mistral-large-latest",  # Mistral AI
    messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)

Why use Mistral AI via VerticalAPI

Four reasons developers route Mistral AI through us

Zero token markup

You pay Mistral AI directly with your own key. VerticalAPI's revenue is the gateway subscription, not a tax on your tokens.

One key, every provider

Mistral AI alongside OpenAI, Anthropic, Gemini and 12 more — same OpenAI-compatible endpoint, same SDK, switchable per-request.

Latency & cost monitoring

Per-request token counts, p50/p95 latency and cost dashboards out of the box. Compare Mistral AI to other providers on identical prompts.

Observability built in

Every Mistral AI call gets a trace ID, replayable payload and audit log entry. Wire to Datadog or Sentry via OpenTelemetry.

Best for

Where Mistral AI shines

EU data residency code completion (Codestral) open-weights deployment fine-tuning

FAQ

Common questions about Mistral AI on VerticalAPI

Why use Mistral via VerticalAPI?

EU-hosted inference for GDPR-sensitive workloads, plus a single key/dashboard alongside your other providers. Codestral is one of the strongest fill-in-the-middle code models available.

Are open-weights models like Mistral 7B included?

VerticalAPI routes to la-plateforme.mistral.ai endpoints. For self-hosted open weights, point your Mistral key at your own deployment URL via the dashboard.

Does function calling work?

Yes. Mistral Large, Small and Codestral support OpenAI-format tools. tool_choice is forwarded as Mistral's tool_choice mode.

Switch providers

All supported LLM providers

Same endpoint, same SDK — just change the model and the BYOK header.

OpenAI Anthropic Google Gemini Mistral AI Meta Llama xAI Grok Groq Together AI Fireworks AI Perplexity Sonar Cohere AI21 Labs AWS Bedrock Azure OpenAI Google Vertex AI

Ship on Mistral AI in 60 seconds

Free tier — bring your own Mistral AI key, zero markup, OpenAI-compatible endpoint.

Get your VerticalAPI key →