Mistral · Embeddings
Mistral Embed API pricing
mistral/mistral-embed
Text embeddings for search and retrieval. Mistral Embed by Mistral, routed through INFRO on a Mistral account you connect — alongside every other provider you run. Mistral bills you for it directly, on that account and at your own rate. INFRO adds routing, failover, request logs, cost attribution and policy around it, and takes no part of what you pay Mistral.
Pricing
Mistral rate
$0.10
per 1M tokens, billed to you by Mistral
INFRO adds
$0
0% markup on model spend
Calling Mistral Embed
POST /v1/embeddingsimport os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["INFRO_API_KEY"],
base_url="https://api.infro.io/v1",
)
response = client.embeddings.create(
model="mistral/mistral-embed",
input=["How do I rotate a gateway key?"],
)What this modality supports
- OpenAI-compatible
- Same-model failover
- Budgets before the call
- Vectors never stored
OpenAI's embeddings request shape on your own OpenAI, Azure OpenAI, Mistral or OpenAI-compatible connection. Failover moves only to the same model, because vectors from different models are not comparable. Each request records the tokens embedded and an estimate of what your provider will bill; vectors are never stored.
Providers that serve Mistral Embed
You request "mistral/mistral-embed" from INFRO; it sends each provider the id that provider expects. Connect your own account with any of them, and INFRO routes and fails over between the ones you connect.
| Provider | Model id sent |
|---|---|
| Mistral | mistral-embed |
Alternatives for text embeddings for search and retrieval
Same modality, nearest in price. All of them share the request shape above, so comparing them is a one-word change.
More Mistral models
All Mistral models- Mistral Large 3mistral/mistral-large-3$0.50 / $1.50
- Mistral Medium 3.5mistral/mistral-medium-3.5$1.50 / $7.50
- Mistral Small 4mistral/mistral-small-4$0.15 / $0.60
- Ministral 3 14Bmistral/ministral-3-14b$0.20 / $0.20
- Ministral 3 8Bmistral/ministral-3-8b$0.15 / $0.15
- Ministral 3 3Bmistral/ministral-3-3b$0.10 / $0.10
Mistral Embed: questions
- How much does the Mistral Embed API cost?
- Mistral's published list rate for Mistral Embed is $0.10 per 1M tokens (checked 2026-10-05). The provider account you connect bills you at the rate on that account, so a negotiated rate replaces the list rate. INFRO adds 0% to model spend.
- Which providers serve Mistral Embed?
- In INFRO's provider registry, Mistral Embed can be served by Mistral. You connect your own account with any of them, and INFRO routes and fails over between the ones you connect.
- What is the Mistral Embed model ID?
- Request it from INFRO as "mistral/mistral-embed". INFRO sends each provider its own id: Mistral "mistral-embed".
- How do I call Mistral Embed through an OpenAI-compatible API?
- Point an OpenAI SDK, or any HTTP client, at https://api.infro.io/v1 with an INFRO gateway key and send model "mistral/mistral-embed" to POST /v1/embeddings. INFRO runs the request on a provider account you connected and returns the provider's response with an estimated cost.
- Does INFRO mark up Mistral Embed usage?
- No. Mistral or the provider you connect bills model usage to your own account. INFRO charges a software subscription for routing, failover, observability, budgets and policy, and takes 0% of model spend.
Work out what Mistral Embed would cost you
Put your monthly usage of this model into the calculator to see the provider cost on your own account and the INFROsubscription side by side, never summed.