Mistral
on Orq.ai
Use Mistral’s foundation models through a single Orq.ai API. Route models such as Mistral Large 3, Mistral Medium 3, Mistral Small 4, and Ministral 8B via Orq’s AI Router for chat, reasoning, coding, and multimodal workloads.
Capabilities:
Chat
Embeddings
Reasoning
Vision
Models Supported:
Mistral Moderation 2603
codestral-2508
codestral-embed-2505
codestral-embed-2505
devstral-2512
Provider HQ:
Mistral AI, headquartered in Paris, France
Access Mistral through Orq.ai’s AI Router
Mistral AI is a European LLM provider offering a family of text and code models (Large, Medium, Small, Nemo, Ministral, Codestral) via a managed cloud API, with options for self‑hosting and enterprise deployments. These models cover high‑end reasoning, general‑purpose coding, and cost‑efficient high‑volume use cases with strong EU data‑sovereignty guarantees.
Mistral models available on Orq.ai
Model | Type | Context / scope | Best for | Pricing tier |
|---|---|---|---|---|
Mistral Large 3 | Chat / reasoning / coding | Long context (hundreds of thousands of tokens; check Mistral / Orq docs) | Complex reasoning, analysis, coding, and high‑stakes tasks where you want Mistral’s most capable cloud model | Premium – around 0.50 USD / 1M input tokens and 1.50 USD / 1M output tokens on Mistral’s latest Large pricing; older “Large 2 / 2407” generation appears at about 2.00 USD input and 6.00 USD output per 1M tokens depending on provider |
Mistral Medium 3 | Chat / reasoning / coding | Medium–large context (verify in docs) | Everyday production workloads, RAG, coding, and product features that balance quality with cost and latency | Mid‑tier – commonly around 0.40 USD / 1M input tokens and 2.00 USD / 1M output tokens |
Mistral Small 4 / Ministral 8B | Chat / fast / cost‑efficient | Medium context (confirm in docs) | Fast, lower‑cost tasks such as classification, extraction, lightweight chat, routing, and high‑volume support workflows | Cost‑efficient – Mistral Small 4 is typically around 0.15 USD / 1M input and 0.60 USD / 1M output tokens; Ministral 8B around 0.10 USD / 1M input and 0.10 USD / 1M output tokens |
Why use Mistral through Orq.ai?
This gives teams a practical way to use Mistral where it performs best while centralising routing, observability, evals, and cost controls across the wider model stack.
Pricing
Plans and API access
Mistral AI cloud pricing is pay‑per‑token, with free credits and startup programs layered on top:
Entry‑tier / cheapest models:
Mistral Nemo: about 0.02 USD / 1M input tokens and 0.04 USD / 1M output tokens
Ministral 8B: about 0.10 USD / 1M input and 0.10 USD / 1M output tokens
Tier / model | Input / price | Output / included | Cached / notes |
|---|---|---|---|
Mid‑tier: | Mistral Small 4: roughly 0.15 USD / 1M input and 0.60 USD / 1M output tokens.margindash+1 | Mistral Medium 3: roughly 0.40 USD / 1M input and 2.00 USD / 1M output tokens.margindash+1 | |
Premium: | Mistral Large 3: about 0.50 USD / 1M input and 1.50 USD / 1M output tokens on the latest published pricing.getapipulse+2 | Legacy Mistral Large 2 / 2407 still appears at around 2.00 USD input and 6.00 USD output per 1M tokens with some providers. | Mistral also offers free experiment tiers and startup credits (for example up to roughly 30K USD in credits via partner programs) |
Check the Orq.ai pricing page and your workspace’s provider configuration for current per‑model rates, quotas, and plan details.
Compatible frameworks and tools
Orq.ai exposes Mistral AI through:
a Mistral provider configuration in the AI Gateway / Model Garden, and
an OpenAI‑compatible API layer for applications that expect that interface
That means:
Existing backend workflows that already talk to Orq’s OpenAI‑compatible endpoint can be wired to call Mistral models through Orq.ai without a separate direct integration.
Agents, code assistants, and tools that integrate with Orq.ai (for example, via OpenAI‑compatible or HTTP tools) can be configured so that text and code steps are served by Mistral, while other steps use different providers.
Check the Orq.ai integration docs for the latest supported frameworks and tools for Mistral AI.
FAQs
Do I need a separate Mistral account to use Mistral through Orq.ai?
You can either connect your own Mistral API key into Orq.ai or, where available, use Mistral usage billed via Orq.ai; the exact options depend on your Orq plan, region, and how Mistral is configured in your workspace. In both cases, Orq.ai gives you one place to manage routing, observability, and cost controls around that Mistral usage.
Can I route only some workflows to Mistral and others to different providers?
Yes. You define routes per workflow in Orq.ai and decide which ones should use Mistral vs other models, so you can reserve Mistral for specific regions, compliance needs, or workloads while sending other tasks to different providers.
Does using Mistral through Orq.ai add latency?
Orq.ai is designed as a lightweight router layer, so the added overhead is small compared to the model’s own latency. You can use routing policies, caching, and provider selection to keep end‑to‑end performance within your targets.
Alternatives to
Mistral
Anthropic
Use Claude Opus 4.7, Sonnet 4.6, Haiku 4.5, and other supported Claude models through one API.
Chat
Code
Reasoning
Vision
Models:
claude-opus-5
claude-sonnet-5
claude-fable-5
Open AI
Use OpenAI's foundation models through a single Orq.ai API. Route models such as GPT-4.1, GPT-4.1-mini, o3-mini, and GPT-4o-class models via Orq's AI Router for chat, reasoning, coding, and multimodal workloads.
Chat
Code
Image Generation
Reasoning
Speech
Vision
Models:
gpt-5.5 (EU)
gpt-5.6-luna (EU)
gpt-5.6-sol (EU)
Google AI
Use Google’s Gemini models through a single Orq.ai API. Route models such as Gemini 3.1 Pro, Gemini 2.5 Flash, and Gemini 2.0 Flash‑Lite via Orq’s AI Router for chat, reasoning, coding, and multimodal workloads.
Chat
Code
Embeddings
Image Generation
Reasoning
Speech
Vision
Models:
gemini-3.5-flash-lite (Gemini API)
gemini-3.6-flash (Gemini API)
Gemini 3 Pro Image
AWS
Use AWS Bedrock’s foundation models through a single Orq.ai API. Route models such as Amazon Nova, Amazon Titan Text, and compatible third‑party models exposed via Bedrock through Orq’s AI Router for chat, reasoning, coding, and multimodal workloads.
Chat
Code
Embeddings
Reasoning
Vision
Models:
eu.anthropic.claude-opus-5
global.anthropic.claude-opus-5
us.anthropic.claude-opus-5
