Mistral Agents API
Agent API from Mistral AI
The Mistral Agents API is a Mistral AI interface for building agents with Mistral models and built-in connectors such as web search, code interpreter, image generation and a document library. Conversations are stored server side so context persists across sessions, and external tools can be connected via MCP. For multi-agent flows, you list other agents under an agent's handoffs, to which it can pass tasks or the whole conversation, executed either server side at Mistral or client side. The API is proprietary and billed per token and per tool call.
Good fit if
Focus: Developers building agents with Mistral models without their own orchestration infrastructure
- your project is about Research agents with web search, Multi-step flows with handoffs or Document-based assistants
- someone on your team writes code
- you want to get started quickly (learning curve: flat)
Probably not if
- nobody on your team writes code (1/5 for use without developers)
Key figures
- Usable without developers
- 1/5
- Scalability
- 5/5
- Integrations
- 3/5
- Versioning
- 2/5
- Observability
- 2/5
Editorial rating on a scale from 1 to 5. Methodology
Fact sheet
- Category
- Developer
- Type
- Agent API from Mistral AI
- Licence
- Proprietär
- Pricing
- Usage-basedBilled per token by model, e.g. Mistral Large at $0.50 per million input tokens and $1.50 per million output tokens; batch processing 50% cheaper, cached input tokens up to 90% cheaper. Tool APIs are billed per call. SAML SSO requires an Enterprise plan.
- Deployment
- Cloud
- Models
- Mistral AI
- Compliance
- SOC 2, ISO 27001
- RAG
- Yes
- Multi-Agent
- Yes
- SSO, roles (RBAC)
- SSO yes, RBAC yes
- Latest version
- mistralai 3.2.0 (Python-SDK, PyPI, 2026-10-09)
Key features
- Handoffs between agents
- Built-in connectors (web search, code, images)
- Document library for RAG
- Server-side conversations
- MCP integration
Typical use cases
- Research agents with web search
- Multi-step flows with handoffs
- Document-based assistants
- Data analysis with code interpreter
Market notes
Changes to Mistral Agents API by email
We let you know when the status, pricing or license of Mistral Agents API changes, together with the weekly market notes.
Implementation
Get Mistral Agents API implemented
Free for you. Partners only pay for requests they accept.
Alternatives
Similar systems
Similar in category, features or use cases.
- DeveloperVoltAgentVoltAgent is an open source TypeScript framework for building AI agents with tools, memory, RAG and workflows. For multi-agent systems, specialized subagents work under a supervisor agent that distributes tasks through the automatically provided delegate_task tool and combines the results. The VoltOps platform adds tracing, logs, evals and prompt management, as a cloud service or self-hosted. The framework is MIT licensed, and VoltOps has a free entry plan plus paid plans.View profile
- DeveloperAgent SquadAgent Squad is an open source framework for Python, TypeScript and Swift that distributes requests across multiple specialized agents. A classifier selects the right agent for each message based on agent descriptions and conversation history; the SupervisorAgent additionally coordinates a team of agents in parallel using an agents-as-tools approach. The project was formerly called Multi-Agent Orchestrator, was hosted under awslabs and is now maintained by 2FastLabs. It is licensed under Apache-2.0 and runs locally, in containers or on AWS Lambda.View profile
- DeveloperHaystackHaystack by deepset is a Python framework that developers use to build modular pipelines and agents for RAG, semantic search and assistants. The Agent component calls the model and tools in a loop, shares data via a typed state schema, loads tools from MCP servers and allows human review before tool calls. For multi-agent systems, an agent is wrapped as an AgentTool and given to a coordinator agent as a tool, creating coordinator/specialist architectures. Haystack is licensed under Apache-2.0; deepset additionally offers the Haystack Enterprise Platform with a free Studio plan and an Enterprise plan on request.View profile
- DeveloperLangChain Deep AgentsDeep Agents is an agent harness from LangChain for long, multi-step tasks, built on LangChain and the LangGraph runtime. It includes filesystem backends for context management, optional planning with todo lists, skills, long-term memory and human approval. For multi-agent work, the main agent delegates via the task tool to subagents with their own fresh context, each returning a final report; custom subagents are defined in the subagents parameter, and async subagents handle long-running or parallel work. The library is available for Python and JavaScript under the MIT license; tracing and deployment optionally run on the paid LangSmith platform.View profile