Mistral AI Studio
Researched 21d agoAI LabTier 1Mistral AI
Mistral AI Studio offers 18 tracked models (11 with output token pricing). This catalog covers coding, rag, and agents; open any model detail page for benchmarks, batch tiers, and migration prompts. 16 retired models are listed below.
Covers 7 workload areas across 18 available models and 16 retired; last verified 2026-10-29.
Use it for
- Teams comparing token and batch pricing across this provider's models
- Operators routing coding, rag, and agents workloads through this API
- Batch buyers auditing discount coverage model-by-model
Do not use it for
- Final benchmark picks without opening the relevant model detail page
Tracked models
18
Models available through this provider
Priced output routes
11
Models with output token pricing tracked
Cheapest output
$0.100
Ministral 3B on this route
Batch-ready models
2
Models with discounted batch pricing
Latest model release
2026-10-20
30d since newest release
Freshness
2026-10-29
Researched 21d ago
Routes available via routers & gateways
LiteLLM
GatewayOpen-source Python SDK and proxy server that unifies 100+ LLM APIs behind a single OpenAI-compatible interface, with load balancing, cost tracking, and configurable failover.
OpenRouter
HybridUnified hybrid gateway to 500+ models from 80+ providers via a single OpenAI-compatible API, with an optional Auto Router that selects a model per prompt from market spend data.
Portkey
GatewayProduction AI gateway routing to 1,600+ LLMs with failover, load balancing, caching, and guardrails; MIT-licensed open-source core is self-hostable. Now part of Palo Alto Networks as Prisma AIRS AI Gateway.
AIRouter
RouterCommercial LLM router (branded "AI Router" on its site) that picks the best model per request via a Decision API or an OpenAI-compatible Chat Completions endpoint, with a private selection mode that routes on anonymized patterns; sold as BYOK subscription plans priced by routed tokens.
Martian
RouterMartian Gateway: unified OpenAI- and Anthropic-compatible API to 200+ models with per-model token pricing, from Martian, whose site now presents it as an interpretability research lab.
Neutrino AI
RouterCommercial LLM router that dynamically routes each query to the best-suited model with load balancing and fallback handling.
Information
Mistral AI is a French company developing advanced language models and AI technologies. Their platform focuses on creating fast, open-source, and secure language models that can be specialized for specific business use cases. Mistral AI's offerings include: 1. Large language models: Their flagship model, Mistral Large 2, excels in code generation, mathematics, reasoning, and multilingual support . 2. Specialized models: They offer models like Codestral for code generation tasks and MathΣtral for mathematical computations . 3. Fine-tuning capabilities: Mistral AI allows users to fine-tune their models on custom datasets and code using their platform . 4. Agent creation: Users can create custom AI agents by tweaking Mistral Large 2 with specific instructions . 5. SDK support: They provide SDKs for both Python and TypeScript to facilitate easier integration of their models into applications . 6. Cloud partnerships: Mistral AI models are available on major cloud platforms like Amazon Bedrock, Google Cloud's Vertex AI, and others, making them easily accessible to businesses . The company aims to make AI ubiquitous and accessible, targeting a global market while maintaining a strong focus on security and ethical AI development.
Where this host wins
- Coding: 3 tracked models with SWE-bench / HumanEval-style scores.
- RAG: 4 tracked models with ruler / needle retrieval benchmarks.
- Agentic: 5 tracked models with BFCL, tau-bench, and SWE-bench tool-use coverage.
- Long-context: 5 tracked models with context-token or InfiniteBench-class signal.
Getting started
Platform Overview
Mistral AI's platform offers a comprehensive suite of generative AI capabilities, centered around its open-source language models. The platform features models like Mistral 7B and Mistral Large 2, which excel in various natural language processing tasks, including text generation, code creation, and summarization. These models boast impressive context lengths, with Mistral Large 2 capable of processing up to 128,000 tokens, enabling the handling of complex, lengthy inputs. The platform's multilingual proficiency, supporting languages such as English, French, and Spanish, enhances its versatility across different regions and use cases.
Available Models(18)
View all →All models available as Serverless
| Model | Input (per 1M) | Output (per 1M) | Batch input (per 1M) | Batch output (per 1M) |
|---|---|---|---|---|
| $0.0035/min | — | — | — | |
| $0.008/min | — | — | — | |
| $0.004/min | — | — | — | |
| $13.00/1M chars | — | — | — | |
| $0.70 | $2.10 | — | — | |
| $1.50 | $7.50 | — | — | |
| — | — | — | — | |
| $0.10 | $0.30 | — | — | |
| $0 | $0 | — | — | |
| — | — | — | — |
Retired models(16)
View all →| Model | Input (per 1M) | Output (per 1M) | Batch input (per 1M) | Batch output (per 1M) |
|---|---|---|---|---|
Mistral Small 3.1 24B InstructDeprecated Retired November 30, 2025 | — | — | $0.10 | $0.30 |
Devstral Small 2Deprecated Retired March 31, 2026 | $0.10 | $0.30 | — | — |
Devstral 2 123BDeprecated Retired July 31, 2026 | $0.40 | $2.00 | — | — |
Ministral 8BDeprecated Retired December 31, 2025 | $0.15 | $0.15 | $0.05(-67%) | $0.05(-67%) |
Mistral Medium 3Deprecated Retired August 31, 2026 | $0.40 | $2.00 | $0.20(-50%) | $1.00(-50%) |
Mistral Large 2.1 (2411)Deprecated Retired May 31, 2026 | — | — | — | — |
Pixtral LargeDeprecated Retired May 31, 2026 | $2 | $6 | — | — |
Mistral Large 2 (2407)Deprecated Retired March 30, 2025 | — | — | $1.00 | $3.00 |
Mistral NeMo Instruct (2407)Deprecated Retired July 31, 2026 | $0.15 | $0.15 | — | — |
Codestral 22BDeprecated | $0.30 | $0.90 | — | — |