Mistral Large 2
Mistral Large 2 is worth evaluating for coding, rag, and agents when its provider route and context window match the workload.
Use it for
- Teams evaluating coding, rag, and agents
- Workloads that can use a 128k context window
- Buyers comparing 3 tracked provider routes
Do not use it for
- Workloads where another current model has stronger sourced task evidence
- Family
- Mistral Large
- Released
- 2025-11-25
- Context
- 128k
- Parameters
- 123B
- Architecture
- Decoder Only
- Knowledge cutoff
- 2025-07
- Specialization
- general
- Openness
- Open weights
- License
- Mistral LicenseCommercial use: non-commercial
- Weights
- Unknown
- Code
- Unknown
- Training
- Fine-tuned
Cheapest of 3 routes · AWS Bedrock
About
Advanced reasoning and coding model, multilingual with native function calling and JSON output
Mistral Large 2 is an open-weight model in the Mistral Large family. The structured metadata tracks a 128k-token context window, multimodal input, function calling, tool use, and structured outputs. This page tracks provider routes through IBM watsonx, AWS Bedrock, and Mistral AI Studio, with the cheapest tracked route listed at $0.48 input and $2.4 output per 1M tokens. Headline tracked benchmarks include HellaSwag 93.8, HumanEval 84.8, and Massive Multitask Language Understanding 84.0.
Top use-case fit: coding, agents, and build tasks
Coding
Q/$ C1 relevant benchmark in the decision map.
RAG
Included by capability and metadata signals in the decision map.
Agents
Included by capability and metadata signals in the decision map.
Provider price ladder
Compare all 3Compare API pricing across 3 providers for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Batch in / out | Route |
|---|---|---|---|---|
| AWS Bedrock | $0.480 | $2.40 | - | Serverless |
| IBM watsonx | $2.00 | $6.00 | - | Serverless |
| Mistral AI Studio | - | - | $1.00 / $3.00 | ServerlessPartial |
Available via routers & gateways(11)
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 400+ models from 60+ providers via a single OpenAI-compatible API, with optional auto-routing that selects the best model per prompt.
Portkey
GatewayProduction AI gateway routing to 1,600+ LLMs with failover, load balancing, semantic caching, and guardrails; Apache 2.0 core is fully self-hostable with the complete feature set.
AIRouter
RouterCommercial LLM router that analyzes incoming requests and routes to the optimal model for cost/quality/latency via a drop-in OpenAI-compatible API, with a privacy-preserving embedding mode that avoids sending prompt content.
Amazon Bedrock Intelligent Prompt Routing
RouterAWS Bedrock's native intelligent prompt router that routes prompts between Anthropic Claude model tiers (Haiku/Sonnet) based on predicted task complexity, with no extra per-routing charge.
Martian
RouterAI-powered LLM router that analyzes each prompt in real-time to select the optimal model, targeting 20–97% cost reduction while maintaining quality; San Francisco startup reportedly nearing $1.3B valuation.
Capabilities
Benchmark peer barsfor Coding
Benchmark scores(6)
| Benchmark | Score | Version | Evaluation | Source |
|---|---|---|---|---|
| HellaSwag | 93.8 | 10-shotObserved 2026-03-06 | — | Source |
| HumanEval | 84.8 | pass@1Observed 2026-03-06 | — | Source |
| Massive Multitask Language Understanding | 84.0 | 5-shotObserved 2026-03-06 | — | Source |
| Chatbot Arena | 1265.0 | —Observed 2026-04-15 | — | Source |
| BFCL | 38.4 | —Observed 2026-04-14 | — | Source |
| MMLU PRO | 69.7 | —Observed 2026-04-14 | — | Source |
Migration checks
No linked migration route is available for this model yet.
Rankings & picks(2)
Compare Mistral Large 2 with other models
Comparison and alternatives
Browse all comparisons →Show all 57 popular comparisonssorted by 7-day search impressions
Frequently asked questions
What is the context window of Mistral Large 2?
Mistral Large 2 has a context window of 128k tokens.
How much does Mistral Large 2 cost?
Mistral Large 2 pricing ranges from $0.48/1M to $2/1M input tokens depending on the provider.
When was Mistral Large 2 released?
Mistral Large 2 was released on 2025-11-25.
Which providers offer Mistral Large 2?
Mistral Large 2 is available from 3 providers: IBM watsonx, AWS Bedrock, Mistral AI Studio.
What benchmarks has Mistral Large 2 been tested on?
Mistral Large 2 has been evaluated on 6 benchmarks, including HellaSwag, HumanEval, Massive Multitask Language Understanding, Chatbot Arena, BFCL.
Cheapest of 3 routes · AWS Bedrock