Mistral Small 3.2 is a 24B parameter model optimized for efficiency and performance. Ideal for general-purpose tasks with balanced speed and capability.
Private|256K context|$0.0938/M input|$0.25/M output
Mistral AI
mistralai/ · 13 models
Access 13 Mistral AI models through AnonRouter's privacy-first gateway, including Mistral Small 3.2 24B Instruct, Mistral Small 4, and Mistral Nemo Instruct 2407. Compare pricing, context windows, and capabilities across Mistral AI's text routes — every request anonymized, with no payload logging.
Models
13
Modalities
1
Text
From (input)
$0.019
per 1M tokens
Max context
256K
Private routes
13 / 13
not anonymous-only
Catalog by modality
13 routesText13
Mistral AI models13
Mistral Small 4 unifies instruction following, reasoning, coding, and vision in a single 119B MoE model with 256K context and configurable reasoning effort.
Private|256K context|$0.1875/M input|$0.75/M output
12B model trained jointly by Mistral AI and NVIDIA, it significantly outperforms existing models smaller or similar in size.
Private|131K context|$0.019/M input|$0.03/M output
Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed for efficient local deployment. The model achieves 81% accuracy on the MMLU benchmark and performs competitively with larger models like Llama 3.3 70B and Qwen 32B, while operating at three times the speed on equivalent hardware.
Private|33K context|$0.05/M input|$0.08/M output
Mistral-Small-3.2-24B-Instruct is a drop-in upgrade over the 3.1 release, with markedly better instruction following, roughly half the infinite-generation errors, and a more robust function-calling interface—while otherwise matching or slightly improving on all previous text and vision benchmarks.
Private|128K context|$0.075/M input|$0.20/M output
Mistral Large 3 675B Instruct through Amazon Bedrock Mantle with zero retention.
Private|256K context|$0.50/M input|$1.50/M output
Devstral 2 123B served through Amazon Bedrock with support for AWS zero-data-retention mode.
Private|256K context|$0.40/M input|$2.00/M output
Magistral Small 2509 served through Amazon Bedrock with support for AWS zero-data-retention mode.
Private|128K context|$0.50/M input|$1.50/M output
Ministral 3 3B Instruct served through Amazon Bedrock with support for AWS zero-data-retention mode.
Private|128K context|$0.10/M input|$0.10/M output
Ministral 3 8B Instruct served through Amazon Bedrock with support for AWS zero-data-retention mode.
Private|128K context|$0.15/M input|$0.15/M output
Ministral 3 14B Instruct served through Amazon Bedrock with support for AWS zero-data-retention mode.
Private|128K context|$0.20/M input|$0.20/M output
Voxtral Mini 3B 2507 served through Amazon Bedrock with support for AWS zero-data-retention mode.
Private|32K context|$0.04/M input|$0.04/M output
Voxtral Small 24B 2507 served through Amazon Bedrock with support for AWS zero-data-retention mode.
Private|32K context|$0.10/M input|$0.30/M output