Catalogue
Models
376 models, cross-linked to hardware verdicts and live provider pricing.
19 models
Mistral10 sizes here
Mistral Medium 3.5Mistral AIMistral Medium 3.5 is a 128-billion-parameter text-and-image model with a quarter-million-token request limit and broad measured coverage across coding, maths and creative tasks.Mar 2026128B262K$1.50 / $7.50per 1Mvia OpenRouter—Mistral Small 4Mistral AIMistral Small 4 is a 119.4-billion-parameter text-and-image model released in January 2026 with a permissive Apache licence.Jan 2026119B262K$0.15 / $0.60per 1Mvia OpenRouter—Mistral Large 3 2512Mistral AIDec 2025—262K$0.50 / $1.50per 1Mvia OpenRouter—Mistral Medium 3.1Mistral AIMistral Medium 3.1 is a hosted-only multimodal model that accepts text, images and files, with a 131,072-token request limit.Aug 2025—131K$0.40 / $2.00per 1Mvia OpenRouter—Mistral Small 3.2 24BMistral AIMistral Small is a 24-billion-parameter text-and-image model released in 2025 with a permissive Apache licence.Jun 202524B256K$0.075 / $0.20per 1Mvia OpenRouter—Mistral Medium 3Mistral AIMistral Medium 3 is a hosted-only text-and-image model from Mistral AI that can handle up to 131,072 tokens in a single request.May 2025—131K$0.40 / $2.00per 1Mvia OpenRouter—Mistral Small 3.1 24BMistral AIMistral Small 3.1 is a 24-billion-parameter text-and-image model released in 2025 with a permissive Apache licence.Mar 202524B128K$0.35 / $0.56per 1Mvia OpenRouter—Mistral Small 3Mistral AIMistral Small 3 is a 23.6-billion-parameter text model released in early 2025 with a permissive Apache licence.Jan 202523.6B33K$0.050 / $0.080per 1Mvia OpenRouter—Mistral Large 2407Mistral AIMistral Large 2407 is a hosted-only text model from Mistral AI that accepts file attachments and handles up to 131,072 tokens in a single request.Nov 2024—131K$2.00 / $6.00per 1Mvia OpenRouter—Mistral LargeMistral AIMistral Large is a hosted-only text model from Mistral AI that handles up to 128,000 tokens in a single request.Feb 2024—128K$2.00 / $6.00per 1Mvia OpenRouter—Devstral 2 2512Mistral AIDevstral 2 is a 125-billion-parameter coding specialist from Mistral AI that accepts text and files for web development and code generation tasks.Nov 2025125B262K$0.40 / $2.00per 1Mvia OpenRouter—
Ministral3 sizes here
Ministral 3 14B 2512Mistral AIMinistral 3 is a compact downloadable model from Mistral AI that accepts text and images and handles up to 262,144 tokens in a single request.Oct 202513.9B262K$0.20 / $0.20per 1Mvia OpenRouter—Ministral 3 8B 2512Mistral AIMinistral is a small downloadable model with a permissive Apache licence and a 262,144-token request limit.Oct 20258.9B262K$0.15 / $0.15per 1Mvia OpenRouter—Ministral 3 3B 2512Mistral AIMinistral 3 is a small downloadable model from Mistral AI that accepts text and images and returns text.Oct 20253.8B131K$0.10 / $0.10per 1Mvia OpenRouter—Codestral 2508Mistral AICodestral 2508 is Mistral AI's hosted-only coding specialist, built for long-context code analysis with a 256,000-token request limit.Aug 2025—256K$0.30 / $0.90per 1Mvia OpenRouter—Voxtral Small 24B 2507Mistral AIVoxtral Small is a 24.3-billion-parameter speech-to-text model from Mistral AI with a permissive Apache licence.Jul 202524.3B32K$0.10 / $0.30per 1Mvia OpenRouter—SabaMistral AISaba is a lightweight text-and-file model from Mistral AI with a 32,768-token request limit.Feb 2025—33K$0.20 / $0.60per 1Mvia OpenRouter—Mistral NemoMistral AIMistral Nemo is a compact downloadable text model with a permissive Apache licence and a generous request limit for its size.Jul 202412.2B131K$0.019 / $0.030per 1Mvia OpenRouter—Mixtral 8x22B InstructMistral AIMixtral is a large downloadable text model from Mistral AI that uses a mixture-of-experts design, keeping 39 billion parameters active per word out of 140.6 billion total.Apr 2024141B / 39B66K$2.00 / $6.00per 1Mvia OpenRouter—