Tasks and inputs
Mistral Small 4 is listed for Image-text-to-text, Text generation. It accepts text, image and produces text. Use the publisher’s input format and preprocessing for your chosen deployment.
SyncDev model directory · Profile updated Oct 13, 2026
Mistral Small 4 combines instruction-following, reasoning and coding in an Apache-2.0 open-weight model released.
The specification score summarizes recorded features and limits. It is not a benchmark result.
Recorded modality support shows what this model can accept and produce. An undocumented modality is shown as unknown rather than assumed to be unsupported.
Accepts
Produces
Mistral Small 4 combines instruction-following, reasoning and coding in an Apache-2.0 open-weight model released.
The publisher documents 119B total parameters and 6.5B active parameters. The model still needs access to the full set of weights when serving. Context length, precision, batching and the inference engine add further memory costs. Do not size a deployment using the active count alone.
The documented API context allowance is 256,000 tokens, with rates of $0.15 input and $0.60 output per million tokens. This makes Small 4 a useful candidate to evaluate before routing every ordinary task through a more expensive model. Whether it is sufficient depends on your accepted-result rate and the corrections it needs.
Test short code repairs, document extraction and requests with strict formatting. Include ambiguous inputs and facts that are missing from the source. Check schema validity and tool arguments in addition to prose quality.
For a longer agent task, measure whether the model completes the deliverable and recovers when a tool fails. Keep the same runtime and time budget when comparing with Mistral Medium 3.5. A higher token rate can still be cheaper per finished task when it reduces enough retries; the reverse can also be true.
Publisher source 1 Deployment limits and commercial terms belong to the selected checkpoint or API route.
Compare the model on the work you need to complete.
Mistral Small 4 is listed for Image-text-to-text, Text generation. It accepts text, image and produces text. Use the publisher’s input format and preprocessing for your chosen deployment.
Documented limits: 256K context and 256K maximum output. The listed route charges $0.15 input and $0.60 output per million tokens. Measure a completed task using the prompts, documents and tools your application will use. Include reasoning and retries in the result.
The weights are downloadable under Apache-2.0. Check runtime support and size the complete model and working context for your expected concurrency.
These records share a directory category. Check the source card, output type and deployment requirements before treating a model as a replacement.
Anthropic
Claude’s small model for high-volume extraction, classification and routing, with adaptive thinking and a 1M-token context window.
Mistral AI
Mistral Large 4 is an open-weight multimodal model released in public preview on the publisher’s announced release, for general reasoning, coding and agent applications.
OpenAI
GPT-6.1 Sol is OpenAI's updated Sol model for coding and professional tasks. It accepts text and images and returns text.
inclusionAI
Ling 3.1 Flash is inclusionAI’s hybrid reasoning model for coding and tool agents, available through a hosted AI Gateway route.
Anthropic
Claude Sonnet 5.5 is an Anthropic language model that accepts text and images and returns text.
MiniMax
MiniMax M3.1 Flash Preview is a multimodal reasoning model for code and agent workflows, accessed through eligible MiniMax plans and tools.