Tasks and inputs
Step 5 Preview is listed for Image-text-to-text, Text generation, Video-text-to-text. It accepts text, image, video and produces text. Use the publisher’s input format and preprocessing for your chosen deployment.
Step 5 Preview is StepFun’s multimodal reasoning API for coding, research and tool workflows, with a one-million-token context.
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
Step 5 Preview is StepFun’s multimodal reasoning API for coding, research and tool workflows, with a one-million-token context.
Step 5 Preview accepts text, images and video and returns text. Its one-million-token context is useful when an agent needs source files, logs and screenshots in the same conversation. The maximum output is 64K tokens. Tool calling, streaming, JSON Mode and JSON Schema are documented features; the application supplies the tools and executes approved calls.
Use step-5-preview on the StepFun API. Reasoning effort supports low, medium and high. Set an output allowance that fits the job instead of assuming the service will stop at a short answer. Images can be supplied by URL or Base64, while video can also use a Files API reference. Preserve tool responses and the relevant source material as the conversation progresses.
The standard API rate is $1 per million uncached input tokens, $0.05 for cached input and $2.70 for output. Output billing includes reasoning as well as the final answer. A Step Plan subscription uses a different allowance from ordinary API billing.
For an engineering trial, provide a failing test, the relevant files and a screenshot of the expected result. Check the resulting patch, test outcome and number of retries. For document work, ask for a conclusion with supporting passages, then verify whether every cited passage actually establishes the claim.
Compare the model on the work you need to complete.
Step 5 Preview is listed for Image-text-to-text, Text generation, Video-text-to-text. It accepts text, image, video and produces text. Use the publisher’s input format and preprocessing for your chosen deployment.
Documented limits: 1M context and 65.54K maximum output. The listed route charges $1.00 input and $2.70 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.
Use the model identifier and account requirements for the selected API route. Confirm its request limits and output format with one complete task before connecting a larger workflow.
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.