

Qwen4 Max and Step 5 Preview side by side: specs, capabilities, parameters, and live pricing from the EmpirioLabs catalog.
Qwen4 Max from Alibaba Cloud and Step 5 Preview from StepFun are both in the Text Generation category, available through the EmpirioLabs API.
| Spec | Qwen4 Max | Step 5 Preview |
|---|---|---|
| Model ID | qwen4-max | step-5-preview |
| Author | Alibaba Cloud | StepFun |
| Released | Nov 16, 2026 | Sep 15, 2026 |
| Context window | 983.6K tokens | 1.02M tokens |
| Max output | 262,144 tokens | 131,072 tokens |
| Input | Text Image Video | Text Image Video |
| Output | Text | Text |
| Structured output | JSON Schema | JSON Schema |
| Region | Singapore | International |
| Endpoints | POST /v1/chat/completions POST /v1/responses POST /v1/messages POST /v1beta/models/qwen4-max:generateContent | POST /v1/chat/completions POST /v1/responses POST /v1/messages POST /v1beta/models/step-5-preview:generateContent |
| Capabilities |
Live rates from the EmpirioLabs catalog for both models. Each rate card always matches what the API charges.
Request parameters each model lists on EmpirioLabs, with the allowed values or range where one applies. A dash marks a parameter the model does not list.
| Parameter | Qwen4 Max | Step 5 Preview |
|---|---|---|
| temperature | 0 to 1.99 Default: 0.7 | 0 to 2 Default: 0.5 |
| top_p | 0 to 1 Default: 0.9 | 0.01 to 1 Default: 0.9 |
| max_tokens | 1 to 262144 | 1 to 131072 Default: 4096 |
| stop | string | array |
| enable_thinking | boolean Default: true | - |
| reasoning_effort | low, high, xhigh Default: high | low, medium, high Default: low |
| thinking_budget | 1 to 262144 | - |
| preserve_thinking | boolean Default: true | - |
| seed | 0 to 2147483647 | - |
| top_k | 1 to 100 | - |
| presence_penalty | -2 to 2 | - |
| repetition_penalty | 0.1 to 2 | - |
| n | 1 to 4 Default: 1 | - |
| logprobs | boolean Default: false | - |
| top_logprobs | 0 to 5 Default: 0 | - |
| vl_high_resolution_images | boolean Default: true | - |
Text, image, and video input are supported. Web search, web extractor, code interpreter, text-to-image search, and image-to-image search are optional built-in tools exposed through tool_* parameters. Web search, text-to-image search, and image-to-image search add $0.02 for each invoked call; web extractor and code interpreter run at no extra cost. Web extractor requires web search, and both web extractor and code interpreter require thinking. A single request can invoke a tool more than once, and each invoked call is billed. Thinking is on by default; reasoning_effort sets its depth (low, high, or xhigh, default high), and thinking tokens are billed as output tokens. max_tokens and max_completion_tokens cap reasoning and answer together. Repeated prompt prefixes are cached automatically, and cached input tokens bill at the implicit cache read rate. Explicit cache controls such as cache_control are not supported.
Supports text, image, and video input with a 1M token context, parallel function tools, strict JSON schema output, and reasoning_effort low, medium, or high. Prompt-cache hits are billed at the cache-read rate. Video input supports MP4 under 128 MB, with clips under 5 minutes recommended. This is a preview release, so its behavior and identifier may change.
Qwen4 Max serves the OpenAI-compatible Chat Completions API. Point any OpenAI SDK at https://api.empiriolabs.ai/v1 with your EmpirioLabs API key and use the model id qwen4-max. Both models are called through the same endpoint. Set model to qwen4-max or step-5-preview. Get an API key from the EmpirioLabs dashboard.
curl https://api.empiriolabs.ai/v1/chat/completions \
-H "Authorization: Bearer $EMPIRIOLABS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "qwen4-max",
"messages": [
{"role": "user", "content": "Write a haiku about the ocean."}
]
}'Qwen4 Max is the newer release (Nov 16, 2026); Step 5 Preview was released on Sep 15, 2026. Step 5 Preview has the larger context window: 1.02M tokens, against 983.6K for Qwen4 Max. Qwen4 Max returns up to 262,144 output tokens per response, Step 5 Preview up to 131,072. The specs, rate cards, and parameters on this page come from the live EmpirioLabs catalog.
Qwen4 Max is the newer release (Nov 16, 2026); Step 5 Preview was released on Sep 15, 2026.
Step 5 Preview lists the lower rate for Input (per 1M prompt tokens) and Output (per 1M generated tokens). Both live rate cards are on this page and always match what the API charges.
Yes. Both models use POST /v1/chat/completions with the same EmpirioLabs API key, so most integrations switch by changing the model value. Check the parameters table on this page first if you rely on a model-specific parameter.
Yes. Open each model in the EmpirioLabs playground and run the same prompt on both, with the parameters the API exposes.
Check out our pricing or reach out if you want your own model deployed on our stack.