Black Friday Sale 2026. Get up to 20% bonus credits.

Ends inSee the offer

qwen4-max

Input price
$1.50/1M tokens
Output price
$4.50/1M tokens
Context window
1M
Modalities
Text · Image · Video → Text

Pricing

Per million tokens

API call price

Input

$1.50

Output

$4.50

Cache write

$1.875

Cache read

$0.075

Server tools

Billed per successful upstream call

  • Web Search

    The model searches the live web. The search runs upstream.

    $10.00/1K calls



Integration & capabilities

Supported protocols

Compatible formatAnthropic
Routes
POST /v1/messages
POST /v1/messages/count_tokens
FeaturesStreaming · Prompt caching · Function calling · System messages
Request parametersmodel, messages, system, tools, stream, metadata

cURL Example

curl -X POST https://api.openmodel.ai/v1/messages \
  -H "Content-Type: application/json" \
  -H "x-api-key: $API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "qwen4-max",
    "max_tokens": 1024,
    "messages": [
      {"role": "user", "content": "Hello"}
    ]
  }'

Supported capabilities

Function Calling
Function calling (also known as tool calling) provides a powerful and flexible way for models to interface with external systems and access data outside their training data.
Parallel Function Calling
The model may choose to call multiple functions in a single turn.
Tool Choice
By default the model will determine when and how many tools to use. You can force specific behavior with the tool_choice parameter.
Structured Outputs
Ensures the model will always generate responses that adhere to your supplied JSON Schema.
Streaming
Lets you start printing or processing the beginning of the model's output while it continues generating the full response.
Reasoning
Reasoning models use internal reasoning tokens before producing a response.
Prompt Caching
Optimizes API usage by allowing resuming from specific prefixes in your prompts. This significantly reduces processing time and costs for repetitive tasks or prompts with consistent elements.
Vision
Models can process image inputs and analyze them — a capability known as vision.
Image Input
Multimodal from the ground up, unlocking a wide range of image processing and computer vision tasks including image captioning, classification, and visual question answering.
Video Input
Processes videos, enabling many frontier developer use cases that would have historically required domain specific models.
Web Search
Allows models to access up-to-date information from the internet and provide answers with sourced citations.

Context & limits

Context window

1M

Max output tokens

131.1K