Text model · Alibaba Qwen
Qwen 4 Max API
Qwen 4 Max is Alibaba Qwen's current flagship text model, available on TokenRa at 30% off the official price. It supports a 1,000,000-token context window (shared between input and output), accepts text, image, and video input, and includes a built-in thinking mode that returns reasoning in reasoning_content. Set enable_thinking: false to skip thinking. Priced at $1.34 / $4.03 / $0.095 per 1M input / output / cached tokens.
- Model ID
qwen4-max- Context
- 1,000,000 tokens
- Input
- Text, image, video
- Output
- Text (with reasoning)
- Input price
- $1.34 / 1M tokens
- Output price
- $4.03 / 1M tokens
- Cache read
- $0.095 / 1M tokens
- Discount
- 30% off official
Capabilities
Capabilities & endpoints
Chat generation through three API formats. Each was called successfully on tokenra.io on 2026-11-16; pick one to switch the code examples.
base_url="https://tokenra.io/v1". Auth: Authorization: Bearer. Recommended.output_text.https://tokenra.io. Auth: x-api-key (or Bearer) plus anthropic-version.Request
Request parameters
Fields for POST /v1/chat/completions. Everything listed was accepted by the model in testing.
| Parameter | Type | Required | Description |
|---|---|---|---|
model | string | Yes | The model ID to call: qwen4-max. |
messages | array | Yes | Conversation messages in order (system, user, assistant, tool). content can be a string or an array of text, image_url, or video parts. |
stream | boolean | No | Return the answer as server-sent events. Default false. |
stream_options | object | No | With {"include_usage": true}, the last chunk carries usage and an empty choices array. |
max_tokens | integer | No | Caps the answer text only. Reasoning tokens are not limited by it and are billed as output. |
max_completion_tokens | integer | No | Upper limit for all generated tokens, reasoning included. Non-thinking mode max: 131,072. Thinking mode max: 262,144. |
temperature | number | No | Sampling temperature. |
top_p | number | No | Nucleus sampling threshold. Usually tune either this or temperature, not both. |
presence_penalty | number | No | Penalises tokens that already appeared, nudging the model toward new topics. |
frequency_penalty | number | No | Penalises frequent tokens to reduce repetition. |
response_format | object | No | {"type": "json_object"} returns a JSON object. {"type": "json_schema", "json_schema": {...}} returns JSON matching your schema. |
tools | array | No | Function tools the model may call (type: "function"). |
tool_choice | string / object | No | auto, none, required, or a specific function. |
parallel_tool_calls | boolean | No | Allow several tool calls in one response. |
reasoning_effort | string | No | low, medium, or high. Controls reasoning depth. |
enable_thinking | boolean | No | Thinking is on by default. Set false to skip reasoning entirely; the answer then uses far fewer output tokens. |
top_k | integer | No | Qwen sampling parameter: sample only from the k most likely tokens. |
user | string | No | Your own end-user identifier for auditing. Not part of the conversation. |
- Non-thinking mode: max input 991,808 tokens, max output 131,072 tokens.
- Thinking mode: max input 983,616 tokens, max output 262,144 tokens (thinking content + final answer combined). Default thinking budget is 131,072 tokens; control total output length with
max_completion_tokens.
Other formats
| Format | Required fields | Answer location |
|---|---|---|
| OpenAI Responses | model, input | output_text |
| Anthropic Messages | model, max_tokens, messages | content[] blocks of type text |
Response
Response format
{
"id": "chatcmpl-1794802386001",
"object": "chat.completion",
"created": 1794802386,
"model": "qwen4-max",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "An API gateway is the single entry point that receives client requests and routes them to the right backend service. It also handles shared concerns such as authentication, rate limiting and logging.",
"reasoning_content": "The user wants two sentences about API gateways..."
},
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 26,
"completion_tokens": 62,
"total_tokens": 88,
"prompt_tokens_details": { "cached_tokens": 0 },
"completion_tokens_details": { "reasoning_tokens": 24 }
}
}| Field | Type | Description |
|---|---|---|
id | string | Completion ID. Include it when you contact support. |
object | string | chat.completion, or chat.completion.chunk when streaming. |
created | integer | Unix timestamp in seconds. |
model | string | The model that produced the answer. |
choices[].message.content | string | The answer text. |
choices[].message.reasoning_content | string | The model's reasoning, returned separately from the answer. |
choices[].message.tool_calls | array | Tool calls requested by the model, when tools were sent. |
choices[].finish_reason | string | stop, length or tool_calls. |
usage | object | prompt_tokens, completion_tokens, total_tokens, plus prompt_tokens_details.cached_tokens and completion_tokens_details.reasoning_tokens. |
With stream: true the answer arrives as data: lines of chat.completion.chunk objects and ends with data: [DONE].
Errors
Errors & limits
Common errors
| HTTP | error.code | Meaning | What to do |
|---|---|---|---|
401 | — | Missing, wrong or deleted API key. | Check the Authorization: Bearer header and the key in the console. |
400 | — | The body is not valid JSON. | Fix the JSON and send Content-Type: application/json. |
500 | invalid_request | A required field is missing, for example messages. | Add the field named in the message. |
403 | insufficient_user_quota | Balance or plan quota used up. | Top up in the console, then retry. |
503 | model_not_found | Unknown model ID or no channel for your group. | Check the ID against the model list. |
429 | — | Too many requests. | Back off exponentially and retry. |
5xx | — | Upstream provider failed or timed out. | Retry a few times; keep the request id if it persists. |
Limits and notes
- Video input: pass the video URL as an
image_url-style part withtype: "video_url"in the content array. - Reasoning is returned in
reasoning_content, separate from the answer incontent. Keep it out of what you show users unless you intend to display it. - Minimum account top-up is $10; credits do not expire while the account is active.