Online

Qwen3.8-Max

Qwen · OpenAI-compatible API

qwen/qwen3.8-max

USD / 1M tokens

Input: $1.95
Cache Read: $0.25
Cache Write: —
Output: $5.7
Context: 1M
Max Output: 128K
Tool Calling: ✓ Supported
Reasoning: ✓ Supported
Vision: ✓ Supported
Streaming: ✓ Supported
JSON mode: ✓ Supported

OpenAI-compatible API

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.iteracompute.com/v1",
    api_key=os.environ["ITERACOMPUTE_API_KEY"],
)
response = client.chat.completions.create(
    model="qwen/qwen3.8-max",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.iteracompute.com/v1",
  apiKey: process.env.ITERACOMPUTE_API_KEY,
});
const response = await client.chat.completions.create({
  model: "qwen/qwen3.8-max",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);

curl https://api.iteracompute.com/v1/chat/completions \
  -H "Authorization: Bearer $ITERACOMPUTE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen/qwen3.8-max",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

qwen/qwen3.8-maxView Docs →

Catalog updated: 2026-10-27.

Overview

Qwen3.8-Max is served through the IteraCompute OpenAI-compatible API. See the tested Gateway controls below; the official API and this route do not accept every parameter identically.

Tasks and selection tradeoffs

Coding, professional work, research and long-horizon agentic tasks.

Choose your tool

OpenAI SDKCall from Python or JavaScript Vercel AI SDKBuild a TypeScript application

Choose a model and tool for your task →

Pricing

Prices in USD per 1M tokens.

Input$1.95

Cache Read$0.25

Cache Write—

Output$5.7

Estimate your monthly cost

Uses current Gateway prices and billing rules. An estimate, not a bill.

Text estimates include configured context tiers and cache durations. Image output and tool calls require their actual usage.

Model

Total input tokens / request

Billable output tokens / request

Cache-hit tokens / request

Requests / month

Cache writes · 5 minutes

Cache writes · 1 hour

Cached share of input

Cache-hit share = cache-hit tokens ÷ total input. Changing total input keeps the current share; dragging the slider updates cache-hit tokens. Output includes billable reasoning. Count agent steps and retries as requests.

Estimated monthly cost

—USD / month

Qwen3.8-Max

Uncached input: —
Cache read: —
Billable output: —
Cache writes: —

Connect this model →

Calculation and billing basis

Monthly cost = requests × the current Gateway quote for the selected token usage.

Cached tokens are part of total input, never added on top. Use actual cache-read hits from usage; repeating a prompt does not guarantee a hit. Missing rates are unconfirmed, not $0. Storage and unreported tool fees are excluded. Settle against actual usage and current Console prices.

Usage limits

Use the context and output limits shown above when configuring clients. Account limits also apply.
Start with one representative task. Check correctness, actual usage and response time before increasing traffic.

API parameters

Parameters	Usage
`messages[].content`	`text + image` → `text`
`max_tokens`	128K
`temperaturetop_p`	Start with the request example. Adjust temperature or top_p one at a time; omit top_k.
`thinkingreasoningreasoning_effort`	Use reasoning=false to turn reasoning off, or reasoning_effort=low to reduce it. Use one control style per request.
`toolstool_choicetool_calls`	Define functions in tools and use tool_choice=auto. Execute tool_calls in your application, then return role=tool with the matching tool_call_id.
`response_format`	Use response_format={"type":"json_object"} and request JSON in the prompt. Validate the returned JSON and required fields in your application.
`streamstream_options.include_usage`	`stream=true, stream_options={"include_usage":true}`

Input and requested output share the context budget. Reasoning tokens count toward output usage.

Raw HTTP request body

{
  "model": "qwen/qwen3.8-max",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ],
  "max_tokens": 512,
  "reasoning": false,
  "stream": true,
  "stream_options": {
    "include_usage": true
  }
}

Python SDK example

from openai import OpenAI

client = OpenAI(
    api_key="ITERACOMPUTE_API_KEY",
    base_url="https://api.iteracompute.com/v1",
)
stream = client.chat.completions.create(
    model='qwen/qwen3.8-max',
    messages=[{'role': 'user', 'content': 'Hello!'}],
    max_tokens=512,
    stream=True,
    stream_options={'include_usage': True},
    extra_body={'reasoning': False},
)
for chunk in stream:
    print(chunk.model_dump_json(exclude_none=True))

SDK extra_body merges its entries into the HTTP body. When the raw request itself contains an extra_body object, preserve that object as nested extra_body in the SDK example.

Response fields and tool results

choices[0].message.contentdelta.content: Final text; concatenate streamed fragments.
reasoning_content: Optional reasoning text. Preserve it in assistant history when required; its absence does not prove thinking was disabled.
tool_calls[].function.argumentstool_call_id: Parse arguments as JSON, execute the function, and return role=tool with the original call ID.
usagefinish_reason[DONE]: Check final usage and the stream terminal. length means truncation; HTTP 200 alone is not successful completion.
error.typeerror.codeHTTP status: Read the error code and message. For rate limits, honor Retry-After and avoid parallel retries.

Checked parameter constraints

Parameters	Usage
`max_tokensmax_completion_tokensmax_output_tokens`	Chat uses max_tokens or max_completion_tokens; Responses uses max_output_tokens. Use positive integers within Gateway limits.
`temperaturetop_p`	temperature: 0–2; top_p: greater than 0 and at most 1. Start with the model defaults.

2026-10-26 · Official parameter references

API

Base URL: https://api.iteracompute.com/v1
Endpoint: POST /v1/chat/completions
Model ID: qwen/qwen3.8-max
Authentication: Authorization: Bearer ITERACOMPUTE_API_KEY

View Docs

FAQ

How do I use Qwen3.8-Max with the OpenAI SDK?

Set base_url to https://api.iteracompute.com/v1 and model to qwen/qwen3.8-max. Authenticate with your IteraCompute API key.

What does Qwen3.8-Max cost?

See the pricing section for current input, cached-input and output rates in USD per 1M tokens. Check the refresh time before use.

What context length is available?

See the summary above for the context and maximum output available through this API. Input and requested output share the context budget.

Ready for your first request?

Create your key, choose a tool and get a non-empty first reply.

Create an account →Choose a tutorial

Qwen3.8-Max

Overview

Tasks and selection tradeoffs

Choose your tool

Pricing

Estimate your monthly cost

More Qwen models on IteraCompute

Usage limits

API parameters

Response fields and tool results

Checked parameter constraints

API

FAQ

Ready for your first request?