Stable Qwen3.8-Max uses the model ID qwen3.8-max. Do not carry preview-only limitations or the preview model name into a production configuration. The model is designed for long coding and agent tasks, but its published scores use specific harnesses and budgets, so the decision should come from a controlled test on your repository.

Want a separate compatible endpoint for the same test shape? Check current availability and pricing in the BetterToken model catalog, use your own API key, and compare one fixed task with the same model ID, token limits, and acceptance criteria. Record the provider and date because catalog values can change.

Stable release versus preview

The official Qwen3.8 release identifies qwen3.8-max as the stable API model. Qwen describes a 2.4-trillion-parameter MoE model with 95 billion active parameters. The release announced that open weights would follow the next week; until that happens, an article should describe the plan rather than claim that the weights were already available on release day.

When migrating from qwen3.8-max-preview, update the model ID, verify the key type and region, and send a minimal request. A model-name change without matching the regional endpoint can produce authentication or model-not-found errors that say nothing about coding quality.

Calculate the regional API price

Alibaba Model Studio publishes pay-as-you-go prices by region. The current pricing table lists CNY 12 input and CNY 36 output per million tokens for Beijing and global deployments. Singapore lists CNY 14.988 input and CNY 44.965 output.

For 200,000 input tokens and 20,000 output tokens, the Beijing/global calculation is:

0.2 × 12 + 0.02 × 36 = CNY 3.12.

The Singapore calculation is CNY 3.8969. Keep the source currency. Do not mix a Token Plan, a subscription quota, or a third-party gateway price into the same pay-as-you-go row without a shared denominator.

Read the benchmark footnotes

Qwen reports 86.6 on Terminal-Bench 2.1, 67.7 on SWE-bench Pro, 56.6 on DeepSWE 1.1, 73.5 on FrontierSWE, and 93.0 on PaperBench. These are vendor-reported scores. The release notes describe different harnesses, token budgets, timeouts, and competitor result sources across the table.

Use each benchmark only for the capability it measures. A PaperBench score does not predict the outcome of a repository issue, and a small leaderboard difference does not reveal tool-call errors, latency, or manual correction cost.

Configure Qwen Code

Qwen Code supports modelProviders with an OpenAI-compatible endpoint. A US-region profile can reference the key by environment-variable name:

{
  "modelProviders": {
    "openai": [
      {
        "id": "qwen3.8-max",
        "name": "Qwen3.8-Max",
        "baseUrl": "https://dashscope-us.aliyuncs.com/compatible-mode/v1",
        "envKey": "DASHSCOPE_API_KEY"
      }
    ]
  }
}

Use a key from the same region as the endpoint. The provider configuration guide treats nested provider configuration as an atomic value, so back up the file and review the diff before replacing an existing profile. Select qwen3.8-max, ask the client to read one file, and confirm the effective model before allowing edits.

Configure Claude Code

Model Studio also documents Anthropic-compatible endpoints. For the US region, the minimal environment is:

export ANTHROPIC_BASE_URL="https://dashscope-us.aliyuncs.com/apps/anthropic"
export ANTHROPIC_AUTH_TOKEN="YOUR_API_KEY"
export ANTHROPIC_MODEL="qwen3.8-max"

Restart Claude Code and run a harmless read-only task. Confirm the model, one tool call, and usage. Protocol compatibility does not make Qwen an Anthropic model or guarantee identical agent behavior.

Check failures at the correct layer

Qwen Code issue #7332 concerned the preview model and an enable_thinking=false request; it should not be generalized to the stable API. Other reports describe relative-path behavior in an Anthropic-compatible setup and an image attachment not reaching the VS Code companion. Treat each as a versioned reproduction, then separate four layers: API authentication, thinking/tools serialization, harness path or attachment handling, and the model's final instruction following.

Run three fixed repository tasks with the same commit, tools, timeout, and pass criteria. Record reasoning mode, input and output tokens, tool errors, tests, and manual corrections. That measures the cost of an accepted change rather than the cost of a token in isolation.

Qwen3.8-Max for Coding: Cost, Benchmarks, and Setup