Skip to content

4 Uncensored LLM model added, currently available for only pay-as-you-go users.See Models

Qwen 3.8 Max 0902 logo

Other

Qwen 3.8 Max 0902

Qwen 3.8 Max 0902 from Other, with a 1M-token context window. Call it as qwen/qwen-3.8-max-0902 through the OpenAI- or Anthropic-compatible endpoint with a Tokens key.

qwen/qwen-3.8-max-0902
Input, per 1M tokens
৳275.00$2.20
Output, per 1M tokens
৳825.00$6.60
Context window
1M1,000,000 tokens
Available on
Pay as you go

Measured speed and reliability

How Qwen 3.8 Max 0902 has performed for real requests, timed at our gateway in Dhaka.

Not enough data yet

Speed and success rate appear once this model has had at least 100 requests from several customers in the last 7 days.

What it costs in practice

Estimates at the current price. Coding agents send far more input than output; your own mix depends on the agent and the task.
WorkloadUSDBDT
One agent turn25K input, 1.5K output$0.06৳8.11
An hour of agent work1M input, 60K output$2.60৳324.50
A month of daily use20M input, 1.2M output$51.92৳6,490.00

Use Qwen 3.8 Max 0902

Each setup already points at Tokens with this model selected. Replace the key with one from your dashboard. Quickstart
~/.claude/settings.json
{
  "env": {
    "ANTHROPIC_BASE_URL": "https://tokens.bd",
    "ANTHROPIC_AUTH_TOKEN": "tok_live_your_key",
    "ANTHROPIC_MODEL": "qwen/qwen-3.8-max-0902",
    "ANTHROPIC_DEFAULT_OPUS_MODEL": "qwen/qwen-3.8-max-0902",
    "ANTHROPIC_DEFAULT_SONNET_MODEL": "qwen/qwen-3.8-max-0902",
    "ANTHROPIC_DEFAULT_HAIKU_MODEL": "qwen/qwen-3.8-max-0902",
    "CLAUDE_CODE_SUBAGENT_MODEL": "qwen/qwen-3.8-max-0902"
  }
}

Configure Claude Code CLI via ~/.claude/settings.json or environment exports.