Skip to content

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

GPT-6 Luna logo

OpenAI

GPT-6 Luna

GPT-6 Luna from OpenAI, with a 1.1M-token context window. Call it as openai/gpt-6-luna through the OpenAI- or Anthropic-compatible endpoint with a Tokens key.

openai/gpt-6-luna
Input, per 1M tokens
৳13.75$0.15
Output, per 1M tokens
৳68.75$0.60
Context window
1.1M1,100,000 tokens
Available on
Weekly, Monthly, Pay as you go

Measured speed and reliability

How GPT-6 Luna has performed for real requests, timed at our gateway in Dhaka.
First token, median
3.79 sHalf of requests started answering sooner
First token, 90th percentile
14.9 sNine in ten started answering sooner
Success rate
90.5%Requests that got a complete answer
Output speed, median
126 tokens/sAfter the first token

Measured at our gateway in Dhaka over the last 7 days, from real requests. A figure needs at least 100 requests; your own network adds to these times. Updated 23 Nov 2026, 02:39 Dhaka time.

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$0.0046৳0.45
An hour of agent work1M input, 60K output$0.19৳17.88
A month of daily use20M input, 1.2M output$3.72৳357.50

Use GPT-6 Luna

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": "openai/gpt-6-luna",
    "ANTHROPIC_DEFAULT_OPUS_MODEL": "openai/gpt-6-luna",
    "ANTHROPIC_DEFAULT_SONNET_MODEL": "openai/gpt-6-luna",
    "ANTHROPIC_DEFAULT_HAIKU_MODEL": "openai/gpt-6-luna",
    "CLAUDE_CODE_SUBAGENT_MODEL": "openai/gpt-6-luna"
  }
}

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