InclusionAI
Ling 3.1 Flash
Ling 3.1 Flash from InclusionAI, with a 262K-token context window. Call it as inclusionai/ling-3.1-flash through the OpenAI- or Anthropic-compatible endpoint with a Tokens key.
inclusionai/ling-3.1-flash- Input, per 1M tokens
- ৳9.38$0.08
- Output, per 1M tokens
- ৳28.13$0.23
- Context window
- 262K262,000 tokens
- Available on
- Pay as you go, Weekly
Measured speed and reliability
- First token, median
- 3.75 sHalf of requests started answering sooner
- First token, 90th percentile
- 20.9 sNine in ten started answering sooner
- Success rate
- 85.8%Requests that got a complete answer
- Output speed, median
- Not enough dataAfter 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
| Workload | USD | BDT |
|---|---|---|
| One agent turn25K input, 1.5K output | $0.0022 | ৳0.28 |
| An hour of agent work1M input, 60K output | $0.09 | ৳11.07 |
| A month of daily use20M input, 1.2M output | $1.77 | ৳221.36 |
Use Ling 3.1 Flash
{
"env": {
"ANTHROPIC_BASE_URL": "https://tokens.bd",
"ANTHROPIC_AUTH_TOKEN": "tok_live_your_key",
"ANTHROPIC_MODEL": "inclusionai/ling-3.1-flash",
"ANTHROPIC_DEFAULT_OPUS_MODEL": "inclusionai/ling-3.1-flash",
"ANTHROPIC_DEFAULT_SONNET_MODEL": "inclusionai/ling-3.1-flash",
"ANTHROPIC_DEFAULT_HAIKU_MODEL": "inclusionai/ling-3.1-flash",
"CLAUDE_CODE_SUBAGENT_MODEL": "inclusionai/ling-3.1-flash"
}
}Configure Claude Code CLI via ~/.claude/settings.json or environment exports.
# ~/.codex/config.toml model = "inclusionai/ling-3.1-flash" model_provider = "tokens" [model_providers.tokens] name = "Tokens" base_url = "https://tokens.bd/v1" env_key = "TOKENS_API_KEY" wire_api = "responses" # In your shell profile (~/.bashrc, ~/.zshrc): export TOKENS_API_KEY="tok_live_your_key"
Add a custom model provider to ~/.codex/config.toml and export the key in your shell.
{
"provider": {
"tokens": {
"npm": "@ai-sdk/openai-compatible",
"options": {
"baseURL": "https://tokens.bd/v1",
"apiKey": "tok_live_your_key"
},
"models": {
"inclusionai/ling-3.1-flash": {}
}
}
},
"model": "tokens/inclusionai/ling-3.1-flash"
}Project or global configuration for OpenCode CLI / IDE agent.
1. Open Cursor Settings -> Models 2. Under "OpenAI API Key", enter: tok_live_your_key 3. Click "Override OpenAI Base URL" and enter: https://tokens.bd/v1 4. Click "Add Custom Model" and enter: inclusionai/ling-3.1-flash
Add to Cursor: Settings (Gear icon) → Models → Add Custom Model & OpenAI Override.
from openai import OpenAI
client = OpenAI(
base_url="https://tokens.bd/v1",
api_key="tok_live_your_key",
)
response = client.chat.completions.create(
model="inclusionai/ling-3.1-flash",
messages=[
{"role": "system", "content": "You are an expert coding assistant."},
{"role": "user", "content": "Write a quick hello world in Python"},
],
temperature=0.7,
)
print(response.choices[0].message.content)Official OpenAI Python library pointing to Tokens endpoint.
curl -X POST "https://tokens.bd/v1/chat/completions" \
-H "Authorization: Bearer tok_live_your_key" \
-H "Content-Type: application/json" \
-d '{
"model": "inclusionai/ling-3.1-flash",
"messages": [
{"role": "system", "content": "You are an expert coding assistant."},
{"role": "user", "content": "Write a quick hello world in Python"}
],
"temperature": 0.7
}'Raw HTTP POST request to OpenAI-compatible chat completions.