StepFun
Step 3.7 Flash
Step 3.7 Flash from StepFun, with a 256K-token context window. Call it as stepfun/step-3.7-flash through the OpenAI- or Anthropic-compatible endpoint with a Tokens key.
stepfun/step-3.7-flash- Input, per 1M tokens
- ৳27.50$0.22
- Output, per 1M tokens
- ৳158.13$1.27
- Context window
- 256K256,000 tokens
- Available on
- Monthly, Pay as you go
Measured speed and reliability
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
| Workload | USD | BDT |
|---|---|---|
| One agent turn25K input, 1.5K output | $0.0074 | ৳0.92 |
| An hour of agent work1M input, 60K output | $0.30 | ৳36.99 |
| A month of daily use20M input, 1.2M output | $5.92 | ৳739.76 |
Use Step 3.7 Flash
{
"env": {
"ANTHROPIC_BASE_URL": "https://tokens.bd",
"ANTHROPIC_AUTH_TOKEN": "tok_live_your_key",
"ANTHROPIC_MODEL": "stepfun/step-3.7-flash",
"ANTHROPIC_DEFAULT_OPUS_MODEL": "stepfun/step-3.7-flash",
"ANTHROPIC_DEFAULT_SONNET_MODEL": "stepfun/step-3.7-flash",
"ANTHROPIC_DEFAULT_HAIKU_MODEL": "stepfun/step-3.7-flash",
"CLAUDE_CODE_SUBAGENT_MODEL": "stepfun/step-3.7-flash"
}
}Configure Claude Code CLI via ~/.claude/settings.json or environment exports.
# ~/.codex/config.toml model = "stepfun/step-3.7-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": {
"stepfun/step-3.7-flash": {}
}
}
},
"model": "tokens/stepfun/step-3.7-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: stepfun/step-3.7-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="stepfun/step-3.7-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": "stepfun/step-3.7-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.