CherryText 1.0 Flash
Fast, low-cost language model with a 1M-token context window, tool calls, and reasoning.
Request
Conversation messages in the OpenAI Chat Completions format.
Maximum number of tokens to generate, including the tokens the model spends on reasoning. A value that is too small can end the response before the answer is written. The balance hold is based on this value.1 to 131,072 · Default: 4,096
Sampling temperature.0 to 2 · Default: 1
Stream tokens as server-sent events.Default: false
Code
curl -X POST "https://api.sakuranbo.ai/v1/chat/completions" \
-H "Authorization: Bearer $SAKURANBO_API_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "sakuranbo/cherrytext-1.0-flash",
"max_tokens": 4096,
"temperature": 1,
"stream": false
}
JSON- Set your API key in the SAKURANBO_API_KEY environment variable.
- Requests go to https://api.sakuranbo.ai/v1/chat/completions.
Estimated cost
Estimated total $0.00676
Estimated total
$0.00676
| Item | Quantity | Unit price | Amount |
|---|---|---|---|
| Input tokens | 1 token | $0.4125 / 1M tokens | $0.000001 |
| Output tokens (up to max_tokens) | 4,096 tokens | $1.65 / 1M tokens | $0.006759 |
Assumptions
- Output is estimated at max_tokens; you are billed for actual usage.
- Input tokens are approximated from message length.
This estimate is calculated in your browser from catalog prices. The final charge is calculated by the server.
Sign-in is not available in this environment, so requests cannot be run here.
Model details
- Context length
- 1,000,000
- Max output tokens
- 131,072
- Streaming
- Yes
- Asynchronous job
- No
- Output retention
- Not retained
- Prompts stored
- No
- Tags
- long-context
- tool-calling
Estimated total
$0.00676
Sign-in is not available in this environment, so requests cannot be run here.