A general-availability Gemini Flash tuned for code development and agent scenarios, with configurable thinking depth, a 1M-token context, and multimodal input. Strong tool use and multi-step execution for high-volume production traffic.
Every rate is 50% of the provider's official list price. USD per million tokens.
| Token type | List price | Tokenless |
|---|---|---|
| Input | $0.75 | $0.38 |
| Output | $3.75 | $1.88 |
| Cache write | $0.75 | $0.38 |
| Cache read | $0.08 | $0.04 |
Tokenless speaks the OpenAI Chat Completions format. Point your client at the base URL, set model to gemini-3.7-flash, and you are done.
curl https://api.tokenless.store/api/v1/chat/completions \
-H "Authorization: Bearer $TOKENLESS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-3.7-flash",
"messages": [{ "role": "user", "content": "Hello" }]
}'