The top of the Gemini 4 line: Google's most capable reasoning model, built for complex software engineering and agentic work across a 1M-token context. Its list price doubles on December 1, 2026, and Tokenless stays at half of list.
Every rate is 50% of the provider's official list price. USD per million tokens.
| Token type | List price | Tokenless |
|---|---|---|
| Input | $2.00 | $1.00 |
| Output | $10.00 | $5.00 |
| Cache write | $2.00 | $1.00 |
| Cache read | $0.10 | $0.05 |
Tokenless speaks the OpenAI Chat Completions format. Point your client at the base URL, set model to gemini-4-carbon, 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-4-carbon",
"messages": [{ "role": "user", "content": "Hello" }]
}'On Tokenless, Gemini 4 Carbon costs $1.00 per million input tokens and $5.00 per million output tokens, half of Google's list price of $2.00 and $10.00.
Yes. Tokenless routes a request for gemini-4-carbon to the genuine Gemini 4 Carbon and returns its response unchanged. No cheaper model is substituted.
Point any OpenAI-compatible SDK at https://api.tokenless.store/api/v1, use your Tokenless API key, and set the model to gemini-4-carbon. You pay per token from a prepaid balance, and your first $1 is free.
Gemini 4 Carbon accepts up to 1,000,000 tokens of context and returns up to 65,536 output tokens per request.