Gemini 4 Carbon is available on BetterToken
Explore Gemini 4 Carbon use cases, how it compares with Argon, official context and output limits, implicit caching, and the introductory pricing period.
Updated: November 12, 2026
Gemini 4 Carbon is available on BetterToken. Use your existing BetterToken API Key with Model ID gemini-4-carbon.
Choose a model
Use Carbon for root-cause investigations, architecture design, complex code changes, and research that needs thorough verification. Google positions Argon as the more efficient choice for everyday coding and knowledge work. Carbon spends more thinking tokens, so usage and waiting time per task can be higher.
Compare task quality, latency, and actual token usage, not just the price per token.
Official specifications
| Property | Google specification |
|---|---|
| Model ID | gemini-4-carbon |
| Input | Text, images, video, audio, and PDF |
| Output | Text |
| Unified context | Input, thinking, and output share 1,048,576 tokens |
| Ordinary synchronous output limit | 65,536 tokens |
| Thinking levels | low, medium (default), high |
| Caching | Implicit caching only; explicit caching is not supported |
These are Google specifications.
BetterToken setup
BetterToken supports non-streaming text conversations through native Gemini generateContent, and non-streaming or streaming text through OpenAI-compatible Chat Completions.
Use your existing BetterToken API Key, or register and create one.
| Protocol | Base URL | Authentication header |
|---|---|---|
| Native Gemini / Google GenAI SDK | https://bettertoken.ai | x-goog-api-key: YOUR_BETTERTOKEN_API_KEY |
| OpenAI-compatible Chat Completions | https://bettertoken.ai/v1 | Authorization: Bearer YOUR_BETTERTOKEN_API_KEY |
Native text requests use POST /v1beta/models/gemini-4-carbon:generateContent. Do not append /v1beta to the SDK Base URL. Chat Completions uses POST /v1/chat/completions. Use Chat Completions for Carbon streaming text.
For complete setup and text request examples, see the Gemini API guide.
Pricing and caching
Google Standard introductory pricing runs through November 30, 2026. Regular pricing starts December 1, 2026. Check the model plaza for BetterToken input, output, and cache-read prices.
These are Google’s promotion dates. Future BetterToken prices remain subject to the model plaza.
Google’s output billing includes thinking tokens. Implicit caching is handled automatically, without creating cache objects. Cache hits are not guaranteed; evaluate caching from actual usage records.

