Release and model choices
The launch lists flat uncached input pricing of $0.15 and output pricing of $0.60 per million tokens, with cached input at $0.015. Confirm current provider pricing and token usage before calculating a production bill.
At launch MiniMax said model weights would be released later. An available API does not by itself provide a verified browser tokenizer, and a reference encoding cannot reproduce its real request count.
| Model | Local counting | Open tool |
|---|---|---|
| MiniMax M3.1 Flash | Reference encoding | Select MiniMax M3.1 Flash |
How to count MiniMax M3.1 Flash tokens
Uses o200k_base for text comparison only. This site has not verified a browser tokenizer for MiniMax M3.1 Flash. The displayed count, boundaries and IDs belong to o200k_base and must not be treated as MiniMax M3.1 Flash usage, a billing estimate or a context-limit guarantee.
Paste text into Plain text mode, or use Chat messages to count each message body independently. Switching models preserves your input. Chat mode excludes role names, separators and provider wrappers; adding bodies does not reproduce a serialized API conversation.
Local processing does not send your prompt to a model API or generate a response. Published tokenizer assets may be loaded by the browser, while the text analysis itself runs on your device.
Request limits and usage
Do not multiply this page's o200k_base reference total by MiniMax's rate and treat the result as an actual bill. Use MiniMax's reported input, cache and output token usage, including repeated calls in an agent task.
For a production request, include the actual conversation, system instructions, tool schemas and supported media in the provider's counting workflow when available. Check response usage after generation and account for subsequent calls, cache behavior, reasoning and output separately.
- A model's advertised context window is not a guaranteed amount of pasted text.
- A faster model or a cheaper token rate does not establish a lower total bill for every task.
- Recheck the exact model version and counting method when migrating an existing prompt.
Tiktokenizer Reference Sources
Tokenizer behavior and model limits change. Verify production decisions with current provider documentation: