TensorX / tensorx/minimax-m3-tensorx
MiniMax M3 - access through LLMTR
MiniMax M3 offers a 1,048,576-token context window, accepts image input and supports tool/function calling. Repeated prompt prefixes can be served from a cache, and those tokens bill at roughly a quarter of the input rate, which lowers the cost of agent loops that resend one long system prompt. It reasons by default and those tokens bill as output.
Same model, other providers: MiniMax
Technical specifications
| Canonical ID | tensorx/minimax-m3-tensorx |
|---|---|
| Provider | TensorX |
| Context window | 1,048,576 tokens |
| Operations | CHAT_COMPLETIONS |
| Modalities | text, image |
Pricing
An 8% platform margin applies to credit top-ups; model usage prices are not separately marked up.
| Operation | Metric | Unit | Price |
|---|---|---|---|
| CHAT_COMPLETIONS | INPUT_TEXT | PER_1M_TOKENS | $0.400000 |
| CHAT_COMPLETIONS | CACHE_READ | PER_1M_TOKENS | $0.100000 |
| CHAT_COMPLETIONS | OUTPUT_TEXT | PER_1M_TOKENS | $2.00 |
Example usage
With existing OpenAI SDK flows, change only the base URL and model identifier.
curl https://llmtr.com/v1/chat/completions -H "Authorization: Bearer llmtr-your_key" -H "Content-Type: application/json" -d '{"model":"tensorx/minimax-m3-tensorx","messages":[{"role":"user","content":"Hello"}]}'Guides about this model
- EU-Hosted Models for AI Agents and Coding - Every TensorX chat model on LLMTR supports tool (function) calling and streaming. Eight rows suited to agents and coding are compared, with a session cost example, reasoning token notes, API key scoping and the TensorX data-transfer consent.
Related models
- Kimi K3 tensorx/kimi-k3-tensorx
- Kimi K2.7 Code tensorx/kimi-k2.7-code-tensorx
- GLM-5.3 tensorx/glm-5.3-tensorx
- GLM-5.3 Flash tensorx/glm-5.3-flash-tensorx
- GLM-5.2 tensorx/glm-5.2-tensorx
- DeepSeek V4 Pro 0813 tensorx/deepseek-v4-pro-0813-tensorx
- DeepSeek V4.1 Flash tensorx/deepseek-v4.1-flash-tensorx
- DeepSeek V4 Flash 0731 tensorx/deepseek-v4-flash-0731-tensorx