EVREN / evren/mimo-v2.6-pro-tr
MiMo V2.6 Pro - access through LLMTR
MiMo V2.6 Pro on EVREN is Xiaomi's mixture-of-experts model with about 1.02 trillion total parameters and roughly 42 billion active per token, which EVREN presents as the largest model in its fleet, for long-running agent work. Its 1,048,576-token window is shared by input and output. It takes text and image input and returns text, and supports tool calling, JSON mode and schema-conforming structured output. Thinking is on by default; send `reasoning_effort` none or minimal to turn it off. Thinking tokens come out of the output budget (`max_tokens` or `max_completion_tokens`), so keep it generous while thinking is on. Requests are served with your own EVREN API key, which you register in Settings; LLMTR charges nothing for them and the model runs on infrastructure hosted in Turkey.
Technical specifications
| Canonical ID | evren/mimo-v2.6-pro-tr |
|---|---|
| Provider | EVREN |
| 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 | Not available |
| CHAT_COMPLETIONS | OUTPUT_TEXT | PER_1M_TOKENS | Not available |
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":"evren/mimo-v2.6-pro-tr","messages":[{"role":"user","content":"Hello"}]}'Guides about this model
- EVREN model selection for text, images, and video - Compares the six EVREN rows by input type and by the role EVREN describes, and explains which rows stand out for text, image and video work.
- EVREN long documents, context, and output budgets - Explains what goes into the context window, how the output budget is set, the difference between sending a document in one request and splitting it, and how long inputs affect the EVREN quota.
- EVREN response waiting and streaming experience - Explains the difference between real streaming and chunked delivery after completion, the factors behind waiting time on EVREN rows, and timeout and retry behaviour.
- EVREN API errors: choosing the right remedy - Explains the error types on EVREN rows, the meaning of the three separate 403 errors, the upstreamStatus field, and the cases that return no error but still give an unexpected result.
- Source verification for visual documents with EVREN - Covers the EVREN rows suited to visual documents, asking the model for the source alongside each value, the fields that carry error risk, and where human review comes in.
- Using the EVREN API through LLMTR: your own key, one endpoint - You do not have to go to EVREN to use EVREN. Register your key with LLMTR once and call the model from the usual endpoint; LLMTR does not charge for these requests and your EVREN key never travels in them.
- Turkey-hosted LLM models: what sits beside EVREN in the catalog - EVREN is not the only Turkey-hosted option. This is every Turkey row in the catalog in one table: which context, which price, which input type, and which rows declare tool calling.
- Moving from an EVREN row to a global model: one field changes - Moving from an EVREN row to a global model needs no code change: the endpoint, the header and the body schema stay the same and only the model id differs. How an agent verifies capability before calling is read from the same place.
- What is EVREN? How to use SAYZEK's LLM API - Explains the EVREN LLM Inference Service with sources: who runs it, that it is free until 1 November, its eleven-model list, its OpenAI compatibility and the setup path from e-Devlet login to a first chat request.
- Logging in to EVREN with e-Devlet: your API key is tied to your identity - Covers the practical consequences of an API key living in an account opened with e-Devlet: who owns the key, what happens when it is shared, and what to watch for in team and company use.
- Does EVREN keep logs? Terms of use, records and data privacy - Covers what is and is not publicly known about EVREN's data and logging side, and what to check before sending sensitive data. It states just as openly what LLMTR does and does not keep.
- EVREN quota and credit system: free, but metered - Explains, with sources, the meters that run on EVREN even during the free period: a sliding-window token cap, a credit balance, per-request charge state, the cooldown on consecutive requests and how auto mode affects consumption.
- An EVREN alternative: the same OpenAI code, a two-line switch to LLMTR - Compares EVREN and LLMTR through the same OpenAI SDK code: the two lines that change, the LLMTR catalog counterparts of EVREN's models and their prices, context differences on the same models, and when each service makes sense.
Related models
- Gemma 4 31B evren/gemma-4-31b
- DeepSeek V4 Flash evren/deepseek-v4-flash-tr
- Qwen3.8 Flash Next evren/qwen3.8-flash-next
- GLM-5.3 evren/glm-5.3-fp8
- Qwen3 VL 30B evren/qwen3-vl-30b
- Gemma 4 llmtr/gemma-4
- Qwen 3.6 35B-A3B llmtr/qwen3-6-35b
- Trendyol Asure 12B llmtr/trendyol-asure-12b