Nex-N2.5-Mini
by Nex AGInex-agi/nex-n2.5-mini
LLMCompare cannot run Nex-N2.5-Mini yet.No route to this model is configured on this site yet. Its prices and parameters are listed below for reference.
See the models that can be run nowNex-N2.5-Mini at a glance
- Context length
- 262,144 tokens
- Maximum output
- 235,929 tokens
- Accepts
- Text, Image
- Returns
- Text
- Features
- ReasoningJSON outputPrompt cachingImage input
- Reasoning effort levels
highmediumnoneReasoning can be turned off.- Released
- 8 Sep 2026
- Knowledge cutoff
- Not published
Model facts synced from the OpenRouter model list on 21 Oct 2026.
Nex-N2.5-Mini pricing by route
A route is the service LLMCompare calls to reach the model. Nex-N2.5-Mini has 1 route. Prices are in US dollars.
| Route | On LLMCompare | Inputper 1M tokens | Outputper 1M tokens | Cache readper 1M tokens | Price verified on | Source |
|---|---|---|---|---|---|---|
| OpenRouterDefault | Not configured | $0.025 | $0.10 | $0.0025 | openrouter.ai/nex-agi/nex-n2.5-mini |
The cost shown in an LLMCompare report is calculated from these prices as they were at the time of the run.
Cost calculator
Estimate what a batch of calls to Nex-N2.5-Mini costs. The starting numbers are examples. Change them to match your task.
Part of the input tokens above, billed at the cache read price.
Billed in addition to the output tokens.
- Cost per call
- $0.000075
- 1 credits
- Cost of 100 calls
- $0.0075
- 100 credits
Calculated from the OpenRouter prices verified on 21 Oct 2026. Credits are the cost plus a 20% service fee, at $0.001 per credit, rounded up for each call, with a minimum of 1 per call. A real run is charged for the usage the provider reports.
Parameters you can set
These are the parameters LLMCompare can set when it calls the model through OpenRouter.
| Parameter | Type | Range or options | Default |
|---|---|---|---|
temperature | Number | 0 to 2in steps of 0.1 | Provider default |
top_p | Number | 0 to 1in steps of 0.05 | Provider default |
max_tokens | Integer | 1 to 235,929 | Provider default |
reasoning_effort | One of | highmediumnone | high |
About Nex-N2.5-Mini
Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback loop: it can explore codebases, implement multi-file...
Description as published for this model. LLMCompare has not edited it.
Models to compare with Nex-N2.5-Mini
Text models from the same provider and models at the nearest price. The order is not a ranking.
| Add to comparison | Model | Context | Max output | Input priceper 1M tokens | Output priceper 1M tokens | Features | Released | On LLMCompare |
|---|---|---|---|---|---|---|---|---|
Nex-N2.5-ProNex AGInex-agi/nex-n2.5-pro | 262k | 236k | $0.075 | $0.25 | ReasoningJSONToolsCacheVision | No route yet | ||
Granite 4.0 MicroIBMibm-granite/granite-4.0-h-micro | 131k | 118k | $0.017 | $0.112 | JSON | No route yet | ||
Mistral Small 3Mistralmistralai/mistral-small-24b-instruct-2501 | 32.8k | 16.4k | $0.05 | $0.08 | JSON | No route yet | ||
Llama 3.1 8B InstructMetameta-llama/llama-3.1-8b-instruct | 131k | 118k | $0.05 | $0.08 | JSONToolsCache | No route yet | ||
gpt-oss-20bOpenAIopenai/gpt-oss-20b | 131k | 32.8k | $0.018 | $0.09 | ReasoningJSONToolsCache | No route yet | ||
Qwen3.7 FlashQwenqwen/qwen3.7-flash | 1M | 65.5k | $0.03 | $0.13 | JSONToolsCacheVision | No route yet |
Questions about Nex-N2.5-Mini
- How much does Nex-N2.5-Mini cost?
- On the OpenRouter route, Nex-N2.5-Mini costs $0.025 per 1 million input tokens and $0.10 per 1 million output tokens, in US dollars. Input tokens that Nex-N2.5-Mini reads from the prompt cache cost $0.0025 per 1 million tokens. LLMCompare verified this price on 21 Oct 2026.
- What is the context length of Nex-N2.5-Mini?
- Nex-N2.5-Mini has a context length of 262,144 tokens and returns up to 235,929 output tokens in one call.
- What inputs does Nex-N2.5-Mini accept?
- Nex-N2.5-Mini accepts these inputs: Text, Image. Nex-N2.5-Mini returns: Text.
- Which reasoning effort levels does Nex-N2.5-Mini support?
- Nex-N2.5-Mini supports these reasoning effort levels: high, medium, none. Reasoning can be turned off for Nex-N2.5-Mini.
- Can I test Nex-N2.5-Mini on my own data?
- Not yet. LLMCompare lists the prices and parameters of Nex-N2.5-Mini, but no route to Nex-N2.5-Mini is configured on LLMCompare, so it cannot be selected for an evaluation.