Nex-N2.5-Pro is a Nex-AGI model with 262K context, $0.075 in / $0.25 out per million tokens, last verified October 2, 2026. Open weights: yes. Public-board scores are linked to the publisher; vendor-only figures stay in the watch-out, not on the board.
A downloadable text and image model for agent workflows, also offered through the Nex-AGI OpenRouter endpoint.
Recorded profile verification October 2, 2026·Individual provider fields may change
Pricing tiers: Nex AGI via OpenRouter, October 2 capture: $0.075/$0.25 per MTok, cached input $0.015; FP8 route. Route context 262,144, maximum completion 235,929; native config also has 262,144 positions. These tariffs and generation limits are specific to this route, not every deployment.
Publisher evidence
Published benchmark results
Each result keeps its source date visible. Dates refer to source publication or capture unless the source explicitly states when it measured the result. A missing benchmark is not treated as a zero.
Published benchmark results for Nex-N2.5-Pro
Benchmark
Score
Source date
Source
Terminal-Bench 2.1Vendor NexAU coding harness; temperature 0.7, top-p 0.95, top-k 40; reasoning effort and experiment date unpublishedCross-model comparability not verified
DeepSWE 1.1Vendor NexAU coding harness; temperature 0.7, top-p 0.95, top-k 40; reasoning effort and experiment date unpublishedCross-model comparability not verified
Release day is unverified; repository creation and route version strings are not release receipts. Apache-2.0 is declared in publisher metadata; a standalone licence file remains unverified. reasoning_effort=medium is adaptive and the default; none disables reasoning and high always enables it. The chat template directly consumes reasoning_effort; enable_thinking/thinking_mode require gateway translation. Use qwen3 reasoning parser for Pro/mini, deepseek-r1 for Max, and qwen3_coder for tools. Vendor NexAU scores have incomplete run/effort metadata, so verdicts are withheld. Hosted endpoint context/completion limits and quantization are route-specific. Do not infer video capability from token IDs; the current route advertises text/image input and text output.
Source receipts
Catalog figures for this model were checked against the following sources.
Answered from the verified figures on this page rather than general guidance.
How much does Nex-N2.5-Pro cost per million tokens?
Nex-N2.5-Pro lists base rates of $0.075 per million input tokens and $0.25 per million output tokens. Estimate both input and output token volume and any additional charges for your workload. Nex AGI via OpenRouter, October 2 capture: $0.075/$0.25 per MTok, cached input $0.015; FP8 route. Route context 262,144, maximum completion 235,929; native config also has 262,144 positions. These tariffs and generation limits are specific to this route, not every deployment.
What is Nex-N2.5-Pro's context window?
Nex-N2.5-Pro accepts about 262K tokens of context. That only matters if you routinely send very long documents, large codebases, or multi-turn histories that approach that limit.
What is Nex-N2.5-Pro best for?
Nex-N2.5-Pro is a balanced tier from Nex-AGI. It suits evaluating self-hosted agent workflows, evaluating image-grounded tasks. Release day is unverified; repository creation and route version strings are not release receipts. Apache-2.0 is declared in publisher metadata; a standalone licence file remains unverified. reasoning_effort=medium is adaptive and the default; none disables reasoning and high always enables it. The chat template directly consumes reasoning_effort; enable_thinking/thinking_mode require gateway translation. Use qwen3 reasoning parser for Pro/mini, deepseek-r1 for Max, and qwen3_coder for tools. Vendor NexAU scores have incomplete run/effort metadata, so verdicts are withheld. Hosted endpoint context/completion limits and quantization are route-specific. Do not infer video capability from token IDs; the current route advertises text/image input and text output.
Can I self-host Nex-N2.5-Pro?
Nex-N2.5-Pro publishes open weights, but self-hosting depends on the licence, hardware footprint, quantisation quality, and serving stack. A hosted API is often cheaper until you have measured throughput and concurrency on your own hardware.
