Primary use stated or inferred cautiously from official documentation.
Nex-N2.6
Nex AGI multimodal model based on GLM-5.3-Flash, with about 321 billion parameters and downloadable FP8 weights. It targets coding, computer use and long tool-based tasks. Public weights and OpenRouter access date to November 10, 2026. It accepts text and images and returns text and function calls.
The essential
Maximum input capacity when published by the source.
Documented maximum generation limit.
Verified availability channels.
Primary functional family and verified specialties.
Declared terms for API access, model weights, or self-hosting.
Limits and integration
| API ID | nex-agi/nex-n2.6 |
|---|---|
| Model type | Multimodal · Code · Text and reasoning |
| Access model | API and open weights |
| License | Apache 2.0 |
| Deployment | API or self-hosted deployment |
| Release | 10 NOV 2026 |
| Knowledge cutoff | Not published |
| Entrance | Text · Image |
| Exit | Text |
| Context window | 262,144 tokens on OpenRouter; weight configuration with 1,048,576 positions |
| maximum output | The endpoint declares 235,929 tokens; the limit depends on the provider |
| Reasoning | Not published |
| Published tools | Features |
| Structured Outings | Not published |
| Batch processing | Not published |
| Prompt cache | Not published |
| Fine-tuning | Not published |
| Verified platforms | OpenRouter · Hugging Face · SGLang |
Coding and visual automation agents that alternate planning, tools and result checks. The template provides low, high and max reasoning effort, defaulting to max. The client executes functions and returns results; calls do not by themselves grant system access. Self-hosting requires a GLM-5.3-Flash and FP8-compatible runtime, preserving the checkpoint’s tokenizer, processor and chat template.
The configuration declares 1,048,576 positions, but OpenRouter limits context to 262,144 tokens. Its endpoint API gives a 235,929-token maximum output while the commercial page says 262,144: apply the selected endpoint’s limit and remaining context, not the highest figure. FP8 is a format of the same model, not another version. Autonomous computer use requires bounded permissions, isolation and checks on irreversible actions.
What it can do
Orientation
Coding and visual automation agents that alternate planning, tools and result checks. The template provides low, high and max reasoning effort, defaulting to max. The client executes functions and returns results; calls do not by themselves grant system access. Self-hosting requires a GLM-5.3-Flash and FP8-compatible runtime, preserving the checkpoint’s tokenizer, processor and chat template.
Context
262,144 tokens on OpenRouter; weight configuration with 1,048,576 positions · The endpoint declares 235,929 tokens; the limit depends on the provider
Tools and integration
Features
Access
OpenRouter · Hugging Face
Documented cost
| Concept | Worth | Unit/condition |
|---|---|---|
| Standard input | 0.12 USD / 1M tokens | Standard API rate |
| Cached input | 0.024 USD / 1M tokens | Reading reused prefixes |
| Cache write or storage | Not published | The condition varies by provider |
| Standard output | USD 0.40 / 1M tokens | May include reasoning tokens |
| Batch input | Not published | Asynchronous processing |
| Batch output | Not published | Asynchronous processing |
Nex AGI endpoint prices on OpenRouter checked on November 22: USD 0.12 input, USD 0.024 cached input and USD 0.40 output per million tokens. These are that service’s prices, not self-hosting or universal distributor prices. The weights’ Apache 2.0 license does not remove infrastructure costs. Separate batch rates have not been verified.
i Prices change and may depend on level, region or context length. Check the source before making a decision.
How to read the results
Nex AGI reports 83.0 on OSWorld, 84.1 on Terminal-Bench 2.1 and 45.7 on AutomationBench. These are model-level results, not a separate evaluation of this FP8 export or Inferama measurements. Reasoning repetition falls from 16.0% to 1.6% in an internal issue-replay test; 100% valid tool selection is not a universal success guarantee either. Comparisons require the same harness, tools and budget.
| Benchmark | Result | Metric | Source |
|---|---|---|---|
| OSWorld | 83,0 | Published score | View source ↗ |
| Terminal-Bench 2.1 | 84,1 | Published score | View source ↗ |
| AutomationBench | 45,7 | Published score | View source ↗ |
Inferama only highlights a “best result” when the metric, test set, configuration, and date allow for an equivalent comparison. The supplier's figures are presented as claims from its own source.
Chronology
nex-agi/nex-n2.6
Version added to Inferama's verified catalog.