Nex-N2.5-Mini API Pricing
nex-agi · Budget · released 2026-09. Prices in USD per 1 million tokens. Data snapshot: 2026-09-22.
Nex-N2.5-Mini is the 5th cheapest of 138 Budget models on blended price. Only one host, Nex AGI, sells it, so there is no second price to shop. No Arena score is published for it, so it carries no Efficiency score and cannot hold the FinOps Friendly badge.
- Input: $0.03 per 1M tokens
- Output: $0.10 per 1M tokens
- Batch API (input/output): not published
- Prompt-cache read: $0.0025
- Context window: 262K
Nex-N2.5-Mini market position
On blended price ($0.077 per 1M tokens at 30% input, 70% output) it is cheaper than 97% of Budget models: 5th cheapest of 138. Across every category it is cheaper than 99% of priced text models in the catalogue: 5th cheapest of 269.
- Next cheaper Budget model: Llama 3.1 8B Instruct (Meta) at $0.071 blended, 8% less.
- Next more expensive: Granite 4.0 Micro (ibm-granite) at $0.083 blended, 8% more.
Nex-N2.5-Mini licence, size and capabilities
No licence is recorded for Nex-N2.5-Mini, so this page does not say whether it can be self-hosted. Its parameter count is not published. Listed capabilities: Text, Vision, Reasoning. Filling its 262K context window once costs $0.0066 in input tokens at list price.
Cost per 1,000 requests by business use case
List price vs after discounts (prompt caching on the cached input share, batch API for async workloads, only where the provider publishes those rates). The monthly budget runs from the after-discounts figure, which assumes you implement both, to the list-price one.
| Use case | Tokens (in/out) | Cost / 1K req (list price) | Cost / 1K req (after discounts) | Monthly @100K req (after discounts – list) |
|---|---|---|---|---|
| Support Ticket | 1,500 / 500 | $0.09 | $0.07 | $7 – $9 |
| Knowledge Q&A | 2,000 / 800 | $0.13 | $0.10 | $10 – $13 |
| Meeting Summary | 10,000 / 1,200 | $0.37 | $0.35 | $35 – $37 |
| Marketing Content | 2,500 / 1,800 | $0.24 | $0.23 | $23 – $24 |
| Coding Task | 3,000 / 2,000 | $0.28 | $0.24 | $24 – $28 |
| Invoice Processing | 1,500 / 600 | $0.10 | $0.09 | $9 – $10 |
| Call Summary | 2,000 / 700 | $0.12 | $0.12 | $12 |
| Agent Workflow | 6,000 / 3,000 | $0.45 | $0.36 | $36 – $45 |
Nex-N2.5-Mini pricing by host
A host is a company that runs the model and sells it by the token — the lab that made it, a cloud platform like Amazon Bedrock, Azure or Vertex, or an independent provider. One model, several sellers, and often several prices. This model is sold by 1 host. The price quoted above is the one we publish so that models stay comparable; it is not necessarily the cheapest way to buy this model. List prices as published on 2026-09-22 via OpenRouter — negotiated rates, committed-use discounts and provisioned capacity are not shown.
Nex AGI is the only host with a published rate, $0.03 input / $0.10 output per 1M tokens, which is the price shown on this page.
| Host | Input $/1M | Output $/1M |
|---|---|---|
| Nex AGI (the price shown above) — bf16 | $0.03 | $0.10 |
Common questions about Nex-N2.5-Mini pricing
- How much does Nex-N2.5-Mini cost?
- Nex-N2.5-Mini costs $0.03 per million input tokens and $0.10 per million output tokens on the API.
- Does Nex-N2.5-Mini offer batch or cached pricing?
- Prompt-cache reads cost $0.0025/M input tokens. No batch pricing is published.
- What would Nex-N2.5-Mini cost per month?
- For a support-ticket workload (1,500 input + 500 output tokens per request) at 100K requests/month, Nex-N2.5-Mini costs about $9 at list prices.
These are list prices: real cost also depends on caching, batching, negotiated discounts, marketplace agreements, and existing contracts. Get a FinOps review from OptimNow or compare all models.
Build the business case for Nex-N2.5-Mini in the AI ROI Calculator: add your business value on top of these costs to get ROI, break-even and payback.
All models · Compare side by side · Cloud compute pricing · Price barometer · FinOps guides · API and MCP server