MiMo-V2.6-Pro API Pricing
Xiaomi · Budget · Proprietary · released 2026-09. Prices in USD per 1 million tokens. Data snapshot: 2026-09-22.
MiMo-V2.6-Pro is the 89th cheapest of 138 Budget models on blended price. Only one host, Xiaomi, 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: $0.43 per 1M tokens
- Output: $0.87 per 1M tokens
- Batch API (input/output): not published
- Prompt-cache read: $0.0036
- Context window: 1M
MiMo-V2.6-Pro market position
On blended price ($0.740 per 1M tokens at 30% input, 70% output) it is cheaper than 35% of Budget models: 89th cheapest of 138, tied with one other. Across every category it is cheaper than 67% of priced text models in the catalogue: 89th cheapest of 269, tied with one other.
- Next cheaper Budget model: Codestral 2508 (Mistral) at $0.720 blended, 3% less.
- Next more expensive: DeepSeek V3.1 (DeepSeek) at $0.740 blended, under 1% more.
MiMo-V2.6-Pro licence, size and capabilities
MiMo-V2.6-Pro is recorded here as proprietary: access is through an API, priced by the token. Its parameter count is not published. Listed capabilities: Text, Vision, Audio, Reasoning, Code, Agents. Filling its 1M context window once costs $0.43 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 | $1.09 | $0.70 | $70 – $109 |
| Knowledge Q&A | 2,000 / 800 | $1.57 | $0.96 | $96 – $157 |
| Meeting Summary | 10,000 / 1,200 | $5.39 | $4.96 | $496 – $539 |
| Marketing Content | 2,500 / 1,800 | $2.65 | $2.44 | $244 – $265 |
| Coding Task | 3,000 / 2,000 | $3.05 | $2.40 | $240 – $305 |
| Invoice Processing | 1,500 / 600 | $1.17 | $0.98 | $98 – $117 |
| Call Summary | 2,000 / 700 | $1.48 | $1.39 | $139 – $148 |
| Agent Workflow | 6,000 / 3,000 | $5.22 | $3.41 | $341 – $522 |
MiMo-V2.6-Pro 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.
Xiaomi is the only host with a published rate, $0.43 input / $0.87 output per 1M tokens, which is the price shown on this page. It serves a quantized fp8 build, which is not the same product as the full-precision model.
| Host | Input $/1M | Output $/1M |
|---|---|---|
| Xiaomi (the price shown above) — fp8 | $0.43 | $0.87 |
Common questions about MiMo-V2.6-Pro pricing
- How much does MiMo-V2.6-Pro cost?
- MiMo-V2.6-Pro costs $0.43 per million input tokens and $0.87 per million output tokens on the API.
- Does MiMo-V2.6-Pro offer batch or cached pricing?
- Prompt-cache reads cost $0.0036/M input tokens. No batch pricing is published.
- What would MiMo-V2.6-Pro cost per month?
- For a support-ticket workload (1,500 input + 500 output tokens per request) at 100K requests/month, MiMo-V2.6-Pro costs about $109 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 MiMo-V2.6-Pro 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