MiMo-V2.6-Flash API pricing
Xiaomi · Budget price tier · MIT · released 2026-09. Prices in USD per 1 million tokens. Data snapshot: 2026-11-12.
A support ticket workload of 100K requests a month costs $35.00 on MiMo-V2.6-Flash; the next cheaper model in the Budget price tier for this workload, Particle-1, does it for $32.50. MiMo-V2.6-Flash has held the same list price since 2026-09-22 and is the 50th cheapest of 160 models in the Budget price tier. Buying from GMICloud rather than at the price we quote lowers the token price by about 20%. It holds the FinOps Friendly badge: top-40% Arena quality, top-30% Efficiency, not among the dearest 30%, and no stability flag.
- Input: $0.14 per 1M tokens
- Output: $0.28 per 1M tokens
- Batch API (in/out): Not published
- Prompt-cache read: $0.0028 per 1M tokens
- Context window: 1M tokens
- Arena ELO: 1451 as of 2026-11-08
Market position
On blended price ($0.238 per 1M tokens at 30% input, 70% output) it is cheaper than 69% of models in the Budget price tier: 50th cheapest of 160. Across every price tier it is cheaper than 84% of priced text models in the catalogue: 50th cheapest of 303. Its Arena ELO of 1451 ranks 36th of the 160 models that carry one, tied with 3 others, above 76% of them. With an Arena score of 1451, MiMo-V2.6-Flash clears OptimNow's Standard working quality threshold: Standard (Arena 1420+), used for meeting summary, invoice processing and call summary. It is 19 points under the Strong bar (Arena 1470+), within the benchmark's 20-point noise. Each threshold is a distance below the best ranked model, which scores 1530 on Arena scores as of 8 Nov 2026.
Licence, size and capabilities
MiMo-V2.6-Flash is open source: its weights are published under MIT, an OSI-approved licence with no field-of-use limit, so it can be self-hosted as well as bought by the token. Its published size is 309B parameters. Listed capabilities: Text, Vision, Audio, Reasoning, Agents. Filling its 1M context window once costs $0.14 in input tokens at list price.
Pricing by host
A host is a company that runs the model and sells it by the token: the model maker, a cloud platform like Amazon Bedrock, Azure or Vertex, or an independent host. One model, several hosts, and often several prices. This model is sold by 8 different hosts. The price we quote elsewhere on this page is marked. We quote one host's rate so that models stay comparable; it is not a recommendation to buy there.
Cheapest host: GMICloud at $0.112 input / $0.224 output per 1M tokens, 20% below the price we quote on the blended price (30% input, 70% output). A support ticket workload at 100K requests a month costs $28.00 there against $35.00 at the price we quote, a difference of $7.00 a month. The dearest, Venice, charges 1.6x the cheapest.
| Host | Input $/1M | Output $/1M | Precision |
|---|---|---|---|
| GMICloud | $0.112 | $0.224 | bf16 |
| Darkbloom | $0.10 | $0.28 | fp4 |
| Xiaomi (model maker, price we quote) | $0.14 | $0.28 | fp8 |
| Cohere (price we quote) | $0.14 | $0.28 | fp8 |
| DeepInfra (price we quote) | $0.14 | $0.28 | fp8 |
| Tenstorrent | $0.165 | $0.33 | fp8 |
| Makora | $0.17 | $0.33 | fp8 |
| Venice | $0.175 | $0.35 | fp8 |
List prices as published on 2026-11-12, via OpenRouter. Negotiated rates, committed-use discounts and provisioned capacity are not shown. These hosts do not all serve the model at the same numeric precision, so the cheapest is not a like-for-like substitute for the dearest. GMICloud's listing is a promotional rate: 20% off its standard rate.
Monthly cost at 100K requests, by business use case
From the after-discounts figure (prompt caching on the cached input share, batch API for async workloads, only where Xiaomi publishes those rates), which assumes you implement both, to the list price. One figure means no discount is published.
| Use case | Tokens (in/out) | Monthly (after discounts – list) |
|---|---|---|
| Support Ticket | 1,500 / 500 | $23 – $35 |
| Knowledge Q&A | 2,000 / 800 | $31 – $50 |
| Meeting Summary | 10,000 / 1,200 | $160 – $174 |
| Marketing Content | 2,500 / 1,800 | $79 – $85 |
| Coding Task | 3,000 / 2,000 | $77 – $98 |
| Invoice Processing | 1,500 / 600 | $32 – $38 |
| Call Summary | 2,000 / 700 | $45 – $48 |
| Agent Workflow | 6,000 / 3,000 | $110 – $168 |
Price history
MiMo-V2.6-Flash entered our daily price archive on 2026-09-22; tracking began on 2026-08-15. It listed at $0.14 input / $0.28 output per 1M tokens that day. No list price change since 2026-09-22. Last checked against the 2026-11-12 snapshot.
Alternatives to MiMo-V2.6-Flash
None of the 4 comparable models below costs less than MiMo-V2.6-Flash on the blended price.
- Next cheaper model in the Budget price tier: Hy-MT2-30B-A3B (Tencent) at $0.2287 blended, 4% less.
- Next more expensive: Qwen3 30B A3B Instruct 2507 (Alibaba) at $0.24 blended, 1% more.
The nearest models in the Budget price tier on Arena ELO, each with its blended price and score difference against MiMo-V2.6-Flash.
- DeepSeek V4 Pro 0423 (DeepSeek): $0.9553 in / $1.9105 out per 1M, Arena ELO 1451 (582% more expensive, same Arena ELO)
- Qwen3.7 Plus (Alibaba): $0.32 in / $1.28 out per 1M, Arena ELO 1454 (317% more expensive, 3 ELO points higher)
- Gemma 4 31B (Google): $0.20 in / $0.40 out per 1M, Arena ELO 1443 (43% more expensive, 8 ELO points lower)
- DeepSeek V4.1 Flash (DeepSeek): $0.022 in / $0.40 out per 1M, Arena ELO 1463 (20% more expensive, 12 ELO points higher)
- Cheapest within 15 Arena points: MiMo-V2.6-Flash is itself the cheapest of the 36 models scoring within 15 points of its ELO.
- Highest Arena ELO within 20% of this price: MiMo-V2.6-Flash itself has the highest score of the 9 models priced within 20% of it.
Other models from Xiaomi
Xiaomi has 4 other models in the catalogue. Prices per 1M tokens, input then output.
- MiMo-V2.6-Pro: $0.435 / $0.87
- MiMo-V2.5-Pro: $0.48 / $1.80
- MiMo-V2.5: $0.40 / $2.00
- MiMo-V2.6-Pro-UltraSpeed: $4.35 / $8.70
All 5 Xiaomi models and prices
Common questions about MiMo-V2.6-Flash pricing
- How much does MiMo-V2.6-Flash cost?
- MiMo-V2.6-Flash costs $0.14 per 1M input tokens and $0.28 per 1M output tokens. That is the model maker's own rate (Xiaomi). Prices as listed on 2026-11-12.
- Which host is cheapest for MiMo-V2.6-Flash?
- Cheapest host: GMICloud at $0.112 input / $0.224 output per 1M tokens, 20% below the price we quote on the blended price (30% input, 70% output). A support ticket workload at 100K requests a month costs $28.00 there against $35.00 at the price we quote, a difference of $7.00 a month. The dearest, Venice, charges 1.6x the cheapest. Host rates as listed on 2026-11-12.
- Does MiMo-V2.6-Flash offer batch or cached pricing?
- Yes, for prompt caching only. Cache reads cost $0.0028 per 1M tokens, as listed on 2026-11-12. No batch pricing is published.
- What would MiMo-V2.6-Flash cost per month?
- With the Support Ticket profile (1,500 input and 500 output tokens per request), 100,000 requests a month cost about $35 on MiMo-V2.6-Flash at the list price quoted on 2026-11-12.
- Can MiMo-V2.6-Flash be self-hosted?
- Yes. MiMo-V2.6-Flash is open source: its weights are published under MIT, an OSI-approved licence with no field-of-use limit, so it can be self-hosted as well as bought by the token.
- Has the price of MiMo-V2.6-Flash changed?
- MiMo-V2.6-Flash entered our daily price archive on 2026-09-22; tracking began on 2026-08-15. It listed at $0.14 input / $0.28 output per 1M tokens that day. No list price change since 2026-09-22. Last checked against the 2026-11-12 snapshot.
Its weights are published, which changes what you may run yourself: the cost gap between open weights and proprietary APIs.
These are list prices. Your real cost also depends on caching and batching, negotiated discounts, marketplace agreements, and the contracts you already have. OptimNow audits exactly that.
Build the business case · Get a FinOps review
LLM pricing · Models by maker · Cloud compute pricing · Compare models · Price barometer · FinOps guides · API and MCP server