MiMo-V2.5-Pro model profile
Evidence snapshot:
MiMo-V2.5-Pro is a Xiaomi model profile with a 1,050,000-token context window. The dated catalog snapshot records text modalities and interfaces for prompt caching, reasoning controls, structured output, text generation, tool calling.
MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro. It can independently and autonomously complete professional tasks that would take human experts days or weeks, involving more than a thousand tool calls. Its context length of up to 1M makes it well suited for integration with a wide range of agent frameworks.
MiMo-V2.5-Pro is a reference profile: Xiaomi publishes it, Kendr documents it for comparison, and it carries no Kendr alias to call.
MiMo-V2.5-Pro is an independent knowledge profile. It does not claim that Kendr hosts the model, quote a Kendr customer price, promise API availability, or advertise a Kendr routing receipt.
MiMo-V2.5-Pro accepts text and returns text. The snapshot records prompt caching, reasoning controls, structured output, text generation, and tool calling as capabilities or interfaces.
The dated reference snapshot lists $0.3045 input and $0.609 output per million tokens. Cached input is $0.0028 per million tokens.
The 2026-09-06 snapshot includes 3 Artificial Analysis indexes, 8 Design Arena categories, and AutoExacto results for 8 provider observations. Publisher-reported launch results are labeled and are not presented as Kendr measurements; scores from different suites are not treated as interchangeable.
MiMo-V2.5-Pro ranked #44 in the cited trailing-7-day third-party catalog usage dataset as of 2026-09-06. Observed within the cited trailing-7-day third-party catalog usage dataset; this is not global AI market share.
Profile data was reviewed for the 2026-09-06 snapshot. Claims retain their source dates, and unavailable fields are shown as unavailable instead of estimated.
Profile facts
- Profile type
- Model research profile
- Provider or publisher
- Xiaomi
- Context window
- 1,050,000 tokens
- Snapshot date
- 2026-09-06
- Knowledge cutoff
- Not disclosed
- Reference catalog ID
- xiaomi/mimo-v2.5-pro
When to pick MiMo-V2.5-Pro
MiMo-V2.5-Pro is a reference profile: Xiaomi publishes it, Kendr documents it for comparison, and it carries no Kendr alias to call.
Each condition below is derived from this model's own values in the 2026-09-06 snapshot, compared only against models publishing the same field.
- Reach for it when a whole corpus has to fit in one prompt. The 1.05M-token context window is in the top quarter of the 163 models publishing a limit here, so long documents can go in whole rather than chunked.
- Reach for it when the model has to call tools. Tool calling is recorded in the snapshot, so this route can drive an agent loop rather than only answer in prose.
- Look elsewhere when you need to call it through Kendr today. This is a research reference profile with no Kendr alias. The facts and evidence here are published for comparison; the model is not routable on Kendr.
- Look elsewhere when the task is hard reasoning. Its 32.6 Artificial Analysis intelligence index is below the median of the 32 models carrying that field. Scores from different suites are not interchangeable, so treat this as one signal rather than a ranking.
Context, modalities, and identity
MiMo-V2.5-Pro accepts text and returns text. The snapshot records prompt caching, reasoning controls, structured output, text generation, and tool calling as capabilities or interfaces.
- Provider or publisher
- Xiaomi
- Context window
- 1,050,000 tokens
- Maximum output
- 131,072 tokens
- Input modalities
- text
- Output modalities
- text
- Knowledge cutoff
- Not disclosed
Model overview
MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro. It can independently and autonomously complete professional tasks that would take human experts days or weeks, involving more than a thousand tool calls. Its context length of up to 1M makes it well suited for integration with a wide range of agent frameworks.
- Reference model ID
- xiaomi/mimo-v2.5-pro
- Canonical version
- xiaomi/mimo-v2.5-pro-20260422
- Hugging Face ID
- XiaomiMiMo/MiMo-V2.5-Pro
Capabilities and supported controls
Capabilities and parameters are reported from the dated catalog and source records; their presence does not guarantee identical behavior across every provider route.
- Supported parameters
- frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, min_p, presence_penalty, reasoning, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p
- prompt caching
- reasoning controls
- structured output
- text generation
- tool calling
Dated pricing snapshot
The dated reference snapshot lists $0.3045 input and $0.609 output per million tokens. Cached input is $0.0028 per million tokens.
These are dated third-party reference prices, not Kendr prices or an availability offer. Routes, tiers, caching, region, and provider policy can change the landed price.
- Price date
- 2026-09-06
- Input
- $0.3045 per 1M tokens
- Cached input
- $0.0028 per 1M tokens
- Output
- $0.609 per 1M tokens
Provider routes, performance, and uptime
The snapshot retains 7 provider endpoints. Provider prices, context limits, p50 performance, and uptime can differ by route and are not Kendr guarantees.
- Active provider endpoints
- 2
- Best p50 latency
- 0.79 s
- Best p50 throughput
- 33 tok/s
- Availability with routing
- 99.85% over the sampled window
- Availability without routing
- 96.94% over the sampled window
- Performance date
- 2026-09-06
| Provider | Quantization | Input / 1M | Output / 1M | Cache read / 1M | Context | p50 latency | p50 throughput | Uptime (1d) |
|---|---|---|---|---|---|---|---|---|
| AtlasCloud | fp8 | $0.435 / 1M | $0.87 / 1M | $0.0036 / 1M | 1,024,000 tokens | 1.93 s | 20 tok/s | 90.86% |
| Xiaomi | fp8 | $0.435 / 1M | $0.87 / 1M | $0.0036 / 1M | 1,048,576 tokens | 2.93 s | 29 tok/s | 98.05% |
| DeepInfra | fp8 | $0.39 / 1M | $1.17 / 1M | $0.078 / 1M | 1,048,576 tokens | 1.71 s | 31 tok/s | 96.05% |
| DigitalOcean | unknown | $0.4 / 1M | $1.5 / 1M | $0.08 / 1M | 262,144 tokens | 0.79 s | 17 tok/s | 99.10% |
| NovitaAI | unknown | $0.48024 / 1M | $0.96048 / 1M | $0.003956 / 1M | 1,048,576 tokens | 4.93 s | 33 tok/s | 97.14% |
| GMICloud | bf16 | $0.3045 / 1M | $0.609 / 1M | $0.0028 / 1M | 1,050,000 tokens | 3.49 s | 27 tok/s | 75.21% |
| StreamLake | unknown | $0.522 / 1M | $1.044 / 1M | $0.00432 / 1M | 1,000,000 tokens | 2.00 s | 24 tok/s | 92.26% |
Benchmark evidence and limitations
The 2026-09-06 snapshot includes 3 Artificial Analysis indexes, 8 Design Arena categories, and AutoExacto results for 8 provider observations. Publisher-reported launch results are labeled and are not presented as Kendr measurements; scores from different suites are not treated as interchangeable.
Third-party catalog fields normalized from the cited model dataset; benchmark methodology and coverage differ by source.
- Intelligence Index
- 32.6
- Coding Index
- 60.2
- Agentic Index
- 22.7
- AutoExacto coverage
- 8 provider observations over 32 days
| Design Arena category | Elo | Win rate | Rank |
|---|---|---|---|
| 3d | 1285 | 55.7% | #23 |
| asciiart | 1183 | 48.4% | #28 |
| codecategories | 1288 | 54.4% | #20 |
| dataviz | 1281 | 52.4% | #19 |
| gamedev | 1291 | 55.3% | #20 |
| svg | 1223 | 51.3% | #23 |
| uicomponent | 1284 | 54.7% | #24 |
| website | 1287 | 54% | #18 |
AutoExacto provider benchmarks
Rolling provider observations from the cited third-party benchmark view. The lookback is 32 days; GPQA Diamond and TAU-Bench Airline measure different abilities and should not be blended into one score.
| Provider | GPQA Diamond | TAU-Bench Airline | Runs |
|---|---|---|---|
| AtlasCloud | 64.91% | 57.41% | 5 |
| auto-routing | 84.39% | 74.69% | 4 |
| DeepInfra | 81.51% | 74.68% | 5 |
| DigitalOcean | 81.73% | 69.99% | 4 |
| GMICloud | 85.03% | — | 5 |
| NovitaAI | 84.61% | 76.18% | 5 |
| StreamLake | 83.98% | 70.37% | 5 |
| Xiaomi | 85.3% | 74.68% | 5 |
Popularity and market context
MiMo-V2.5-Pro ranked #44 in the cited trailing-7-day third-party catalog usage dataset as of 2026-09-06. Observed within the cited trailing-7-day third-party catalog usage dataset; this is not global AI market share.
- Third-party catalog rank
- #44
- Global market share
- Not inferred
- Observation date
- 2026-09-06
Frequently asked questions
When should I use MiMo-V2.5-Pro?
MiMo-V2.5-Pro is a reference profile: Xiaomi publishes it, Kendr documents it for comparison, and it carries no Kendr alias to call. Reach for it when a whole corpus has to fit in one prompt: The 1.05M-token context window is in the top quarter of the 163 models publishing a limit here, so long documents can go in whole rather than chunked. Reach for it when the model has to call tools: Tool calling is recorded in the snapshot, so this route can drive an agent loop rather than only answer in prose. Look elsewhere when you need to call it through Kendr today: This is a research reference profile with no Kendr alias. The facts and evidence here are published for comparison; the model is not routable on Kendr. Look elsewhere when the task is hard reasoning: Its 32.6 Artificial Analysis intelligence index is below the median of the 32 models carrying that field. Scores from different suites are not interchangeable, so treat this as one signal rather than a ranking.
What is MiMo-V2.5-Pro?
MiMo-V2.5-Pro is a Xiaomi model profile with a 1,050,000-token context window. The dated catalog snapshot records text modalities and interfaces for prompt caching, reasoning controls, structured output, text generation, tool calling.
What context window does MiMo-V2.5-Pro have?
The dated profile lists 1,050,000 tokens of context and up to 131,072 output tokens. Provider routes, variants, and runtime configuration can impose lower effective limits.
What benchmark evidence is available for MiMo-V2.5-Pro?
The 2026-09-06 snapshot includes 3 Artificial Analysis indexes, 8 Design Arena categories, and AutoExacto results for 8 provider observations. Publisher-reported launch results are labeled and are not presented as Kendr measurements; scores from different suites are not treated as interchangeable. Third-party catalog fields normalized from the cited model dataset; benchmark methodology and coverage differ by source.
Is MiMo-V2.5-Pro available through Kendr?
This is an independent knowledge profile, not a Kendr-hosted availability claim. Check Kendr's live public model API for currently enabled Kendr aliases.
Does the popularity rank represent MiMo-V2.5-Pro's global market share?
MiMo-V2.5-Pro ranked #44 in the cited trailing-7-day third-party catalog usage dataset as of 2026-09-06. Observed within the cited trailing-7-day third-party catalog usage dataset; this is not global AI market share. No global market-share percentage is inferred when the source does not publish one.
Sources and evidence dates
- MiMo-V2.5-Pro third-party catalog record (catalog, checked 2026-09-06)
- Third-party model catalog methodology (methodology, checked 2026-09-06)
- Artificial Analysis capability indices methodology (benchmark, checked 2026-09-06)
- Design Arena leaderboard and methodology (benchmark, checked 2026-09-06)
- MiMo-V2.5-Pro third-party catalog record (benchmark, checked 2026-09-06)