MiMo-V2.5 API Benchmarks, Pricing & Provider Data
Compare MiMo-V2.5 with another model
Choose a model to open its comparison page.
MiMo-V2.5 benchmark, API pricing, and provider data cover undefined API provider} other undefined API providers}}, with prices starting at $0.0000515/request. MiMo-V2.5 free API options are available from undefined provider} other undefined providers}}. The page also shows measured API speed and first-token latency.
Xiaomi MiMo-V2.5 is a native omnimodal sparse MoE model (310B total, 15B active) with unified text, image, video, and audio understanding, built on the MiMo-V2-Flash backbone with dedicated vision and...
Category Performance
Observed-capability estimates with uncertainty reported separately from independent benchmark families.
- Coverage
- 4 / 8
- Methodology
- V3.0
#1Reasoning55.5Provisional1/4 Measured dimensions
#2Agents50.2RatedGlobal rank #373/4 Measured dimensions
#3Coding49.5Estimated3/4 Measured dimensions
#4Multimodal48.9Estimated2/4 Measured dimensions
Specifications
Input and output token limits for this model, plus how it ranks on long-context understanding.
Features
Technical Details
- Input
- Output
- Released
- Apr 2026
- Tokenizer
- Other
- Architecture
- text+image+audio+video->text
- Moderated
- No
- Supported parameters
- frequency_penaltyinclude_reasoninglogit_biasmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p
Rankings
Excels at
Falls behind in
Detailed scores
Updated: Sep 13, 2026Overall
undefined metric} other undefined metrics}}
Overall score56.0#65 / 112
Overall
undefined metric} other undefined metrics}}
Speed & latency
undefined metric} other undefined metrics}}
Output speed56.7 tok/s#69 / 80Time to first token6.53 s#61 / 80
Speed & latency
undefined metric} other undefined metrics}}
Pricing
undefined metric} other undefined metrics}}
Input price$0.140/M#20 / 186Output price$0.280/M#10 / 186
Pricing
undefined metric} other undefined metrics}}
Agents
V3.0undefined metric} other undefined metrics}} · Rated
Score50.2#3780% interval41.3–59.13/4 Measured dimensionsAgentic score58.2#44 / 77Claw-Eval62.3#10 / 27
Agents
V3.0undefined metric} other undefined metrics}} · Rated
Coding
V3.0undefined metric} other undefined metrics}} · Estimated
Score49.580% interval40.3–58.83/4 Measured dimensionsSciCode43.9%#50 / 89Coding score40.8#75 / 87
Coding
V3.0undefined metric} other undefined metrics}} · Estimated
Reasoning
V3.0undefined metric} other undefined metrics}} · Provisional
Score55.580% interval41.6–69.41/4 Measured dimensionsGPQA84.9%#67 / 218HLE27.2%#68 / 216
Reasoning
V3.0undefined metric} other undefined metrics}} · Provisional
Knowledge
V3.0undefined metric} other undefined metrics}} · No data
No data80% interval30.8–69.20/4 Measured dimensions
Knowledge
V3.0undefined metric} other undefined metrics}} · No data
Math
V3.0undefined metric} other undefined metrics}} · No data
No data80% interval30.8–69.20/4 Measured dimensions
Math
V3.0undefined metric} other undefined metrics}} · No data
Multilingual
V3.0undefined metric} other undefined metrics}} · No data
No data80% interval30.8–69.20/4 Measured dimensions
Multilingual
V3.0undefined metric} other undefined metrics}} · No data
Multimodal
V3.0undefined metric} other undefined metrics}} · Estimated
Score48.980% interval37.0–60.82/4 Measured dimensionsMultimodal Grounded score62.9#37 / 56Video-MME (with subtitle)87.7#3 / 6
Multimodal
V3.0undefined metric} other undefined metrics}} · Estimated
Instruction following
V3.0undefined metric} other undefined metrics}} · No data
No data80% interval30.8–69.20/4 Measured dimensions
Instruction following
V3.0undefined metric} other undefined metrics}} · No data
OpenRouter endpoints
5 endpointsThird-party OpenRouter endpoint data, shown separately from LMSpeed measurements. Some 30-minute live performance fields only appear after syncing with an OpenRouter API key.
| Provider endpoint | Input | Output | 1d uptime | 30m latency | 30m throughput | Context / output |
|---|---|---|---|---|---|---|
DeepInfra deepinfra/fp8 | $0.133/M | $0.266/M | 98.8% | — | — | undefined tokens / undefined tokens |
Xiaomi xiaomi/fp8 | $0.140/M | $0.280/M | 97.9% | — | — | undefined tokens / undefined tokens |
Novita novita/fp8 | $0.168/M | $0.336/M | 97.7% | — | — | undefined tokens / undefined tokens |
StreamLake streamlake | $0.168/M | $0.336/M | 96.8% | — | — | undefined tokens / undefined tokens |
GMICloud gmicloud/fp8 | $0.119/M | $0.238/M | 76.8% | — | — | undefined tokens / undefined tokens |
Pricing Comparison
Compare MiMo-V2.5 API pricing across 125 providers. Prices range from $0.0000515/request to $150.00/M. S3AI API offers the lowest rate at $0.0000515/request. 5 providers offer free API credits or a free tier.
| Provider | Health | Model Variant | Group | Input ($/M) | Output ($/M) | Speed (t/s) | First token | Audit |
|---|---|---|---|---|---|---|---|---|
L1 100% | mimo-v2.5 | default | -40%$0.084/M Cache read$0.0017/M | -40%$0.168/M | 86.1 t/s+52% | 2.08 s-68% | — | |
L1 100% L2 100% | mimo-v2.5 | Free | -93%$0.010/M Cache read$0.0002/M | -93%$0.020/M | 75.4 t/s+33% | 2.21 s-66% | — | |
L1 99% | mimo-v2.5 | 临时渠道 | -96%$0.0055/M Cache read$0.0011/M | -90%$0.027/M | 65.8 t/s+16% | 6.20 s-5% | — | |
L1 99% | mimo-v2.5-free | 临时渠道2 | -27%$0.103/M | -63%$0.103/M | — | — | — | |
L1 94% L2 97% | mimo-v2.5 | default | -26%$0.103/M Cache read$0.010/M | -26%$0.206/M | 65.0 t/s+15% | 4.32 s-34% | — | |
L1 94% L2 97% | go/oc/mimo-v2.5 | Go Plan | Free | Free | — | — | — | |
L1 94% L2 97% | oc/mimo-v2.5 | default | $0.0000515/request | - | — | — | — | |
L1 100% | mimo-v2.5 | default | -51%$0.068/M Cache read$0.0014/M | -51%$0.137/M | — | — | — | |
L1 100% | mimo-v2.5 | mimo-officially | -18%$0.114/M Cache read$0.0023/M | -18%$0.229/M | — | — | — | |
BUZZ Free | L1 100% | mimo-v2.5-free | Free | Free | Free | — | — | — |
L1 100% | mimo-v2.5 | default | -2%$0.137/M | -2%$0.274/M | — | — | — | |
L1 100% | mimo-v2.5 | default | -51%$0.068/M Cache read$0.0014/M | -51%$0.137/M | — | — | — | |
L1 100% | mimo-v2.5 | default | -93%$0.0096/M Cache read$0.0002/M | -93%$0.019/M | — | — | — | |
L1 100% | mimo-v2.5 | Xiaomi-1 | -78%$0.031/M Cache read$0.0006/M | -78%$0.062/M | — | — | — | |
L1 100% | mimo-v2.5 | default | $2.00/M | $2.00/M | — | — | — | |
L1 100% | [按次]mimo-v2.5 | default | $0.100/request | - | — | — | — | |
L1 100% | mimo-v2.5 | default | -32%$0.095/M | $0.284/M | — | — | — | |
L1 100% L2 0% | mimo-v2.5 | default | $0.400/M Cache read$0.080/M | $2.00/M | — | — | — | |
L1 100% | mimo-v2.5 | default | $0.767/M | $3.84/M | — | — | — | |
L1 100% | mimo-v2.5-free | default | $7.50/M | $7.50/M | — | — | — |
Alternatives & Similar Models
DeepSeek V4 Flash
deepseek-v4-flash
DeepSeek V4 Flash is a fast, cost-efficient language model in the DeepSeek V4 family, optimized for low-latency chat, coding assistance, and high-throughput API workloads while retaining strong reasoning quality.
DeepSeek V4 Pro
deepseek-v4-pro
DeepSeek V4 Pro is the professional-tier DeepSeek V4 model, targeting frontier reasoning, coding, and agent workflows with maximum capability.
MiMo-V2.5-Pro
mimo-v2-5-pro
Xiaomi MiMo-V2.5-Pro is a large open-source language model in the MiMo series, offering advanced reasoning and general-purpose capabilities.
GPT-5.4
gpt-5-4
OpenAI GPT-5.4 extends the GPT-5 family with stronger instruction following, deeper tool use, and improved performance on coding, math, and long-document analysis.
GLM-5.1
glm-5-1
Zhipu GLM-5.1 is a next-generation GLM model aimed at frontier reasoning, coding, and bilingual agent applications.
Kimi K2.5
kimi-k2-5
Moonshot Kimi K2.5 is an open-weight multimodal agent model with native vision and text input, strong coding performance, and a 256K context window.
Frequently Asked Questions
- What benchmark data does MiMo-V2.5 include?
- LMSpeed shows MiMo-V2.5 benchmark context, API price, output speed, first-token latency, and provider data across 130 providers when those signals are available.
- What is the MiMo-V2.5 API price?
- MiMo-V2.5 has pricing from undefined provider} other undefined providers}}, ranging from $0.0000515/request to $150.00/M. S3AI API has the lowest listed price.
- What does the MiMo-V2.5 API pricing table include?
- The MiMo-V2.5 API pricing table compares 130 providers by input price, output price, free tier status, speed, first-token latency, and recent health data when available.
- Which provider has the cheapest MiMo-V2.5 API pricing?
- S3AI API currently has the lowest listed MiMo-V2.5 price at $0.0000515/request across undefined provider} other undefined providers}}.
- Can I compare MiMo-V2.5 API price and speed together?
- Yes. LMSpeed shows MiMo-V2.5 API price, output speed, first-token latency, and provider health on the same page so you can compare cost and performance together.
- Is MiMo-V2.5 API free?
- Yes, MiMo-V2.5 free API options are available through 5 providerundefined other undefined} on LMSpeed, including S3AI API, 初叶🍂Furry API, Zero API, Dext API, BUZZ. These providers offer free API credits or a free tier with no per-token charges.
- Where can I get MiMo-V2.5 free API access?
- LMSpeed currently lists 5 free API providerundefined other undefined} for MiMo-V2.5: S3AI API, 初叶🍂Furry API, Zero API, Dext API, BUZZ. Check each provider row before using it because free tier limits can change.