Tencent: WeMM-Embedding 2B
tencent/wemm-embedding-2bHugging FaceEmbeddingsenfeature-extractionimage-embeddingimage-text-to-textmrlmultimodal-embeddingqwen3_5text-embeddingvideo-embeddingzh
Providers
Live endpoints for this model. Response is the time from request to result; uptime is measured over the last day and week. Nothing here streams, so there is no first token to time and no token rate to report.
| Provider | Context | Input | Cache read | Response | Capacity | Uptime 1d | Uptime 7d | Health | Data |
|---|---|---|---|---|---|---|---|---|---|
| Consensus Protocolbf1690% offUS | 33K | $0.003 | $0.00075 | 681ms30m | 4/4 free | 100.0% | 99.7% | Healthy | ZDR |
| ImpCCbf1690% offCA | 33K | $0.003 | — | 166ms30m | 8/8 free | 100.0% | 100.0% | Healthy | ZDR |
Pricing
USD per million tokens.
| Provider | Input | Cache read |
|---|---|---|
| Consensus Protocolbf1690% off | $0.003 | $0.00075 |
| ImpCCbf1690% off | $0.003 | — |
Price history
Input price · USD per million tokens
Performance
Percentiles cover the labelled window: the last 30 minutes when it has enough samples, otherwise the last day. Response is the time in seconds from request to result. This model answers whole rather than streaming, so there is no first token to time and no rate between tokens to report — response time is the whole measurement there is.
| Provider | Response p50 | p75 | p90 | p99 |
|---|---|---|---|---|
| Consensus Protocolbf16 | 681ms30m | 965ms | 3.63s | 5.72s |
| ImpCCbf16 | 166ms30m | 235ms | 426ms | 426ms |
Rotating benchmark probes
Diagnostic scores from rotating dataset subsets. Percentages cover graded replies only and are not full benchmark results. Each score belongs to the provider’s serving configuration.
| Provider | Banking77 triplets | scidocs-triplet |
|---|---|---|
| Consensus Protocolbf16 | 96.6%356 graded | 92.3%287 graded |
| ImpCCbf16 | 96.6%596 graded | 92.2%499 graded |
Benchmark answers are graded mechanically against the vendored dataset reference answers — numeric comparison of the final number for GSM8K, MATH-500 and AIME 2025, the committed multiple-choice letter for MMLU, MMLU-Pro, MMMU and MMBench, cosine ranking of the returned vectors for the Banking77 and SciDocs retrieval triplets, and per-utterance word match for LibriSpeech and FLEURS — never by another model; a reply that ran into the probe’s token cap before it committed to an answer is recorded but not graded.
Uptime
Share of successful requests and probes over the last day and week.
- Consensus Protocolbf161d 100.0%7d 99.7%Healthy
- ImpCCbf161d 100.0%7d 100.0%Healthy
Availability by hour · last 7 days
Share of successful requests and probes per hour and provider. The line spans hours with nothing to measure; where samples are sparse, a dot marks each hour actually measured.
Activity
Tokens embedded per UTC day over the last 30 days. Every billed request counts, the platform's own paid probe traffic included.
curl https://api-staging.impossiblecarrot.cc/api/v1/embeddings \ -H "Authorization: Bearer $HEIMDALL_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "tencent/wemm-embedding-2b", "input": "The quick brown fox" }'Set HEIMDALL_API_KEY to a key from your account. See the quickstart for routing suffixes and provider preferences.
About
A 2.7B-parameter multimodal embedding model built on a Qwen3.5 backbone, reading text, images, short video clips and interleaved text-and-image documents, and returning a 2,048-dimension L2-normalized vector. Served through the embeddings API; it has no generative path. It has two input bases, and their vectors are not interchangeable: a string, a list of strings or token ids is embedded as the text it stands for, while a content item, { "content": [...] }, a text-only one included, is wrapped in the model's chat template with its role turns and the <embedding> token. The same short text embeds 0.1189 apart (cosine distance) through the two. Embed images and mixed items as content items and query them the same way.
- Author
- Tencent
- Family
- tencent/wemm-embedding-2b
- Weights
- tencent/WeMM-Embedding-2B
- Parameters
- dimensions (6 choices), encoding_format (float, base64)
- Licence
- apache-2.0
- Size
- 2.7B parameters, BF16 weights
- Tokenizer
- —
- Available until
- —
From the model card
What the repository states about these weights, read from tencent/WeMM-Embedding-2B on Oct 11, 2026.
- Languages
- Chinese, English
- Papers
- 2608.24053
- Datasets
- —
- Revision
- bbd6cd4Sep 3, 2026
- Downloads
- —
- Likes
- —