Granite Embedding English r2 vs Hy4 preview
At a Glance
| Compare |  Hy4 previewTencent | |
|---|---|---|
| Pricing and Limits | ||
| Input priceFrom · USD / 1M tokens | Not reported | $0.834Openrouter ↗ · Sep 22, 2026 |
| Output priceFrom · USD / 1M tokens | Not reported | $2.501Openrouter ↗ · Sep 22, 2026 |
| Context windowMaximum documented tokens | 8K | 1,000K |
| Model facts checked | Aug 28, 2026View model evidence → | Sep 2, 2026View model evidence → |
Token prices are the lowest available sourced USD rates; input and output may use different providers. Cost ranking estimates output spend on LiveBench, not a full request bill. Ranking methodology →
Available Benchmarks
Side-by-Side Facts
| Field | granite-embedding-english-r2 | Hy4 preview |
|---|---|---|
| Developer | IBM | Tencent |
| Family | Granite Embedding English R2 | Hy4 |
| Model | granite-embedding-english-r2 | Hy4 preview |
| Version | granite-embedding-english-r2 | Hy4 preview |
| Lifecycle | active | preview |
| Released | 2025-08-15 | 2026-08-28 |
| Knowledge cutoff | Unknown | Unknown |
| Input modalities | Text | Text |
| Output modalities | Embedding | Text |
| Context window | 8K | 1,000K |
| Total parameters | 149M | 770B |
| Active parameters | Unknown | 49B |
| License | apache-2.0 | apache-2.0 |
| Open weights | Yes | Yes |
| API available | Unknown | Yes |
| Self-hostable | Yes | Yes |
| Provider access | Unknown | Openrouter (Standard) |
| Capabilities | embeddings | chat, generation, reasoning, tools |
Granite Embedding English r2 Capabilities
Hy4 preview Capabilities
Related Comparisons
| A | Pair | B | Context |
|---|---|---|---|
| vs |  GPT-6 AstraOpenAI | cross-developer peers | |
Claude Fable 5.1Anthropic | vs | cross-developer peers | |
 Gemini 3.1 ProGoogle DeepMind | vs | cross-developer peers | |
 DeepSeek-V4.1-FlashDeepSeek | vs | cross-developer peers | |
| vs | Grok 4.6xAI | cross-developer peers | |
| vs |  Qwen3.8-MaxQwen | cross-developer peers | |
| vs |  Kimi-K3Moonshot AI | cross-developer peersembedding | |
 MiniMax-M3MiniMax | vs | cross-developer peers | |
| vs |  GLM-5.3Z.ai | cross-developer peers | |
Seed 2.1 ProByteDance Seed | vs | cross-developer peers | |
| vs |  Mistral Large 3Mistral AI | cross-developer peers | |
| vs | cross-developer peers |
Primary Evidence
Sources and Freshness
Questions
Granite Embedding English r2 vs Hy4 preview FAQs
Is Granite Embedding English r2 or Hy4 preview better for coding?+
This comparison does not currently contain a protocol-matched coding benchmark for both Granite Embedding English r2 and Hy4 preview, so Model Markets cannot name a coding leader from pricing, context size, or capability labels alone.
Which is cheaper, Granite Embedding English r2 or Hy4 preview?+
Only Hy4 preview has a directly sourced input price: $0.834 per million tokens. Only Hy4 preview has a directly sourced output price: $2.501 per million tokens.
Which has a larger context window, Granite Embedding English r2 or Hy4 preview?+
Hy4 preview has the larger sourced context window. Granite Embedding English r2 supports 8K and Hy4 preview supports 1,000K.
Which performs better in benchmarks, Granite Embedding English r2 or Hy4 preview?+
There is no overall benchmark winner: At least two independently verified, protocol-matched benchmarks are required for an overall winner.
Can Granite Embedding English r2 or Hy4 preview be self-hosted?+
Both models have the same recorded self-hosting status: supported. Granite Embedding English r2 is open weight; Hy4 preview is open weight.
Can Granite Embedding English r2 and Hy4 preview understand images?+
Granite Embedding English r2 is not documented with image input; Hy4 preview is not documented with image input. This reflects supported input modalities, not vision quality.
Which can generate longer answers, Granite Embedding English r2 or Hy4 preview?+
Neither has a larger sourced maximum output. Granite Embedding English r2 is — and Hy4 preview is —.
Do Granite Embedding English r2 and Hy4 preview support reasoning and tool use?+
Granite Embedding English r2: none of these features are definitively sourced. Hy4 preview: reasoning and tool calling. Feature support does not establish relative quality.
Which is available from more inference providers, Granite Embedding English r2 or Hy4 preview?+
Granite Embedding English r2 has 0 sourced provider routes; Hy4 preview has 1, so Hy4 preview has broader tracked availability.
Which offers better value, Granite Embedding English r2 or Hy4 preview?+
There is no universal value winner. Compare the input and output prices above with the matched benchmark result for your workload: cheaper tokens can be offset by different quality, token usage, latency, or provider availability.