MiniMax M2.5 vs Granite Embedding 30m English
At a Glance
| Compare |  MiniMax M2.5MiniMax | |
|---|---|---|
| Pricing and Limits | ||
| Input priceFrom · USD / 1M tokens | $0.27Openrouter ↗ · Aug 28, 2026 | Not reported |
| Output priceFrom · USD / 1M tokens | $1.08Openrouter ↗ · Aug 28, 2026 | Not reported |
| Context windowMaximum documented tokens | 197K | 1K |
| Model facts checked | Aug 28, 2026View model evidence → | Aug 28, 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 | MiniMax-M2.5 | granite-embedding-30m-english |
|---|---|---|
| Developer | MiniMax | IBM |
| Family | Minimax M2 5 | Granite Embedding 30m English |
| Model | MiniMax-M2.5 | granite-embedding-30m-english |
| Version | MiniMax-M2.5 | granite-embedding-30m-english |
| Lifecycle | active | active |
| Released | 2026-02-12 | 2025-08-29 |
| Knowledge cutoff | Unknown | Unknown |
| Input modalities | Text | Text |
| Output modalities | Text | Embedding |
| Context window | 197K | 1K |
| Total parameters | 228.7B | 30.3M |
| Active parameters | Unknown | Unknown |
| License | other | apache-2.0 |
| Open weights | Yes | Yes |
| API available | Yes | Yes |
| Self-hostable | Yes | Yes |
| Provider access | Hugging Face (Standard), Openrouter (Standard) | Hugging Face (Standard) |
| Capabilities | chat, generation, tools | embeddings |
MiniMax M2.5 Capabilities
Granite Embedding 30m English Capabilities
Related Comparisons
| A | Pair | B | Context |
|---|---|---|---|
MiniMax-M2.5MiniMax | vs |  GPT-6 AstraOpenAI | cross-developer peerstext |
MiniMax-M2.5MiniMax | vs | Claude Fable 5.1Anthropic | cross-developer peerstext |
MiniMax-M2.5MiniMax | vs |  Gemini 3.1 ProGoogle DeepMind | cross-developer peerstext |
MiniMax-M2.5MiniMax | vs |  DeepSeek-V4.1-FlashDeepSeek | cross-developer peerstext |
MiniMax-M2.5MiniMax | vs | Grok 4.6xAI | cross-developer peerstext |
MiniMax-M2.5MiniMax | vs |  Qwen3.8-MaxQwen | cross-developer peerstext |
MiniMax-M2.5MiniMax | vs |  Kimi-K3Moonshot AI | cross-developer peerstext |
MiniMax-M2.5MiniMax | vs | MiniMax-M3MiniMax | family variantstext |
MiniMax-M2.5MiniMax | vs |  GLM-5.3Z.ai | cross-developer peerstext |
MiniMax-M2.5MiniMax | vs |  Hy4 previewTencent | cross-developer peerstext |
MiniMax-M2.5MiniMax | vs | Seed 2.1 ProByteDance Seed | cross-developer peerstext |
MiniMax-M2.5MiniMax | vs |  Mistral Large 3Mistral AI | cross-developer peerstext |
Primary Evidence
Sources and Freshness
Questions
MiniMax M2.5 vs Granite Embedding 30m English FAQs
Is MiniMax M2.5 or Granite Embedding 30m English better for coding?+
This comparison does not currently contain a protocol-matched coding benchmark for both MiniMax M2.5 and Granite Embedding 30m English, so Model Markets cannot name a coding leader from pricing, context size, or capability labels alone.
Which is cheaper, MiniMax M2.5 or Granite Embedding 30m English?+
Only MiniMax M2.5 has a directly sourced input price: $0.27 per million tokens. Only MiniMax M2.5 has a directly sourced output price: $1.08 per million tokens.
Which has a larger context window, MiniMax M2.5 or Granite Embedding 30m English?+
MiniMax M2.5 has the larger sourced context window. MiniMax M2.5 supports 197K and Granite Embedding 30m English supports 1K.
Which performs better in benchmarks, MiniMax M2.5 or Granite Embedding 30m English?+
There is no overall benchmark winner: At least two independently verified, protocol-matched benchmarks are required for an overall winner.
Can MiniMax M2.5 or Granite Embedding 30m English be self-hosted?+
Both models have the same recorded self-hosting status: supported. MiniMax M2.5 is open weight; Granite Embedding 30m English is open weight.
Can MiniMax M2.5 and Granite Embedding 30m English understand images?+
MiniMax M2.5 is not documented with image input; Granite Embedding 30m English is not documented with image input. This reflects supported input modalities, not vision quality.
Which can generate longer answers, MiniMax M2.5 or Granite Embedding 30m English?+
Neither has a larger sourced maximum output. MiniMax M2.5 is — and Granite Embedding 30m English is —.
Do MiniMax M2.5 and Granite Embedding 30m English support reasoning and tool use?+
MiniMax M2.5: tool calling. Granite Embedding 30m English: none of these features are definitively sourced. Feature support does not establish relative quality.
Which is available from more inference providers, MiniMax M2.5 or Granite Embedding 30m English?+
MiniMax M2.5 has 2 sourced provider routes; Granite Embedding 30m English has 1, so MiniMax M2.5 has broader tracked availability.
Which offers better value, MiniMax M2.5 or Granite Embedding 30m English?+
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.