text-embedding-004 vs Granite Embedding 278M Multilingual
Side-by-side API pricing comparison · Google vs IBM
🏆
text-embedding-004 is 324% cheaper on blended cost ($0.025 vs $0.106/Mtok)
text-embedding-004
by Google
Current embeddingInput
$0.025/Mtok
Output
$0.025/Mtok
✓ Cheaper
| Blended avg | $0.025/Mtok |
|---|---|
| Context | 2K tokens |
| Modality | text |
| Parameters | Proprietary |
| Released | Oct 1, 2024 |
Granite Embedding 278M Multilingual
by IBM
Current embedding Open weightsInput
$0.106/Mtok
Output
$0.106/Mtok
| Blended avg | $0.106/Mtok |
|---|---|
| Context | — tokens |
| Modality | text |
| Parameters | 278M |
| Released | Jun 1, 2025 |
Cost at scale — 1M tokens (50/50 input/output)
| Volume | text-embedding-004 | Granite Embedding 278M Multilingual | Savings |
|---|---|---|---|
| 1M tokens | $0.03 | $0.11 | $0.08 (75.5%) |
| 10M tokens | $0.25 | $1.06 | $0.81 (76.4%) |
| 100M tokens | $2.5 | $10.6 | $8.1 (76.4%) |
| 1000M tokens | $25 | $106 | $81 (76.4%) |
Summary
text-embedding-004 by Google costs $0.025/Mtok input and $0.025/Mtok output, with a 2K-token context window. It supports text input.
Granite Embedding 278M Multilingual by IBM costs $0.106/Mtok input and $0.106/Mtok output, with a —-token context window. It supports text input.
On a blended cost basis, text-embedding-004 is 324% cheaper than Granite Embedding 278M Multilingual. It also has a larger context window.
Note: Pricing is per million tokens. Actual costs vary with usage patterns, prompt caching, and batch discounts. Always verify against official provider pricing pages.