Granite 4.0 Micro Pricing
FastIBM · 131K tokens context
Granite 4.0 Micro from IBM costs $0.017 per 1 million input tokens and $0.112 per 1 million output tokens as of July 2026 (live OpenRouter data). The model supports a 131,000-token context window (approximately 98,250 words) with a 131K-token maximum output. A typical 1,000-token request costs $0.0000 in input charges; a 10,000-token request costs $0.0002.
| Input price | $0.017 / 1M tokens |
|---|---|
| Output price | $0.112 / 1M tokens |
| Output / input ratio | 6.6× |
| Context window | 131,000 tokens (~98,250 words) |
| Maximum output | 131,000 tokens |
| Cost per 1K tokens (input) | $0.0000 |
| Tier | Fast |
| Last verified |
Granite-4.0-H-Micro is a 3B parameter from the Granite 4 family of models. These models are the latest in a series of models released by IBM.
Input Price
$0.017
per 1 million tokens
Output Price
$0.112
per 1 million tokens
Context Window
131K tokens
max 131K output
Cost Examples
| Request Type | Tokens | Input Cost | Output Cost |
|---|---|---|---|
| 1,000 word article | 1,333 | $0.0000227 | $0.0000448 |
| 10-page document (2,500 words) | 3,333 | $0.0000567 | $0.000112 |
| 1,000 lines of code | 5,000 | $0.000085 | $0.000168 |
| 100K token document | 100,000 | $0.0017 | $0.00336 |
Output cost estimated at 30% of input token count. Use the calculator for exact figures.
Strengths
- ✓Extremely cheap at $0.017/1M input tokens
- ✓Low latency for high-throughput workloads
- ✓Cost-effective at scale
Limitations
- –Less capable than flagship models on complex reasoning
- –Quality and availability can vary by hosting provider
Best Use Cases
Calculate Granite 4.0 Micro Costs
Use the TokenRate calculator to convert any budget, token count, or text into exact Granite 4.0 Micro costs — and compare across all models.
Open Calculator →Granite 4.0 Micro — FAQ
Related Models
Related Guides