Granite 3.3 8B (Non-reasoning) API Pricing
IBM · released 2025-04-16
Pricing
< 0.01¢ / 1K
0.025¢ / 1K
< 0.01¢ / 1K
What it actually costs
| Workload | Tokens | Cost |
|---|---|---|
| Short chat reply | 500 in / 300 out | 0.009¢ |
| RAG query | 4,000 in / 500 out | 0.0245¢ |
| Long document summary | 50,000 in / 1,000 out | 0.175¢ |
| Code review of a 2k-line file | 30,000 in / 2,000 out | 0.14¢ |
| 1,000 chat replies/day for 30 days | 30,000 × (500 in / 300 out) | $2.70 |
Cost = (input tokens ÷ 1,000,000 × $0.03) + (output tokens ÷ 1,000,000 × $0.25).
Benchmarks
#514 of 533
#222 of 249
Similar intelligence, lower price
| Model | Intelligence | Blended $/1M |
|---|---|---|
| Llama 3.1 Instruct 8B | 6.9 | $0.028 |
| Sarvam 30B (high) | 6.6 | $0.047 |
| Nova Micro | 5.9 | $0.061 |
| Granite 4.1 8B | 6.6 | $0.063 |
| NVIDIA Nemotron Nano 9B V2 (Reasoning) | 7.4 | $0.07 |
Leaderboard neighbours
| Model | Intelligence | Blended $/1M |
|---|---|---|
| Molmo2-8B | 5.0 | — |
| Qwen Chat 14B | 5.0 | — |
| Gemma 3 27B Instruct | 4.9 | — |
| Granite 3.3 8B (Non-reasoning) | 4.9 | $0.085 |
| LFM2 8B A1B | 4.9 | — |
| Qwen3 1.7B (Non-reasoning) | 4.9 | — |
| Apertus 8B Instruct | 4.8 | $0.125 |
More from IBM
| Model | Intelligence | Blended $/1M |
|---|---|---|
| Granite 4.2 30B | 14.8 | $0.282 |
| Granite 4.2 8B | 11.1 | $0.107 |
| Granite 4.2 3B | 9.1 | $0.052 |
| Granite 4.1 30B | 7.4 | — |
| Granite 4.1 8B | 6.6 | $0.063 |
| Granite 4.0 H Small | 6.0 | $0.107 |
| Granite 4.1 3B | 5.9 | — |
| Granite 4.0 H 1B | 5.2 | — |
Count tokens & estimate cost for Granite 3.3 8B (Non-reasoning) See Granite 3.3 8B (Non-reasoning) on the leaderboard
Source: Artificial Analysis · last synced 2026-09-22
FAQ
Who develops Granite 3.3 8B (Non-reasoning)?
Granite 3.3 8B (Non-reasoning) is developed by IBM, released 2025-04-16.
How much does Granite 3.3 8B (Non-reasoning) cost per million tokens?
Granite 3.3 8B (Non-reasoning) costs $0.03 per 1M input tokens and $0.25 per 1M output tokens ($0.085 blended), per Artificial Analysis's official pricing data.
How does Granite 3.3 8B (Non-reasoning) rank on benchmarks?
Granite 3.3 8B (Non-reasoning) scores 4.9 on the Artificial Analysis Intelligence Index, ranking #514 of 533 models we track.
Is there a cheaper model with similar intelligence to Granite 3.3 8B (Non-reasoning)?
Yes — Llama 3.1 Instruct 8B scores similar intelligence (6.9) at $0.028/1M blended, versus $0.085/1M for Granite 3.3 8B (Non-reasoning).
Where does this data come from?
Pricing and benchmark data for Granite 3.3 8B (Non-reasoning) comes from Artificial Analysis (artificialanalysis.ai), synced daily. Last synced 2026-09-22.