Cost-efficient reasoning with selectable effort.
Pricing
Launch price (from Jan 31, 2025)
$1.10 in / $4.40 out per 1M tokens
Current price (since Jan 31, 2025)
$1.10 in / $4.40 out per 1M tokens
Cache read: $0.550/M
| Tier | Effective | In $/M | Out $/M | Cache $/M | Per image | Per second | Source |
|---|---|---|---|---|---|---|---|
| Standard | Jan 31, 2025 – now | $1.10 | $4.40 | $0.550 | - | - | - |
| Batch | Jan 31, 2025 – now | $0.550 | $2.20 | - | - | - | - |
Specifications
| Model type | Text LLM |
|---|---|
| Architecture | Dense |
| Parameters | Not disclosed |
| Context window | 200K tokens |
| Max output | 100K tokens |
| Knowledge cutoff | Oct 1, 2023 |
| License | Proprietary |
| Modalities | Text input Text output |
| Tags | Coding Reasoning Small LM |
| End of life | Not disclosed |
| Last verified | Aug 20, 2026 |
Benchmarks
| Benchmark | Score | Src |
|---|---|---|
| LiveCodeBench | 68.2% | - |
| MATH | 96.9% | official |