Pricing · per 1M tokens
Input
$0.600
per million tokens
Output
$3.60
per million tokens
| Cached input | $0.350/Mtok (58% of input — prompt caching) |
|---|---|
| Blended avg cost* | $2.10/Mtok |
Overview
Large MoE Qwen model (397B total, 17B active) on Together. $0.60/$3.60 per 1M tokens.
Specifications
| Provider | Together |
|---|---|
| Context window | 128K tokens |
| Modality | text |
| Parameters | 397B (A17B) |
| Open source | Yes — open weights available |
| Released | Jan 1, 2026 |
| Status | Current |
| Last updated | Jun 24, 2026 |
| Tags | caching mid-tier open-weights moe |