Pricing · per 1M tokens
| Cached input | $0.130/Mtok (10% of input — prompt caching) |
|---|---|
| Blended avg cost* | $2.50/Mtok |
Overview
Alibaba's flagship agent model — reasoning-first with a 1M-token context and native extended thinking, built for long-horizon autonomy (up to ~35 hours / 1,000+ tool calls) across coding and workflow automation. Text-only. $1.25/$3.75 per 1M tokens via Together.
Deploy this open model on rented GPUs
Open weights mean you can self-host instead of paying per-token API prices. These platforms let you serve it on demand — often cheaper at scale.
Partner links — we may earn a commission if you sign up, at no cost to you. We only list platforms we'd recommend regardless.
Capabilities
Benchmark performance
- Artificial Analysis Intelligence Index: 46
- Strongest at MATH 500 — 76%, #19 of 57
Source: Together AI, Qwen model card · Updated Apr 1, 2026 · See full rankings →
Specifications
| Provider | Together |
|---|---|
| Context window | 1M tokens |
| Modality | text |
| Parameters | Proprietary |
| Open source | Yes — open weights available |
| Released | May 20, 2026 |
| Status | Current |
| Last updated | Jun 25, 2026 |
| Tags | caching mid-tier open-weights |
Cost calculator
At a glance
Embed this price
A live, auto-updating badge for your README or docs:
Price history
Last updated: Jul 10, 2026 · price links to the official provider pricing page (source above)
No price changes detected — this model's pricing has been stable since we began tracking it.