Today's price · per 1M tokens
Input
$0.600
per 1M tokens
Output
$3.60
per 1M tokens
Blended
$2.10
avg of input & output $/1M
Cached input
$0.350
58% of input — prompt caching
Overview
Large MoE Qwen model (397B total, 17B active) on Together. $0.60/$3.60 per 1M tokens. Retired from Together serverless 2026-06-29.
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
struck through = not supportedBenchmark performance
accuracy % · higher is betterWe hold no per-benchmark accuracy scores for this model yet, so it has no accuracy average. That is a gap in our coverage, not a sign the model is untested — independent evaluators often publish a composite index for a new model long before releasing its per-benchmark numbers. The percentile above is its standing across the independent composites below.
- AA Intelligence Index: 33.7 (Artificial Analysis composite across reasoning, knowledge and coding evals)
- AA Agentic Index: 19.8 (Tool use, planning, autonomy)
- AA-Omniscience Index: -29.8 (−100–100)
- Ranks #89 of 133 comparably-measured models by percentile score, across 3 independent measurements
- Ranks #92 of 133 comparably-tested models by normalized performance per dollar
Source: Artificial Analysis · updated Jun 29, 2026 · See full rankings →
Specifications
- Provider
- Together
- Context window
- 128K tokens
- Modality
- text
- Parameters
- 397B (A17B)
- Open source
- Yes — open weights available
- Released
- Jan 1, 2026
- Status
- Retired ended Jun 29, 2026
- Last updated
- Jul 31, 2026
- Tags
Availability verified: Not re-verified. We have no recent evidence that Together still lists this model — treat availability as unconfirmed.