Start free

Models and pricing

Qwen 3.5 397B A17B

A strong general-purpose open model.

Input price (cached) Pricing unavailable.
Input price (non-cached) Pricing unavailable.
Output price Pricing unavailable.
Max context 262,144 tokens

Benchmarks

Benchmark Qwen3.5-397B-A17B gpt-oss-120b Claude Opus 4.5 (closed model)
SWE-bench Verified 76.4 62.4 80.9
Terminal-Bench 2.0 52.5 18.7 59.3
IFEval 91.5 90.2 90.9
AIME 2025 92.3 93.4 98.0
LiveCodeBench v6 83.0 78.4 84.8
MMLU-Pro 87.6 79.7 89.5
GPQA-Diamond 88.4 78.9 87.0
HLE 27.5 18.3 30.8

Bold marks the higher score between the open models; Claude is included as a closed-model reference.

Sources: BenchGecko Qwen3.5 BenchGecko gpt-oss-120b BenchGecko Claude Opus 4.5 Qwen model card OpenAI model card Terminal-Bench BenchLM Claude Opus 4.5

Subscription

Fixed-price subscription

Monthly commitment
5,000 DKK
Included usage value
6,000 DKK
Effective discount
16.7%

Usage above the included amount returns to regular token pricing.

Custom pricing

For larger plans, enterprise terms, or dedicated capacity.

Contact us