stepping stone AG
15 modelsProvider docs
As of Nov 22, 2026, stepping stone AG lists 15 supported models in the Sovyron catalog, including Apertus v1.5 8B, GLM-5.3-Flash, Qwen3.8 27B, DeepSeek V4 Flash 0731 and Gemma 4 31B IT across the apertus, glm-flash, qwen, deepseek-flash, gemma and nemotron-super families. The cheapest rate in the table is LightOnOCR 2 1B at $0.0714 per 1M output tokens, the priciest MiniMax-M2.5 at $11.543. On a 3:1 input:output blend the metered rates span $0.0357–$4.6172 per 1M tokens, and every price is stepping stone AG's own, normalized to USD. Offer mix: metered per-token rates only, with no free-tier or subscription offers in the catalog. Open a model to compare it with the cheapest offer across all providers.
Supported models and pricing
15 of 15 models
| Model | 1M input | 1M output | 1M cache read | Context | Released |
|---|---|---|---|---|---|
| Apertus v1.5 8B | $0.0238 | $0.119 | $0.0036 | 131k | Oct 15, 2026 |
| GLM-5.3-Flash | $0.357 | $1.785 | $0.0536 | 262k | Aug 26, 2026 |
| Qwen3.8 27B | $0.2975 | $1.785 | $0.0607 | 262k | Aug 14, 2026 |
| DeepSeek V4 Flash 0731 | $0.5355 | $2.142 | $0.0803 | 524k | Jul 31, 2026 |
| Gemma 4 31B IT | $0.2975 | $1.19 | $0.0446 | 164k | Apr 2, 2026 |
| Nemotron 3 Super 120B A12B | $2.38 | $5.95 | $0.357 | 131k | Mar 11, 2026 |
| Qwen3.5 35B-A3B FP8 | $0.2023 | $1.19 | $0.0303 | 131k | Feb 23, 2026 |
| MiniMax-M2.5 | $2.3086 | $11.543 | $0.3463 | 197k | Feb 12, 2026 |
| Qwen3 Coder Next | $0.4046 | $2.023 | $0.0446 | 262k | Feb 3, 2026 |
| LightOnOCR 2 1B | $0.0238 | $0.0714 | $0.0036 | 16k | Jan 16, 2026 |
| olmOCR 2 7B | $0.0714 | $0.3451 | $0.0107 | 8k | Oct 22, 2025 |
| MinerU2.5 2509 1.2B | $0.0238 | $0.0714 | $0.0036 | 16k | Sep 17, 2025 |
| GPT OSS 120B | $0.476 | $1.904 | $0.0714 | 131k | Aug 5, 2025 |
| BGE Reranker V2 M3 | $0.119 | free | — | 8k | Mar 15, 2024 |
| BGE M3 | $0.119 | free | — | 8k | Jan 30, 2024 |