Arcee
7 modelsProvider docs
As of Oct 4, 2026, Arcee lists 7 supported models in the Sovyron catalog, including DeepSeek V4 Pro 0813, DeepSeek V4 Flash, Inkling Small, Kimi K3 and GLM-5.2 — deepseek-thinking, deepseek-flash, ling, kimi-k3, glm and trinity families. Its metered rates span $0.175–$6 per 1M tokens on a 3:1 input:output blend, and every price in the table is Arcee's own, normalized to USD — open a model to compare it with the cheapest offer across all providers.
Supported models and pricing
7 of 7 models
| Model | 1M input | 1M output | 1M cache read | Context | Released |
|---|---|---|---|---|---|
| DeepSeek V4 Pro 0813 | $1.32 | $3.96 | $0.044 | 1.0M | Aug 12, 2026 |
| DeepSeek V4 Flash | $0.14 | $0.28 | $0.028 | 1.0M | Jul 31, 2026 |
| Inkling Small | $0.5 | $1.2 | $0.1 | 262k | Jul 30, 2026 |
| Kimi K3 | $3 | $15 | $0.3 | 1.0M | Jul 16, 2026 |
| GLM-5.2 | $1.4 | $4.4 | $0.26 | 262k | Jun 13, 2026 |
| DeepSeek V4 Pro | $1.74 | $3.48 | $0.2 | 512k | Apr 24, 2026 |
| Trinity Large Thinking | $0.25 | $0.8 | $0.06 | 262k | Apr 1, 2026 |