Skip to content
Sovyron

Clarifai

12 modelsProvider docs

As of Nov 22, 2026, Clarifai lists 12 supported models in the Sovyron catalog, including Kimi K2.6, MiniMax-M2.5 High Throughput, Ministral 3 14B Reasoning 2512, Trinity Mini and Ministral 3 3B Reasoning 2512 across the kimi, minimax-m, ministral, trinity-mini, deepseek and gpt-oss families. The cheapest rate in the table is Trinity Mini at $0.15 per 1M output tokens, the priciest Kimi K2.6 at $4. On a 3:1 input:output blend the metered rates span $0.0713–$2.3 per 1M tokens, and every price is Clarifai'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

12 of 12 models
Clarifai model prices in USD per 1M tokens, updated Nov 22, 2026
Model1M input1M output1M cache readContextReleased
Kimi K2.6$0.95$4—262kApr 20, 2026
MiniMax-M2.5 High Throughput$0.3$1.2—205kFeb 12, 2026
Ministral 3 14B Reasoning 2512$2.5$1.7—262kDec 1, 2025
Trinity Mini$0.045$0.15—131kDec 1, 2025
Ministral 3 3B Reasoning 2512$1.039$0.5483—262kDec 1, 2025
DeepSeek OCR$0.2$0.7—8kOct 20, 2025
GPT OSS 120B High Throughput$0.09$0.36—131kAug 5, 2025
GPT OSS 20B$0.045$0.18—131kAug 5, 2025
Qwen3 30B A3B Thinking 2507$0.36$1.3—262kJul 31, 2025
Qwen3-Coder 30B-A3B Instruct$0.1146$0.7481—262kJul 31, 2025
Qwen3 30B-A3B Instruct 2507$0.3$0.5—262kJul 28, 2025
MM Poly 8B$0.658$1.11—33kJun 1, 2025