Skip to content
Sovyron

Deep Infra

55 modelsProvider docs

As of Oct 4, 2026, Deep Infra lists 55 supported models in the Sovyron catalog, including MiMo-V2.6-Flash, MiMo-V2.6-Pro, DeepSeek V4.1 Flash, Hy4 preview and GLM-5.3-Flash — mimo, deepseek-flash, Hy, glm-flash, qwen and glm families. Its metered rates span $0.0575–$5.7 per 1M tokens on a 3:1 input:output blend, and every price in the table is Deep Infra's own, normalized to USD — open a model to compare it with the cheapest offer across all providers.

Supported models and pricing

55 of 55 models
Deep Infra model prices in USD per 1M tokens, updated Oct 4, 2026
Model1M input1M output1M cache readContextReleased
MiMo-V2.6-Flash$0.14$0.28$0.00281.0MSep 22, 2026
MiMo-V2.6-Pro$0.43$0.87$0.00361.0MSep 22, 2026
DeepSeek V4.1 Flash$0.2$0.6$0.0061.0MSep 10, 2026
Hy4 preview$0.834$2.501$0.0421.0MAug 28, 2026
GLM-5.3-Flash$0.15$0.5$0.031.0MAug 26, 2026
Qwen3.8 Flash$0.113$0.382$0.01411.0MAug 26, 2026
DeepSeek V4 Flash Vision Exp$0.44$1.32$0.0141.0MAug 21, 2026
GLM-5.3$0.9$4$0.21.0MAug 14, 2026
Qwen3.8 27B$0.2$2.5$0.05262kAug 14, 2026
DeepSeek V4 Pro 0813$1.3$2.6$0.11.0MAug 12, 2026
Qwen3.8 2.4T A95B$2$6$0.2262kAug 12, 2026
Qwen3.8 Max$1.65$4.951$0.206256kAug 3, 2026
DeepSeek V4 Flash 0731$0.06$0.18$0.0151.0MJul 31, 2026
Inkling Small$0.45$1.2$0.1524kJul 30, 2026
Kimi K3$2.85$14.25$0.2851.0MJul 16, 2026
Inkling$0.95$4.05$0.16524kJul 15, 2026
Hy3$0.13$0.53$0.033262kJul 6, 2026
GLM-5.2$0.75$2.4$0.141.0MJun 13, 2026
MiniMax-M3$0.28$1.1$0.056524kJun 1, 2026
Qwen3.7 Max$2.5$7.5$0.5256kMay 21, 2026
DeepSeek V4 Flash$0.09$0.18$0.0181.0MApr 24, 2026
DeepSeek V4 Pro$1.3$2.6$0.11.0MApr 24, 2026
Qwen3.6 27B$0.32$3.2—262kApr 22, 2026
Kimi K2.6$0.75$3.5$0.15262kApr 21, 2026
Gemma 4 26B A4B IT$0.07$0.34—262kApr 2, 2026
Gemma 4 31B IT$0.15$0.4—262kApr 2, 2026
Qwen3.6 35B-A3B$0.1$0.95$0.1262kApr 1, 2026
Qwen3.5 27B$0.26$2.6—262kFeb 23, 2026
Qwen3.5 9B$0.1$0.15—262kFeb 23, 2026
Seed 2.0 Code$0.5$3$0.1256kFeb 14, 2026
Seed 2.0 Mini$0.1$0.4$0.02256kFeb 14, 2026
Seed 2.0 Pro$0.5$3$0.1256kFeb 14, 2026
Qwen 3.5 35B A3B$0.14$1$0.05262kFeb 1, 2026
Qwen 3.5 397B A17B$0.45$3$0.22262kFeb 1, 2026
GLM-4.7$0.4$1.75$0.08203kDec 22, 2025
Nemotron 3 Nano 30B A3B$0.05$0.2$0.025262kDec 15, 2025
DeepSeek V3.2$0.26$0.38$0.13164kDec 2, 2025
GLM-4.6$0.5$2$0.1203kSep 30, 2025
Qwen3 Max$1.2$6$0.24256kSep 23, 2025
Qwen3 VL 235B A22B Instruct$0.2$0.88$0.11262kSep 23, 2025
Qwen3-Next 80B-A3B Instruct$0.09$1.1—262kSep 1, 2025
DeepSeek V3.1$0.25$0.95$0.13164kAug 21, 2025
GPT OSS 120B$0.037$0.17—131kAug 5, 2025
GPT OSS 20B$0.03$0.14—131kAug 5, 2025
Qwen3 Coder 480B A35B Instruct Turbo$0.3$1$0.1262kJul 23, 2025
Qwen3 235B A22B Instruct 2507$0.09$0.55—262kJul 21, 2025
DeepSeek R1 0528$0.5$2.15$0.35164kMay 28, 2025
Qwen3 30B A3B$0.12$0.5—41kApr 28, 2025
Llama 4 Scout 17B$0.1$0.3—328kApr 5, 2025
Qwen3 32B$0.08$0.28—41kApr 1, 2025
Gemma 3 12B IT$0.05$0.15—131kMar 12, 2025
Gemma 3 27B IT$0.08$0.16—131kMar 12, 2025
Gemma 3 4B IT$0.05$0.1—131kMar 12, 2025
DeepSeek-V3$0.32$0.89—164kDec 26, 2024
Llama 3.3 70B Turbo$0.1$0.32—131kDec 6, 2024