Skip to content
Sovyron

LLM Gateway

263 modelsProvider docs

As of Oct 4, 2026, LLM Gateway lists 263 supported models in the Sovyron catalog, including GPT-6.1 Sol, Claude Sonnet 5.5, Claude Opus 5.5, GPT-6 Luna and GPT-6 Sol — gpt-sol, claude-sonnet, claude-opus, gpt-luna, mimo and grok families. Its metered rates span $0.035–$67.5 per 1M tokens on a 3:1 input:output blend, and every price in the table is LLM Gateway's own, normalized to USD — open a model to compare it with the cheapest offer across all providers. Offer mix: 1 free-tier offer.

Supported models and pricing

263 of 263 models
LLM Gateway model prices in USD per 1M tokens, updated Oct 4, 2026
Model1M input1M output1M cache readContextReleasedTags
GPT-6.1 Sol$2$10$0.11.1MSep 29, 2026
Claude Sonnet 5.5$2$10$0.21.0MSep 28, 2026
Claude Opus 5.5$4$20$0.21.0MSep 22, 2026
GPT-6 Luna$0.1$0.5$0.011.1MSep 22, 2026
GPT-6 Sol$2$10$0.21.1MSep 22, 2026
MiMo-V2.6-Flash$0.14$0.28$0.00281.0MSep 22, 2026
MiMo-V2.6-Pro$0.435$0.87$0.00361.0MSep 22, 2026
Grok 4.7$2$6$0.5524kSep 21, 2026
Atria Dawn Preview (Atria)freefree—262kSep 12, 2026free
Fugu Max$2$6$0.251.0MSep 11, 2026
Fugu Ultra v2.0$5$30$0.51.0MSep 11, 2026
DeepSeek V4.1 Flash$0.15$0.6$0.0031.1MSep 10, 2026
DeepSeek V4.1 Flash (Baidu)$0.3$1.2$0.0061.0MSep 10, 2026
DeepSeek V4.1 Flash (Consensus Protocol)$0.15$0.55$0.0051.0MSep 10, 2026
DeepSeek V4.1 Flash (Runware)$0.15$0.6$0.011.0MSep 10, 2026
Ling 3.0 Flash VL$0.06$0.18$0.012131kSep 10, 2026
GPT-6 Astra$10$50$11.1MSep 4, 2026
GPT-6 Astra (AWS Mantle)$10$50$11.1MSep 4, 2026
Gemini 3.8 Flash$0.75$3.75$0.0751.0MSep 2, 2026
Muse Spark 1.3$1.25$4.25$0.151.0MSep 2, 2026
Muse Spark 1.3 Contributor (Meta Contributor)$0.1$0.2$0.0021.0MSep 2, 2026
Qwen3.8 27B (Consensus Protocol)$0.08$0.35$0.05262kSep 2, 2026
Claude Fable 5.1$10$50$0.251.0MSep 1, 2026
Granite 4.2 8B$0.06$0.25$0.015131kSep 1, 2026
Hy4 preview$0.834$2.501$0.0421.0MAug 28, 2026
GLM-5.3 Flash (Consensus Protocol)$0.1$0.25$0.021.0MAug 26, 2026
GLM-5.3 Flash (Gonka24)$0.15$0.3$0.035200kAug 26, 2026
GLM-5.3 Flash (Runware)$0.15$0.5$0.031.0MAug 26, 2026
GLM-5.3-Flash$0.088$0.25$0.0251.0MAug 26, 2026
Qwen3.8 Flash$0.15$0.47$0.016984kAug 26, 2026
GLM-5.3$0.9$3$0.151.0MAug 14, 2026
GLM-5.3 (Baidu)$1.4$4.4$0.261.0MAug 14, 2026
GLM-5.3 (Runware)$1.2$4$0.21.0MAug 14, 2026
Qwen3.8 27B$0.42$3$0.0851.0MAug 14, 2026
Gemini 3.7 Flash$0.75$3.75$0.0751.0MAug 13, 2026
Grok 4.6$2$6$0.5500kAug 12, 2026
Qwen3.8 2.4T A95B$2$6$0.2262kAug 12, 2026
Muse Glimmer 30B$0.3$1.2$0.04131kAug 10, 2026
Muse Spark 1.2 Contributor (Meta Contributor)$0.1$0.2$0.0021.0MAug 6, 2026
Muse Spark 1.2$1.25$4.25$0.151.0MAug 5, 2026
Qwen3.8 Max$2$6$0.25984kAug 3, 2026
Ling 3.0 Flash$0.06$0.18$0.012262kAug 2, 2026
Claude Opus 5$5$25$0.51.0MJul 24, 2026
Gemini 3.5 Flash Lite$0.3$2.5$0.031.0MJul 21, 2026
Gemini 3.6 Flash$0.75$3.75$0.0751.0MJul 21, 2026
Kimi K3$3$15$0.31.0MJul 16, 2026
Kimi K3 (CanopyWave)$3$15$0.31.0MJul 16, 2026
Kimi K3 (Runpod)$3$15$0.31.0MJul 16, 2026
Kimi K3 (Runware)$3$15$0.31.0MJul 16, 2026
Kimi K3 Fast$4.5$22.5$0.451.0MJul 16, 2026
Inkling$0.95$4.05$0.16524kJul 15, 2026
Qwen3.7 Flash$0.03$0.13$0.006984kJul 15, 2026
GPT-5.6 Luna$0.2$1.2$0.021.1MJul 9, 2026
GPT-5.6 Luna (AWS Mantle)$0.22$1.32$0.022922kJul 9, 2026
GPT-5.6 Sol$4$20$0.41.1MJul 9, 2026
GPT-5.6 Sol (AWS Mantle)$4.4$22$0.44922kJul 9, 2026
GPT-5.6 Terra$2$12$0.21.1MJul 9, 2026
GPT-5.6 Terra (AWS Mantle)$2.2$13.2$0.22922kJul 9, 2026
Grok 4.5$2$6$0.3500kJul 8, 2026
Hy3$0.132$0.528$0.033262kJul 6, 2026
Claude Sonnet 5$2$10$0.21.0MJun 30, 2026
Fugu Ultra$5$30$0.51.0MJun 15, 2026
GLM-5.2$0.88$2.55$0.161.0MJun 13, 2026
GLM-5.2 (Baidu)$1.4$4.4$0.261.0MJun 13, 2026
GLM-5.2 (ByteDance)$1.4$4.4$0.261.0MJun 13, 2026
GLM-5.2 (CanopyWave)$1.4$4.4$0.26200kJun 13, 2026
GLM-5.2 (EmberCloud)$1.26$3.96$0.234203kJun 13, 2026
GLM-5.2 (Runware)$0.8$2.55$0.161.0MJun 13, 2026
GLM-5.2 Turbo$2.2$6.5$0.451.0MJun 13, 2026
Kimi K2.7 Code$0.95$4$0.19262kJun 12, 2026
Kimi K2.7 Code Highspeed$1.9$8$0.38262kJun 12, 2026
Claude Fable 5$10$50$11.0MJun 9, 2026
Qwen3.7 Plus$0.4$1.6$0.08984kJun 2, 2026
MiniMax-M3$0.3$1.2$0.061.0MJun 1, 2026
Nemotron 3 Ultra 550B$0.5$2.2$0.1262kJun 1, 2026
Step 3.7 Flash$0.2$1.15$0.04262kMay 29, 2026
Claude Opus 4.8$5$25$0.51.0MMay 28, 2026
Hy-MT2 Plus$0.074$0.295—8kMay 21, 2026
Qwen3.7 Max$1.25$3.75$0.251.0MMay 21, 2026
Grok Build 0.1$1$2$0.2256kMay 20, 2026
Gemini 3.5 Flash$1.5$9$0.151.0MMay 19, 2026
Gemini 3.1 Flash Lite$0.25$1.5$0.0251.0MMay 7, 2026
Mistral Medium 3.5$1.5$7.5—262kMay 1, 2026
Grok 4.3$1.25$2.5$0.21.0MApr 30, 2026
Seed 2.0 Lite (260428) (ByteDance)$0.25$2$0.05262kApr 28, 2026
Seed 2.0 Mini (260428) (ByteDance)$0.1$0.4$0.02262kApr 28, 2026
Qwen3.6 Flash$0.25$1.5$0.05984kApr 27, 2026
DeepSeek V4 Flash$0.08$0.18$0.0161.0MApr 24, 2026
DeepSeek V4 Flash (Baidu)$0.44$1.32$0.0141.0MApr 24, 2026
DeepSeek V4 Flash (ByteDance)$0.44$1.32$0.0141.0MApr 24, 2026
DeepSeek V4 Flash (CanopyWave)$0.14$0.28$0.031.0MApr 24, 2026
DeepSeek V4 Flash (Consensus Protocol)$0.1$0.2$0.005524kApr 24, 2026
DeepSeek V4 Flash (Gonka24)$0.065$0.116$0.012390kApr 24, 2026
DeepSeek V4 Flash (RanoAI)$0.14$0.28$0.0281.0MApr 24, 2026
DeepSeek V4 Flash (Runware)$0.076$0.153$0.0141.0MApr 24, 2026
DeepSeek V4 Pro$0.435$0.87$0.00361.1MApr 24, 2026
DeepSeek V4 Pro (Baidu)$1.32$3.96$0.0421.0MApr 24, 2026
DeepSeek V4 Pro (ByteDance)$1.32$3.96$0.0441.0MApr 24, 2026
DeepSeek V4 Pro (CanopyWave)$1.74$3.48$0.011.0MApr 24, 2026
DeepSeek V4 Pro (Runware)$0.961$1.922$0.0791.0MApr 24, 2026
GPT-5.5$5$30$0.51.1MApr 23, 2026
GPT-5.5 Pro$30$180—1.1MApr 23, 2026
MiMo-V2.5$0.14$0.28$0.00281.0MApr 22, 2026
MiMo-V2.5-Pro$0.435$0.87$0.00361.0MApr 22, 2026
Kimi K2.6$0.8$3.4$0.16262kApr 21, 2026
Kimi K2.6 (Baidu)$0.95$4$0.16262kApr 21, 2026
Kimi K2.6 (CanopyWave)$0.95$4$0.16262kApr 21, 2026
Kimi K2.6 (Runware)$0.6$3.05$0.13262kApr 21, 2026
Qwen3.6 Max Preview$1.3$7.8$0.13262kApr 20, 2026
Qwen3.6 35B-A3B$0.248$1.485—262kApr 17, 2026
Claude Opus 4.7$5$25$0.51.0MApr 16, 2026
Muse Spark 1.1$1.25$4.25$0.151.0MApr 8, 2026
GLM-5.1$1.38$4.4$0.26205kApr 7, 2026
GLM-5.1 (Baidu)$1.4$4.4$0.26203kApr 7, 2026
GLM-5.1 (EmberCloud)$0.931$2.93$0.173203kApr 7, 2026
Gemma 4 26B A4B IT$0.07$0.34—262kApr 2, 2026
Gemma 4 31B IT$0.14$0.4—262kApr 2, 2026
Gemma 4 31B IT (Consensus Protocol)$0.1$0.25$0.01262kApr 2, 2026
Gemma 4 31B IT (Runware)$0.102$0.297$0.012262kApr 2, 2026
Gemma 4 31B IT (SCX.ai (Turbo))$0.3$0.91—131kApr 2, 2026
Qwen3.6 Plus$0.5$3$0.05984kApr 2, 2026
GLM-5V-Turbo$1.2$4$0.24200kApr 1, 2026
Seed 2.0 Code Preview (260328) (ByteDance)$0.5$3$0.1262kMar 28, 2026
Seed 2.0 Pro (260328) (ByteDance)$0.5$3$0.1262kMar 28, 2026
MiniMax M2.7 (Gonka24)$0.08$0.32$0.017205kMar 18, 2026
MiniMax M2.7 (SCX.ai (Turbo))$0.48$1.79$0.05197kMar 18, 2026
MiniMax-M2.7$0.3$1.2$0.06205kMar 18, 2026
MiniMax-M2.7-highspeed$0.6$2.4$0.06205kMar 18, 2026
GPT-5.4 mini$0.75$4.5$0.075400kMar 17, 2026
GPT-5.4 nano$0.2$1.25$0.02400kMar 17, 2026
GLM-5-Turbo$1.2$4$0.24200kMar 16, 2026
Mistral Small 4$0.15$0.6—262kMar 16, 2026
Grok 4.20 (Non-Reasoning)$1.25$2.5$0.22.0MMar 9, 2026
Grok 4.20 (Reasoning)$1.25$2.5$0.22.0MMar 9, 2026
GPT-5.4$2.5$15$0.251.1MMar 5, 2026
GPT-5.4 Pro$30$180—1.1MMar 5, 2026
Gemini Pro Latest$2$12$0.21.0MFeb 27, 2026
Qwen3.5 122B-A10B$0.4$3.2—262kFeb 23, 2026
Qwen3.5 27B$0.3$2.4—262kFeb 23, 2026
Qwen3.5 35B-A3B$0.25$2—262kFeb 23, 2026
Qwen3.5 9B$0.1$0.15—262kFeb 23, 2026
Gemini 3.1 Pro (Quartz)$2$12$0.21.0MFeb 19, 2026
Gemini 3.1 Pro Preview$2$12$0.21.0MFeb 19, 2026
Claude Sonnet 4.6$3$15$0.31.0MFeb 17, 2026
Qwen3.5 397B-A17B$0.6$3.6—262kFeb 16, 2026
MiniMax-M2.5-highspeed$0.6$2.4$0.03205kFeb 13, 2026
GLM-5$0.573$2.58—203kFeb 12, 2026
GLM-5 (Baidu)$1$3.2$0.2203kFeb 12, 2026
GLM-5 (EmberCloud)$0.72$2.3$0.144203kFeb 12, 2026
MiniMax-M2.5$0.3$1.2$0.03205kFeb 12, 2026
Claude Opus 4.6$5$25$0.51.0MFeb 5, 2026
GPT-5.3 Codex$1.75$14$0.175400kFeb 5, 2026
Qwen3 Coder Next (EmberCloud)$0.108$0.675$0.06262kFeb 3, 2026
GLM-4.7 Flash (EmberCloud)$0.06$0.4$0.01200kJan 19, 2026
GLM-4.7-FlashX$0.07$0.4$0.01200kJan 19, 2026
Kimi K2.5$0.6$3$0.1262kJan 1, 2026
Kimi K2.5 (EmberCloud)$0.405$1.98$0.225262kJan 1, 2026
MiniMax M2.1 Lightning$0.12$0.48—197kDec 23, 2025
MiniMax-M2.1$0.27$1.1—197kDec 23, 2025
GLM-4.7$0.45$2—203kDec 22, 2025
GLM-4.7 (ByteDance)$0.6$2.2$0.11200kDec 22, 2025
GLM-4.7 (EmberCloud)$0.38$1.98$0.19200kDec 22, 2025
Seed 1.8 (251228) (ByteDance)$0.25$2$0.05256kDec 18, 2025
Gemini 3 Flash Preview$0.5$3$0.051.0MDec 17, 2025
GPT-5.2$1.75$14$0.175400kDec 11, 2025
GPT-5.2 Codex$1.75$14$0.175400kDec 11, 2025
GPT-5.2 Pro$21$168—400kDec 11, 2025
Devstral 2$0.4$2—262kDec 9, 2025
GLM-4.6V$0.3$0.9$0.055131kDec 8, 2025
GLM-4.6V FlashX$0.04$0.4$0.004128kDec 8, 2025
Ministral 14B$0.2$0.2—262kDec 2, 2025
Ministral 3B$0.1$0.1—131kDec 2, 2025
Ministral 8B$0.15$0.15—262kDec 2, 2025
Mistral Large 3$0.5$1.5—262kDec 2, 2025
DeepSeek V3.2$0.26$0.38$0.13160kDec 1, 2025
DeepSeek V3.2 (ByteDance)$0.28$0.42$0.056131kDec 1, 2025
Grok 4.1 Fast (Non-Reasoning)$0.2$0.5—2.0MNov 19, 2025
Grok 4.1 Fast Reasoning$0.2$0.5—2.0MNov 19, 2025
GPT-5.1$1.25$10$0.125400kNov 13, 2025
GPT-5.1 Codex$1.25$10—400kNov 13, 2025
GPT-5.1 Codex mini$0.25$2$0.025400kNov 13, 2025
Kimi K2 Thinking$0.6$2.5$0.06262kNov 6, 2025
Claude Opus 4.5$5$25$0.5200kNov 1, 2025
MiniMax-M2$0.2$1$0.03197kOct 27, 2025
Claude Haiku 4.5$1$5$0.1200kOct 15, 2025
Qwen3 VL Flash$0.05$0.4$0.01262kOct 15, 2025
GPT-5 Pro$15$120—400kOct 6, 2025
Qwen3 VL 30B A3B Instruct$0.15$0.6—262kOct 5, 2025
GLM-4.6$0.55$2.2$0.11205kSep 30, 2025
Claude Sonnet 4.5$3$15$0.3200kSep 29, 2025
Qwen3 Max$0.845$3.38—262kSep 23, 2025
Qwen3 VL 235B A22B Instruct$0.2$0.88$0.11262kSep 23, 2025
Qwen3 VL 235B A22B Thinking$0.98$3.95—131kSep 23, 2025
Qwen3-VL Plus$0.2$1.6$0.04262kSep 23, 2025
Seed 1.6 (250915) (ByteDance)$0.25$2$0.05256kSep 15, 2025
Qwen3 Next 80B A3B Thinking$0.15$1.2—131kSep 1, 2025
Qwen3-Next 80B-A3B Instruct$0.15$1.2—131kSep 1, 2025
GLM-4.5V$0.6$1.8$0.1166kAug 11, 2025
GPT-5$1.25$10$0.125400kAug 7, 2025
GPT-5 Mini$0.25$2$0.025400kAug 7, 2025
GPT-5 Nano$0.05$0.4$0.005400kAug 7, 2025
Claude Opus 4.1$15$75$1.5200kAug 5, 2025
GPT OSS 120B$0.15$0.6—131kAug 5, 2025
GPT OSS 120B (ByteDance)$0.1$0.5$0.02128kAug 5, 2025
GPT OSS 120B (Runware)$0.032$0.14$0.032131kAug 5, 2025
GPT OSS 120B (SCX.ai (Turbo))$0.17$0.55—131kAug 5, 2025
GPT OSS 20B$0.1$0.5—131kAug 5, 2025
GPT OSS 20B (Consensus Protocol)$0.04$0.19$0.01128kAug 5, 2025
Codestral$0.3$0.9—256kJul 30, 2025
GLM-4.5$0.6$2.2$0.11128kJul 28, 2025
GLM-4.5 (EmberCloud)$0.6$2.2$0.11131kJul 28, 2025
GLM-4.5 Air (EmberCloud)$0.13$0.85$0.025131kJul 28, 2025
GLM-4.5 AirX$1.1$4.5$0.22128kJul 28, 2025
GLM-4.5 X$2.2$8.9$0.45128kJul 28, 2025
GLM-4.5-Air$0.2$1.1$0.03128kJul 28, 2025
Qwen Flash$0.05$0.4$0.011.0MJul 28, 2025
Qwen3 Coder Flash$0.3$1.5$0.06998kJul 28, 2025
Seed 1.6 Flash (250715) (ByteDance)$0.07$0.3$0.015256kJul 26, 2025
Qwen3 235B A22B Thinking 2507$0.3$3—131kJul 25, 2025
Qwen3 Coder Plus$1$5$0.21.0MJul 23, 2025
Qwen3 235B A22B Instruct 2507$0.09$0.58—131kJul 21, 2025
Kimi K2$0.57$2.3—131kJul 11, 2025
Grok 4$3$15$0.75256kJul 9, 2025
ERNIE 4.5 VL 424B A47B$0.42$1.25—123kJun 30, 2025
Seed 1.6 (250615) (ByteDance)$0.25$2$0.05256kJun 25, 2025
Mistral Small 3.2$0.1$0.3—128kJun 20, 2025
Gemini 2.5 Flash$0.3$2.5$0.031.0MJun 17, 2025
Gemini 2.5 Flash-Lite$0.1$0.4$0.011.0MJun 17, 2025
Gemini 2.5 Pro$1.25$10$0.1251.0MJun 17, 2025
Qwen3 235B A22B FP8$0.2$0.8—41kApr 28, 2025
o3$2$8$0.5200kApr 16, 2025
o4-mini$1.1$4.4$0.275200kApr 16, 2025
GLM-4 32B (0414-128k)$0.1$0.1—128kApr 14, 2025
GPT-4.1$2$8$0.51.0MApr 14, 2025
GPT-4.1 mini$0.4$1.6$0.11.0MApr 14, 2025
GPT-4.1 nano$0.1$0.4$0.0251.0MApr 14, 2025
Llama 4 Maverick 17B Instruct$0.27$0.85—1.0MApr 5, 2025
Llama 4 Maverick 17B Instruct (SCX.ai (Turbo))$0.53$1.62—131kApr 5, 2025
Llama 4 Scout 17B Instruct$0.18$0.59—131kApr 5, 2025
Qwen3 32B (SCX.ai (Turbo))$0.36$0.87—33kApr 1, 2025
Qwen3 Coder 480B A35B Instruct$0.38$1.55—262kApr 1, 2025
Qwen3-Coder 30B-A3B Instruct$0.07$0.27—160kApr 1, 2025
GPT-4o Mini Transcribe$1.25$5—16kMar 20, 2025
GPT-4o Transcribe$2.5$10—16kMar 20, 2025
Qwen-Omni Turbo$0.2$0.8—33kJan 19, 2025
MiniMax Text 01$0.2$1.1—1.0MJan 15, 2025
o3-mini$1.1$4.4$0.55200kDec 20, 2024
Llama-3.3-70B-Instruct$0.135$0.4—131kDec 6, 2024
o1$15$60$7.5200kDec 5, 2024
Mistral Large$4$12—128kNov 1, 2024
Llama 3.2 11B Instruct$0.07$0.33—128kSep 25, 2024
Llama 3.2 3B Instruct$0.03$0.05—33kSep 18, 2024
Qwen Coder Plus$0.502$1.004—131kSep 18, 2024
Llama 3.1 70B Instruct$0.72$0.72—128kJul 23, 2024
GPT-4o mini$0.15$0.6$0.075128kJul 18, 2024
GPT-4o$2.5$10$1.25128kMay 13, 2024
Llama 3 70B Instruct$0.51$0.74—8kApr 18, 2024
Qwen Max$1.6$6.4—33kApr 3, 2024
Qwen Plus$0.4$1.2$0.08131kJan 25, 2024
Sonar$0.25$2.5—130kJan 1, 2024
GPT-4$30$60—8kNov 6, 2023
GPT-4 Turbo$10$30—128kNov 6, 2023
GPT-3.5-turbo$0.5$1.5—16kMar 1, 2023