Model Catalog
One API for all models. Search our library, deploy and run inference on NVIDIA GPUs in seconds
Generate up to ~4M tokens on first deposit of $5
| Model | Category | Context | Provider | Parameters | Price(/1M tokens) | Action |
|---|---|---|---|---|---|---|
| Vision | Per MiniMax M3 limits | MiniMax | MiniMax-M3 | Context <= 512K43% off Input: $0.60$0.35 Cached: $0.12$0.069 Output: $2.4$1.38 See more (2 tiers)Pricing by context · 2 tiers Context <= 512K43% off Input: $0.60$0.35 Cached: $0.12$0.069 Output: $2.4$1.38 Context 512K ~ 1M20% off Input: $0.86$0.69 Cached: $0.17$0.14 Output: $3.45$2.76 | ||
| Vision | Up to 256K tokens / multi-image | Alibaba (Cloud) | Undisclosed | Input <=256k20% off Input: $0.58$0.46 Cached: $0.0575$0.046 Output: $2.3$1.84 See more (2 tiers)Pricing by context · 2 tiers Input <=256k20% off Input: $0.58$0.46 Cached: $0.0575$0.046 Output: $2.3$1.84 256k < Input <= 1m20% off Input: $1.72$1.38 Cached: $0.17$0.14 Output: $6.9$5.52 | ||
| Chat | 128K Tokens | Alibaba (Cloud) | Undisclosed | 20% off Input: $3.59$2.88 Cached: $0.36$0.29 Output: $10.78$8.63 | ||
| Chat | 300K Tokens | NVIDIA | Undisclosed | 20% off Input: $0.0992$0.0794 Output: $0.40$0.32 | ||
| Vision | 256K Tokens | Moonshot AI | 1T (32B active) | 20% off Input: $1.28$1.03 Cached: $0.13$0.10 Output: $5.34$4.27 | ||
| Chat | 256K Tokens (up to 1M) | NVIDIA | 120B (12B active) | 20% off Input: $0.50$0.40 Output: $1.49$1.19 | ||
| Chat | 393,216 Tokens | DeepSeek | V4 family | 20% off Input: $0.20$0.16 Cached: $0.0402$0.0322 Output: $0.40$0.32 | ||
| Chat | 200K Tokens | Z.ai (Zhipu AI) | 744B (40B active) | Input <=32k20% off Input: $0.82$0.66 Cached: $0.17$0.13 Output: $3.71$2.97 See more (2 tiers)Pricing by context · 2 tiers Input <=32k20% off Input: $0.82$0.66 Cached: $0.17$0.13 Output: $3.71$2.97 32k < Input <= 200k20% off Input: $1.24$0.99 Cached: $0.25$0.20 Output: $4.53$3.63 | ||
| Chat | 200K Tokens | MiniMax | MoE (MiniMax-M2.7) | 20% off Input: $0.52$0.41 Cached: $0.10$0.0828 Output: $2.07$1.66 | ||
| Chat | 200K Tokens | MiniMax | 230B (10B active) | 20% off Input: $0.44$0.35 Cached: $0.0877$0.0701 Output: $1.74$1.39 | ||
| Vision | 256K Tokens | Moonshot AI | 1T (32B active) | 20% off Input: $0.83$0.66 Cached: $0.0819$0.0656 Output: $4.33$3.46 | ||
| Code | Up to 1M Tokens | Alibaba (Cloud) | Input <=32k20% off Input: $1.44$1.15 Cached: $0.14$0.11 Output: $7.19$5.75 See more (4 tiers)Pricing by context · 4 tiers Input <=32k20% off Input: $1.44$1.15 Cached: $0.14$0.11 Output: $7.19$5.75 32k < Input <= 128k20% off Input: $2.59$2.07 Cached: $0.26$0.21 Output: $12.94$10.35 128k < Input <= 256k20% off Input: $4.31$3.45 Cached: $0.43$0.35 Output: $21.56$17.25 256k < Input <= 1m20% off Input: $8.62$6.9 Cached: $0.86$0.69 Output: $86.25$69 | |||
| Chat | 32K Tokens | MistralAI | 7.3B | 8% off Input: $0.11$0.10 Output: $0.19$0.17 | ||
| Code | 262K Tokens | Alibaba (Cloud) | 79.7B (3B active) | Input <= 32k20% off Input: $0.43$0.35 Output: $2.16$1.72 See more (3 tiers)Pricing by context · 3 tiers Input <= 32k20% off Input: $0.43$0.35 Output: $2.16$1.72 32k < Input <= 128k20% off Input: $0.72$0.58 Output: $3.59$2.88 128k < Input <= 256k20% off Input: $1.15$0.92 Output: $5.75$4.6 | ||
| Chat | 128K | Alibaba (Cloud) | Input <= 256k20% off Input: $0.58$0.46 Output: $1.72$1.38 See more (2 tiers)Pricing by context · 2 tiers Input <= 256k20% off Input: $0.58$0.46 Output: $1.72$1.38 256k < Input <= 1m20% off Input: $1.72$1.38 Output: $5.17$4.14 | |||
| Code | Up to 1M Tokens | Alibaba (Cloud) | Input <= 32k20% off Input: $0.43$0.35 Cached: $0.0431$0.0345 Output: $2.16$1.72 See more (4 tiers)Pricing by context · 4 tiers Input <= 32k20% off Input: $0.43$0.35 Cached: $0.0431$0.0345 Output: $2.16$1.72 32k < Input <= 128k20% off Input: $0.72$0.58 Cached: $0.0719$0.0575 Output: $3.59$2.88 128k < Input <= 256k20% off Input: $1.15$0.92 Cached: $0.11$0.092 Output: $5.75$4.6 256k < Input <= 1m20% off Input: $2.3$1.84 Cached: $0.23$0.18 Output: $13.8$11.04 | |||
| Vision | Up to 256K Tokens | Alibaba (Cloud) | Input <= 32k20% off Input: $0.29$0.23 Output: $2.3$1.84 See more (3 tiers)Pricing by context · 3 tiers Input <= 32k20% off Input: $0.29$0.23 Output: $2.3$1.84 32k < Input <= 128k20% off Input: $0.43$0.35 Output: $3.45$2.76 128k < Input <= 256k20% off Input: $0.86$0.69 Output: $6.9$5.52 | |||
| Vision | Up to 256K Tokens | Alibaba (Cloud) | Input <= 32k20% off Input: $0.0719$0.0575 Cached: $0.0072$0.0058 Output: $0.58$0.46 See more (3 tiers)Pricing by context · 3 tiers Input <= 32k20% off Input: $0.0719$0.0575 Cached: $0.0072$0.0058 Output: $0.58$0.46 32k < Input <= 128k20% off Input: $0.11$0.0863 Cached: $0.0108$0.0086 Output: $0.86$0.69 128k < Input <= 256k20% off Input: $0.17$0.14 Cached: $0.0172$0.0138 Output: $1.38$1.1 | |||
| Vision | Up to 256K tokens / 10 images | Alibaba Cloud | Undisclosed (frontier-scale) | Input <= 256k20% off Input: $0.72$0.58 Cached: $0.0719$0.0575 Output: $4.31$3.45 See more (2 tiers)Pricing by context · 2 tiers Input <= 256k20% off Input: $0.72$0.58 Cached: $0.0719$0.0575 Output: $4.31$3.45 256k < Input <= 1m20% off Input: $2.87$2.3 Cached: $0.29$0.23 Output: $8.62$6.9 | ||
| Chat | 128K Tokens | Alibaba (Cloud) | Undisclosed | Input <= 128k20% off Input: $1.87$1.49 Cached: $0.19$0.15 Output: $11.21$8.97 See more (2 tiers)Pricing by context · 2 tiers Input <= 128k20% off Input: $1.87$1.49 Cached: $0.19$0.15 Output: $11.21$8.97 128k < Input <= 256k20% off Input: $2.87$2.3 Cached: $0.29$0.23 Output: $17.25$13.8 | ||
| Vision | 256K Tokens | Alibaba (Cloud) | 235B | 20% off Input: $0.58$0.46 Output: $2.3$1.84 | ||
| Vision | 256K Tokens | Alibaba (Cloud) | 9B | 8% off Input: $0.080$0.0736 Output: $0.080$0.0736 | ||
| Vision | 256K Tokens | Alibaba (Cloud) | 30B(3B active) | 8% off Input: $0.13$0.12 Output: $0.13$0.12 | ||
| Chat | 128k Tokens | OpenAI | 117B | 8% off Input: $0.15$0.14 Cached: $0.015$0.0138 Output: $0.60$0.55 | ||
| Code | 262K Tokens | Alibaba (Cloud) | 30.5B | Input <= 32k20% off Input: $0.65$0.52 Output: $3.23$2.59 See more (4 tiers)Pricing by context · 4 tiers Input <= 32k20% off Input: $0.65$0.52 Output: $3.23$2.59 32k < Input <= 128k20% off Input: $1.08$0.86 Output: $5.39$4.31 128k < Input <= 256k20% off Input: $1.72$1.38 Output: $8.62$6.9 256k < Input <= 1m20% off Input: $3.45$2.76 Output: $20.7$16.56 | ||
| Chat | 8192 Tokens | Microsoft | 7B | 8% off Input: $0.21$0.19 Output: $0.25$0.23 | ||
| Chat | 128k Tokens | DeepSeek | 70B | 8% off Input: $0.70$0.64 Output: $0.80$0.74 | ||
| OCR | 16K Tokens | Tencent Hunyuan | 1.0B | Input: $0.19 Output: $0.32 | ||
| Chat | 128K Tokens | Meta | 70B | 8% off Input: $0.12$0.11 Output: $0.38$0.35 | ||
| Chat | 128k Tokens | NVIDIA | 31.6B Total / 3.2B Active | 8% off Input: $0.050$0.046 Output: $0.20$0.18 | ||
| Chat | 256K Tokens | Alibaba Cloud | 80B (3.9B active) | 20% off Input: $0.22$0.17 Output: $1.72$1.38 | ||
| Code | 262K Tokens | Alibaba Cloud | 480B (35B active) | Input <= 32k20% off Input: $2.16$1.72 Output: $10.78$8.63 See more (4 tiers)Pricing by context · 4 tiers Input <= 32k20% off Input: $2.16$1.72 Output: $10.78$8.63 32k < Input <= 128k20% off Input: $3.88$3.11 Output: $19.41$15.52 128k < Input <= 256k20% off Input: $6.47$5.18 Output: $32.34$25.87 256k < Input <= 1m20% off Input: $12.94$10.35 Output: $129.37$103.5 | ||
| Vision | 256K Tokens (up to 1M) | Alibaba Cloud | 235B (22B active) | 20% off Input: $0.58$0.46 Output: $5.75$4.6 | ||
| Chat | 128K Tokens | Alibaba (Cloud) | 235B (22B active) | Input <= 32k20% off Input: $1.72$1.38 Output: $8.62$6.9 See more (3 tiers)Pricing by context · 3 tiers Input <= 32k20% off Input: $1.72$1.38 Output: $8.62$6.9 32k < Input <= 128k20% off Input: $3.45$2.76 Output: $17.25$13.8 128k < Input <= 256k20% off Input: $4.31$3.45 Output: $21.56$17.25 | ||
| Chat | 128K Tokens | DeepSeek | 671B (37B active) | 20% off Input: $0.83$0.66 Output: $3.3$2.64 | ||
| Chat | 160K Tokens | DeepSeek | 685B(37B active) | 20% off Input: $0.41$0.33 Cached: $0.0417$0.0334 Output: $0.62$0.50 | ||
| Chat | 128K Tokens | DeepSeek | 671B (37B active) | 20% off Input: $0.41$0.33 Cached: $0.0819$0.0656 Output: $1.65$1.32 | ||
| Chat | 393,216 Tokens | DeepSeek | V4 family | 20% off Input: $2.37$1.9 Cached: $0.20$0.16 Output: $4.75$3.8 | ||
| Chat | 256K Tokens | Moonshot AI | 1T (32B active) | 20% off Input: $0.83$0.66 Cached: $0.17$0.13 Output: $3.3$2.64 | ||
| Vision | 1M Tokens (API) / 256K Tokens (self-hosted base) | Alibaba (Cloud) | 35B (3B active) — hosted | 20% off Input: $0.14$0.11 Cached: $0.0144$0.0115 Output: $0.58$0.46 | ||
| Vision | 1M Tokens (API) / 262K Tokens (self-hosted base) | Alibaba (Cloud) | 397B (17B active) — hosted | Input <= 256k20% off Input: $0.58$0.46 Cached: $0.0575$0.046 Output: $3.45$2.76 See more (2 tiers)Pricing by context · 2 tiers Input <= 256k20% off Input: $0.58$0.46 Cached: $0.0575$0.046 Output: $3.45$2.76 256k < Input <= 1m20% off Input: $0.72$0.58 Cached: $0.0719$0.0575 Output: $4.31$3.45 | ||
| Vision | 256K Tokens (up to 1M) | Alibaba (Cloud) | 27B (dense) | 20% off Input: $0.43$0.35 Output: $3.45$2.76 | ||
| Vision | 256K Tokens (up to 1M) | Alibaba (Cloud) | 35B (3B active) | 20% off Input: $0.36$0.29 Output: $2.87$2.3 | ||
| Vision | 256K Tokens (up to 1M) | Alibaba (Cloud) | 122B (10B active) | 20% off Input: $0.58$0.46 Output: $4.6$3.68 | ||
| Vision | 256K Tokens (up to 1M) | Alibaba (Cloud) | 27B | 20% off Input: $0.86$0.69 Output: $5.17$4.14 | ||
| Vision | 256K Tokens (up to 1M) | Alibaba (Cloud) | 35B (A3B active) | 20% off Input: $0.54$0.43 Output: $3.23$2.59 | ||
| Vision | 256K Tokens (up to 1M via Qwen3.5-Plus API) | Alibaba Cloud | 397B (17B active) | 20% off Input: $0.86$0.69 Output: $5.17$4.14 | ||
| Chat | 205K Tokens | Z.ai (Zhipu AI) | 355B (32B active) | 20% off Input: $1.08$0.86 Cached: $0.20$0.16 Output: $3.96$3.17 | ||
| Chat | 200K Tokens | Z.ai (Zhipu AI) | Flagship MoE | 20% off Input: $2.52$2.02 Cached: $0.47$0.37 Output: $7.92$6.34 | ||
| Chat | 1M Tokens | Z.ai (Zhipu AI) | Flagship MoE | 21% off Input: $1.68$1.32 Cached: $0.41$0.33 Output: $5.28$4.62 | ||
| Chat | 200K Tokens | Z.ai (Zhipu AI) | Foundation model | 20% off Input: $1.8$1.44 Cached: $0.36$0.29 Output: $6$4.8 | ||
| Chat | 200K Tokens | Z.ai (Zhipu AI) | 106B (12B active) | 20% off Input: $0.30$0.24 Cached: $0.045$0.036 Output: $1.65$1.32 | ||
| Chat | 200K Tokens | Z.ai (Zhipu AI) | 30B | Input: -- Cached: -- Output: -- | ||
| Chat | 256K Tokens | Moonshot AI | 1T (32B active) | 20% off Input: $0.83$0.66 Cached: $0.17$0.13 Output: $3.3$2.64 | ||
| Chat | 200K Tokens | Z.ai (Zhipu AI) | 20% off Input: $0.90$0.72 Cached: $0.17$0.13 Output: $3.3$2.64 | |||
| Chat | 200K Tokens | Z.ai (Zhipu AI) | 20% off Input: $0.90$0.72 Cached: $0.17$0.13 Output: $3.3$2.64 | |||
| Chat | 200K Tokens | Z.ai (Zhipu AI) | 20% off Input: $3.3$2.64 Cached: $0.68$0.54 Output: $13.35$10.68 | |||
| Chat | 200K Tokens | Z.ai (Zhipu AI) | 20% off Input: $1.65$1.32 Cached: $0.33$0.26 Output: $6.75$5.4 | |||
| Chat | 200K Tokens | Z.ai (Zhipu AI) | 20% off Input: $0.11$0.084 Cached: $0.015$0.012 Output: $0.60$0.48 | |||
| Chat | 200K Tokens | Z.ai (Zhipu AI) | Input: -- Cached: -- Output: -- | |||
| Chat | 128K Tokens | Z.ai (Zhipu AI) | 20% off Input: $0.15$0.12 Output: $0.15$0.12 | |||
| Vision | 200K Tokens | Z.ai (Zhipu AI) | 20% off Input: $1.8$1.44 Cached: $0.36$0.29 Output: $6$4.8 | |||
| Vision | 200K Tokens | Z.ai (Zhipu AI) | 20% off Input: $0.45$0.36 Cached: $0.075$0.060 Output: $1.35$1.08 | |||
| Vision | 200K Tokens | Z.ai (Zhipu AI) | 20% off Input: $0.060$0.048 Cached: $0.006$0.0048 Output: $0.60$0.48 | |||
| Vision | 200K Tokens | Z.ai (Zhipu AI) | 20% off Input: $0.90$0.72 Cached: $0.17$0.13 Output: $2.7$2.16 | |||
| Vision | 200K Tokens | Z.ai (Zhipu AI) | Input: -- Cached: -- Output: -- | |||
| Vision | 1,048,576 Tokens | Moonshot AI | 2.8T | 20% off Input: $3.75$3 Cached: $0.37$0.30 Output: $18.75$15 | ||
| Chat | 1M Tokens | Moonshot AI | 20% off Input: $1.42$1.14 Cached: $0.29$0.23 Output: $6$4.8 | |||
| Chat | 1M Tokens | Moonshot AI | 20% off Input: $2.85$2.28 Cached: $0.57$0.46 Output: $12$9.6 |
Showing 0 of 0 models
No models match your search. Try a different keyword or category.
Sign up to get $1.00 free API credit on first deposit of $5. Test out the latest models now.
Access enterprise-grade open-source AI models including Llama 3, DeepSeek, Qwen, and more via our high-performance serverless API. Experience low-latency inference on the latest NVIDIA GPUs optimized for production workloads.
"Qubrid AI reduced our document processing time by over 60% and significantly improved retrieval accuracy across our RAG workflows."
Enterprise AI Team
Document Intelligence Platform