Models
Every model we serve, with the figures their vendors publish. Ask for what you need in plain words, or filter by category.
22 of 22 models
| Parameters | ||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| GLM 5.3zai-org/GLM-5.3 | Z.ai | text | text | English, Chinese | 753.3B | Aug 2026 | 1.1M | 44.9 | FP8 | 1.3M | n/a | $0.915 | $2.875 | GLM 5.3 | 🤗 | |
| Kimi K3moonshotai/Kimi-K3 | Moonshot AI | textimagevideo | text | not published | 2.8T | 104B | Jun 2026 | 1.9M | 43.8 | FP8 | 1M | n/a | $2.250 | $11.475 | Kimi K3 | 🤗 |
| GLM 5.3 Flashzai-org/GLM-5.3-Flash | Z.ai | textimage | text | English, Chinese | 321.3B | 18B | Aug 2026 | 3.8M | 41.9 | FP8 | 1M | n/a | $0.081 | $0.270 | MIT | 🤗 |
| Qwen3.8 2.4T A95BQwen/Qwen3.8-2.4T-A95B | Qwen | text | text | not published | 2.4T | 95B | Aug 2026 | 54.4K | 40 | FP8 | 1M | n/a | $1.800 | $5.400 | Qwen3.8 Max | 🤗 |
| DeepSeek V4.1 Flashdeepseek-ai/DeepSeek-V4.1-Flash | DeepSeek | textimage | text | not published | 552B | 16B | Sept 2026 | 570.9K | 39.5 | MXFP4/MXFP8 | 1M | n/a | $0.135 | $0.540 | MIT | 🤗 |
| DeepSeek V4 Pro 0813deepseek-ai/DeepSeek-V4-Pro-0813 | DeepSeek | text | text | not published | 1.7T | 49B | Aug 2026 | 153K | 36.3 | FP8 | 1M | n/a | $0.522 | $1.568 | MIT | 🤗 |
| DeepSeek V4 Flash 0731deepseek-ai/DeepSeek-V4-Flash-0731 | DeepSeek | text | text | not published | 284B | 13B | Jul 2026 | 4M | 34.5 | FP8 | 1M | n/a | $0.027 | $0.117 | MIT | 🤗 |
| Qwen3.8 27BQwen/Qwen3.8-27B-FP8 | Qwen | textimagevideo | text | not published | 27.8B | Aug 2026 | 6.3M | 33.9 | FP8 | 262K | n/a | $0.180 | $1.980 | Apache 2.0 | 🤗 | |
| DeepSeek V4 Prodeepseek-ai/DeepSeek-V4-Pro | DeepSeek | text | text | not published | 1.6T | 49B | Apr 2026 | 537.4K | 30.9 | FP8 | 1M | n/a | $0.939 | $1.879 | MIT | 🤗 |
| Minimax M3MiniMaxAI/MiniMax-M3 | MiniMax | textimagevideo | text | not published | 427B | 23B | Jun 2026 | 167.7K | 29.6 | FP8 | 1M | n/a | $0.252 | $0.990 | MiniMax Community | 🤗 |
| Kimi K2.6moonshotai/Kimi-K2.6 | Moonshot AI | textimage | text | not published | 1T | 32B | Apr 2026 | 441K | 27.5 | FP8 | 262K | n/a | $0.513 | $2.160 | Modified MIT | 🤗 |
| Qwen3.5 35B A3BQwen/Qwen3.5-35B-A3B | Qwen | textimagevideo | text | 201 | 36B | 3B | Feb 2026 | 1.8M | 19.3 | FP8 | 262K | n/a | $0.126 | $0.900 | Apache 2.0 | 🤗 |
| Voxtral Small 24Bmistralai/Voxtral-Small-24B-2507 | Mistral AI | textaudiofile | text | 8 named | 24.3B | Jul 2025 | 24.4K | not rated | FP8 | 33K | n/a | $0.090 | $0.270 | Apache 2.0 | 🤗 | |
| MiMo V2.5XiaomiMiMo/MiMo-V2.5 | Xiaomi MiMo | textaudioimagevideo | text | English, Chinese | 310.8B | 15B | Apr 2026 | 282.1K | 22.3 | FP8 | 1.1M | n/a | $0.126 | $0.252 | MIT | 🤗 |
| GLM OCRzai-org/GLM-OCR | Z.ai | textimage | text | 8 named | 0.9B | Jan 2026 | 1.7M | not rated | FP8 | not published | n/a | $0.027 | $0.027 | MIT | 🤗 | |
| Qwen3 Embedding 8BQwen/Qwen3-Embedding-8B | Qwen | text | vector | 100+ | 7.6B | Jun 2025 | 2.6M | 70.58 | FP8 | 33K | 4096 | $0.009 | n/a | Apache 2.0 | 🤗 | |
| Qwen3 Embedding 4BQwen/Qwen3-Embedding-4B | Qwen | text | vector | 100+ | 4B | Jun 2025 | 2M | 69.45 | FP8 | 33K | 2560 | $0.009 | n/a | Apache 2.0 | 🤗 | |
| Qwen3 Embedding 0.6BQwen/Qwen3-Embedding-0.6B | Qwen | text | vector | 100+ | 0.6B | Jun 2025 | 9.1M | 64.34 | FP8 | 33K | 1024 | $0.004 | n/a | Apache 2.0 | 🤗 | |
| BGE M3BAAI/bge-m3 | BAAI | text | vector | 100+ | 0.568B | Jan 2024 | 37.2M | 59.56 | FP8 | 8K | 1024 | $0.009 | n/a | MIT | 🤗 | |
| Nemotron 3 Embed 8Bnvidia/Nemotron-3-Embed-8B-BF16 | NVIDIA | text | vector | not published | 7.953B | Jul 2026 | 97.1K | not rated | FP8 | 33K | 4096 | $0.031 | n/a | OpenMDW 1.1 | 🤗 | |
| EmbeddingGemma 300Mgoogle/embeddinggemma-300m | text | vector | 100+ | 0.308B | Jul 2025 | 2.9M | 61.15 | FP8 | 2K | 768 | $0.001 | n/a | Gemma | 🤗 | ||
| Faster Whisper Large v3Systran/faster-whisper-large-v3 | Systran | audio | text | 100 | 1.55B | Nov 2023 | 973.5K | not rated | FP16 | 0K | n/a | $0.024 /hr | n/a | MIT | 🤗 | |