Models
数据更新于 2026-10-10
厂商:
系列:
价格单位:美元/百万 tokens;OR 有免费变体时展示免费价。输出速度为实测参考。
| # | 模型 | 场景 | 输入价格 | 输出价格 | OR 输入价 | OR 输出价 | 速度 | 更新时间 | 对比 |
|---|---|---|---|---|---|---|---|---|---|
| – | Claude Opus 5.5 | 编程通用对话看图 / 文档理解数学 / 数据分析 | $4/M | $20/M | $4/M | $20/M | 97 tokens/秒 | 2026-09 | |
| – | Claude Fable 5.1 | 编程通用对话看图 / 文档理解长文档处理数学 / 数据分析Agent 自动化 | $10/M | $50/M | $10/M | $50/M | 62 tokens/秒 | 2026-09 | |
| – | GPT-6.1 Sol | 编程通用对话看图 / 文档理解数学 / 数据分析 | $2/M | $10/M | $2/M | $10/M | — | 2026-09 | |
| – | Claude Sonnet 5.5 | 编程通用对话数学 / 数据分析 | $2/M | $10/M | $2/M | $10/M | 128 tokens/秒 | 2026-09 | |
| – | Claude Opus 5 | 编程通用对话看图 / 文档理解长文档处理Agent 自动化 | $5/M | $25/M | $5/M | $25/M | 57 tokens/秒 | 2026-07 | |
| – | GPT-6 Astra | 编程通用对话看图 / 文档理解数学 / 数据分析 | $10/M | $50/M | $10/M | $50/M | 63 tokens/秒 | 2026-09 | |
| – | Muse Spark 1.3 | 编程通用对话看图 / 文档理解 | $1.25/M | $4.25/M | $1.25/M | $4.25/M | 187 tokens/秒 | 2026-09 | |
| – | GPT-5.6 Sol | 通用对话看图 / 文档理解长文档处理数学 / 数据分析 | $4/M | $20/M | $2/M | $10/M | 97 tokens/秒 | 2026-07 | |
| – | MiMo-V2.6-Pro | 编程通用对话 | $0.435/M | $0.87/M | $0.435/M | $0.87/M | 47 tokens/秒 | 2026-09 | |
| – | Kimi K3 | 编程通用对话数学 / 数据分析 | $3/M | $15/M | $0.8/M | $13.5/M | 52 tokens/秒 | 2026-07 | |
| – | GPT-6 Sol | 编程数学 / 数据分析 | $2/M | $10/M | $2/M | $10/M | — | 2026-09 | |
| – | Gemini 3.7 Flash | 通用对话看图 / 文档理解数学 / 数据分析Agent 自动化 | $0.75/M | $3.75/M | $0.75/M | $3.75/M | 284 tokens/秒 | 2026-08 | |
| – | Claude Opus 4.7 | 通用对话看图 / 文档理解长文档处理 | $5/M | $25/M | $5/M | $25/M | 50 tokens/秒 | 2026-04 | |
| – | GPT-5.5 | 通用对话看图 / 文档理解长文档处理数学 / 数据分析 | $5/M | $30/M | $5/M | $30/M | 104 tokens/秒 | 2026-04 | |
| – | Qwen3.8 Max | 编程 | — | — | — | — | 37 tokens/秒 | 2026-08 | |
| – | Gemini 3.8 Flash | 通用对话看图 / 文档理解数学 / 数据分析 | $0.75/M | $3.75/M | $0.75/M | $3.75/M | 242 tokens/秒 | 2026-09 | |
| – | Claude Opus 4.8 | 通用对话看图 / 文档理解长文档处理 | $5/M | $25/M | $5/M | $25/M | 64 tokens/秒 | 2026-05 | |
| – | MiMo-V2.6-Flash | 编程Agent 自动化 | $0.14/M | $0.28/M | $0.14/M | $0.28/M | — | 2026-09 | |
| – | Grok 4.6 | 编程数学 / 数据分析Agent 自动化 | $2/M | $6/M | $2/M | $6/M | 73 tokens/秒 | 2026-08 | |
| – | GLM-5.3 | 编程通用对话Agent 自动化 | 免费 | 免费 | $0.039/M | $6/M | 75 tokens/秒 | 2026-08 | |
| – | Mistral Large 4 | — | $0.68/M | $2.09/M | $0.68/M | $2.09/M | 116 tokens/秒 | 2026-10 | |
| – | Ling 3.1 Flash | — | — | — | 免费 | 免费 | 211 tokens/秒 | 2026-09 | |
| – | d1-3B 待核实 | — | 免费 | 免费 | — | — | — | 2026-10 | |
| – | d1-omni-600M 待核实 | — | 免费 | 免费 | — | — | — | 2026-10 | |
| – | EmbeddingGemma 2 | — | 免费 | 免费 | — | — | — | 2026-10 | |
| – | MAI-Transcribe-2-Streaming | — | — | — | — | — | — | 2026-10 | |
| – | MAI-Voice-2.1 | — | — | — | — | — | — | 2026-10 | |
| – | MAI-Voice-2.1-Flash | — | — | — | — | — | — | 2026-10 | |
| – | GPT-6 Luna | — | $0.1/M | $0.5/M | $0.1/M | $0.5/M | — | 2026-09 | |
| – | Command A+ | — | $2.5/M | $10/M | $2.5/M | $10/M | 139 tokens/秒 | 2026-05 | |
| – | Grok 4.7 | 编程 | $2/M | $6/M | $2/M | $6/M | 92 tokens/秒 | 2026-09 | |
| – | Qwen3.8-Omni-Flash | — | — | — | $0.15/M | $0.47/M | — | 2026-09 | |
| – | Ternary Bonsai 2 27B | — | 免费 | 免费 | $0.075/M | $0.5/M | — | 2026-09 | |
| – | DeepSeek V4.1 Flash | 编程通用对话Agent 自动化 | $0.3/M | $1.2/M | — | — | 222 tokens/秒 | 2026-09 | |
| – | Ling 3.0 Flash VL | — | 免费 | 免费 | $0.021/M | $0.0616/M | — | 2026-09 | |
| – | Mercury 2.5 | — | $0.04/M | $0.15/M | $0.04/M | $0.15/M | 691 tokens/秒 | 2026-09 | |
| – | Claude Mythos 5.1 | — | — | — | — | — | — | 2026-09 | |
| – | ElevenLabs Eleven v4 | — | — | — | — | — | — | 2026-09 | |
| – | ElevenLabs Eleven v4 Turbo | — | — | — | — | — | — | 2026-09 | |
| – | Embed 5 Fast | — | $0.08/M | — | — | — | — | 2026-09 | |
| – | Embed 5 Pro | — | $0.12/M | — | — | — | — | 2026-09 | |
| – | Gemini 3.8 Flash Cyber | — | — | — | — | — | — | 2026-09 | |
| – | Gemini 3.8 Flash TTS | — | — | — | $0.75/M | $3.75/M | — | 2026-09 | |
| – | Gemini 3.8 Flash-Lite TTS | — | — | — | $0.25/M | $1.5/M | — | 2026-09 | |
| – | Gemini 3.8 Live | — | $0.75/M | $4.5/M | — | — | — | 2026-09 | |
| – | Gemini 3.8 Live Extended Thinking | — | $0.75/M | $4.5/M | — | — | — | 2026-09 | |
| – | Gemini 4 Argon | 编程通用对话 | $2/M | $10/M | — | — | — | 2026-09 | |
| – | GLiDE | — | $0.3/M | 免费 | — | — | — | 2026-09 | |
| – | GPT-Live-1 | — | — | — | — | — | — | 2026-09 | |
| – | Grok Voice Transcribe 2.0 | — | — | — | — | — | — | 2026-09 | |
| – | MAI-Transcribe-2 | — | — | — | — | — | — | 2026-09 | |
| – | Mercury Voice | — | $0.4/M | $1.5/M | — | — | — | 2026-09 | |
| – | MiniMax M3.1 Flash Preview | — | — | — | — | — | — | 2026-09 | |
| – | Muse Voice Transcribe | — | — | — | — | — | — | 2026-09 | |
| – | North Small Translate | — | — | — | — | — | — | 2026-09 | |
| – | Step 5 Preview | — | $1/M | $2.7/M | $1/M | $2.7/M | 87 tokens/秒 | 2026-09 | |
| – | VibeVoice-ASR-Streaming 1.5B | — | — | — | — | — | — | 2026-09 | |
| – | VibeVoice-ASR-Streaming 7B | — | — | — | — | — | — | 2026-09 | |
| – | Granite 4.2 8B | — | 免费 | 免费 | $0.06/M | $0.25/M | 46 tokens/秒 | 2026-08 | |
| – | Hy4 preview | — | 免费 | 免费 | $0.834/M | $2.501/M | — | 2026-08 | |
| – | Ling 3.0 Flash Fin | — | — | — | $0.042/M | $0.1232/M | — | 2026-08 | |
| – | GLM-5.3-Flash | 编程通用对话数学 / 数据分析Agent 自动化 | 免费 | 免费 | $0.15/M | $0.5/M | — | 2026-08 | |
| – | Hy-MT2-1.8B | — | 免费 | 免费 | $0.044/M | $0.177/M | — | 2026-05 | |
| – | Hy-MT2-30B-A3B | — | 免费 | 免费 | $0.074/M | $0.295/M | — | 2026-05 | |
| – | Qwen3.8-27B | 编程Agent 自动化 | 免费 | 免费 | $0.425/M | $2.55/M | 47 tokens/秒 | 2026-08 | |
| – | Seed 2.1 Turbo | — | — | — | $0.5/M | $2.5/M | — | 2026-06 | |
| – | LFM2.5-2.6B | — | 免费 | 免费 | — | — | 197 tokens/秒 | 2026-08 | |
| – | Muse Glimmer 30B | — | 免费 | 免费 | $0.3/M | $1.2/M | — | 2026-08 | |
| – | Muse Spark 1.2 | 通用对话看图 / 文档理解 | $1.25/M | $4.25/M | $1.25/M | $4.25/M | 154 tokens/秒 | 2026-08 | |
| – | DeepSeek V4 Pro 0813 | 数学 / 数据分析Agent 自动化 | $1.32/M | $3.96/M | $0.2088/M | $0.4176/M | 170 tokens/秒 | 2026-08 | |
| – | AuK | — | — | — | — | — | — | 2026-08 | |
| – | Gemini 3.5 Transcribe | — | — | — | — | — | — | 2026-08 | |
| – | GPT-5.6 Cyber | — | — | — | — | — | — | 2026-08 | |
| – | Granite 4.2 30B | — | 免费 | 免费 | $0.06/M | $0.25/M | — | 2026-08 | |
| – | Granite 4.2 3B | — | 免费 | 免费 | $0.06/M | $0.25/M | — | 2026-08 | |
| – | Granite Speech 5.0 470M TurboCTC | — | — | — | — | — | — | 2026-08 | |
| – | Hy ASR 3.0 preview | — | — | — | — | — | — | 2026-08 | |
| – | LFM2.5-VL-3B | — | 免费 | 免费 | — | — | — | 2026-08 | |
| – | Ling 3.0 Flash FP8 | — | — | — | $0.021/M | $0.063/M | — | 2026-08 | |
| – | Ling 3.0 Tiny | — | 免费 | 免费 | — | — | — | 2026-08 | |
| – | MAI-Code-1.1-Flash | — | — | — | — | — | — | 2026-08 | |
| – | Mercury 2.5 Preview | — | — | — | — | — | 691 tokens/秒 | 2026-08 | |
| – | Nemotron 3.5 Lightning 30B A3B NVFP4 | — | 免费 | 免费 | — | — | — | 2026-08 | |
| – | North Micro Vision Instruct | — | 免费 | 免费 | — | — | — | 2026-08 | |
| – | Qwen3.8-Flash-Next | 编程 | 免费 | 免费 | — | — | 55 tokens/秒 | 2026-08 | |
| – | SeedRealtime | — | — | — | — | — | — | 2026-08 | |
| – | UI-Mate-27B | — | 免费 | 免费 | — | — | — | 2026-08 | |
| – | UI-Mate-9B | — | 免费 | 免费 | — | — | — | 2026-08 | |
| – | Qwen3.7 Flash | — | $0.03/M | $0.13/M | $0.03/M | $0.13/M | — | 2026-07 | |
| – | Ling 3.0 Flash | — | — | — | $0.021/M | $0.063/M | 344 tokens/秒 | 2026-07 | |
| – | Gemini 3.5 Flash-Lite | Agent 自动化 | $0.3/M | $2.5/M | $0.3/M | $2.5/M | 347 tokens/秒 | 2026-07 | |
| – | Gemini 3.6 Flash | 通用对话看图 / 文档理解数学 / 数据分析 | $0.75/M | $3.75/M | $0.75/M | $3.75/M | 197 tokens/秒 | 2026-07 | |
| – | Muse Spark 1.1 | 通用对话 | — | — | $1.25/M | $4.25/M | 217 tokens/秒 | 2026-07 | |
| – | GPT-5.6 Luna | — | $0.2/M | $1.2/M | $0.2/M | $1.2/M | — | 2026-07 | |
| – | GPT-5.6 Terra | 长文档处理 | $2/M | $12/M | $2/M | $12/M | — | 2026-07 | |
| – | Grok 4.5 | — | $2/M | $6/M | $2/M | $6/M | 67 tokens/秒 | 2026-07 | |
| – | Hy3 | — | 免费 | 免费 | $0.132/M | $0.528/M | 88 tokens/秒 | 2026-07 | |
| – | 1-bit Bonsai 27B | — | 免费 | 免费 | — | — | — | 2026-07 | |
| – | Agents-A1-4B | — | 免费 | 免费 | — | — | — | 2026-07 | |
| – | Agents-A1-F16-GGUF | — | — | — | — | — | — | 2026-07 | |
| – | Agents-A1-FP8 | — | — | — | — | — | — | 2026-07 | |
| – | Agents-A1-Q4_K_M-GGUF | — | — | — | — | — | — | 2026-07 | |
| – | Agents-A1-Q8_0-GGUF | — | — | — | — | — | — | 2026-07 | |
| – | Cohere Transcribe Arabic 07-2026 | — | — | — | — | — | — | 2026-07 | |
| – | Cosmos3-Edge | — | 免费 | 免费 | — | — | — | 2026-07 | |
| – | DeepSeek V4 Flash 0731 | — | $0.14/M | $0.28/M | $0.0079/M | $1.28/M | 223 tokens/秒 | 2026-07 | |
| – | Fara1.5-27B | — | 免费 | 免费 | — | — | — | 2026-07 | |
| – | Fara1.5-4B | — | 免费 | 免费 | — | — | — | 2026-07 | |
| – | Gemini 3.5 Flash Cyber | — | — | — | — | — | — | 2026-07 | |
| – | GPT Live Transcribe | — | — | — | — | — | — | 2026-07 | |
| – | GPT Realtime 2.1 | — | $4/M | $24/M | — | — | — | 2026-07 | |
| – | GPT Realtime 2.1 Mini | — | $0.6/M | $2.4/M | — | — | — | 2026-07 | |
| – | GPT Transcribe | — | — | — | — | — | — | 2026-07 | |
| – | Leanstral 1.5 | — | 免费 | 免费 | — | — | — | 2026-07 | |
| – | LLaDA2.2-flash | — | 免费 | 免费 | — | — | — | 2026-07 | |
| – | LLaDA2.2-mini | — | 免费 | 免费 | — | — | — | 2026-07 | |
| – | MAI-Cyber-1-Flash | — | — | — | — | — | — | 2026-07 | |
| – | MAI-Voice-2-Flash | — | — | — | — | — | — | 2026-07 | |
| – | Qwen3.8 Max Preview | — | — | — | — | — | — | 2026-07 | |
| – | Ternary Bonsai 27B | — | 免费 | 免费 | $0.075/M | $0.5/M | — | 2026-07 | |
| – | Claude Sonnet 5 | Agent 自动化 | $2/M | $10/M | $2/M | $10/M | 86 tokens/秒 | 2026-06 | |
| – | North Mini Code | — | 免费 | 免费 | — | — | 83 tokens/秒 | 2026-06 | |
| – | GLM-5.2 | 编程通用对话 | $1.4/M | $4.4/M | $0.06/M | $7/M | 93 tokens/秒 | 2026-06 | |
| – | Kimi K2.7 Code | — | $0.95/M | $4/M | $0.6712/M | $3.35/M | 76 tokens/秒 | 2026-06 | |
| – | Claude Fable 5 | — | $10/M | $50/M | $10/M | $50/M | 65 tokens/秒 | 2026-06 | |
| – | Nemotron 3 Ultra | — | 免费 | 免费 | — | — | — | 2026-06 | |
| – | Qwen3.7 Plus | — | — | — | $0.32/M | $1.28/M | 56 tokens/秒 | 2026-06 | |
| – | Agents-A1 | — | — | — | — | — | — | 2026-06 | |
| – | Claude Mythos 5 | — | $10/M | $50/M | — | — | — | 2026-06 | |
| – | Gemma 4 12B | — | — | — | — | — | — | 2026-06 | |
| – | Holo3.1-0.8B | — | 免费 | 免费 | — | — | — | 2026-06 | |
| – | Holo3.1-35B-A3B | — | $0.25/M | $1.8/M | — | — | — | 2026-06 | |
| – | Holo3.1-35B-A3B-FP8 | — | 免费 | 免费 | — | — | — | 2026-06 | |
| – | Holo3.1-35B-A3B-GGUF | — | 免费 | 免费 | — | — | — | 2026-06 | |
| – | Holo3.1-35B-A3B-NVFP4 | — | 免费 | 免费 | — | — | — | 2026-06 | |
| – | Holo3.1-4B | — | 免费 | 免费 | — | — | — | 2026-06 | |
| – | Holo3.1-9B | — | 免费 | 免费 | — | — | — | 2026-06 | |
| – | LFM2.5-230M | — | 免费 | 免费 | — | — | — | 2026-06 | |
| – | LFM2.5-ColBERT-350M | — | 免费 | 免费 | — | — | — | 2026-06 | |
| – | LFM2.5-Embedding-350M | — | 免费 | 免费 | — | — | — | 2026-06 | |
| – | MAI-Thinking-1 | — | — | — | — | — | — | 2026-06 | |
| – | MAI-Transcribe-1.5 | — | — | — | — | — | — | 2026-06 | |
| – | MAI-Voice-2 | — | — | — | — | — | — | 2026-06 | |
| – | Qwen-AgentWorld-35B-A3B | — | 免费 | 免费 | — | — | — | 2026-06 | |
| – | Qwen3-ASR 0.6B | — | — | — | — | — | — | 2026-06 | |
| – | Qwen3-ASR 1.7B | — | — | — | — | — | — | 2026-06 | |
| – | Seed 2.1 Pro | — | — | — | — | — | — | 2026-06 | |
| – | MiniMax M3 | 数学 / 数据分析 | $0.3/M | $1.2/M | $0.3/M | $1.2/M | 103 tokens/秒 | 2026-06 | |
| – | Step 3.7 Flash | Agent 自动化 | $0.2/M | $1.15/M | $0.2/M | $1.15/M | 172 tokens/秒 | 2026-05 | |
| – | Qwen3.7 Max | 通用对话数学 / 数据分析 | — | — | $1.475/M | $4.425/M | 199 tokens/秒 | 2026-05 | |
| – | Grok Build 0.1 | — | $1/M | $2/M | $1/M | $2/M | — | 2026-05 | |
| – | Gemini 3.5 Flash | 通用对话看图 / 文档理解数学 / 数据分析 | $1.5/M | $9/M | $1.5/M | $9/M | 213 tokens/秒 | 2026-05 | |
| – | Gemini 3.1 Flash-Lite | — | $0.25/M | $1.5/M | $0.25/M | $1.5/M | 286 tokens/秒 | 2026-03 | |
| – | LFM2.5-1.2B-JP-202606 | — | — | — | — | — | — | 2026-05 | |
| – | LFM2.5-8B-A1B | — | 免费 | 免费 | — | — | 335 tokens/秒 | 2026-05 | |
| – | LFM2.5-VL-1.6B-Extract | — | — | — | — | — | — | 2026-05 | |
| – | LFM2.5-VL-450M-Extract | — | — | — | — | — | — | 2026-05 | |
| – | Grok 4.3 | — | $1.25/M | $2.5/M | $1.25/M | $2.5/M | 139 tokens/秒 | 2026-04 | |
| – | Qwen 3.6 Max (preview) | — | — | — | — | — | — | 2026-04 | |
| – | Qwen3.6-27B | — | 免费 | 免费 | $0.32/M | $3.2/M | 56 tokens/秒 | 2026-04 | |
| – | Qwen3.6-35B-A3B | — | — | — | $0.15/M | $1/M | 135 tokens/秒 | 2026-04 | |
| – | GPT-5.5 Pro | — | $30/M | $180/M | $30/M | $180/M | — | 2026-04 | |
| – | Hy3 Preview | — | 免费 | 免费 | $0.18/M | $0.6/M | — | 2026-04 | |
| – | MiMo-V2.5 | — | — | — | $0.14/M | $0.28/M | 62 tokens/秒 | 2026-04 | |
| – | MiMo-V2.5-Pro | — | — | — | $0.435/M | $0.87/M | — | 2026-04 | |
| – | GLM-5.1 | Agent 自动化 | $1.4/M | $4.4/M | $0.966/M | $3.036/M | 59 tokens/秒 | 2026-04 | |
| – | Qwen3.6 Plus | — | — | — | $0.325/M | $1.95/M | 56 tokens/秒 | 2026-04 | |
| – | GLM-5V-Turbo | — | $1.2/M | $4/M | $1.2/M | $4/M | — | 2026-03 | |
| – | Claude Mythos Preview | — | $25/M | $125/M | — | — | — | 2026-04 | |
| – | Claude Opus 4.7 (Adaptive) | — | $5/M | $25/M | — | — | — | 2026-04 | |
| – | Gemini 3.1 Flash TTS Preview | — | — | — | $0.5/M | $3/M | — | 2026-04 | |
| – | Gemma 4 26B A4B | — | 免费 | 免费 | 免费 | 免费 | — | 2026-04 | |
| – | Gemma 4 31B | — | 免费 | 免费 | 免费 | 免费 | 36 tokens/秒 | 2026-04 | |
| – | Gemma 4 E2B | — | 免费 | 免费 | — | — | — | 2026-04 | |
| – | Gemma 4 E4B | — | 免费 | 免费 | — | — | — | 2026-04 | |
| – | GPT Audio 1.5 | — | $2.5/M | $10/M | $2.5/M | $10/M | — | 2026-04 | |
| – | Grok TTS | — | — | — | — | — | — | 2026-04 | |
| – | Kimi K2.6 | — | $0.95/M | $4/M | $0.465/M | $2.45/M | 59 tokens/秒 | 2026-04 | |
| – | LFM2.5-VL-450M | — | 免费 | 免费 | — | — | — | 2026-04 | |
| – | Ling 2.6 Flash | — | — | — | — | — | 104 tokens/秒 | 2026-04 | |
| – | Mistral Medium 3.5 128B | — | $1.5/M | $7.5/M | $0.4/M | $2/M | — | 2026-04 | |
| – | Muse Spark | 通用对话看图 / 文档理解 | — | — | $1.25/M | $4.25/M | — | 2026-04 | |
| – | Nemotron 3 Nano Omni 30B A3B | — | 免费 | 免费 | $0.06/M | $0.24/M | 268 tokens/秒 | 2026-04 | |
| – | Ternary Bonsai 1.7B | — | 免费 | 免费 | $0.075/M | $0.5/M | — | 2026-04 | |
| – | Ternary Bonsai 4B | — | 免费 | 免费 | $0.075/M | $0.5/M | — | 2026-04 | |
| – | Ternary Bonsai 8B | — | 免费 | 免费 | $0.075/M | $0.5/M | — | 2026-04 | |
| – | Grok 4.20 | — | $1.25/M | $2.5/M | $1.25/M | $2.5/M | 123 tokens/秒 | 2026-03 | |
| – | MiniMax M2.7 | — | $0.3/M | $1.2/M | $0.21/M | $0.84/M | 76 tokens/秒 | 2026-03 | |
| – | GPT-5.4 mini | — | $0.75/M | $4.5/M | $0.75/M | $4.5/M | 201 tokens/秒 | 2026-03 | |
| – | GPT-5.4 nano | — | $0.2/M | $1.25/M | $0.2/M | $1.25/M | 191 tokens/秒 | 2026-03 | |
| – | Mistral Small 4 (Reasoning) | — | $0.15/M | $0.6/M | — | — | — | 2026-02 | |
| – | GLM-5-Turbo | — | $1.2/M | $4/M | $1.2/M | $4/M | — | 2026-03 | |
| – | Nemotron 3 Super 120B A12B | — | 免费 | 免费 | 免费 | 免费 | 153 tokens/秒 | 2026-01 | |
| – | Seed-2.0-Lite | — | — | — | $0.25/M | $2/M | — | 2026-03 | |
| – | GPT-5.4 | 通用对话看图 / 文档理解数学 / 数据分析Agent 自动化 | $2.5/M | $15/M | $2.5/M | $15/M | 101 tokens/秒 | 2026-03 | |
| – | GPT-5.4 Pro | — | $30/M | $180/M | $30/M | $180/M | 74 tokens/秒 | 2026-03 | |
| – | Mercury 2 | — | $0.25/M | $0.75/M | $0.25/M | $0.75/M | 682 tokens/秒 | 2026-02 | |
| – | 1-bit Bonsai 1.7B | — | 免费 | 免费 | — | — | — | 2026-03 | |
| – | 1-bit Bonsai 4B | — | 免费 | 免费 | — | — | — | 2026-03 | |
| – | 1-bit Bonsai 8B | — | 免费 | 免费 | — | — | — | 2026-03 | |
| – | GPT-5.3 Instant | — | $1.75/M | $14/M | — | — | — | 2026-03 | |
| – | Grok 4.20 Multi-agent | — | — | — | $1.25/M | $2.5/M | — | 2026-03 | |
| – | Holo3-122B-A10B | — | $0.4/M | $3/M | — | — | — | 2026-03 | |
| – | Holo3-35B-A3B | — | — | — | — | — | — | 2026-03 | |
| – | Leanstral | — | 免费 | 免费 | — | — | — | 2026-03 | |
| – | LFM2.5-1.2B-Instruct | — | 免费 | 免费 | — | — | — | 2026-03 | |
| – | LFM2.5-1.2B-Thinking | — | 免费 | 免费 | — | — | — | 2026-03 | |
| – | LFM2.5-350M | — | 免费 | 免费 | — | — | — | 2026-03 | |
| – | Mercury Edit 2 | — | $0.25/M | $0.75/M | — | — | — | 2026-03 | |
| – | MiMo-V2-Flash | — | 免费 | 免费 | $0.14/M | $0.28/M | 129 tokens/秒 | 2026-03 | |
| – | MiMo-V2-Omni | — | — | — | — | — | — | 2026-03 | |
| – | MiMo-V2-Pro | — | — | — | $0.435/M | $0.87/M | — | 2026-03 | |
| – | Seed-2.0-Mini | — | — | — | $0.1/M | $0.4/M | — | 2026-03 | |
| – | Qwen3.5 Flash | — | $0.1/M | $0.4/M | $0.1875/M | $1.125/M | — | 2026-03 | |
| – | Qwen3.5-122B-A10B | Agent 自动化 | 免费 | 免费 | $0.26/M | $2.08/M | 129 tokens/秒 | 2026-03 | |
| – | Qwen3.5-27B | — | 免费 | 免费 | $0.26/M | $2.6/M | 77 tokens/秒 | 2026-03 | |
| – | Qwen3.5-35B-A3B | — | 免费 | 免费 | $0.08/M | $0.75/M | 147 tokens/秒 | 2026-03 | |
| – | GPT-5.3 Codex | Agent 自动化 | $1.75/M | $14/M | $1.75/M | $14/M | 105 tokens/秒 | 2026-02 | |
| – | Claude Sonnet 4.6 | 长文档处理 | $3/M | $15/M | $3/M | $15/M | 49 tokens/秒 | 2026-02 | |
| – | Qwen3.5 Plus | — | $0.4/M | $2.4/M | $0.325/M | $1.95/M | — | 2026-03 | |
| – | MiniMax M2.5 | — | $0.3/M | $1.2/M | $0.27/M | $1.08/M | 106 tokens/秒 | 2025-10 | |
| – | GLM-5 | Agent 自动化 | $1/M | $3.2/M | $0.6/M | $1.92/M | 78 tokens/秒 | 2026-03 | |
| – | GLM-5 (Reasoning) | — | $1/M | $3.2/M | — | — | — | 2026-03 | |
| – | Claude Opus 4.6 | 通用对话看图 / 文档理解长文档处理 | $5/M | $25/M | $5/M | $25/M | 42 tokens/秒 | 2026-02 | |
| – | Claude Opus 4.6 (Adaptive) | — | — | — | — | — | — | 2026-02 | |
| – | ElevenLabs Eleven v3 | — | — | — | — | — | — | 2026-02 | |
| – | ElevenLabs Eleven v3 Conversational | — | — | — | — | — | — | 2026-02 | |
| – | Gemini 3 Pro Deep Think | — | — | — | — | — | — | 2026-02 | |
| – | Gemini 3.1 Pro | 通用对话 | $2/M | $12/M | — | — | 125 tokens/秒 | 2026-02 | |
| – | GPT Realtime 1.5 | — | $4/M | $16/M | — | — | — | 2026-02 | |
| – | GPT-5.3-Codex-Spark | — | — | — | — | — | — | 2026-02 | |
| – | Llama 4 Behemoth | — | 免费 | 免费 | — | — | — | 2026-02 | |
| – | Mistral Small 4 | — | $0.15/M | $0.6/M | — | — | 178 tokens/秒 | 2026-02 | |
| – | Nemotron Ultra 253B | — | 免费 | 免费 | — | — | — | 2026-02 | |
| – | Qwen3.5 397B | — | $0.6/M | $3.6/M | $0.1/M | $0.15/M | 90 tokens/秒 | 2026-02 | |
| – | Qwen3.5 397B (Reasoning) | — | $0.6/M | $3.6/M | — | — | — | 2026-02 | |
| – | Step 3.5 Flash | — | $0.1/M | $0.3/M | $0.1/M | $0.3/M | 136 tokens/秒 | 2026-01 | |
| – | Kimi K2.5 | — | $0.6/M | $3/M | $0.45/M | $2.25/M | 82 tokens/秒 | 2026-02 | |
| – | Kimi K2.5 (Reasoning) | — | $0.6/M | $3/M | — | — | — | 2026-02 | |
| – | GLM-4.7-Flash | — | 免费 | 免费 | $0.0605/M | $0.4/M | 81 tokens/秒 | 2025-10 | |
| – | GPT-5.2-Codex | — | $1.75/M | $14/M | $1.75/M | $14/M | 123 tokens/秒 | 2025-12 | |
| – | LFM2-24B-A2B | — | 免费 | 免费 | — | — | 92 tokens/秒 | 2026-01 | |
| – | MiniMax Speech 2.8 HD | — | — | — | — | — | — | 2026-01 | |
| – | Nemotron 3 Nano 30B | — | 免费 | 免费 | $0.06/M | $0.24/M | 172 tokens/秒 | 2026-01 | |
| – | Nemotron 3 Super 100B | — | 免费 | 免费 | 免费 | 免费 | 153 tokens/秒 | 2026-01 | |
| – | Seed 1.6 | — | — | — | $0.25/M | $2/M | — | 2025-06 | |
| – | Seed 1.6 Flash | — | — | — | $0.075/M | $0.3/M | — | 2025-06 | |
| – | GLM-4.7 | — | 免费 | 免费 | $0.6/M | $2.2/M | 45 tokens/秒 | 2025-10 | |
| – | GPT-5.2 | — | $1.75/M | $14/M | $1.75/M | $14/M | 91 tokens/秒 | 2025-12 | |
| – | GPT-5.2 Pro | — | $21/M | $168/M | $21/M | $168/M | — | 2025-12 | |
| – | GPT-5.1-Codex-Max | — | $1.25/M | $10/M | $1.25/M | $10/M | — | 2025-11 | |
| – | Ministral 3 14B | — | $0.2/M | $0.2/M | — | — | 89 tokens/秒 | 2025-12 | |
| – | Ministral 3 3B | — | $0.1/M | $0.1/M | — | — | 233 tokens/秒 | 2025-12 | |
| – | Ministral 3 8B | — | $0.15/M | $0.15/M | — | — | 101 tokens/秒 | 2025-12 | |
| – | DeepSeek V3.2 | — | $0.28/M | $0.42/M | $0.259/M | $0.42/M | 35 tokens/秒 | 2025-12 | |
| – | DeepSeek V3.2 (Thinking) | — | $0.55/M | $2.19/M | — | — | — | 2025-12 | |
| – | Gemini 2.5 Flash Native Audio Preview (12-2025) | — | — | — | — | — | — | 2025-12 | |
| – | Gemini 3 Flash | — | $0.5/M | $3/M | $1.5/M | $9/M | 201 tokens/秒 | 2025-12 | |
| – | GPT-5.2 Instant | — | $1.5/M | $6/M | — | — | — | 2025-12 | |
| – | Ministral 3 14B (Reasoning) | — | $0.2/M | $0.2/M | — | — | — | 2025-12 | |
| – | Ministral 3 3B (Reasoning) | — | $0.1/M | $0.1/M | — | — | — | 2025-12 | |
| – | Ministral 3 8B (Reasoning) | — | $0.15/M | $0.15/M | — | — | — | 2025-12 | |
| – | Claude Opus 4.5 | — | $5/M | $25/M | $5/M | $25/M | 50 tokens/秒 | 2025-11 | |
| – | GPT-5.1 | Agent 自动化 | $1.25/M | $10/M | $1.25/M | $10/M | 142 tokens/秒 | 2025-11 | |
| – | GPT-5.1-Codex | — | $1.25/M | $10/M | $1.25/M | $10/M | — | 2025-10 | |
| – | Claude Opus 4.5 Thinking | — | — | — | — | — | — | 2025-11 | |
| – | Gemini 3 Pro | 通用对话看图 / 文档理解 | $2/M | $12/M | $1.25/M | $10/M | 109 tokens/秒 | 2025-11 | |
| – | Grok 4.1 | — | — | — | — | — | — | 2025-11 | |
| – | Grok 4.1 Fast | — | $0.2/M | $0.5/M | — | — | 138 tokens/秒 | 2025-11 | |
| – | Grok 4.1 Fast (Reasoning) | — | — | — | — | — | — | 2025-11 | |
| – | Claude Haiku 4.5 | — | $1/M | $5/M | $1/M | $5/M | — | 2025-10 | |
| – | Claude Haiku 4.5 Thinking | — | — | — | — | — | — | 2025-10 | |
| – | Granite-4.0-1B | — | 免费 | 免费 | — | — | — | 2025-10 | |
| – | Granite-4.0-350M | — | 免费 | 免费 | — | — | — | 2025-10 | |
| – | Granite-4.0-H-1B | — | 免费 | 免费 | — | — | — | 2025-10 | |
| – | Granite-4.0-H-350M | — | 免费 | 免费 | — | — | — | 2025-10 | |
| – | GLM-4.6 | — | — | — | $0.5/M | $2/M | 37 tokens/秒 | 2025-09 | |
| – | Claude Sonnet 4.5 | — | $3/M | $15/M | $3/M | $15/M | — | 2025-09 | |
| – | Qwen3 Max | — | — | — | $1.475/M | $4.425/M | 64 tokens/秒 | 2026-04 | |
| – | Claude Sonnet 4.5 Thinking | — | — | — | — | — | — | 2025-09 | |
| – | Grok 4 Fast (Reasoning) | — | — | — | — | — | — | 2025-09 | |
| – | Qwen3-Omni-30B-A3B-Instruct | — | — | — | $0.15/M | $0.6/M | 96 tokens/秒 | 2025-09 | |
| – | Qwen3-Omni-30B-A3B-Thinking | — | — | — | $0.29/M | $1/M | — | 2025-09 | |
| – | DeepSeek V3.1 | — | 免费 | 免费 | $0.259/M | $0.42/M | — | 2025-08 | |
| – | GPT-5 (high) | — | $1.25/M | $10/M | — | — | 98 tokens/秒 | 2025-08 | |
| – | GPT-5 mini | — | $0.25/M | $2/M | $0.25/M | $2/M | 86 tokens/秒 | 2025-08 | |
| – | GPT-5 nano | — | $0.05/M | $0.4/M | $0.05/M | $0.4/M | 137 tokens/秒 | 2025-08 | |
| – | GPT-OSS 120B | — | 免费 | 免费 | $0.037/M | $0.17/M | 197 tokens/秒 | 2025-08 | |
| – | GPT-OSS 20B | — | 免费 | 免费 | $0.018/M | $0.09/M | 313 tokens/秒 | 2025-08 | |
| – | Claude 4.1 Opus | — | $15/M | $75/M | $5/M | $25/M | 29 tokens/秒 | 2025-08 | |
| – | Claude 4.1 Opus Thinking | — | — | — | — | — | 29 tokens/秒 | 2025-08 | |
| – | DeepSeek V3.1 (Reasoning) | — | 免费 | 免费 | — | — | — | 2025-08 | |
| – | GPT-5 (medium) | — | — | — | — | — | 83 tokens/秒 | 2025-08 | |
| – | Grok Code Fast 1 | — | $0.2/M | $1.5/M | — | — | 172 tokens/秒 | 2025-08 | |
| – | GLM-4.5 | — | $0.6/M | $2.2/M | $0.6/M | $2.2/M | 51 tokens/秒 | 2025-06 | |
| – | GLM-4.5-Air | — | $0.2/M | $1.1/M | $0.13/M | $0.85/M | 69 tokens/秒 | 2025-06 | |
| – | Kimi K2 | — | $0.6/M | $2.5/M | $0.57/M | $2.3/M | 54 tokens/秒 | 2025-07 | |
| – | Audio Flamingo 3 7B | — | — | — | — | — | — | 2025-07 | |
| – | Grok 4 | — | — | — | $1.25/M | $2.5/M | 54 tokens/秒 | 2025-07 | |
| – | Qwen3 235B 2507 | — | 免费 | 免费 | $0.09/M | $0.55/M | — | 2025-07 | |
| – | Qwen3 235B 2507 (Reasoning) | — | 免费 | 免费 | — | — | — | 2025-07 | |
| – | Gemini 2.5 Flash | — | $0.3/M | $2.5/M | $0.3/M | $2.5/M | 186 tokens/秒 | 2025-06 | |
| – | Gemini 2.5 Pro | — | $1.25/M | $10/M | $1.25/M | $10/M | 136 tokens/秒 | 2025-03 | |
| – | MiniMax M1 80k | — | — | — | $0.55/M | $2.2/M | — | 2025-01 | |
| – | o3-pro | — | $20/M | $80/M | $20/M | $80/M | 27 tokens/秒 | 2025-04 | |
| – | Mistral Medium 3 | — | $0.4/M | $2/M | $0.4/M | $2/M | 152 tokens/秒 | 2026-02 | |
| – | Claude 4 Sonnet | — | $3/M | $15/M | $3/M | $15/M | 40 tokens/秒 | 2025-05 | |
| – | Gemini 2.5 Flash TTS Preview | — | — | — | $0.5/M | $3/M | — | 2025-05 | |
| – | Gemini 2.5 Pro TTS Preview | — | — | — | $1.25/M | $10/M | — | 2025-05 | |
| – | o3 | — | $2/M | $8/M | $2/M | $8/M | 137 tokens/秒 | 2025-04 | |
| – | o4-mini (high) | — | — | — | $1.1/M | $4.4/M | 145 tokens/秒 | 2025-04 | |
| – | GPT-4.1 | — | $2/M | $8/M | $2/M | $8/M | 165 tokens/秒 | 2025-04 | |
| – | GPT-4.1 mini | — | $0.4/M | $1.6/M | $0.4/M | $1.6/M | 80 tokens/秒 | 2025-04 | |
| – | GPT-4.1 nano | — | $0.1/M | $0.4/M | $0.1/M | $0.4/M | 181 tokens/秒 | 2025-04 | |
| – | Llama 4 Maverick | — | 免费 | 免费 | $0.1875/M | $0.6525/M | 66 tokens/秒 | 2026-02 | |
| – | Llama 4 Scout | — | 免费 | 免费 | $0.1/M | $0.3/M | 68 tokens/秒 | 2026-02 | |
| – | Kimi-Audio 7B | — | — | — | — | — | — | 2025-04 | |
| – | DeepSeek V3 | — | $0.27/M | $1.1/M | $0.259/M | $0.42/M | — | 2024-12 | |
| – | DeepSeek V3 0324 | — | — | — | $0.259/M | $0.42/M | — | 2025-03 | |
| – | o1-pro | — | $150/M | $600/M | $150/M | $600/M | — | 2024-12 | |
| – | Gemma 3 27B | — | 免费 | 免费 | $0.08/M | $0.45/M | 31 tokens/秒 | 2025-03 | |
| – | GPT-4o mini TTS | — | $0.6/M | $12/M | $0.15/M | $0.6/M | — | 2025-03 | |
| – | Phi-4 Multimodal Instruct | — | — | — | — | — | 17 tokens/秒 | 2025-03 | |
| – | Qwen2.5-Omni 7B | — | — | — | — | — | — | 2025-03 | |
| – | Grok 3 [Beta] | — | — | — | — | — | — | 2025-02 | |
| – | Grok 3 Mini | — | $0.3/M | $0.5/M | — | — | 83 tokens/秒 | 2025-02 | |
| – | Step-Audio | — | — | — | — | — | — | 2025-02 | |
| – | o3-mini | — | $1.1/M | $4.4/M | $1.1/M | $4.4/M | 160 tokens/秒 | 2025-01 | |
| – | DeepSeek-R1 | — | $0.55/M | $2.19/M | $0.7/M | $2.5/M | — | 2025-01 | |
| – | Phi-4 | — | 免费 | 免费 | $0.07/M | $0.14/M | 40 tokens/秒 | 2025-01 | |
| – | DeepSeek R1 Distill Qwen 32B | — | 免费 | 免费 | — | — | 60 tokens/秒 | 2025-01 | |
| – | Qwen2.5 Coder 32B Instruct | — | 免费 | 免费 | $0.66/M | $1/M | — | 2025-01 | |
| – | Qwen2.5-1M | — | 免费 | 免费 | — | — | — | 2025-01 | |
| – | Qwen2.5-VL-32B | — | 免费 | 免费 | — | — | — | 2025-01 | |
| – | o1 | — | $15/M | $60/M | $15/M | $60/M | 98 tokens/秒 | 2024-12 | |
| – | GLM-4-Voice | — | — | — | — | — | — | 2024-12 | |
| – | o1-preview | — | $15/M | $60/M | — | — | — | 2024-09 | |
| – | Qwen2.5-72B | — | 免费 | 免费 | — | — | — | 2024-09 | |
| – | GPT-4o mini | — | $0.15/M | $0.6/M | $0.15/M | $0.6/M | 33 tokens/秒 | 2024-07 | |
| – | Llama 3.1 405B | — | 免费 | 免费 | — | — | 29 tokens/秒 | 2024-07 | |
| – | Mistral Large 2 | — | — | — | $2/M | $6/M | 38 tokens/秒 | 2024-07 | |
| – | Qwen2-Audio 7B Instruct | — | — | — | — | — | — | 2024-07 | |
| – | Claude 3.5 Sonnet | — | $3/M | $15/M | $3/M | $15/M | — | 2024-06 | |
| – | GPT-4o | — | $2.5/M | $10/M | $2.5/M | $10/M | 151 tokens/秒 | 2024-05 | |
| – | GPT-4 Turbo | — | $10/M | $30/M | $10/M | $30/M | 32 tokens/秒 | 2023-11 | |
| – | Llama 3 70B | — | 免费 | 免费 | — | — | — | 2024-04 | |
| – | Claude 3 Haiku | — | $0.25/M | $1.25/M | $1/M | $5/M | 138 tokens/秒 | 2024-03 | |
| – | Claude 3 Opus | — | $15/M | $75/M | $5/M | $25/M | — | 2024-03 | |
| – | Mistral Large 3 | — | $0.5/M | $1.5/M | $2/M | $6/M | 83 tokens/秒 | 2025-12 | |
| – | Gemini 1.5 Pro | — | $1.25/M | $5/M | $1.25/M | $10/M | — | 2024-02 | |
| – | Voxtral 4B TTS 2603 待核实 | — | — | — | — | — | — | — | |
| – | Voxtral Mini 4B Realtime 2602 待核实 | — | — | — | — | — | — | — | |
| – | Whisper large-v3-turbo 待核实 | — | — | — | — | — | — | — | |
| – | Claude Haiku 5.5 | — | $0.1/M | $0.5/M | $0.1/M | $0.5/M | — | — | |
| – | Alibaba GTE Reranker ModernBERT-base | — | — | — | — | — | — | — | |
| – | Canary 180M Flash | — | — | — | — | — | — | — | |
| – | Cohere Transcribe 03-2026 | — | — | — | — | — | — | — | |
| – | d1 | — | — | — | — | — | — | — | |
| – | DeepSeek Coder 2.0 | — | — | — | — | — | — | — | |
| – | DeepSeek LLM 2.0 | — | 免费 | 免费 | — | — | — | — | |
| – | DeepSeekMath V2 | — | 免费 | 免费 | — | — | — | — | |
| – | Gemini 1.0 Pro | — | — | — | — | — | — | — | |
| – | Gemini 3.1 Flash Live Preview | — | — | — | $0.25/M | $1.5/M | — | — | |
| – | GLiNER2 large | — | — | — | — | — | — | — | |
| – | GLiNER2.5 base | — | — | — | — | — | — | — | |
| – | GLiNER2.5 multi | — | — | — | — | — | — | — | |
| – | GLiNER2.5 small | — | — | — | — | — | — | — | |
| – | GLM Realtime Air | — | — | — | — | — | — | — | |
| – | GLM Realtime Flash | — | — | — | — | — | — | — | |
| – | GPT Realtime | — | $4/M | $16/M | — | — | — | — | |
| – | GPT Realtime 2 | — | $4/M | $24/M | — | — | — | — | |
| – | GPT Realtime mini | — | $0.6/M | $2.4/M | — | — | — | — | |
| – | GPT-4o Audio | — | $2.5/M | $10/M | $2.5/M | $10/M | — | — | |
| – | GPT-4o mini Audio | — | $0.15/M | $0.6/M | — | — | — | — | |
| – | GPT-5.6 Luna (low) | — | — | — | $0.2/M | $1.2/M | — | — | |
| – | GPT-6 Luna (low) | — | — | — | — | — | — | — | |
| – | GPT-6 Luna (medium) | — | — | — | — | — | — | — | |
| – | Grok Realtime | — | — | — | — | — | — | — | |
| – | Grok Voice Think Fast 1.0 | — | — | — | — | — | — | — | |
| – | Grok Voice Think Fast 2.0 | — | — | — | — | — | — | — | |
| – | Holo2-235B-A22B | — | — | — | — | — | — | — | |
| – | Holo2-30B-A3B | — | — | — | — | — | — | — | |
| – | Holo2-4B | — | — | — | — | — | — | — | |
| – | Holo2-8B | — | — | — | — | — | — | — | |
| – | Holotron-12B | — | — | — | — | — | — | — | |
| – | MiniMax Speech-02 HD | — | — | — | — | — | — | — | |
| – | Mistral 7B v0.3 | — | 免费 | 免费 | — | — | — | — | |
| – | Mistral 8x7B | — | 免费 | 免费 | — | — | — | — | |
| – | Mistral 8x7B v0.2 | — | 免费 | 免费 | — | — | — | — | |
| – | Mixtral 8x22B Instruct v0.1 | — | 免费 | 免费 | $2/M | $6/M | — | — | |
| – | Moonshot v1 | — | — | — | — | — | — | — | |
| – | Nemotron 3.5 ASR Streaming 0.6B | — | — | — | — | — | — | — | |
| – | Nemotron-4 15B | — | 免费 | 免费 | — | — | — | — | |
| – | Parakeet CTC 1.1B | — | — | — | — | — | — | — | |
| – | Parakeet TDT 0.6B v3 | — | — | — | — | — | — | — | |
| – | Qwen-Audio 7B | — | — | — | — | — | — | — | |
| – | Qwen-Audio-Chat 7B | — | — | — | — | — | — | — | |
| – | Qwen3-Reranker-4B | — | — | — | — | — | — | — | |
| – | Qwen3.8-27B (Chutes TEE) | — | — | — | — | — | — | — | |
| – | Qwen4 27B | — | — | — | — | — | — | — | |
| – | Qwen4 Flash & Plus | — | — | — | — | — | — | — | |
| – | Qwen4 Max | — | — | — | — | — | — | — | |
| – | Raw Phi-4 mini direct logits | — | — | — | — | — | — | — | |
| – | Raw Qwen3 0.6B direct logits | — | — | — | — | — | — | — | |
| – | Raw Qwen3 1.7B direct logits | — | — | — | — | — | — | — | |
| – | Raw Qwen3 4B Instruct 2507 direct logits | — | — | — | — | — | — | — | |
| – | Raw Qwen3 8B direct logits | — | — | — | — | — | — | — | |
| – | Scribe v2.2 Realtime | — | — | — | — | — | — | — | |
| – | Step-Audio-Chat 130B | — | — | — | — | — | — | — | |
| – | Ultravox GLM-4P6 | — | — | — | — | — | — | — | |
| – | Ultravox GLM-4P7 | — | — | — | — | — | — | — | |
| – | Ultravox v0.4.1 Llama 3.1 8B | — | — | — | — | — | — | — | |
| – | Ultravox v0.5 Llama 3.1 8B | — | — | — | — | — | — | — | |
| – | Ultravox v0.5 Llama 3.2 1B | — | — | — | — | — | — | — | |
| – | Ultravox v0.6 Llama 3.3 70B | — | — | — | — | — | — | — | |
| – | Ultravox v0.7 | — | — | — | — | — | — | — |