blog••
0
大模型 API 生态日报 —— 2026-11-21
无人值守每日汇总大模型 API 生态:4 条发布动态、2 个新模型、19 项价格变动与 1 条社区热议。
一、今日速览
- 覆盖模型:476
- 新增模型:2
- 价格变动:19
- 社区信号:1
本篇日报由 AINode 无人值守内容引擎自动生成,信源包括公开模型库、GitHub 官方发布与开发者社区讨论。
二、新增模型
| 模型 ID | 厂商 | 上下文 | 输入 /1M | 输出 /1M |
|---|---|---|---|---|
thinkingmachines/inkling-2-mini |
thinkingmachines | 1.0M | $0.100 | $0.400 |
radixark/daisyrose-27b |
radixark | 262K | $0.150 | $1.88 |
三、价格变动
nvidia/nemotron-3.5-super-vl输出 $0.500 → $0.470 (−6%)~deepseek/deepseek-pro-latest输入 $0.119 → $0.100 (−16%)deepseek/deepseek-v4.1-flash输入 $0.300 → $0.050 (−83%)deepseek/deepseek-v4.1-flash输出 $1.20 → $0.199 (−83%)deepseek/deepseek-v4-flash-vision-exp输入 $0.440 → $0.216 (−51%)deepseek/deepseek-v4-flash-vision-exp输出 $1.32 → $0.647 (−51%)google/gemma-4-26b-a4b-it输入 $0.090 → $0.068 (−25%)google/gemma-4-26b-a4b-it输出 $0.300 → $0.225 (−25%)minimax/minimax-m2.7输入 $0.210 → $0.600 (+186%)minimax/minimax-m2.7输出 $0.840 → $1.80 (+114%)minimax/minimax-m2.5输入 $0.295 → $0.270 (−8%)minimax/minimax-m2.5输出 $1.20 → $0.950 (−21%)
四、官方与开源发布动态
- ollama/ollama v0.40.17:v0.40.17
- ollama launch claude supports Claude Code's deferred tool loading, so MCP tools are loaded when needed instead of all at once
- Ollama on Apple silicon now serves multiple requests at once.
- ollama launch opencode sets thinking options from the model's metadata
- ollama launch pi refreshes Pi's model list after sign-in and passes along prompt arguments
- vllm-project/vllm v0.34.0:v0.34.0
- 10 new models (Mistral Large 4, MiniMax-M3.1-Flash, Nemotron-3.5-Transcribe, and more!)
- Extensible KV cache is on by default: vLLM sizes the KV cache from memory actually free after warmup, so most models get a bigger cache and more throughput - in most cases you should now remove gpu_memory_utilization from your configs.
- Model Runner V1 is gone. Model Runner V2 is now the only GPU runner.
- Big speedups on Blackwell and MI355X: up to 1.95× decode (Step5 on GB200), 1.6× throughput (GLM-5.3-Flash), 1.24–1.40× faster long-prompt TTFT (GLM-5.3).
- deepseek-ai/DeepSeek-V3 v1.0.0:v1.0.0 查看发布 ↗
- meta-llama/llama-models v0.2.0:v0.2.0 查看发布 ↗
五、社区热议
六、网关小贴士
统一 OpenAI 兼容入口与单一密钥,跨厂商做故障转移、Token 计量与按模型计费,无需逐个对接厂商 SDK。