blog••
0
AI model ecosystem briefing — 2026-11-21
Unattended daily digest of the LLM API landscape: 4 releases, 2 new models, 19 pricing updates and 1 community signal.
1. Today at a glance
- Models tracked: 476
- New models: 2
- Pricing updates: 19
- Community signals: 1
This briefing is generated by the unattended AINode content engine from public model catalogs, GitHub releases and developer community discussions.
2. New models
| Model ID | Provider | Context | Input /1M | Output /1M |
|---|---|---|---|---|
thinkingmachines/inkling-2-mini |
thinkingmachines | 1.0M | $0.100 | $0.400 |
radixark/daisyrose-27b |
radixark | 262K | $0.150 | $1.88 |
3. Pricing updates
nvidia/nemotron-3.5-super-vloutput $0.500 → $0.470 (−6%)~deepseek/deepseek-pro-latestinput $0.119 → $0.100 (−16%)deepseek/deepseek-v4.1-flashinput $0.300 → $0.050 (−83%)deepseek/deepseek-v4.1-flashoutput $1.20 → $0.199 (−83%)deepseek/deepseek-v4-flash-vision-expinput $0.440 → $0.216 (−51%)deepseek/deepseek-v4-flash-vision-expoutput $1.32 → $0.647 (−51%)google/gemma-4-26b-a4b-itinput $0.090 → $0.068 (−25%)google/gemma-4-26b-a4b-itoutput $0.300 → $0.225 (−25%)minimax/minimax-m2.7input $0.210 → $0.600 (+186%)minimax/minimax-m2.7output $0.840 → $1.80 (+114%)minimax/minimax-m2.5input $0.295 → $0.270 (−8%)minimax/minimax-m2.5output $1.20 → $0.950 (−21%)
4. Official & open-source releases
- 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 View release ↗
- meta-llama/llama-models v0.2.0:v0.2.0 View release ↗
5. Community pulse
- Show HN: I "invented" Model-as-a-Service for 95% Predictable Private AI (2 points · 0 comments)
6. Gateway tip
Keep one OpenAI-compatible endpoint and one key across providers. Route failover, meter tokens and bill by model without touching provider SDKs.