feat: update model specs and API family table

README.md

@@ -15,34 +15,36 @@ pipeline_tag: text-generation
 
 # Zen4 Coder Flash
 
-**Zen4 Coder Flash** is a 31B MoE (3B active) parameter language model from the [Zen4 family](https://zenlm.org) by [Zen LM](https://huggingface.co/zenlm) and [Hanzo AI](https://hanzo.ai).
+**Zen4 Coder Flash** is a fast code-specialized language model from the [Zen4 family](https://zenlm.org) by [Zen LM](https://huggingface.co/zenlm) and [Hanzo AI](https://hanzo.ai).
 
 Built on abliterated (uncensored) weights from GLM-4.7-Flash for unrestricted, open-ended AI assistance.
 
+**API**: Via `api.hanzo.ai`, zen4-coder-flash routes to Qwen3-Coder-30B-A3B (30B MoE, 3B active, 262K context).
+
 ## Model Details
 
 | Property | Value |
 |----------|-------|
-| **Parameters** | 31B MoE total, 3B active |
-| **Context** | 131K tokens |
-| **Base** | GLM-4.7-Flash (abliterated) |
-| **License** | mit |
+| **Local Weights** | GLM-4.7-Flash (abliterated, 31B MoE, 3B active) |
+| **API Upstream** | Qwen3-Coder-30B-A3B (30B MoE, 3B active) |
+| **Context** | 262K tokens |
+| **License** | MIT |
 | **Family** | Zen4 |
 | **Creator** | Zen LM / Hanzo AI |
 
 ## Zen4 Family
 
-| Tier | Model | Params | Active | Context |
-|------|-------|--------|--------|---------|
-| Edge | [Zen4 Mini](https://huggingface.co/zenlm/zen4-mini) | 4B | 4B | 32K |
-| Standard | [Zen4](https://huggingface.co/zenlm/zen4) | 8B | 8B | 32K |
-| Professional | [Zen4 Pro](https://huggingface.co/zenlm/zen4-pro) | 14B | 14B | 32K |
-| Flagship | [Zen4 Max](https://huggingface.co/zenlm/zen4-max) | 30B MoE | 3B | 256K |
-| Ultimate | [Zen4 Max Pro](https://huggingface.co/zenlm/zen4-max-pro) | 80B MoE | 3B | 256K |
-| Code (Fast) | [Zen4 Coder Flash](https://huggingface.co/zenlm/zen4-coder-flash) | 31B MoE | 3B | 131K |
-| Code (Best) | [Zen4 Coder](https://huggingface.co/zenlm/zen4-coder) | 80B MoE | 3B | 256K |
-| Code (Cloud) | [Zen4 Coder Pro](https://huggingface.co/zenlm/zen4-coder-pro) | 355B | 355B | 200K |
-| Cloud | [Zen4 Ultra](https://huggingface.co/zenlm/zen4-ultra) | 1.04T MoE | 32B | 256K |
+### API Models (api.hanzo.ai)
+
+| Model | Upstream | Params | Active | Context |
+|-------|----------|--------|--------|---------|
+| zen4 | GLM-5 | 744B MoE | 40B | 205K |
+| zen4-max | Kimi K2-Thinking | 1.04T MoE | 32B | 256K |
+| zen4-ultra | GLM-5 (thinking) | 744B MoE | 40B | 205K |
+| zen4-pro | Qwen3-Next-80B-A3B | 80B MoE | 3B | 131K |
+| zen4-coder | Qwen3-Coder-480B-A35B | 480B MoE | 35B | 262K |
+| zen4-coder-flash | Qwen3-Coder-30B-A3B | 30B MoE | 3B | 262K |
+| zen4-coder-pro | Qwen3-Coder-480B BF16 | 480B | 480B | 262K |
 
 ## Links