diff --git a/README.md b/README.md
index c68e5a3..8b2df78 100644
--- a/README.md
+++ b/README.md
@@ -134,6 +134,12 @@ zerogpu chat "Why does my API keep getting rate-limited?" -m gpt-oss-120b -r
 
 # Multilingual reasoning
 zerogpu chat "Explique la mise en cache en une phrase." -m qwen3-30b-a3b-fp8
+
+# A 1M-token context, for whole repos and very long documents
+zerogpu chat "$(cat ARCHITECTURE.md)" -m glm-5.2
+
+# Coding and agentic work, at a fraction of the flagship price
+zerogpu chat "Port this helper to async/await." -m deepseek-v4-flash
 ```
 
 | Option | Description |
@@ -148,8 +154,10 @@ zerogpu chat "Explique la mise en cache en une phrase." -m qwen3-30b-a3b-fp8
 | `LFM2.5-1.2B-Thinking` | Compact reasoning model. |
 | `gpt-oss-120b` | 117B MoE, 131K context, reasoning + function calling. |
 | `qwen3-30b-a3b-fp8` | 30.5B MoE, 100+ languages, reasoning + function calling. |
+| `glm-5.2` | 753B MoE, 1M context, reasoning + function calling. The platform's most capable model, and its priciest. |
+| `deepseek-v4-flash` | 284B MoE (13B active), 1M context, coding and agentic workflows. |
 
-`qwen3-30b-a3b-fp8` is served by the Chat Completions API rather than the Responses API; the CLI routes it automatically.
+`qwen3-30b-a3b-fp8`, `glm-5.2`, and `deepseek-v4-flash` are served by the Chat Completions API rather than the Responses API; the CLI routes them automatically.
 
 #### `chat_thinking`
 
diff --git a/docs/ADDING_COMMANDS.md b/docs/ADDING_COMMANDS.md
index 2098554..d4d77e1 100644
--- a/docs/ADDING_COMMANDS.md
+++ b/docs/ADDING_COMMANDS.md
@@ -7,7 +7,7 @@ This guide explains how to add a new CLI command to the ZeroGPU CLI.
 - `src/commands/` — one file per command, each exporting a `register<Name>Command(program)` function.
 - `src/cli.ts` — wires every command into the root program.
 - `src/lib/responses.ts` — shared `RESPONSES_ENDPOINT`, `ResponsesApiResponse`, and the `extractOutputText` / `extractReasoningText` helpers for `/v1/responses` calls.
-- `src/lib/chatCompletions.ts` — the same for `/v1/chat/completions`, used by models the platform serves only there (currently `qwen3-30b-a3b-fp8`), plus `toResponsesUsage` to normalize token counts for savings tracking.
+- `src/lib/chatCompletions.ts` — the same for `/v1/chat/completions`, used by models the platform serves only there (currently `qwen3-30b-a3b-fp8`, `glm-5.2`, and `deepseek-v4-flash`), plus `toResponsesUsage` to normalize token counts for savings tracking.
 - `src/lib/auth.ts` — `getApiKey()` for authenticated requests.
 
 ## Steps
diff --git a/docs/DOCUMENTATION.md b/docs/DOCUMENTATION.md
index 43c0369..9cb5634 100644
--- a/docs/DOCUMENTATION.md
+++ b/docs/DOCUMENTATION.md
@@ -5,7 +5,7 @@
 `zerogpu-cli` is the official command-line interface for [ZeroGPU](https://zerogpu.ai), a distributed / edge inference platform for small language models (SLMs) and nano language models. The CLI is a thin, OpenAI-compatible client around the ZeroGPU **Responses API** (`https://api.zerogpu.ai/v1/responses`) — and, for models served only there, the **Chat Completions API** (`https://api.zerogpu.ai/v1/chat/completions`) — that lets you call a curated set of edge-optimized models directly from your terminal for common NLP workloads:
 
 - Conversational chat (`LFM2.5-1.2B-Instruct`, `LFM2.5-1.2B-Thinking`)
-- Reasoning and tool-use chat (`gpt-oss-120b`, `qwen3-30b-a3b-fp8`)
+- Reasoning and tool-use chat (`gpt-oss-120b`, `qwen3-30b-a3b-fp8`, `glm-5.2`, `deepseek-v4-flash`)
 - IAB content/audience classification (`zlm-v1-iab-classify-edge`, `zlm-v2-iab-classify-edge-enriched`)
 - Domain-level IAB classification (`zlm-v1-iab-domain-classifier`)
 - Zero-shot classification (`deberta-v3-small`)
@@ -209,8 +209,10 @@ zerogpu chat <text> [-i <instructions>] [-m <model>] [-r]
 | `LFM2.5-1.2B-Thinking` | Responses | Compact reasoning model. |
 | `gpt-oss-120b` | Responses | 117B MoE, 131K context, reasoning + function calling. |
 | `qwen3-30b-a3b-fp8` | Chat Completions | 30.5B MoE, 100+ languages, reasoning + function calling. |
+| `glm-5.2` | Chat Completions | 753B MoE, 1,048,576-token context, reasoning + function calling. The most capable model on the platform, and the most expensive by an order of magnitude. |
+| `deepseek-v4-flash` | Chat Completions | 284B MoE (13B active), 1,048,576-token context, coding and agentic workflows. |
 
-`qwen3-30b-a3b-fp8` has no Responses endpoint, so the CLI posts it to `/v1/chat/completions` instead, mapping `--instructions` to a `system` message and normalizing `prompt_tokens` / `completion_tokens` back to Responses token names for savings tracking. This routing is transparent — the command and its output are identical either way.
+`qwen3-30b-a3b-fp8`, `glm-5.2`, and `deepseek-v4-flash` have no Responses endpoint, so the CLI posts them to `/v1/chat/completions` instead, mapping `--instructions` to a `system` message and normalizing `prompt_tokens` / `completion_tokens` back to Responses token names for savings tracking. This routing is transparent — the command and its output are identical either way.
 
 **Example**
 ```bash
@@ -680,7 +682,7 @@ Content-Type: application/json
 x-api-key:    <ZEROGPU_API_KEY>
 ```
 
-The one exception is `chat --model qwen3-30b-a3b-fp8`, which the ZeroGPU platform serves only through the OpenAI-compatible Chat Completions endpoint:
+The exceptions are `chat --model qwen3-30b-a3b-fp8`, `chat --model glm-5.2`, and `chat --model deepseek-v4-flash`, which the ZeroGPU platform serves only through the OpenAI-compatible Chat Completions endpoint:
 
 ```
 POST https://api.zerogpu.ai/v1/chat/completions
diff --git a/src/commands/chat.ts b/src/commands/chat.ts
index 4e1df5b..de8f28f 100644
--- a/src/commands/chat.ts
+++ b/src/commands/chat.ts
@@ -17,13 +17,16 @@ import { recordAndMaybeNotify } from "../lib/savings.js";
 const DEFAULT_MODEL = "LFM2.5-1.2B-Instruct";
 
 // Text-generation models `--model` accepts, and the API each one speaks.
-// qwen3-30b-a3b-fp8 is Chat Completions only — it has no Responses endpoint.
+// qwen3-30b-a3b-fp8, glm-5.2, and deepseek-v4-flash are Chat Completions only —
+// they have no Responses endpoint.
 // Source: https://docs.zerogpu.ai/docs/text-generation
 const CHAT_MODELS: Record<string, "responses" | "chat-completions"> = {
   "LFM2.5-1.2B-Instruct": "responses",
   "LFM2.5-1.2B-Thinking": "responses",
   "gpt-oss-120b": "responses",
   "qwen3-30b-a3b-fp8": "chat-completions",
+  "glm-5.2": "chat-completions",
+  "deepseek-v4-flash": "chat-completions",
 };
 
 // Model ids are case-sensitive to the API but not to the person typing them.
diff --git a/src/lib/savings.ts b/src/lib/savings.ts
index 59899b1..d5cab4b 100644
--- a/src/lib/savings.ts
+++ b/src/lib/savings.ts
@@ -21,6 +21,8 @@ const DEFAULT_BASELINE = "claude-opus-4-8";
 const ZGPU_PRICING: Record<string, { in: number; out: number }> = {
   "gpt-oss-120b": { in: 0.03, out: 0.1 },
   "qwen3-30b-a3b-fp8": { in: 0.05, out: 0.3 },
+  "glm-5.2": { in: 1.1, out: 3.5 },
+  "deepseek-v4-flash": { in: 0.07, out: 0.14 },
   "llama-3.1-8b-instruct-fast": { in: 0.02, out: 0.05 },
   "zlm-v1-iab-classify-edge": { in: 0.02, out: 0.05 },
   "zlm-v2-iab-classify-edge-enriched": { in: 0.02, out: 0.05 },
@@ -33,8 +35,9 @@ const ZGPU_PRICING: Record<string, { in: number; out: number }> = {
   "LFM2.5-1.2B-Instruct": { in: 0.02, out: 0.05 },
 };
 // Conservative fallback for any model id not in the table above: the priciest
-// published rate, so an unlisted model never overstates savings.
-const ZGPU_FALLBACK = { in: 0.05, out: 0.3 };
+// published rate, so an unlisted model never overstates savings. Currently
+// glm-5.2, which is an order of magnitude dearer than the edge models.
+const ZGPU_FALLBACK = { in: 1.1, out: 3.5 };
 
 // Cadence: aim to show the savings note roughly once every 2–3 routed calls,
 // never twice in a row, and guaranteed within a bounded window.
diff --git a/tests/savings.test.ts b/tests/savings.test.ts
index ab855c6..bdab8f8 100644
--- a/tests/savings.test.ts
+++ b/tests/savings.test.ts
@@ -78,11 +78,28 @@ describe("computeCallSavings", () => {
   });
 
   it("falls back to a default ZeroGPU rate for an unknown model", () => {
-    const known = computeCallSavings(740, 280, "claude-opus-4-8", "qwen3-30b-a3b-fp8").savingsUsd;
+    const known = computeCallSavings(740, 280, "claude-opus-4-8", "glm-5.2").savingsUsd;
     const unknown = computeCallSavings(740, 280, "claude-opus-4-8", "some-new-zgpu-model").savingsUsd;
-    // fallback equals the priciest published rate, qwen3's {0.05, 0.3}
+    // fallback equals the priciest published rate, glm-5.2's {1.10, 3.50}
     expect(unknown).toBeCloseTo(known, 10);
   });
+
+  it("never overstates savings for an unknown model", () => {
+    // The fallback must be at least as dear as every listed model, so an
+    // unlisted id can only ever under-report what was saved.
+    const unknown = computeCallSavings(740, 280, "claude-opus-4-8", "some-new-zgpu-model").savingsUsd;
+    for (const model of [
+      "gpt-oss-120b",
+      "qwen3-30b-a3b-fp8",
+      "glm-5.2",
+      "deepseek-v4-flash",
+      "LFM2.5-1.2B-Instruct",
+    ]) {
+      expect(unknown).toBeLessThanOrEqual(
+        computeCallSavings(740, 280, "claude-opus-4-8", model).savingsUsd,
+      );
+    }
+  });
 });
 
 describe("resolveBaselineModel", () => {