Skip to content

The easy-to-use open source Business Intelligence and Embedded Analytics tool that lets everyone work with data :bar_chart:

Offer Gemini 3.8 Flash and GLM-5.3-Flash in Metabot (#83848)

Paolo Rascunà69c42e8b5233
diff --git a/docs/ai/providers.md b/docs/ai/providers.md
index 809e8d76153..1ce118f66ad 100644
--- a/docs/ai/providers.md
+++ b/docs/ai/providers.md
@@ -95,6 +95,7 @@ Supported models:
| DeepSeek V4 Flash 0731 | `deepseek/deepseek-v4-flash-0731` | 1,048,576 |
| DeepSeek V4 Pro 0423 | `deepseek/deepseek-v4-pro` | 1,048,576 |
| DeepSeek V4 Pro 0813 | `deepseek/deepseek-v4-pro-0813` | 1,048,575 |
+| Gemini 3.8 Flash | `google/gemini-3.8-flash` | 1,048,576 |
| Mistral Medium 3.5 | `mistralai/mistral-medium-3-5` | 262,144 |
| Kimi K3 | `moonshotai/kimi-k3` | 1,048,576 |
| GPT-5.4 | `openai/gpt-5.4` | 922,000 |
@@ -108,6 +109,7 @@ Supported models:
| Qwen3.8 Max 0902 | `qwen/qwen3.8-max-0902` | 1,000,000 |
| GLM-5.2 | `z-ai/glm-5.2` | 1,048,576 |
| GLM-5.3 | `z-ai/glm-5.3` | 1,048,576 |
+| GLM-5.3-Flash | `z-ai/glm-5.3-flash` | 1,048,575 |
Credentials:
@@ -139,10 +141,11 @@ Credentials:
Supported models:
-| Model | Model ID | Context window (tokens) |
-| ------- | --------- | ----------------------- |
-| GLM-5.2 | `glm-5.2` | 1,048,576 |
-| GLM-5.3 | `glm-5.3` | 1,048,576 |
+| Model | Model ID | Context window (tokens) |
+| ------------- | --------------- | ----------------------- |
+| GLM-5.2 | `glm-5.2` | 1,048,576 |
+| GLM-5.3 | `glm-5.3` | 1,048,576 |
+| GLM-5.3-Flash | `glm-5.3-flash` | 1,048,576 |
Credentials:
@@ -224,6 +227,7 @@ Supported models:
| Gemini 3.5 Flash | `google/gemini-3.5-flash` |
| Gemini 3.6 Flash | `google/gemini-3.6-flash` |
| Gemini 3.7 Flash | `google/gemini-3.7-flash` |
+| Gemini 3.8 Flash | `google/gemini-3.8-flash` |
Credentials:
diff --git a/src/metabase/llm/provider.clj b/src/metabase/llm/provider.clj
index 07bd389a384..bc1166dd122 100644
--- a/src/metabase/llm/provider.clj
+++ b/src/metabase/llm/provider.clj
@@ -215,6 +215,7 @@
:models [{:id "google/gemini-3.5-flash" :display_name "Gemini 3.5 Flash"}
{:id "google/gemini-3.6-flash" :display_name "Gemini 3.6 Flash"}
{:id "google/gemini-3.7-flash" :display_name "Gemini 3.7 Flash"}
+ {:id "google/gemini-3.8-flash" :display_name "Gemini 3.8 Flash"}
{:id "anthropic/claude-fable-5-1" :display_name "Claude Fable 5.1"}
{:id "anthropic/claude-fable-5" :display_name "Claude Fable 5"}
{:id "anthropic/claude-opus-5-5" :display_name "Claude Opus 5.5"}
diff --git a/src/metabase/metabot/self/google/models.clj b/src/metabase/metabot/self/google/models.clj
index 9e253582cd4..21809ae3415 100644
--- a/src/metabase/metabot/self/google/models.clj
+++ b/src/metabase/metabot/self/google/models.clj
@@ -9,17 +9,22 @@
(def catalog
"The Gemini models Metabot supports, with what the adapter needs to know about each.
- The same three models the connection form offers (the google entry in `metabase.llm.provider`);
+ The same four models the connection form offers (the google entry in `metabase.llm.provider`);
a test pins the two lists together. All are Gemini 3 models: they think by default and thinking
cannot be turned off, so [[reasoning-model?]] is membership in this catalog.
https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/thinking
Context windows:
- https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/gemini/3-5-flash
- https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/gemini/3-6-flash
- - https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/gemini/3-7-flash"
+ - https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/gemini/3-7-flash
+ - https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/gemini/3-8-flash"
{"google/gemini-3.5-flash" {:context-window 1048576}
"google/gemini-3.6-flash" {:context-window 1048576}
- "google/gemini-3.7-flash" {:context-window 1048576}})
+ "google/gemini-3.7-flash" {:context-window 1048576}
+ ;; Probed 2026-10-06: the model accepts thinkingLevel LOW. The title call completes.
+ ;; Max output: 65,536 tokens.
+ ;; https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/gemini/3-8-flash
+ "google/gemini-3.8-flash" {:context-window 1048576}})
(defn reasoning-model?
"Whether `model` streams thought summaries that our chain-of-thought UI renders.
diff --git a/src/metabase/metabot/self/openrouter.clj b/src/metabase/metabot/self/openrouter.clj
index 2b6c28e2380..c5aca5d7f87 100644
--- a/src/metabase/metabot/self/openrouter.clj
+++ b/src/metabase/metabot/self/openrouter.clj
@@ -78,6 +78,13 @@
;; Gemma 4 (`google/gemma-4-31b-it`, `google/gemma-4-26b-a4b-it`) is deliberately not listed:
;; through OpenRouter both 31B and 26B failed Metabot smoke tests with results changing between backing hosts.
;; See https://linear.app/metabase/issue/BOT-1932 for details
+ ;; Probed 2026-10-06. The listing passes. A chat turn passes. A title-shaped forced tool call
+ ;; completes at the floored budget. A 4-round Metabot tool turn passes. OpenRouter rejects the
+ ;; disable with a 400. Plain chat streams `reasoning.text`. Tool-call steps carry only
+ ;; `reasoning.encrypted`. The adapter does not replay `reasoning.encrypted`, and the 4-round
+ ;; tool turn worked without it on 2026-10-06.
+ ;; Max output: 65,536 tokens (`max_completion_tokens`, https://openrouter.ai/api/v1/models).
+ "google/gemini-3.8-flash" {:display-name "Gemini 3.8 Flash" :context-window 1048576 :reasoning :renderable :reasoning-mandatory? true}
"mistralai/mistral-medium-3-5" {:display-name "Mistral Medium 3.5" :context-window 262144 :reasoning :renderable}
;; probed 2026-09-08: OpenRouter honors `reasoning {:enabled false}` for kimi-k3 even though the
;; native Moonshot API cannot turn k3's thinking off — a title-shaped forced tool call under the
@@ -103,6 +110,10 @@
;; disable is rejected with a 400 (thinking-only upstream, as on native z.ai), and a forced
;; tool call at the floored budget completes
"z-ai/glm-5.3" {:display-name "GLM-5.3" :context-window 1048576 :reasoning :renderable :reasoning-mandatory? true}
+ ;; Probed 2026-10-06. The enable streams reasoning. OpenRouter rejects the disable with a 400.
+ ;; It honors tool_choice "required". A title-shaped forced tool call completes at the floored
+ ;; budget.
+ "z-ai/glm-5.3-flash" {:display-name "GLM-5.3-Flash" :context-window 1048575 :reasoning :renderable :reasoning-mandatory? true}
"z-ai/glm-5.2" {:display-name "GLM-5.2" :context-window 1048576 :reasoning :renderable}})
(mu/defn context-window-tokens :- [:maybe :int]
@@ -217,12 +228,16 @@
A safety net: in theory the un-disableable reasoning bills against the same `max_tokens` budget as the tool call
(\"max_tokens must be strictly higher than the reasoning budget\" —
https://openrouter.ai/docs/use-cases/reasoning-tokens), so a small caller cap (the conversation-title path sends
- 512) could hit `length` before the mandatory tool call is emitted. In practice this has not been observed: probed
- 2026-09-03, qwen3.8-max reasons only ~150 tokens on title-shaped structured calls and fits the 512 cap, and
- claude-fable-5 emits zero reasoning under a forced tool choice; probed 2026-09-08, gpt-5.4-pro and gpt-5.5-pro
- finish the same calls at the 512 cap with the tool call (242–375 and 22 completion tokens across runs). The floor
- guards against a model update or a longer-thinking mandatory model changing that. Matches vLLM's probe-proven
- floor."
+ 512) could hit `length` before the mandatory tool call is emitted. Earlier models did not need the floor. Probed
+ 2026-09-03, qwen3.8-max reasons only ~150 tokens on title-shaped structured calls and fits the 512 cap. Probed
+ 2026-09-03, claude-fable-5 emits zero reasoning under a forced tool choice. Probed 2026-09-08, gpt-5.4-pro and
+ gpt-5.5-pro finish the same calls at the 512 cap with the tool call. They used 242–375 and 22 completion tokens
+ across runs.
+
+ gemini-3.8-flash has little headroom at a 512 cap. Probed 2026-10-06, a title call capped at 512 completed with 478
+ completion tokens (454 reasoning). With the floor (sent as 2048), the same call used 638 completion tokens (615
+ reasoning). The floor also guards against a model update or a longer-thinking mandatory model. Matches vLLM's
+ probe-proven floor."
2048)
(defn- with-reasoning-directive
diff --git a/src/metabase/metabot/self/zai.clj b/src/metabase/metabot/self/zai.clj
index 192f8ab92d5..959188f515e 100644
--- a/src/metabase/metabot/self/zai.clj
+++ b/src/metabase/metabot/self/zai.clj
@@ -31,8 +31,11 @@
`:thinking-only?` marks a model that rejects `thinking {:type \"disabled\"}` — see
[[thinking-only-model?]]."
- {"glm-5.3" {:display-name "GLM-5.3" :context-window 1048576 :thinking-only? true}
- "glm-5.2" {:display-name "GLM-5.2" :context-window 1048576}})
+ {"glm-5.3" {:display-name "GLM-5.3" :context-window 1048576 :thinking-only? true}
+ ;; https://docs.z.ai/guides/vlm/glm-5.3-flash. Probed 2026-10-06: Z.AI rejects the disable with error 1210.
+ ;; Probed 2026-10-07: a title-shaped forced call spent 19 completion tokens at "low" and 109 at "max".
+ "glm-5.3-flash" {:display-name "GLM-5.3-Flash" :context-window 1048576 :thinking-only? true}
+ "glm-5.2" {:display-name "GLM-5.2" :context-window 1048576}})
(mu/defn context-window-tokens :- [:maybe :int]
"The input context window for `model`, or nil when it isn't one we know."
diff --git a/test/metabase/llm/api/provider_test.clj b/test/metabase/llm/api/provider_test.clj
index eb18b091bdf..79ee394caf6 100644
--- a/test/metabase/llm/api/provider_test.clj
+++ b/test/metabase/llm/api/provider_test.clj
@@ -151,6 +151,7 @@
(is (= [{:id "google/gemini-3.5-flash" :display_name "Gemini 3.5 Flash"}
{:id "google/gemini-3.6-flash" :display_name "Gemini 3.6 Flash"}
{:id "google/gemini-3.7-flash" :display_name "Gemini 3.7 Flash"}
+ {:id "google/gemini-3.8-flash" :display_name "Gemini 3.8 Flash"}
{:id "anthropic/claude-fable-5-1" :display_name "Claude Fable 5.1"}
{:id "anthropic/claude-fable-5" :display_name "Claude Fable 5"}
{:id "anthropic/claude-opus-5-5" :display_name "Claude Opus 5.5"}
@@ -1475,6 +1476,7 @@
:models [{:id "google/gemini-3.5-flash" :display_name "Gemini 3.5 Flash"}
{:id "google/gemini-3.6-flash" :display_name "Gemini 3.6 Flash"}
{:id "google/gemini-3.7-flash" :display_name "Gemini 3.7 Flash"}
+ {:id "google/gemini-3.8-flash" :display_name "Gemini 3.8 Flash"}
{:id "anthropic/claude-fable-5-1" :display_name "Claude Fable 5.1"}
{:id "anthropic/claude-fable-5" :display_name "Claude Fable 5"}
{:id "anthropic/claude-opus-5-5" :display_name "Claude Opus 5.5"}
@@ -1500,7 +1502,7 @@
:project-id "my-project"
:location "us-east5"
:probed-model "anthropic/claude-sonnet-4-6"})]]
- (is (=? [{:key "claude-only" :models [{:id "google/gemini-3.5-flash"} some? some? some? some? some? some? some? some? some? some? some?]}]
+ (is (=? [{:key "claude-only" :models [{:id "google/gemini-3.5-flash"} some? some? some? some? some? some? some? some? some? some? some? some?]}]
(mt/user-http-request :crowberto :get 200 "llm/models")))
(is (= "anthropic/claude-sonnet-4-6" @probed)))))))
@@ -1568,7 +1570,7 @@
:project-id "my-project"})]]
(mt/with-temporary-raw-setting-values [llm-metabot-provider "wrong-model-google/anthropic/claude-opus-5"]
(is (=? [{:key "wrong-model-google"
- :models [{:id "google/gemini-3.5-flash"} some? some? some? some? some? some? some? some? some? some? some?]
+ :models [{:id "google/gemini-3.5-flash"} some? some? some? some? some? some? some? some? some? some? some? some?]
:error "Google API error: model not found"}]
(mt/user-http-request :crowberto :get 200 "llm/models"))))))))
@@ -1584,7 +1586,7 @@
:project-id "my-project"})]]
(mt/with-temporary-raw-setting-values [llm-metabot-provider "forbidden-model-google/anthropic/claude-opus-5"]
(is (=? [{:key "forbidden-model-google"
- :models [{:id "google/gemini-3.5-flash"} some? some? some? some? some? some? some? some? some? some? some?]
+ :models [{:id "google/gemini-3.5-flash"} some? some? some? some? some? some? some? some? some? some? some? some?]
:error "Google API error: PERMISSION_DENIED"}]
(mt/user-http-request :crowberto :get 200 "llm/models"))))))))
@@ -1601,7 +1603,7 @@
(is (=? [{:key "bad-key-google"
:name "bad-key-google"
:type "google"
- :models [{:id "google/gemini-3.5-flash"} some? some? some? some? some? some? some? some? some? some? some?]
+ :models [{:id "google/gemini-3.5-flash"} some? some? some? some? some? some? some? some? some? some? some? some?]
:error "Google API error: invalid authentication credentials"}]
(mt/user-http-request :crowberto :get 200 "llm/models")))))))
diff --git a/test/metabase/metabot/self/chat_max_tokens_test.clj b/test/metabase/metabot/self/chat_max_tokens_test.clj
index aa152c3a5c4..45e363a40c8 100644
--- a/test/metabase/metabot/self/chat_max_tokens_test.clj
+++ b/test/metabase/metabot/self/chat_max_tokens_test.clj
@@ -173,6 +173,7 @@
:gemini {"google/gemini-3.5-flash" 32000
"google/gemini-3.6-flash" 32000
"google/gemini-3.7-flash" 32000
+ "google/gemini-3.8-flash" 32000
"google/gemini-2.0-flash" 32000}
:deepseek {"deepseek-v4-pro" 32000
"deepseek-flash" 32000}
@@ -192,7 +193,9 @@
"deepseek/deepseek-v4-pro" 32000
"deepseek/deepseek-v4-pro-0813" 32000
"deepseek/deepseek-v4-flash-0731" 32000
+ "google/gemini-3.8-flash" 32000
"z-ai/glm-5.3" 32000
+ "z-ai/glm-5.3-flash" 32000
"z-ai/glm-5.2" 32000
"qwen/qwen3.8-max" 32000
;; the id qwen/qwen3.8-max resolves to on OpenRouter today
@@ -212,6 +215,7 @@
"anthropic/claude-fable-6" 32000
"openai/gpt-4o" 32000}
:zai {"glm-5.3" 32000
+ "glm-5.3-flash" 32000
"glm-5.2" 32000
"glm-4.7" 32000}
:moonshot {"kimi-k3" 32000
diff --git a/test/metabase/metabot/self/google/models_test.clj b/test/metabase/metabot/self/google/models_test.clj
index 75d4e143a4b..d2dcd8b452c 100644
--- a/test/metabase/metabot/self/google/models_test.clj
+++ b/test/metabase/metabot/self/google/models_test.clj
@@ -10,6 +10,7 @@
(is (true? (models/reasoning-model? "google/gemini-3.5-flash")))
(is (true? (models/reasoning-model? "google/gemini-3.6-flash")))
(is (true? (models/reasoning-model? "google/gemini-3.7-flash")))
+ (is (true? (models/reasoning-model? "google/gemini-3.8-flash")))
(is (false? (models/reasoning-model? "google/gemini-2.5-flash")))
(is (false? (models/reasoning-model? "gemini-3.5-flash")))
(is (false? (models/reasoning-model? nil)))))
@@ -29,3 +30,8 @@
(doseq [[model {:keys [context-window]}] models/catalog]
(testing model
(is (pos-int? context-window))))))
+
+(deftest ^:parallel gemini-3-8-flash-row-test
+ (testing "the 3.8 row records only its context window: its 65,536 max output is a comment, not a data field"
+ (is (= {:context-window 1048576}
+ (get models/catalog "google/gemini-3.8-flash")))))
diff --git a/test/metabase/metabot/self/google_test.clj b/test/metabase/metabot/self/google_test.clj
index 2833dfd315c..aefc4cc21db 100644
--- a/test/metabase/metabot/self/google_test.clj
+++ b/test/metabase/metabot/self/google_test.clj
@@ -74,6 +74,7 @@
"google/gemini-3.5-flash" 1048576
"google/gemini-3.6-flash" 1048576
"google/gemini-3.7-flash" 1048576
+ "google/gemini-3.8-flash" 1048576
"google/gemini-unknown" nil)))
(deftest context-window-tokens-anthropic-test
diff --git a/test/metabase/metabot/self/openrouter_test.clj b/test/metabase/metabot/self/openrouter_test.clj
index d995dd75cf0..1e2db9312e2 100644
--- a/test/metabase/metabot/self/openrouter_test.clj
+++ b/test/metabase/metabot/self/openrouter_test.clj
@@ -249,6 +249,14 @@
;; uncapped by the caller, so the default cap applies — already far above the floor
32000 {:schema {:type "object"}}
512 {:max-tokens 512}))
+ (testing "z-ai/glm-5.3-flash rejects the disable, so a forced call gets the floor and no directive"
+ (let [body (body-for {:model "z-ai/glm-5.3-flash" :schema {:type "object"} :max-tokens 512})]
+ (is (= 2048 (:max_tokens body)))
+ (is (not (contains? body :reasoning)))))
+ (testing "google/gemini-3.8-flash rejects the disable, so a forced call gets the floor and no directive"
+ (let [body (body-for {:model "google/gemini-3.8-flash" :schema {:type "object"} :max-tokens 512})]
+ (is (= 2048 (:max_tokens body)))
+ (is (not (contains? body :reasoning)))))
(testing "a non-mandatory model keeps its cap — it got the disable instead"
(let [body (body-for {:model "anthropic/claude-sonnet-4.6" :schema {:type "object"} :max-tokens 512})]
(is (= 512 (:max_tokens body)))
@@ -271,8 +279,9 @@
"anthropic/claude-opus-4.8" "anthropic/claude-opus-4.7" "anthropic/claude-opus-4.6"
"anthropic/claude-sonnet-5"
"anthropic/claude-sonnet-4.6" "deepseek/deepseek-v4-pro" "deepseek/deepseek-v4-pro-0813"
- "deepseek/deepseek-v4-flash-0731" "mistralai/mistral-medium-3-5" "moonshotai/kimi-k3"
- "openai/gpt-5.4" "openai/gpt-5.4-mini" "qwen/qwen3.8-max-0902" "z-ai/glm-5.3" "z-ai/glm-5.2"}
+ "deepseek/deepseek-v4-flash-0731" "google/gemini-3.8-flash"
+ "mistralai/mistral-medium-3-5" "moonshotai/kimi-k3" "openai/gpt-5.4" "openai/gpt-5.4-mini"
+ "qwen/qwen3.8-max-0902" "z-ai/glm-5.3" "z-ai/glm-5.3-flash" "z-ai/glm-5.2"}
renderable-default #{"openai/gpt-5.6-sol" "openai/gpt-5.6-terra" "openai/gpt-5.6-luna" "openai/gpt-5.5"
"openai/gpt-5.5-pro" "openai/gpt-5.4-pro"}
budget #{"anthropic/claude-opus-4.5" "anthropic/claude-sonnet-4.5" "anthropic/claude-haiku-4.5"}]
diff --git a/test/metabase/metabot/self/zai_test.clj b/test/metabase/metabot/self/zai_test.clj
index 297178ad036..b77bb742328 100644
--- a/test/metabase/metabot/self/zai_test.clj
+++ b/test/metabase/metabot/self/zai_test.clj
@@ -155,6 +155,22 @@
:input input
:schema {:type "object"}})))))))
+(deftest ^:parallel request-body-glm-5-3-flash-test
+ (let [input [{:role :user :content "hi"}]
+ body #(zai/zai-request-body (assoc % :model "glm-5.3-flash" :input input))]
+ (testing "glm-5.3-flash is thinking-only (error 1210 on the disable): no directive, max effort"
+ (let [chat-body (body {})]
+ (is (not (contains? chat-body :thinking)))
+ (is (= "max" (:reasoning_effort chat-body)))))
+ (testing "a schema drops the effort to low"
+ (is (= "low" (:reasoning_effort (body {:schema {:type "object"}})))))
+ (testing "the forced-call floor raises a cap below 2048 and keeps a cap at or above it"
+ (are [opts expected] (= expected (:max_tokens (body opts)))
+ {:schema {:type "object"} :max-tokens 512} 2048
+ {:schema {:type "object"} :max-tokens 2048} 2048
+ {:schema {:type "object"} :max-tokens 4096} 4096
+ {:max-tokens 512} 512))))
+
(deftest ^:parallel reasoning-model?-test
(are [model expected] (= expected (zai/reasoning-model? model))
"glm-5.2" true
@@ -409,9 +425,12 @@
{:status 200 :body {:data [{:id "glm-4.7"}
{:id "glm-5.2"}
{:id "glm-5.3"}
+ {:id "glm-5.3-flash"}
+ {:id "glm-5.3-flashx"}
{:id "some-other-model"}]}})]
(is (= {:models [{:id "glm-5.2" :display_name "GLM-5.2"}
- {:id "glm-5.3" :display_name "GLM-5.3"}]}
+ {:id "glm-5.3" :display_name "GLM-5.3"}
+ {:id "glm-5.3-flash" :display_name "GLM-5.3-Flash"}]}
(zai/list-models {:credentials byok-credentials}))))))
(deftest list-models-prefers-catalog-display-name-test
diff --git a/test/metabase/metabot/self_test.clj b/test/metabase/metabot/self_test.clj
index b078b22b38d..fc652b85feb 100644
--- a/test/metabase/metabot/self_test.clj
+++ b/test/metabase/metabot/self_test.clj
@@ -1366,10 +1366,14 @@
"metabase/anthropic/claude-sonnet-4-6" 1000000 ; proxy prefix is stripped
"azure/openai/gpt-5.4-mini-prod" 272000 ; longest model-id prefix wins
"google/google/gemini-3.6-flash" 1048576 ; publisher-qualified model reaches Google adapter
+ "google/google/gemini-3.8-flash" 1048576 ; Gemini 3.8 Flash reaches the Google adapter
"zai/glm-5.3" 1048576 ; Z.AI direct
"openrouter/z-ai/glm-5.3" 1048576 ; OpenRouter serving limit
"deepseek/deepseek-v4-pro" 1048576 ; DeepSeek direct, probed overflow message
"deepseek/deepseek-flash" 1048576 ; DeepSeek direct, probed overflow message
+ "zai/glm-5.3-flash" 1048576 ; Z.AI direct
+ "openrouter/z-ai/glm-5.3-flash" 1048575 ; lower of context_length and top_provider.context_length
+ "openrouter/google/gemini-3.8-flash" 1048576 ; OpenRouter serving limit
"azure/openai/my-deployment" nil ; unmatched deployment
"anthropic/some-future-model" nil ; unknown model
"unknown" nil))) ; no such connection
diff --git a/test/metabase/metabot/settings_test.clj b/test/metabase/metabot/settings_test.clj
index 97c956529c1..1cc4c5240a9 100644
--- a/test/metabase/metabot/settings_test.clj
+++ b/test/metabase/metabot/settings_test.clj
@@ -220,9 +220,12 @@
;; a family with no deployment segment names no model
"azure/anthropic" false
"zai/glm-5.2" true
+ "zai/glm-5.3-flash" true
"zai/glm-4.7" false
"openrouter/anthropic/claude-sonnet-4.6" true
"openrouter/z-ai/glm-5.2" true
+ "openrouter/z-ai/glm-5.3-flash" true
+ "openrouter/google/gemini-3.8-flash" true
;; streams reasoning summaries under the server default
"openrouter/openai/gpt-5.5" true
;; re-probed 2026-09-04: streams summaries under the explicit enable
@@ -233,6 +236,7 @@
"google/anthropic/claude-haiku-4-5@20251001" false
"google/google/gemini-3.5-flash" true
"google/google/gemini-3.7-flash" true
+ "google/google/gemini-3.8-flash" true
;; off-catalog: no thinking directive — see google/models.clj
"google/google/gemini-2.5-flash" false
"mistral/mistral-medium-3-5" true