Skip to content

Build AI methods with your coding agent, then run them anywhere: as an MCP for chatbots, as a webapp for people, or via API for your software.

Add gemini-3.5-flash on google backend (#922)

Louis Choquel1a35c081f74d
diff --git a/.pipelex-dev/test_profiles.toml b/.pipelex-dev/test_profiles.toml
index 37f9c9de3..431710e45 100644
--- a/.pipelex-dev/test_profiles.toml
+++ b/.pipelex-dev/test_profiles.toml
@@ -90,6 +90,7 @@ google = [
"gemini-3.0-flash",
"gemini-3.1-flash-lite",
"gemini-3.1-pro",
+ "gemini-3.5-flash",
"gemini-pro-latest",
"gemini-flash-latest",
"gemini-flash-lite-latest",
diff --git a/.pipelex/inference/backends/google.toml b/.pipelex/inference/backends/google.toml
index cad27a0cb..9651f7c0d 100644
--- a/.pipelex/inference/backends/google.toml
+++ b/.pipelex/inference/backends/google.toml
@@ -87,6 +87,15 @@ max_prompt_images = 3000
costs = { input = 2, output = 12.0 }
thinking_mode = "adaptive"
+# --- Gemini 3.5 Series ----------------------------------------
+["gemini-3.5-flash"]
+model_id = "gemini-3.5-flash"
+inputs = ["text", "images", "pdf"]
+outputs = ["text", "structured"]
+max_prompt_images = 3000
+costs = { input = 1.5, output = 9.0 }
+thinking_mode = "adaptive"
+
# --- Latest Aliases (point to current generation, change over time) -----------
["gemini-pro-latest"]
inputs = ["text", "images", "pdf"]
diff --git a/.pipelex/inference/backends/pipelex_gateway_models.md b/.pipelex/inference/backends/pipelex_gateway_models.md
index ddb1b79f8..ad32d8d9c 100644
--- a/.pipelex/inference/backends/pipelex_gateway_models.md
+++ b/.pipelex/inference/backends/pipelex_gateway_models.md
@@ -157,6 +157,14 @@ For configuration details, see the [documentation](https://docs.pipelex.com/late
<td style="text-align:center;background-color:rgba(76,175,80,0.15)">✅</td>
</tr>
<tr>
+<td>gemini-3.5-flash</td>
+<td style="text-align:center;background-color:rgba(33,150,243,0.15)">✅</td>
+<td style="text-align:center;background-color:rgba(33,150,243,0.15)">✅</td>
+<td style="text-align:center;background-color:rgba(33,150,243,0.15)">✅</td>
+<td style="text-align:center;background-color:rgba(76,175,80,0.15)">✅</td>
+<td style="text-align:center;background-color:rgba(76,175,80,0.15)">✅</td>
+</tr>
+<tr>
<td>gemini-flash-latest</td>
<td style="text-align:center;background-color:rgba(33,150,243,0.15)">✅</td>
<td style="text-align:center;background-color:rgba(33,150,243,0.15)">✅</td>
@@ -598,6 +606,6 @@ For configuration details, see the [documentation](https://docs.pipelex.com/late
> **AUTO-GENERATED FILE** - Do not edit manually.
-> Last updated: 2026-04-28T12:50:14Z
+> Last updated: 2026-05-20T11:45:37Z
>
> Run `pipelex-dev update-gateway-models` or `make ugm` to regenerate.
\ No newline at end of file
diff --git a/.pipelex/inference/backends/pipelex_gateway_models_plain.md b/.pipelex/inference/backends/pipelex_gateway_models_plain.md
index e39b82f30..6bf149e0a 100644
--- a/.pipelex/inference/backends/pipelex_gateway_models_plain.md
+++ b/.pipelex/inference/backends/pipelex_gateway_models_plain.md
@@ -58,6 +58,9 @@ For configuration details, see the [documentation](https://docs.pipelex.com/late
- **gemini-3.1-pro**
- inputs: text, images, pdf
- outputs: text, structured
+- **gemini-3.5-flash**
+ - inputs: text, images, pdf
+ - outputs: text, structured
- **gemini-flash-latest**
- inputs: text, images, pdf
- outputs: text, structured
@@ -223,6 +226,6 @@ For configuration details, see the [documentation](https://docs.pipelex.com/late
> **AUTO-GENERATED FILE** - Do not edit manually.
-> Last updated: 2026-04-28T12:50:14Z
+> Last updated: 2026-05-20T11:45:37Z
>
> Run `pipelex-dev update-gateway-models` or `make ugm` to regenerate.
\ No newline at end of file
diff --git a/CHANGELOG.md b/CHANGELOG.md
index 379f16828..6c19c5cbc 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -4,6 +4,8 @@
### Added
+- **`gemini-3.5-flash` model** added to the `google` backend. Adaptive thinking mode, supports text / images / pdf in and structured outputs, `max_prompt_images = 3000`, costs `{ input = 1.5, output = 9.0 }` per million tokens.
+
- **New `PipeStructure` operator** that turns text into a structured concept via a single LLM call. Takes one `Text`-compatible input (or a domain concept that `refines = "Text"`), produces any structured output with the usual multiplicity options (`Foo`, `Foo[]`, `Foo[N]`). Useful whenever the source text comes from a PDF extraction, a search result, an upstream pipe, or any non-LLM origin. Documented at [building-methods/pipes/pipe-operators/PipeStructure.md](building-methods/pipes/pipe-operators/PipeStructure.md).
- **Custom search attributes on the Temporal namespace, with a strict prerequisite at worker boot.** Pipelex sets five custom Keyword search attributes on every workflow start — `PipeCode`, `PipelineRunId`, `SessionId`, `UserId`, `DomainCode` — so the Temporal dashboard can filter, group, and audit workflows by their actual semantic identity rather than by opaque workflow ids. A real Temporal cluster rejects every `StartWorkflowExecution` RPC that references an unregistered attribute, so the check at worker boot is a hard fail (raises `SearchAttributeRegistrationError`) on a reachable namespace — the previous "warn and continue" framing was dishonest because workflows would then fail at every dispatch with a much less actionable error. The exception message embeds both the `pipelex setup-temporal-namespace` invocation and the equivalent raw `temporal operator search-attribute create` command. `RPCError` (control-plane unreachable) stays a soft fail; the in-process test server is registered up front by the integration conftest. Documented at [distributed-execution/cluster-setup.md](distributed-execution/cluster-setup.md).
diff --git a/pipelex/kit/configs/inference/backends/google.toml b/pipelex/kit/configs/inference/backends/google.toml
index cad27a0cb..9651f7c0d 100644
--- a/pipelex/kit/configs/inference/backends/google.toml
+++ b/pipelex/kit/configs/inference/backends/google.toml
@@ -87,6 +87,15 @@ max_prompt_images = 3000
costs = { input = 2, output = 12.0 }
thinking_mode = "adaptive"
+# --- Gemini 3.5 Series ----------------------------------------
+["gemini-3.5-flash"]
+model_id = "gemini-3.5-flash"
+inputs = ["text", "images", "pdf"]
+outputs = ["text", "structured"]
+max_prompt_images = 3000
+costs = { input = 1.5, output = 9.0 }
+thinking_mode = "adaptive"
+
# --- Latest Aliases (point to current generation, change over time) -----------
["gemini-pro-latest"]
inputs = ["text", "images", "pdf"]
diff --git a/pipelex/kit/configs/inference/backends/pipelex_gateway_models.md b/pipelex/kit/configs/inference/backends/pipelex_gateway_models.md
index ddb1b79f8..ad32d8d9c 100644
--- a/pipelex/kit/configs/inference/backends/pipelex_gateway_models.md
+++ b/pipelex/kit/configs/inference/backends/pipelex_gateway_models.md
@@ -157,6 +157,14 @@ For configuration details, see the [documentation](https://docs.pipelex.com/late
<td style="text-align:center;background-color:rgba(76,175,80,0.15)">✅</td>
</tr>
<tr>
+<td>gemini-3.5-flash</td>
+<td style="text-align:center;background-color:rgba(33,150,243,0.15)">✅</td>
+<td style="text-align:center;background-color:rgba(33,150,243,0.15)">✅</td>
+<td style="text-align:center;background-color:rgba(33,150,243,0.15)">✅</td>
+<td style="text-align:center;background-color:rgba(76,175,80,0.15)">✅</td>
+<td style="text-align:center;background-color:rgba(76,175,80,0.15)">✅</td>
+</tr>
+<tr>
<td>gemini-flash-latest</td>
<td style="text-align:center;background-color:rgba(33,150,243,0.15)">✅</td>
<td style="text-align:center;background-color:rgba(33,150,243,0.15)">✅</td>
@@ -598,6 +606,6 @@ For configuration details, see the [documentation](https://docs.pipelex.com/late
> **AUTO-GENERATED FILE** - Do not edit manually.
-> Last updated: 2026-04-28T12:50:14Z
+> Last updated: 2026-05-20T11:45:37Z
>
> Run `pipelex-dev update-gateway-models` or `make ugm` to regenerate.
\ No newline at end of file
diff --git a/pipelex/kit/configs/inference/backends/pipelex_gateway_models_plain.md b/pipelex/kit/configs/inference/backends/pipelex_gateway_models_plain.md
index e39b82f30..6bf149e0a 100644
--- a/pipelex/kit/configs/inference/backends/pipelex_gateway_models_plain.md
+++ b/pipelex/kit/configs/inference/backends/pipelex_gateway_models_plain.md
@@ -58,6 +58,9 @@ For configuration details, see the [documentation](https://docs.pipelex.com/late
- **gemini-3.1-pro**
- inputs: text, images, pdf
- outputs: text, structured
+- **gemini-3.5-flash**
+ - inputs: text, images, pdf
+ - outputs: text, structured
- **gemini-flash-latest**
- inputs: text, images, pdf
- outputs: text, structured
@@ -223,6 +226,6 @@ For configuration details, see the [documentation](https://docs.pipelex.com/late
> **AUTO-GENERATED FILE** - Do not edit manually.
-> Last updated: 2026-04-28T12:50:14Z
+> Last updated: 2026-05-20T11:45:37Z
>
> Run `pipelex-dev update-gateway-models` or `make ugm` to regenerate.
\ No newline at end of file