Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
40 changes: 39 additions & 1 deletion docs/models/google.mdx
Original file line number Diff line number Diff line change
@@ -1,10 +1,32 @@
---
title: "Google"
description: "Gemini 3 and 2.5 series models with specs, pricing, and capabilities"
description: "Gemini 3.6, 3.5, and 2.5 series models with specs, pricing, and capabilities"
---

<Note>Source: [Google AI model docs](https://ai.google.dev/gemini-api/docs/models)</Note>

## Gemini 3.6

<CardGroup cols={2}>
<Card title="gemini-3.6-flash">
<Icon icon="lightbulb" size={14} /> <Icon icon="lightbulb" size={14} /> <Icon icon="lightbulb" size={14} /> <Icon icon="lightbulb" size={14} /> Reasoning · <Icon icon="bolt" size={14} /> <Icon icon="bolt" size={14} /> <Icon icon="bolt" size={14} /> <Icon icon="bolt" size={14} /> <Icon icon="bolt" size={14} /> Speed

`google/gemini-3.6-flash`

Workhorse Flash model with better token efficiency, code generation, and multimodal reasoning for multi-step orchestration and agentic workflows.

- &#36;1.50 / &#36;7.50
- <Icon icon="window-maximize" size={14} /> 1M context
- <Icon icon="right-from-bracket" size={14} /> 64K max output
- <Icon icon="keyboard" size={14} /> Text, Image, Video, Audio, PDF input
- <Icon icon="brain" size={14} /> Thinking
- <Icon icon="globe" size={14} /> Web search
- <Icon icon="calendar" size={14} /> Knowledge cutoff Jan 2025
</Card>
</CardGroup>

---

## Gemini 3.5

<CardGroup cols={2}>
Expand All @@ -23,6 +45,22 @@ description: "Gemini 3 and 2.5 series models with specs, pricing, and capabiliti
- <Icon icon="globe" size={14} /> Web search
- <Icon icon="calendar" size={14} /> Knowledge cutoff Jan 2025
</Card>

<Card title="gemini-3.5-flash-lite">
<Icon icon="lightbulb" size={14} /> <Icon icon="lightbulb" size={14} /> <Icon icon="lightbulb" size={14} /> Reasoning · <Icon icon="bolt" size={14} /> <Icon icon="bolt" size={14} /> <Icon icon="bolt" size={14} /> <Icon icon="bolt" size={14} /> <Icon icon="bolt" size={14} /> Speed

`google/gemini-3.5-flash-lite`

Fastest, most cost-effective 3.5-class model for high-throughput agentic search, document processing, and lightweight subagent workflows.

- &#36;0.30 / &#36;2.50
- <Icon icon="window-maximize" size={14} /> 1M context
- <Icon icon="right-from-bracket" size={14} /> 64K max output
- <Icon icon="keyboard" size={14} /> Text, Image, Video, Audio, PDF input
- <Icon icon="brain" size={14} /> Thinking
- <Icon icon="globe" size={14} /> Web search
- <Icon icon="calendar" size={14} /> Knowledge cutoff Jan 2025
</Card>
</CardGroup>

---
Expand Down
2 changes: 1 addition & 1 deletion docs/models/overview.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,7 @@ Every model supported by Timbal with full specs, pricing, capability scores, and
Open-source models via Fireworks
</Card>
<Card title="Google" icon="https://timbalusercontent.com/assets/gemini_favicon.svg" href="/models/google">
Gemini 3 and 2.5 series
Gemini 3.6, 3.5, 3.1 and 2.5 series
</Card>
<Card title="Groq" icon="https://timbalusercontent.com/assets/groq_favicon.svg" href="/models/groq">
Ultra-low latency via Groq LPU
Expand Down
12 changes: 12 additions & 0 deletions python/tests/core/test_frontier_models_integration.py
Original file line number Diff line number Diff line change
Expand Up @@ -19,6 +19,18 @@
PROMPT = "Reply with exactly one word: ok"

LIVE_MODELS = [
pytest.param(
"google/gemini-3.6-flash",
"GEMINI_API_KEY",
None,
id="google-gemini-3.6-flash",
),
pytest.param(
"google/gemini-3.5-flash-lite",
"GEMINI_API_KEY",
None,
id="google-gemini-3.5-flash-lite",
),
pytest.param(
"xai/grok-4.5",
"XAI_API_KEY",
Expand Down
2 changes: 2 additions & 0 deletions python/timbal/core/models.py
Original file line number Diff line number Diff line change
Expand Up @@ -106,7 +106,9 @@ def get_context_window(model_id: str) -> int | None:
"togetherai/google/gemma-3-27b-it",
"togetherai/deepcogito/cogito-v2-1-671b",
"togetherai/mistralai/Mistral-Small-24B-Instruct-2501",
"google/gemini-3.6-flash",
"google/gemini-3.5-flash",
"google/gemini-3.5-flash-lite",
"google/gemini-3.1-pro-preview",
"google/gemini-3.1-flash-lite",
"google/gemini-3-flash-preview",
Expand Down
18 changes: 18 additions & 0 deletions python/timbal/models.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -551,6 +551,15 @@ models:
output_price: 0.3
context_window: 32000
capabilities: [tools]
- id: google/gemini-3.6-flash
provider: google
display_name: Gemini 3.6 Flash
description: Workhorse Flash model with improved token efficiency, code generation, and multimodal reasoning for multi-step
agentic workflows.
input_price: 1.5
output_price: 7.5
context_window: 1048576
capabilities: [vision, audio, video, tools, reasoning]
- id: google/gemini-3.5-flash
provider: google
display_name: Gemini 3.5 Flash
Expand All @@ -560,6 +569,15 @@ models:
output_price: 9.0
context_window: 1048576
capabilities: [vision, audio, video, tools, reasoning]
- id: google/gemini-3.5-flash-lite
provider: google
display_name: Gemini 3.5 Flash Lite
description: Fastest, most cost-effective 3.5-class model for high-throughput agentic search, document processing, and
lightweight subagent workflows.
input_price: 0.3
output_price: 2.5
context_window: 1048576
capabilities: [vision, audio, video, tools, reasoning]
- id: google/gemini-3.1-pro-preview
provider: google
display_name: Gemini 3.1 Pro
Expand Down
Loading