github-featured/anomalyco--models.dev
2
0
Fork 0
Code Issues Pull Requests Deployments Models Agent Notes Packages Projects Releases Wiki Activity

feat: add Arcee AI lab and Trinity models (#4655)

Browse Source 
* feat: add Arcee AI lab and Trinity models

* fix: correct Trinity metadata dates

* fix: align Trinity descriptions with model cards
This commit is contained in:
Eric W. Tramel
2026-08-13 18:58:59 -04:00
committed by GitHub
parent 9b01dfab0e
commit 142715e73f
14 changed files with 170 additions and 109 deletions
Download Patch File Download Diff File Expand all files Collapse all files
labs/arcee-ai/lab.toml
+1
View File
@@ -0,0 +1 @@
description = "Arcee AI develops open-weight language models focused on efficient reasoning, tool use, and deployable intelligence."
labs/arcee-ai/logo.svg
+1
View File
@@ -0,0 +1 @@
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" fill="currentColor" fill-rule="evenodd"><path d="M13.236 2.377 2.751 20.493H0L11.863 0l1.373 2.377zm3.554 6.156-9.606 11.96H4.13L15.511 6.32l1.279 2.212zm6.908 11.96H14.05l8.406-2.151 1.242 2.15zm-3.42-5.922-7.843 5.92H8.482l10.597-7.997 1.2 2.077z"/></svg>
Side by Side

After

Width:  |  Height:  |  Size: 318 B

models/arcee-ai/trinity-large-preview.toml
+40
View File
@@ -0,0 +1,40 @@
# Source: https://huggingface.co/arcee-ai/Trinity-Large-Preview
name = "Trinity Large Preview"
description = "Lightly post-trained 398B MoE chat model for creative work, long-context prompts, and tool-using agents"
family = "trinity"
release_date = "2026-01-27"
last_updated = "2026-05-28"
attachment = false
reasoning = false
temperature = true
tool_call = true
open_weights = true
license = "OpenMDW-1.1"
[limit]
context = 524_288
output = 262_144
[modalities]
input = ["text"]
output = ["text"]
[[weights]]
label = "Hugging Face"
url = "https://huggingface.co/arcee-ai/Trinity-Large-Preview"
format = "safetensors"
[[links]]
label = "Model card"
url = "https://huggingface.co/arcee-ai/Trinity-Large-Preview"
type = "model_card"
[[links]]
label = "Announcement"
url = "https://www.arcee.ai/blog/trinity-large"
type = "announcement"
[[links]]
label = "License"
url = "https://huggingface.co/arcee-ai/Trinity-Large-Preview/blob/main/LICENSE"
type = "license"
models/arcee-ai/trinity-large-thinking.toml
+40
View File
@@ -0,0 +1,40 @@
# Source: https://huggingface.co/arcee-ai/Trinity-Large-Thinking
name = "Trinity Large Thinking"
description = "Reasoning-optimized 398B MoE agent model with extended thinking for long-horizon and multi-turn tool use"
family = "trinity"
release_date = "2026-04-01"
last_updated = "2026-05-28"
attachment = false
reasoning = true
temperature = true
tool_call = true
open_weights = true
license = "OpenMDW-1.1"
[limit]
context = 524_288
output = 262_144
[modalities]
input = ["text"]
output = ["text"]
[[weights]]
label = "Hugging Face"
url = "https://huggingface.co/arcee-ai/Trinity-Large-Thinking"
format = "safetensors"
[[links]]
label = "Model card"
url = "https://huggingface.co/arcee-ai/Trinity-Large-Thinking"
type = "model_card"
[[links]]
label = "Announcement"
url = "https://www.arcee.ai/blog/trinity-large-thinking"
type = "announcement"
[[links]]
label = "License"
url = "https://huggingface.co/arcee-ai/Trinity-Large-Thinking/blob/main/LICENSE"
type = "license"
models/arcee-ai/trinity-mini.toml
+40
View File
@@ -0,0 +1,40 @@
# Source: https://huggingface.co/arcee-ai/Trinity-Mini
name = "Trinity Mini"
description = "Reasoning-tuned 26B MoE model with 3B active parameters for agents, tools, and multi-step workloads"
family = "trinity"
release_date = "2025-12-01"
last_updated = "2026-05-28"
attachment = false
reasoning = true
temperature = true
tool_call = true
open_weights = true
license = "OpenMDW-1.1"
[limit]
context = 131_072
output = 131_072
[modalities]
input = ["text"]
output = ["text"]
[[weights]]
label = "Hugging Face"
url = "https://huggingface.co/arcee-ai/Trinity-Mini"
format = "safetensors"
[[links]]
label = "Model card"
url = "https://huggingface.co/arcee-ai/Trinity-Mini"
type = "model_card"
[[links]]
label = "Announcement"
url = "https://www.arcee.ai/blog/the-trinity-manifesto"
type = "announcement"
[[links]]
label = "License"
url = "https://huggingface.co/arcee-ai/Trinity-Mini/blob/main/LICENSE"
type = "license"
models/arcee-ai/trinity-nano-preview.toml
+40
View File
@@ -0,0 +1,40 @@
# Source: https://huggingface.co/arcee-ai/Trinity-Nano-Preview
name = "Trinity Nano Preview"
description = "Experimental chat-tuned 6B MoE model with 1B active parameters for low-resource chat and instruction following"
family = "trinity"
release_date = "2025-12-01"
last_updated = "2026-05-28"
attachment = false
reasoning = false
temperature = true
tool_call = true
open_weights = true
license = "OpenMDW-1.1"
[limit]
context = 131_072
output = 131_072
[modalities]
input = ["text"]
output = ["text"]
[[weights]]
label = "Hugging Face"
url = "https://huggingface.co/arcee-ai/Trinity-Nano-Preview"
format = "safetensors"
[[links]]
label = "Model card"
url = "https://huggingface.co/arcee-ai/Trinity-Nano-Preview"
type = "model_card"
[[links]]
label = "Announcement"
url = "https://www.arcee.ai/blog/the-trinity-manifesto"
type = "announcement"
[[links]]
label = "License"
url = "https://huggingface.co/arcee-ai/Trinity-Nano-Preview/blob/main/LICENSE"
type = "license"
providers/clarifai/models/arcee_ai/AFM/models/trinity-mini.toml
+1 -17
View File
@@ -1,24 +1,8 @@
name = "Trinity Mini"
description = "Efficient model for low-latency assistance, extraction, and routine automation"
family = "trinity-mini"
release_date = "2025-12"
base_model = "arcee-ai/trinity-mini"
last_updated = "2026-02-25"
attachment = false
reasoning = true
reasoning_options = []
temperature = true
tool_call = true
knowledge = "2024-10"
open_weights = true
[cost]
input = 0.045
output = 0.15
[limit]
context = 131_072
output = 131_072
[modalities]
input = ["text"]
output = ["text"]
providers/digitalocean/models/arcee-trinity-large-thinking.toml
+1 -12
View File
@@ -1,13 +1,6 @@
base_model = "arcee-ai/trinity-large-thinking"
name = "Arcee Trinity Large Thinking (Public Preview)"
description = "Flagship model for demanding analysis, coding, and production agent workflows"
family = "trinity"
release_date = "2026-04-02"
last_updated = "2026-04-16"
attachment = false
reasoning = true
temperature = true
tool_call = true
open_weights = true
[[reasoning_options]]
type = "effort"
@@ -21,7 +14,3 @@ cache_read = 0.06
[limit]
context = 128_000
output = 32_000
[modalities]
input = ["text"]
output = ["text"]
providers/kilo/models/arcee-ai/trinity-large-thinking.toml
+1 -13
View File
@@ -1,14 +1,6 @@
base_model = "arcee-ai/trinity-large-thinking"
name = "Arcee AI: Trinity Large Thinking"
description = "Flagship model for demanding analysis, coding, and production agent workflows"
family = "trinity"
release_date = "2026-04-01"
last_updated = "2026-04-01"
attachment = false
reasoning = true
temperature = true
tool_call = true
structured_output = true
open_weights = false
[[reasoning_options]]
type = "effort"
@@ -22,7 +14,3 @@ cache_read = 0.06
[limit]
context = 262_144
output = 262_144
[modalities]
input = ["text"]
output = ["text"]
providers/nano-gpt/models/arcee-ai/trinity-large-thinking.toml
+1 -13
View File
@@ -1,14 +1,6 @@
# Not included in subscription
name = "Trinity Large Thinking"
description = "Flagship model for demanding analysis, coding, and production agent workflows"
family = "trinity"
release_date = "2026-04-01"
last_updated = "2026-04-01"
attachment = false
reasoning = true
tool_call = true
base_model = "arcee-ai/trinity-large-thinking"
structured_output = false
open_weights = true
reasoning_options = []
[cost]
@@ -20,7 +12,3 @@ cache_read = 0.125
context = 262_144
input = 262_144
output = 80_000
[modalities]
input = ["text"]
output = ["text"]
providers/opencode/models/trinity-large-preview-free.toml
+1 -12
View File
@@ -1,14 +1,7 @@
name = "Trinity Large Preview"
base_model = "arcee-ai/trinity-large-preview"
description = "Legacy model retained for compatibility with older integrations"
family = "trinity"
release_date = "2026-01-28"
last_updated = "2026-01-28"
attachment = false
reasoning = false
temperature = true
knowledge = "2025-06"
tool_call = true
open_weights = true
status = "deprecated"
[cost]
@@ -18,7 +11,3 @@ output = 0.00
[limit]
context = 131_072
output = 131_072
[modalities]
input = ["text"]
output = ["text"]
providers/openrouter/models/arcee-ai/trinity-large-thinking.toml
+1 -14
View File
@@ -1,14 +1,5 @@
name = "Trinity Large Thinking"
description = "Flagship model for demanding analysis, coding, and production agent workflows"
family = "trinity"
release_date = "2026-04-01"
last_updated = "2026-04-01"
attachment = false
reasoning = true
temperature = true
tool_call = true
base_model = "arcee-ai/trinity-large-thinking"
structured_output = true
open_weights = true
reasoning_options = []
[cost]
@@ -19,7 +10,3 @@ cache_read = 0.06
[limit]
context = 262_144
output = 262_144
[modalities]
input = ["text"]
output = ["text"]
providers/vercel/models/arcee-ai/trinity-large-thinking.toml
+1 -13
View File
@@ -1,14 +1,6 @@
name = "Trinity Large Thinking"
description = "Flagship model for demanding analysis, coding, and production agent workflows"
family = "trinity"
attachment = false
reasoning = true
base_model = "arcee-ai/trinity-large-thinking"
reasoning_options = []
tool_call = true
temperature = true
release_date = "2026-04-01"
last_updated = "2026-04-03"
open_weights = true
[cost]
input = 0.25
@@ -17,7 +9,3 @@ output = 0.8999999999999999
[limit]
context = 262_100
output = 80_000
[modalities]
input = ["text"]
output = ["text"]
providers/vercel/models/arcee-ai/trinity-mini.toml
+1 -15
View File
@@ -1,23 +1,9 @@
name = "Trinity Mini"
description = "Efficient model for low-latency assistance, extraction, and routine automation"
family = "trinity"
release_date = "2025-12-01"
base_model = "arcee-ai/trinity-mini"
last_updated = "2025-12"
attachment = false
reasoning = false
temperature = true
tool_call = false
knowledge = "2024-10"
open_weights = false
[cost]
input = 0.045
output = 0.15
[limit]
context = 131_072
output = 131_072
[modalities]
input = ["text"]
output = ["text"]