chore: import upstream snapshot with attribution
This commit is contained in:
@@ -0,0 +1,4 @@
|
||||
<?xml version="1.0" encoding="UTF-8"?>
|
||||
<svg id="STACKIT" xmlns="http://www.w3.org/2000/svg" version="1.1" viewBox="0 0 41.536063 41.536063">
|
||||
<path d="M13.9510149,10.4421038h20.8374634l-1.1608887,5.4412842h-14.5545654l-1.3522339,6.3352661h-6.2828369l2.5130615-11.7765503ZM22.5114397,25.652614H7.9081072l-1.1605225,5.4413452h20.8855591l2.5210571-11.8130493h-6.2828979l-1.3598633,6.3717041Z" fill="currentColor"/>
|
||||
</svg>
|
||||
|
After Width: | Height: | Size: 420 B |
@@ -0,0 +1,23 @@
|
||||
name = "Qwen3-VL 235B"
|
||||
description = "Qwen vision-language model for visual reasoning, documents, and agent tasks"
|
||||
family = "qwen"
|
||||
release_date = "2024-11-01"
|
||||
last_updated = "2024-11-01"
|
||||
attachment = true
|
||||
reasoning = false
|
||||
temperature = true
|
||||
tool_call = true
|
||||
structured_output = false
|
||||
open_weights = true
|
||||
|
||||
[cost]
|
||||
input = 1.76
|
||||
output = 2.05
|
||||
|
||||
[limit]
|
||||
context = 218_000
|
||||
output = 16_384
|
||||
|
||||
[modalities]
|
||||
input = ["text", "image"]
|
||||
output = ["text"]
|
||||
@@ -0,0 +1,23 @@
|
||||
name = "Qwen3-VL Embedding 8B"
|
||||
description = "Embedding model for semantic search, retrieval, clustering, and ranking pipelines"
|
||||
family = "qwen"
|
||||
release_date = "2026-02-05"
|
||||
last_updated = "2026-02-05"
|
||||
attachment = true
|
||||
reasoning = false
|
||||
temperature = false
|
||||
tool_call = false
|
||||
structured_output = false
|
||||
open_weights = true
|
||||
|
||||
[cost]
|
||||
input = 0.09
|
||||
output = 0.09
|
||||
|
||||
[limit]
|
||||
context = 32_000
|
||||
output = 4_096
|
||||
|
||||
[modalities]
|
||||
input = ["text", "image"]
|
||||
output = ["text"]
|
||||
@@ -0,0 +1,16 @@
|
||||
base_model = "alibaba/qwen3.6-27b"
|
||||
attachment = false
|
||||
reasoning = false
|
||||
structured_output = false
|
||||
|
||||
[cost]
|
||||
input = 0.53
|
||||
output = 0.76
|
||||
|
||||
[limit]
|
||||
context = 262_144
|
||||
output = 16_384
|
||||
|
||||
[modalities]
|
||||
input = ["text"]
|
||||
output = ["text"]
|
||||
@@ -0,0 +1,23 @@
|
||||
name = "Llama 3.3 70B"
|
||||
description = "Open Llama instruction model for multilingual chat, reasoning, and coding"
|
||||
family = "llama"
|
||||
release_date = "2024-12-05"
|
||||
last_updated = "2024-12-05"
|
||||
attachment = false
|
||||
reasoning = false
|
||||
temperature = true
|
||||
tool_call = true
|
||||
structured_output = false
|
||||
open_weights = true
|
||||
|
||||
[cost]
|
||||
input = 0.53
|
||||
output = 0.76
|
||||
|
||||
[limit]
|
||||
context = 128_000
|
||||
output = 4_096
|
||||
|
||||
[modalities]
|
||||
input = ["text"]
|
||||
output = ["text"]
|
||||
@@ -0,0 +1,23 @@
|
||||
name = "Gemma 3 27B"
|
||||
description = "Open Gemma instruction model for efficient chat and self-hosted deployments"
|
||||
family = "gemma"
|
||||
release_date = "2025-05-17"
|
||||
last_updated = "2025-05-17"
|
||||
attachment = true
|
||||
reasoning = false
|
||||
temperature = true
|
||||
tool_call = false
|
||||
structured_output = false
|
||||
open_weights = true
|
||||
|
||||
[cost]
|
||||
input = 0.53
|
||||
output = 0.76
|
||||
|
||||
[limit]
|
||||
context = 37_000
|
||||
output = 4_096
|
||||
|
||||
[modalities]
|
||||
input = ["text", "image"]
|
||||
output = ["text"]
|
||||
@@ -0,0 +1,23 @@
|
||||
name = "E5 Mistral 7B"
|
||||
description = "Embedding model for semantic search, retrieval, clustering, and ranking pipelines"
|
||||
family = "mistral"
|
||||
release_date = "2023-12-11"
|
||||
last_updated = "2023-12-11"
|
||||
attachment = false
|
||||
reasoning = false
|
||||
temperature = false
|
||||
tool_call = false
|
||||
structured_output = false
|
||||
open_weights = true
|
||||
|
||||
[cost]
|
||||
input = 0.02
|
||||
output = 0.02
|
||||
|
||||
[limit]
|
||||
context = 4_096
|
||||
output = 4_096
|
||||
|
||||
[modalities]
|
||||
input = ["text"]
|
||||
output = ["text"]
|
||||
@@ -0,0 +1,18 @@
|
||||
base_model = "openai/gpt-oss-120b"
|
||||
structured_output = false
|
||||
|
||||
[[reasoning_options]]
|
||||
type = "effort"
|
||||
values = ["low", "medium", "high"]
|
||||
|
||||
[cost]
|
||||
input = 0.53
|
||||
output = 0.76
|
||||
|
||||
[limit]
|
||||
context = 131_000
|
||||
output = 8_192
|
||||
|
||||
[modalities]
|
||||
input = ["text"]
|
||||
output = ["text"]
|
||||
@@ -0,0 +1,10 @@
|
||||
base_model = "openai/gpt-oss-20b"
|
||||
structured_output = false
|
||||
reasoning_options = []
|
||||
|
||||
[cost]
|
||||
input = 0.18
|
||||
output = 0.29
|
||||
|
||||
[limit]
|
||||
output = 8_192
|
||||
@@ -0,0 +1,10 @@
|
||||
name = "STACKIT"
|
||||
env = ["STACKIT_API_KEY"]
|
||||
npm = "@ai-sdk/openai-compatible"
|
||||
# Reasoning HTTP format (accessed 2026-06-25):
|
||||
# POST /v1/chat/completions is documented for GPT-OSS, but STACKIT does not
|
||||
# document a caller reasoning toggle, effort field, token budget, or bounds.
|
||||
# Source:
|
||||
# https://docs.stackit.cloud/products/data-and-ai/ai-model-serving/basics/available-shared-models
|
||||
doc = "https://docs.stackit.cloud/products/data-and-ai/ai-model-serving/basics/available-shared-models"
|
||||
api = "https://api.openai-compat.model-serving.eu01.onstackit.cloud/v1"
|
||||
Reference in New Issue
Block a user