Skip to content

Add Regolo-ai Provider #758

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
massaindustries wants to merge 4 commits into
base: dev
Choose a base branch
from
Open

Add Regolo-ai Provider #758

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
19ace44
add-regolo-01
massaindustries Jan 29, 2026
a46966e
add-regolo-02
massaindustries Jan 29, 2026
bb42d0b
add qwen-next-coder
massaindustries Feb 5, 2026
6ecd9ec
add qwen-next-coder-2
massaindustries Feb 5, 2026
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
46 changes: 46 additions & 0 deletions providers/regolo-ai/logo.svg
View file
Open in desktop
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
24 changes: 24 additions & 0 deletions providers/regolo-ai/models/Llama-3.1-8B-Instruct.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,24 @@
name = "Llama‑3.1‑8B‑Instruct"
family = "llama-3.1"
release_date = "2025-04-07"
last_updated = "2025-04-07"
attachment = false
reasoning = false
temperature = true
tool_call = true
open_weights = false

[description]
text = "Llama‑3.1‑8B‑Instruct is a compact multilingual language model by Meta, designed for instruction following and conversational use, with reliable performance in text understanding, code generation, and structured outputs."

[cost]
input = 0.05 # € per 1M tokens (0.00000005 * 1_000_000)
output = 0.25 # € per 1M tokens (0.00000025 * 1_000_000)

[limit]
context = 120000
output = 120000

[modalities]
input = ["text"]
output = ["text"]
24 changes: 24 additions & 0 deletions providers/regolo-ai/models/Llama-3.3-70B-Instruct.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,24 @@
name = "Llama‑3.3‑70B‑Instruct"
family = "llama-3.3"
release_date = "2025-04-28"
last_updated = "2025-04-28"
attachment = false
reasoning = false
temperature = true
tool_call = true
open_weights = false

[description]
text = "Llama‑3.3‑70B‑Instruct is a 70B‑parameter multilingual language model by Meta, designed for instruction following, long‑context understanding, and structured reasoning, with strong capabilities in code generation and complex analytical tasks."

[cost]
input = 0.60 # € per 1M tokens (0.0000006 * 1_000_000)
output = 2.70 # € per 1M tokens (0.0000027 * 1_000_000)

[limit]
context = 16000
output = 16000

[modalities]
input = ["text"]
output = ["text"]
24 changes: 24 additions & 0 deletions providers/regolo-ai/models/Qwen3-8B.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,24 @@
name = "Qwen3‑8B"
family = "qwen3-8b"
release_date = "2025-04-28"
last_updated = "2025-04-28"
attachment = false
reasoning = true
temperature = true
tool_call = true
open_weights = false

[description]
text = "Qwen3‑8B is a versatile 8.2‑billion parameter language model that uniquely allows switching between a step‑by‑step 'thinking mode' for complex tasks and a fast 'non‑thinking mode' for general conversation."

[cost]
input = 0.07 # € per 1M tokens (placeholder from Regolo pricing)
output = 0.35 # € per 1M tokens (placeholder from Regolo pricing)

[limit]
context = 40960
output = 40960

[modalities]
input = ["text"]
output = ["text"]
24 changes: 24 additions & 0 deletions providers/regolo-ai/models/deepseek-r1-70b.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,24 @@
name = "deepseek‑r1‑70b"
family = "deepseek-r1"
release_date = "2025-01-20"
last_updated = "2025-01-20"
attachment = false
reasoning = true
temperature = true
tool_call = true
open_weights = false

[description]
text = "DeepSeek‑R1‑Distill‑Llama‑70B is a 70B‑parameter distilled LLM, combining reasoning, speed, and accuracy for code, math, and complex logic tasks."

[cost]
input = 0.60 # € per 1M tokens (0.0000006 * 1_000_000)
output = 2.70 # € per 1M tokens (0.0000027 * 1_000_000)

[limit]
context = 128000
output = 128000

[modalities]
input = ["text"]
output = ["text"]
24 changes: 24 additions & 0 deletions providers/regolo-ai/models/gpt-oss-120b.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,24 @@
name = "gpt-oss-120b"
family = "gpt-oss"
release_date = "2025-08-05"
last_updated = "2025-08-05"
attachment = false
reasoning = true
temperature = true
tool_call = true
open_weights = false

[description]
text = "GPT‑OSS‑120B is an open‑weight 117B‑parameter Mixture‑of‑Experts model by OpenAI, using only 5.1B active parameters per token. Supports reasoning, chain‑of‑thought, tool use, and fine‑tuning."

[cost]
input = 1.00 # € per 1M tokens (0.000001 * 1_000_000)
output = 4.20 # € per 1M tokens (0.0000042 * 1_000_000)

[limit]
context = 128000
output = 128000

[modalities]
input = ["text"]
output = ["text"]
24 changes: 24 additions & 0 deletions providers/regolo-ai/models/mistral-small3.2.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,24 @@
name = "mistral‑small3.2"
family = "mistral-small3.2"
release_date = "2025-01-31"
last_updated = "2025-01-31"
attachment = false
reasoning = true
temperature = true
tool_call = true
open_weights = false

[description]
text = "Mistral‑Small‑3.2‑24B‑Instruct‑2506: 24B multimodal instruction‑tuned model, optimized for reasoning and STEM, supports robust function calling, reduces repetition, handles both text and vision inputs efficiently."

[cost]
input = 0.50 # € per 1M tokens (0.0000005 * 1_000_000)
output = 2.20 # € per 1M tokens (0.0000022 * 1_000_000)

[limit]
context = 120000
output = 120000

[modalities]
input = ["text"]
output = ["text"]
24 changes: 24 additions & 0 deletions providers/regolo-ai/models/qwen3-coder-30b.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,24 @@
name = "qwen3‑coder‑30b"
family = "qwen3-coder-30b"
release_date = "2025-01-01"
last_updated = "2025-01-01"
attachment = false
reasoning = false
temperature = true
tool_call = true
open_weights = false

[description]
text = "Qwen3‑Coder‑30B is a large‑scale MOE coding model designed for complex software tasks, featuring strong code understanding, long‑context reasoning, and reliable structured outputs for repository‑level analysis and agentic programming workflows."

[cost]
input = 0.50 # € per 1M tokens (0.0000005 * 1_000_000)
output = 2.00 # € per 1M tokens (0.0000020 * 1_000_000)

[limit]
context = 120000
output = 120000

[modalities]
input = ["text"]
output = ["text"]
24 changes: 24 additions & 0 deletions providers/regolo-ai/models/qwen3-coder-next.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,24 @@
name = "qwen3-coder-next"
family = "qwen3-coder-next-fp8"
release_date = "2025-02-05"
last_updated = "2025-02-05"
attachment = false
reasoning = false
temperature = true
tool_call = true
open_weights = false

[description]
text = "Qwen3-Coder-Next-FP8 is a 3B activated (80B total) MoE coding model designed for coding agents and local development. Features 256K context length and advanced tool calling capabilities."

[cost]
input = 0.50 # € per 1M tokens
output = 2.00 # € per 1M tokens

[limit]
context = 262144
output = 65536

[modalities]
input = ["text"]
output = ["text"]
26 changes: 26 additions & 0 deletions providers/regolo-ai/models/qwen3-vl-32b.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,26 @@
name = "qwen3‑vl‑32b"
family = "qwen3-vl-32b"
release_date = "2025-01-01"
last_updated = "2025-01-01"
attachment = true
reasoning = true
temperature = true
tool_call = true
open_weights = false

[description]
text = "Qwen3‑VL‑32B is a 32‑billion‑parameter multimodal vision‑language model from the Qwen 3 family, supporting text, image, audio and video inputs."

[cost]
# Prices need verification against Regolo pricing page
input = 0.50 # € per 1M tokens (official price)
output = 2.50 # € per 1M tokens (official price)

[limit]
context = 128000
output = 128000

[modalities]
input = ["text", "image"]
output = ["text"]

5 changes: 5 additions & 0 deletions providers/regolo-ai/provider.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,5 @@
name = "Regolo AI"
env = ["REGOLO_API_KEY"]
npm = "@ai-sdk/openai-compatible"
doc = "https://docs.regolo.ai/"
api = "https://api.regolo.ai/v1"