add-model

Name: add-model
Author: BerriAI

70stars10forks

How to install add-model?

berriai/litellm-skills/add-model

$npx -y skills add BerriAI/litellm-skills --skill add-model

Installs into the current project.

Summary

Add a new model to a live LiteLLM proxy. Walks the user through picking a provider, entering the deployment name and credentials, calls POST /model/new, then test-calls the model to confirm it routes correctly. Use when the user wants to add, register, deploy, or configure a new

Files · 1

View on GitHub

SKILL.md

1	# Add Model
2
3	Add a new LLM to a live LiteLLM proxy.
4
5	## Setup
6
7	Ask for these if not already known:
8	```
9	LITELLM_BASE_URL — e.g. https://my-proxy.example.com
10	LITELLM_API_KEY — proxy admin key
11	```
12
13	API reference: https://litellm.vercel.app/docs/proxy/model_management
14
15	## Ask the user
16
17	1. Public model name — what callers will send in `"model": "..."` (e.g. `gpt-4o`, `my-claude`, `llama3`)
18	2. Provider — pick from the table below
19	3. Credentials — whatever that provider needs
20
21	## Provider table
22
23	\| Provider \| `litellm_params.model` \| Extra params \|
24	\|---\|---\|---\|
25	\| OpenAI \| `openai/gpt-4o` \| `api_key` \|
26	\| Azure OpenAI \| `azure/<deployment-name>` \| `api_key`, `api_base`, `api_version` \|
27	\| Anthropic \| `anthropic/claude-3-5-sonnet-20241022` \| `api_key` \|
28	\| AWS Bedrock \| `bedrock/anthropic.claude-3-5-sonnet-20241022-v2:0` \| AWS creds via env \|
29	\| Google Vertex \| `vertex_ai/gemini-1.5-pro` \| `vertex_project`, `vertex_location` \|
30	\| Ollama \| `ollama/llama3` \| `api_base` (e.g. `http://localhost:11434`) \|
31	\| Groq \| `groq/llama-3.3-70b-versatile` \| `api_key` \|
32	\| Together AI \| `together_ai/meta-llama/Llama-3-70b` \| `api_key` \|
33	\| Mistral \| `mistral/mistral-large-latest` \| `api_key` \|
34
35	Full list: https://docs.litellm.ai/docs/providers
36
37	## Run
38
39	```bash
40	curl -s -X POST "$BASE/model/new" \
41	-H "Authorization: Bearer $KEY" \
42	-H "Content-Type: application/json" \
43	-d '{
44	"model_name": "<public-name>",
45	"litellm_params": {
46	"model": "<provider/deployment>",
47	"api_key": "<key>",
48	"api_base": "<base_if_needed>",
49	"api_version": "<version_if_azure>"
50	}
51	}'
52	```
53
54	## Test it
55
56	After adding, verify it routes:
57
58	```bash
59	curl -s -X POST "$BASE/chat/completions" \
60	-H "Authorization: Bearer $KEY" \
61	-H "Content-Type: application/json" \
62	-d '{
63	"model": "<public-name>",
64	"messages": [{"role": "user", "content": "say hi"}],
65	"max_tokens": 10
66	}'
67	```
68
69	## Output
70
71	Show `model_id` from the response — needed to update or delete the model later.
72	Report pass/fail from the test call.

People who liked this also viewed

6 picks

Type

add-model

70stars10forks

View on GitHub

How to install add-model?

berriai/litellm-skills/add-model

$npx -y skills add BerriAI/litellm-skills --skill add-model

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Add Model
2
3	Add a new LLM to a live LiteLLM proxy.
4
5	## Setup
6
7	Ask for these if not already known:
8	```
9	LITELLM_BASE_URL — e.g. https://my-proxy.example.com
10	LITELLM_API_KEY — proxy admin key
11	```
12
13	API reference: https://litellm.vercel.app/docs/proxy/model_management
14
15	## Ask the user
16
17	1. Public model name — what callers will send in `"model": "..."` (e.g. `gpt-4o`, `my-claude`, `llama3`)
18	2. Provider — pick from the table below
19	3. Credentials — whatever that provider needs
20
21	## Provider table
22
23	\| Provider \| `litellm_params.model` \| Extra params \|
24	\|---\|---\|---\|
25	\| OpenAI \| `openai/gpt-4o` \| `api_key` \|
26	\| Azure OpenAI \| `azure/<deployment-name>` \| `api_key`, `api_base`, `api_version` \|
27	\| Anthropic \| `anthropic/claude-3-5-sonnet-20241022` \| `api_key` \|
28	\| AWS Bedrock \| `bedrock/anthropic.claude-3-5-sonnet-20241022-v2:0` \| AWS creds via env \|
29	\| Google Vertex \| `vertex_ai/gemini-1.5-pro` \| `vertex_project`, `vertex_location` \|
30	\| Ollama \| `ollama/llama3` \| `api_base` (e.g. `http://localhost:11434`) \|
31	\| Groq \| `groq/llama-3.3-70b-versatile` \| `api_key` \|
32	\| Together AI \| `together_ai/meta-llama/Llama-3-70b` \| `api_key` \|
33	\| Mistral \| `mistral/mistral-large-latest` \| `api_key` \|
34
35	Full list: https://docs.litellm.ai/docs/providers
36
37	## Run
38
39	```bash
40	curl -s -X POST "$BASE/model/new" \
41	-H "Authorization: Bearer $KEY" \
42	-H "Content-Type: application/json" \
43	-d '{
44	"model_name": "<public-name>",
45	"litellm_params": {
46	"model": "<provider/deployment>",
47	"api_key": "<key>",
48	"api_base": "<base_if_needed>",
49	"api_version": "<version_if_azure>"
50	}
51	}'
52	```
53
54	## Test it
55
56	After adding, verify it routes:
57
58	```bash
59	curl -s -X POST "$BASE/chat/completions" \
60	-H "Authorization: Bearer $KEY" \
61	-H "Content-Type: application/json" \
62	-d '{
63	"model": "<public-name>",
64	"messages": [{"role": "user", "content": "say hi"}],
65	"max_tokens": 10
66	}'
67	```
68
69	## Output
70
71	Show `model_id` from the response — needed to update or delete the model later.
72	Report pass/fail from the test call.

People who liked this also viewed

6 picks

Type