Every category where a model named LiteLLM for a mid-market B2B company. Share is first choices across the direct, paraphrase, budget and scale prompts; rank is within every product named in that category.

Category	Function	Share	Rank	Negative rate	Labels	Quadrant
LLM gateways and observability	Data platform	38%	1 of 63	18%	51	endorsed leader
API gateways	Developer platform	0%	50 of 51	67%	3	under 10 labels · led by Kong Gateway at 61%

Movement

This is the first edition on this tier, so no move can be computed for LiteLLM yet. From the next edition this section shows, per buyer segment, whether its share moved by more than the measured noise floor.

By model

How each model treated LiteLLM across every prompt where it was named for a mid-market B2B company. Twelve models, six prompts per category.

Model	First choice	Alternative	Mention	Negative	Labels
Claude Haiku 4.5	2	1	0	0	3
GPT-5.4 mini	2	2	0	0	4
Gemini 3.5 Flash	3	2	1	1	7
Perplexity Sonar	2	0	1	1	4
Grok 4.1 Fast	1	2	1	2	6
Mistral Small	3	0	0	1	4
DeepSeek V4 Flash	2	1	1	1	5
Llama 4 Maverick	1	0	1	0	2
Qwen 3.7 Flash	2	1	1	1	5
Kimi K2	3	0	1	1	5
GLM 4.7 FlashX	1	1	0	2	4
MiniMax M2.5	1	3	0	1	5

By framing

Which of the six questions produced the naming. By model says how often; this says asked what. The first-choice count on the right carries the marks of the models that produced it.

FramingLabels by classFirst choices

Direct34 labels18

Paraphrase12 labels3

Comparative37 labels15not counted in share

Budget-constrained36 labels29

Scale-constrained14 labels5

Negative33 labels4not counted in share

First choiceAlternativeMentionNegative166 labels in all, every segment counted; 55 of the 74 first choices count toward share, since the comparative and negative framings do not. The bar is one segment per label class, to scale within the framing.

What the models said for it

Verbatim evidence the judge attached to positive labels.

“LiteLLM (Best Self-Hosted / Open-Source): The most popular open-source, Python-based gateway... Excellent choice if you want to deploy a gateway inside your own Kubernetes cluster.” Gemini 3.5 Flash · LLM gateways · scale prompt · first choice

“It is the standard choice for building internal developer platforms (IDPs) because it is open-source and fits into any existing architecture.” Qwen 3.7 Flash · LLM gateways · comparative prompt · first choice

“LiteLLM (for flexibility and cost control) or Helicone (for observability and ease of use) are the best LLM gateway choices” Mistral Small · LLM gateways · direct prompt · first choice

“LiteLLM is widely considered the best LLM gateway because it is open-source and free to self-host” Qwen 3.7 Flash · LLM gateways · budget prompt · first choice

And against it

Verbatim evidence attached to negative labels. A warning on a product with few labels is a warning; on a product with many, it is one voice among them.

“Be cautious with self-hosted or open-source LLM gateways like LiteLLM and Ollama, especially if internet-exposed, due to documented security risks... actively exploited and CISA KEV-listed” Grok 4.1 Fast · LLM gateways · negative prompt · hard negative

“LiteLLM (Critical Risk) ... Why it is dangerous: Recent research has shown that compromised LiteLLM instances can lead to Remote Code Execution (RCE) and full privilege escalation.” Qwen 3.7 Flash · LLM gateways · negative prompt · hard negative

“Avoid or exercise extreme caution with LiteLLM and LMDeploy in production or security-sensitive environments” Mistral Small · LLM gateways · negative prompt · hard negative

“there's one LLM gateway that stands out for having significant security issues: LiteLLM.” MiniMax M2.5 · LLM gateways · negative prompt · hard negative

Named alongside

The products named in the same answers as LiteLLM, over the 164 answers that named it. Took the first choice instead counts the answers where the other product was the first choice and LiteLLM was named but was not.

ProductSame answerTook the first choice insteadHead to head

Portkey122 of 16418Compare →

OpenRouter94 of 1647Not in the top three

Bifrost67 of 16414Not in the top three

Cloudflare AI Gateway65 of 1643Not in the top three

Helicone62 of 1641Compare →

Kong AI Gateway51 of 1642Not in the top three

TrueFoundry17 of 1642Not in the top three

Braintrust Gateway14 of 1641Not in the top three

Langfuse12 of 1643Not in the top three

Braintrust11 of 1640Not in the top three

A head-to-head page exists where both products are in a category's top three. The other rows are the same fact without a page behind them, so they link to the product instead.

What carried it into the answer

The sites and pages cited by the answers that named LiteLLM. A fact about retrieval, not a lever on the model.

Citations exist only for the models that return a source list, four of the twelve in this edition, so these counts come from 138 of the 164 answers that named LiteLLM and are not a share of its labels.

Domains cited

getmaxim.ai78

truefoundry.com67

cloudzero.com66

dev.to62

dataiku.com59

respan.ai57

orq.ai56

braintrust.dev52

techsy.io52

openrouter.ai29

578 of the 578 domain citations in answers naming LiteLLM came from somebody else's page.

Pages cited

cloudzero.com/blog/llm-gateways66

dataiku.com/blog/best-llm-gateways59

orq.ai/blog/best-llm-gateways52

respan.ai/articles/best-llm-gateways52

techsy.io/en/blog/best-llm-gateway-tools52

truefoundry.com/blog/best-llm-gateways43

braintrust.dev/articles/best-llm-gateways-202637

getmaxim.ai/articles/top-5-llm-gateways-in-2026-a-production-ready-comparison32

Pages are listed as the models cited them.

Names read as LiteLLM

What the judge wrote, as written, with how often. The vendor table decides that these count as LiteLLM; a claim can dispute any of them.

LiteLLM Enterprise 2LiteLLM (Self-Hosted Instances) 1LiteLLM Proxy 1LiteLLM self-hosted 1

Is this your product?

Claim this page

Claiming is free and changes nothing in the data. A claimed page shows a verified contact who is told when each edition publishes and when LiteLLM's standing changes by more than the noise floor; the right to propose corrections to the vendor table, meaning names the judge wrote that should or should not read as LiteLLM, applied by version and listed in the change log; and a one-line description supplied by the vendor and marked as such.

It does not get any change to labels, shares or verdicts, any preview, or any say over which quotes appear. A verification link goes to your work email; an address at litellm.ai is approved on the spot, any other address is reviewed by hand.

Your name and company appear on the claimed page, or the company alone if you ask below. A title and a LinkedIn address appear there too if you give them, and are left off if you do not. Your email address is never published.