Six of fourteen models named LiteLLM first on the direct prompt; ten named Portkey. Both were named by all fourteen models and LiteLLM carries 66 labels and Portkey 53, so the shares are not directly comparable.
Named in three categories this edition.
Named in two categories this edition.
Share is the count of first choices across the direct, paraphrase, budget and scale prompts over all fourteen models, for a mid-market B2B company; rank is within the category; every quote names the model and the prompt it came from. Both figures come from the LLM gateways and observability page.
Across every category in the November 2026 Edition, LiteLLM and Portkey were named in the same answer 144 times, of the 207 answers naming LiteLLM and the 169 naming Portkey. In those answers Portkey took the first choice thirty-four times and LiteLLM thirty-six.
| Model | Direct | Paraphrase | Comparative | Budget-constrained | Scale-constrained | Negative |
|---|---|---|---|---|---|---|
| Claude Haiku 4.5 | ||||||
| GPT-5.4 mini | ||||||
| Gemini 3.5 Flash | ||||||
| Perplexity Sonar | ||||||
| Grok 4.20 | ||||||
| Mistral Small | ||||||
| DeepSeek V4 Flash | ||||||
| Llama 4 Maverick | ||||||
| Qwen 3.7 Flash | ||||||
| Kimi K2 | ||||||
| GLM 4.7 FlashX | ||||||
| MiniMax M2.5 | ||||||
| GPT-6 Luna | ||||||
| Muse Glimmer 30B |
Bold names in an answer are the products the judge labeled a first choice; a model naming several gives each of them that label. The full answer text for every row is in the record.
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Six of eight in this category shown.
“"LiteLLM put a credential stealer on PyPI and Docker on the day of my test, its second compromised release this year." [6]” Muse Glimmer 30B · negative prompt · hard negative
“you should be especially cautious about—or avoid—self-hosted or open-source LLM gateways like LiteLLM and Ollama” Mistral Small · negative prompt · hard negative
“The clearest current red flag is LiteLLM’s 2026 package/container compromises; avoid unverified versions” Perplexity Sonar · negative prompt · hard negative
“The de facto open-source standard for multi-provider integration... Choose LiteLLM if you want a flexible, open-source proxy to eliminate vendor lock-in” Gemini 3.5 Flash · comparative prompt · first choice
“Best overall for a limited budget: Self‑host LiteLLM (or Bifrost) → pay only provider rates, full control, and strong cost governance.” GLM 4.7 FlashX · budget prompt · first choice
“Choose LiteLLM if you are a Python shop, need to self-host for data compliance, or want granular control over complex routing rules.” Qwen 3.7 Flash · comparative prompt · first choice
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Six of eight in this category shown.
“Avoid percentage-fee gateways until your monthly model spend exceeds $10,000–$35,000, as the fees become cost-prohibitive” MiniMax M2.5 · budget prompt · soft negative
“Providers like standard versions of OpenRouter or Portkey typically process logs across public infrastructure.” Qwen 3.7 Flash · negative prompt · soft negative
“It eliminates the subscription cost associated with commercial gateways (like Merge.dev or Portkey).” Qwen 3.7 Flash · budget prompt · soft negative
“the "best" LLM gateway typically comes down to a choice between the open-source standard, LiteLLM, or the observability-first solution, Portkey” Qwen 3.7 Flash · direct prompt · first choice
“consider starting with self-hosted open-source options (like Portkey's MIT-licensed tier or Envoy AI Gateway) where you control the data plane” Kimi K2 · negative prompt · first choice
“Portkey has long been the mid-market pick for teams that want guardrails, caching and logging in one product” Claude Haiku 4.5 · direct prompt · first choice
Comparisons are drawn for the top eight products in each category, each against each. The output is the models' output; nothing here is a recommendation by the index.