Model rankings

AI model rankings

See which models developers run through LLMFlux, measured from real gateway traffic, with tokens processed, request volume, success rate and latency. When a period has too little traffic to rank fairly, we show featured models from the live catalogue instead and label them that way.

Not enough traffic to rank the last 24 hours. Usage rankings appear once a period has at least 1.0M tokens from 3 or more customers. Until then this list shows featured models in editor order. Any usage figures shown are real. Try All time.

Models available28in the live catalogue
Model makers10Anthropic, DeepSeek, Google
Healthy now00 degraded · from 24h health checks
Largest context1.0Mtokens

Featured models

Editor-selected order, followed by the rest of the catalogue. This is not a popularity ranking.

ModelUptime 24hPrice in / outDetails
1
Claude Fable 5claude-fable-5 · Anthropic
6.2s21.11%$15 / $75Details
2
Claude Opus 4.8claude-opus-4-8 · Anthropic
6.4s20.35%$7.5 / $37.5Details
3
Claude Opus 5claude-opus-5 · Anthropic
6.6s21.11%$7.5 / $37.5Details
4
Claude Opus 5.5claude-opus-5-5 · Anthropic
7.1s20.60%$6 / $30Details
5
Claude Sonnet 5claude-sonnet-5 · Anthropic
5.5s22.05%$3 / $15Details
6
Claude Sonnet 5.5claude-sonnet-5-5 · Anthropic
8.2s12.11%$3 / $15Details
7
DeepSeek Unrestricteddeepseek-unrestricted · DeepSeek
1.9s5.88%$1.5 / $6Details
8
DeepSeek V4-FLASHdeepseek-v4-flash · DeepSeek
907ms5.91%$0.7 / $1.4Details
9
DeepSeek V4.1 Flashdeepseek-v4.1-flash · DeepSeek
869ms0.24%$1.5 / $6Details
10
Gemini 3.8-FLASHgemini-3.8-flash · Google
4.9s9.16%$3.75 / $18.75Details
11
MiniMax M2.7minimax-m2.7 · MiniMax
986ms5.29%$1.5 / $6Details
12
Nemotron 3 Supernemotron-3-super · NVIDIA
41ms76.33%$0.375 / $2Details
13
Nemotron 3 Ultranemotron-3-ultra-550b-a55b · NVIDIA
3.1s22.64%$3 / $12Details
14
Nemotron 3 Ultra 2nemotron-3-ultra-unrestricted · NVIDIA
4.7s27.99%$3 / $12Details
15
Nemotron 3.5 Lightningnemotron-3.5-lightning · NVIDIA
4.2s22.14%$0.35 / $1Details
16
Nemotron 3.5 Super VL 120Bnemotron-3.5-super-vl · NVIDIA
3.3s21.58%$0.75 / $2.35Details
17
Qwen UNRESTRICTEDqwen-unrestricted · Qwen
4.5s2.95%$10 / $30Details
18
Qwen 3.8-27Bqwen3.8-27b · Qwen
5.6s3.93%$0.75 / $9.375Details
19
Xing 4.0 29B-A4Bxing4.0-29b-a4b · TeleAI
33ms75.38%$1.1 / $4.5Details
20
Solar Mini 4solar-mini4 · Upstage
8.5s1.97%$0.5 / $2Details
21
Solar Pro 4solar-pro4 · Upstage
4.5s1.99%$1.5 / $6Details
22
Solar Unrestrictedsolar-unrestricted · Upstage
5.1s1.74%$1.5 / $6Details
23
Grok 4.6grok-4.6 · xAI
8.7s2.00%$10 / $30Details
24
Grok 4.7grok-4.7 · xAI
6.5s1.75%$10 / $30Details
25
Grok Unrestrictedgrok-unrestricted · xAI
10.1s0.50%$10 / $30Details
26
GLM-5.3 Flashglm-5.3-flash · Zhipu AI
10.0s1.75%$0.75 / $2.5Details
27
GLM-5.3 Flash 2glm-5.3-flash-2 · Zhipu AI
34ms75.25%$0.75 / $2.5Details
28
GLM UNRESTRICTEDglm-unrestricted · Zhipu AI
30ms75.19%$7 / $22Details

Methodology

  • Source. Every request through the LLMFlux gateway. Tokens and requests count successful requests (HTTP status below 400) only, so failed attempts are not counted as usage.
  • Ranking. By tokens processed in the period. Change compares with the previous period of the same length.
  • Quality. Success rate = successful ÷ all requests. Latency = median end-to-end time of successful requests.
  • Privacy. Only aggregated totals are published. A model used by fewer than 2 customers shows “Limited” and gets no rank.
  • Thresholds. Usage rankings need 1.0M tokens from 3 customers in the period; otherwise featured models are shown.
  • Freshness. Last updated Nov 20, 2026, 2:56 PM UTC. Recalculated every 10 minutes.

Questions

How are models ranked?
When there is enough real traffic in the selected period, models are ranked by tokens processed through the LLMFlux gateway in successful requests (HTTP status below 400). Request counts, success rate and median latency are measured from the same requests.
What does "Featured models" mean?
When a period has too little traffic to rank fairly, the page lists models from the live catalogue in an order chosen by the LLMFlux team instead. That order is editorial, not a popularity ranking, and any usage figures shown next to it are still real.
Why do some models show "Limited"?
To protect customer privacy, usage figures are hidden for a model that only one or two customers used in the period, and it is not given a rank position.
How often is the data updated?
Rankings are recalculated on the server every few minutes. The time of the last update is shown on the page.
Can I use every ranked model through one API?
Yes. Every model listed is in the LLMFlux catalogue and can be called with one API key through the OpenAI-compatible or Anthropic-compatible endpoints.

Try any ranked model with one API key

OpenAI- and Anthropic-compatible endpoints, streaming, and per-request usage logs.

AI Model Rankings & Usage Trends | LLMFLUX