Top for agents
LMSpeed is an AI model directory for comparing API price, output speed, first-token latency, provider coverage, and benchmark data. Use it to narrow your model and provider choice, then test the endpoint that fits your workload.
Price, speed, latency, and availability can change. Treat this table as a current signal and verify your own endpoint before you deploy.
| Release date | |||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Context— | Input— | Output— | Providers |
Agents, Coding, Reasoning, and the other capability columns are 0–100 observed-capability estimates relative to the eligible model population in a dated Category Score V3 run.
They are not success rates, IQ scores, or an average across all eight categories. Read them with the 80% interval, measured dimensions, benchmark families, and evidence shown on each model page.
Each row brings together the information you need to compare an LLM API. Some fields are blank when LMSpeed has no current data for that model or provider.
Start with the decision that matters most for your workload, then compare the current rows before you test an endpoint.
LMSpeed runs standardized five-round API speed tests on each model, measuring output throughput (tokens per second), first-token latency, and total response time across multiple providers.
Latency varies by provider and model. Use the LMSpeed model directory to sort by latency and find the model with the fastest first-token response time. Check the latency leaderboard for monthly rankings.
LMSpeed lists input and output token prices per million for each model across available providers. Sort by price to find a lower-cost option, or filter by provider to compare rates side by side.
— |
— |
— |
— |
— |
— |
— |
— |
| Throughput — | Latency — |
| Release date— |
|
| GLM-4.5 AirXZhipu AI | Context— | Input— | Output— | Providers +24 | — | — | — | — | — | — | — | — | Throughput 71 t/s | Latency 11.56s | Release date— |
|
| GPT-4o Mini TTSOpenAI | Context— | Input— | Output— | Providers +39 | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| Claude 2.1Anthropic | Context— | Input— | Output— | Providers +8 | — | 34.3±13.9P | 35.4±11.1E | — | 38.2±11.8E | — | — | — | Throughput — | Latency — | Release date— |
|
| Qwen3.5 Plus Image | Context— | Input— | Output— | Providers +1 | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| Grok 3 Mini | Context— | Input— | Output— | Providers +75 | — | — | — | — | — | — | — | — | Throughput 122 t/s | Latency 5.23s | Release date— |
|
| ChatGPT-4oOpenAI | Context— | Input— | Output— | Providers +45 | — | — | — | — | — | — | — | — | Throughput 78 t/s | Latency 4.56s | Release date— |
|
| Claude Instant 1.2Anthropic | Context— | Input— | Output— | Providers +6 | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| GLM-4 LongZhipu AI | Context— | Input— | Output— | Providers +17 | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| MiniMax-Text-01 | Context— | Input— | Output— | Providers +2 | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| Net GPT-4o | Context— | Input— | Output— | Providers | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| MiniMax Feed | Context— | Input— | Output— | Providers +1 | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| GPT-4 GizmoOpenAI | Context— | Input— | Output— | Providers +23 | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| Qwen3 TTS Flash Realtime | Context— | Input— | Output— | Providers +13 | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| GPT Image 1.5OpenAI | Context— | Input— | Output— | Providers +106 | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| GPT-4 NetOpenAI | Context— | Input— | Output— | Providers +2 | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| MiniMax M2.5 Lightning | Context— | Input— | Output— | Providers +6 | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| GPT-4o ImageOpenAI | Context— | Input— | Output— | Providers +27 | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| GPT-5 Codex MiniOpenAI | Context— | Input— | Output— | Providers +62 | — | — | — | — | — | — | — | — | Throughput 38 t/s | Latency 3.35s | Release date— |
|
| ChatGPT Image | Context— | Input— | Output— | Providers +15 | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| FLUX Kontext Pro | Context— | Input— | Output— | Providers +17 | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| GPT-4o Transcribe DiarizeOpenAI | Context— | Input— | Output— | Providers +16 | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| GLM-Z1 AirXZhipu AI | Context— | Input— | Output— | Providers +7 | — | — | — | — | — | — | — | — | Throughput 168 t/s | Latency 0.34s | Release date— |
|
| GLM-Z1 FlashZhipu AI | Context— | Input— | Output— | Providers +18 | — | — | — | — | — | — | — | — | Throughput 109 t/s | Latency 0.45s | Release date— |
|
| GLM-4VZhipu AI | Context— | Input— | Output— | Providers +17 | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| Gemini 2.5 Flash Native AudioGoogle | Context— | Input— | Output— | Providers +6 | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| BGE Reranker V2 M3 | Context— | Input— | Output— | Providers +39 | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| Gemini 2.0 Flash 001Google | Context— | Input— | Output— | Providers +21 | — | — | — | — | — | — | — | — | Throughput 108 t/s | Latency 2.70s | Release date— |
|
| GPT-4o RealtimeOpenAI | Context— | Input— | Output— | Providers +69 | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| Qwen3 TTS Flash | Context— | Input— | Output— | Providers +28 | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| Claude 1.3Anthropic | Context— | Input— | Output— | Providers +1 | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| Grok 3 | Context— | Input$4.00/M | Output$20.00/M | Providers +87 | — | 48.3±13.9P | 48.7±11.1E | — | 47.3±9.3E | — | — | — | Throughput 43 t/s | Latency 2.64s | Release date— |
|
| MiniMax M2.7 HighSpeed | Context— | Input— | Output— | Providers +51 | — | — | — | — | — | — | — | — | Throughput 49 t/s | Latency 3.53s | Release date— |
|
| GPT-4o Mini RealtimeOpenAI | Context— | Input— | Output— | Providers +33 | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| Kimi K2 InstructMoonshot AI | Context— | Input— | Output— | Providers +78 | — | — | — | — | — | — | — | — | Throughput 129 t/s | Latency 1.05s | Release date— |
|
| GLM-3 TurboZhipu AI | Context— | Input— | Output— | Providers +21 | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| Fish Speech 1.5 | Context— | Input— | Output— | Providers +1 | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| MiniMax Video | Context— | Input— | Output— | Providers +1 | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| Qwen3.1Alibaba | Context— | Input— | Output— | Providers +11 | — | — | — | — | — | — | — | — | Throughput 151 t/s | Latency 4.42s | Release date— |
|
| Grok-2 | Context— | Input— | Output— | Providers +16 | — | 41.8±13.9P | 43.1±11.1E | — | 46.1±11.8E | — | — | — | Throughput 59 t/s | Latency 0.60s | Release date— |
|
| GPT-4o Mini AudioOpenAI | Context— | Input— | Output— | Providers +33 | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| DeepSeek OCRDeepSeek | Context— | Input— | Output— | Providers +36 | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| GLM-4V PlusZhipu AI | Context— | Input— | Output— | Providers +9 | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| V0 1.5 MD | Context— | Input— | Output— | Providers | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| GPT-4o AudioOpenAI | Context— | Input— | Output— | Providers +76 | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| Gemini 2.0 FlashGoogle | Context— | Input$0.150/M | Output$0.600/M | Providers +61 | — | 45.3±13.9P | 47.3±11.1E | — | 52.1±11.8E | — | — | — | Throughput 137 t/s | Latency 3.08s | Release date— |
|
| GPT-4 DALL-EOpenAI | Context— | Input— | Output— | Providers +10 | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| Claude 3.7 SonnetAnthropic | Context— | Input$3.00/M | Output$15.00/M | Providers +34 | — | 48.2±13.9P | 48.4±11.1E | — | 48.6±11.8E | — | — | — | Throughput 45 t/s | Latency 7.65s | Release date— |
|
| Claude 3 SonnetAnthropic | Context— | Input$3.00/M | Output$15.00/M | Providers +8 | — | 36.9±13.9P | 38.2±11.1E | — | 39.3±11.8E | — | — | — | Throughput — | Latency — | Release date— |
|
| Gemini 2.0 Flash Lite 001Google | Context— | Input— | Output— | Providers +19 | — | 38.4±13.9P | 43.7±11.1E | — | 49.7±11.8E | — | — | — | Throughput — | Latency — | Release date— |
|
| Gemini 2.0 Flash LiteGoogle | Context— | Input— | Output— | Providers +39 | — | 38±13.9P | 42.3±13.9P | — | 50±11.8E | — | — | — | Throughput 182 t/s | Latency 1.49s | Release date— |
|
| Kimi K2 Thinking TurboMoonshot AI | Context— | Input— | Output— | Providers +9 | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| Gemini 2.0 ProGoogle | Context— | Input— | Output— | Providers +12 | — | 44.5±13.9P | 48.8±11.1E | — | 52±11.8E | — | — | — | Throughput 67 t/s | Latency 8.47s | Release date— |
|
| BGE Large ZH V1.5 | Context— | Input— | Output— | Providers +22 | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| Gemini 1.5 FlashGoogle | Context— | Input— | Output— | Providers +17 | — | 34.1±13.9P | 37.5±11.1E | — | 42.3±11.8E | — | — | — | Throughput 200 t/s | Latency 1.17s | Release date— |
|
| Claude 3 OpusAnthropic | Context— | Input$15.00/M | Output$75.00/M | Providers +11 | — | 39.1±13.9P | 42.1±11.1E | 55.8±16.0P | 41.3±11.8E | — | — | — | Throughput — | Latency — | Release date— |
|
| FLUX Dev | Context— | Input— | Output— | Providers +16 | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| Gemini 3.0 FlashGoogle | Context— | Input— | Output— | Providers +4 | — | — | — | — | — | — | — | — | Throughput 28 t/s | Latency 20.33s | Release date— |
|
| Gemini 1.5 Flash 002Google | Context— | Input— | Output— | Providers +1 | — | — | — | — | — | — | — | — | Throughput 155 t/s | Latency 1.62s | Release date— |
|
| Ring Flash 2.0 | Context— | Input$0.140/M | Output$0.570/M | Providers +5 | — | 39.5±13.9P | 49.9±11.1E | — | 51.9±16.1P | — | — | — | Throughput 107 t/s | Latency 6.09s | Release date— |
|
An AI model directory is a searchable list of models and their comparison data. On LMSpeed, it brings together API price, throughput, first-token latency, provider coverage, and capability data when available.
Start with the metric that matters most for your workload. Then open a model page to compare provider data. Run your own speed test before you use an endpoint in production.
Yes. Price, availability, throughput, and latency can change by model, provider, and time. Use current page values as a comparison signal and confirm with your own endpoint test.
