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— |
|
| Qwen3.0Alibaba | Context— | Input— | Output— | Providers +12 | — | — | — | — | — | — | — | — | Throughput 165 t/s | Latency 1.77s | Release date— |
|
| MiniMax Hailuo 02 | Context— | Input— | Output— | Providers +13 | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| Gemini 1.0 Pro VisionGoogle | Context— | Input— | Output— | Providers | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| GLM-4.5 FlashZhipu AI | Context— | Input— | Output— | Providers +46 | — | — | — | — | — | — | — | — | Throughput 29 t/s | Latency 17.14s | Release date— |
|
| GLM-Z1 AirZhipu AI | Context— | Input— | Output— | Providers +8 | — | — | — | — | — | — | — | — | Throughput 53 t/s | Latency 0.30s | Release date— |
|
| Jamba 1.5 Large Instruct | Context— | Input— | Output— | Providers +18 | — | — | — | — | — | — | — | — | Throughput 56 t/s | Latency 0.29s | Release date— |
|
| Step3 | Context— | Input— | Output— | Providers +2 | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| GLM-4.7 FlashXZhipu AI | Context— | Input— | Output— | Providers +3 | — | — | — | — | — | — | — | — | Throughput 45 t/s | Latency 22.27s | Release date— |
|
| Phi 4 Multimodal Instruct | Context— | Input— | Output— | Providers +30 | — | 28.4±13.9P | 35.1±11.1E | — | 44.1±11.8E | — | — | — | Throughput 83 t/s | Latency 0.39s | Release date— |
|
| Llama 3.2 Nemoretriever 300m Embed v1Meta | Context— | Input— | Output— | Providers +14 | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| TeleSpeechASR | Context— | Input— | Output— | Providers +11 | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| GLM-4.6V FlashZhipu AI | Context— | Input— | Output— | Providers +29 | — | — | — | — | — | — | — | — | Throughput 111 t/s | Latency 11.08s | Release date— |
|
| GLM-4 PlusZhipu AI | Context— | Input— | Output— | Providers +14 | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| PanGu Pro MoE | Context— | Input— | Output— | Providers +4 | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| Solar Instruct | Context— | Input— | Output— | Providers +2 | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| GLM-4 AirZhipu AI | Context— | Input— | Output— | Providers +26 | — | — | — | — | — | — | — | — | Throughput 66 t/s | Latency 0.33s | Release date— |
|
| Gemini ImagenGoogle | Context— | Input— | Output— | Providers | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| DeepSeek Coder InstructDeepSeek | Context— | Input— | Output— | Providers +4 | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| GLM-4 FlashZhipu AI | Context— | Input— | Output— | Providers +52 | — | — | — | — | — | — | — | — | Throughput 31 t/s | Latency 0.96s | Release date— |
|
| Kimi K2 TurboMoonshot AI | Context— | Input— | Output— | Providers +9 | — | — | — | — | — | — | — | — | Throughput 83 t/s | Latency 3.73s | Release date— |
|
| MiniMax M2.1 HighSpeed | Context— | Input— | Output— | Providers +18 | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| Italia Instruct | Context— | Input— | Output— | Providers +3 | — | — | — | — | — | — | — | — | Throughput 36 t/s | Latency 0.49s | Release date— |
|
| Claude Opus 4.6 MaxAnthropic | Context— | Input— | Output— | Providers +21 | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| GLM-4.5-XZhipu AI | Context— | Input— | Output— | Providers +25 | — | — | — | — | — | — | — | — | Throughput 69 t/s | Latency 12.39s | Release date— |
|
| Phi 3.5 MoE Instruct | Context— | Input— | Output— | Providers +21 | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| Qwen3.5 Plus Thinking | Context— | Input— | Output— | Providers +7 | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| Qwen3.5 Max | Context— | Input— | Output— | Providers +6 | — | — | — | — | — | — | — | — | Throughput 31 t/s | Latency 29.33s | Release date— |
|
| GLM-4.1v Thinking FlashXZhipu AI | Context— | Input— | Output— | Providers +12 | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| Arctic Embed L | Context— | Input— | Output— | Providers +19 | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| Colosseum Instruct | Context— | Input— | Output— | Providers +1 | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| Gemini Live 2.5 FlashGoogle | Context— | Input— | Output— | Providers | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| GLM-4V FlashZhipu AI | Context— | Input— | Output— | Providers +14 | — | — | — | — | — | — | — | — | Throughput 56 t/s | Latency 0.62s | Release date— |
|
| Gemini Pro VisionGoogle | Context— | Input— | Output— | Providers | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| DeepSeek Prover v2DeepSeek | Context— | Input— | Output— | Providers +6 | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| MiniMax M2.5 HighSpeed | Context— | Input— | Output— | Providers +31 | — | — | — | — | — | — | — | — | Throughput 56 t/s | Latency 5.39s | Release date— |
|
| GPT-3.5 NetOpenAI | Context— | Input— | Output— | Providers +1 | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| MiMo-V2-Omni | Context— | Input— | Output— | Providers +58 | 41.8±11.9E | 49.6±11.8E | 53.6±10.8E | 48.2±16.0P | — | — | — | 47.5±16.0P | Throughput 83 t/s | Latency 3.43s | Release date— |
|
| Gemini 2.0 Flash Live 001Google | Context— | Input— | Output— | Providers +1 | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| Gemini EmbeddingGoogle | Context— | Input— | Output— | Providers +8 | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| GLM-4 AirXZhipu AI | Context— | Input— | Output— | Providers +20 | — | — | — | — | — | — | — | — | Throughput 95 t/s | Latency 3.81s | Release date— |
|
| DeepSeek Coder v2 InstructDeepSeek | Context— | Input— | Output— | Providers +2 | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| Gemini 3.1 FlashGoogle | Context— | Input— | Output— | Providers +19 | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| Qwen3.6 Plus Thinking | Context— | Input— | Output— | Providers +7 | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| Gemini 2.5 Pro 1MGoogle | Context— | Input— | Output— | Providers | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| MiMo-V2-Pro | Context— | Input— | Output— | Providers +69 | 48.2±8.9 | 54±11.8E | 52.7±10.8E | 54±16.0P | — | — | — | 52.4±16.0P | Throughput 49 t/s | Latency 3.35s | Release date— |
|
| GLM-4.1v Thinking FlashZhipu AI | Context— | Input— | Output— | Providers +13 | — | — | — | — | — | — | — | — | Throughput 85 t/s | Latency 7.49s | Release date— |
|
| GPT-4o DALL-EOpenAI | Context— | Input— | Output— | Providers | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| Gemini 2.5 Flash LiveGoogle | Context— | Input— | Output— | Providers | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| MiniMax M2.1 Lightning | Context— | Input— | Output— | Providers +3 | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| Gemini 3 Pro DeepSearchGoogle | Context— | Input— | Output— | Providers +1 | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| DeepSeek V3.2 ReasonerDeepSeek | Context— | Input— | Output— | Providers +1 | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| Qwen3.5 Omni Plus | Context— | Input$0.400/M | Output$4.80/M | Providers +19 | — | 53.4±16.0P | 53.4±13.9P | — | — | — | — | — | Throughput 36 t/s | Latency 2.15s | Release date— |
|
| MiniMax Voice Clone | Context— | Input— | Output— | Providers +9 | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| DeepSeek Vision ReasonerDeepSeek | Context— | Input— | Output— | Providers | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| Gemini Robotics ER 1.5Google | Context— | Input— | Output— | Providers +17 | — | — | — | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| GLM-4 FlashXZhipu AI | Context— | Input— | Output— | Providers +8 | — | — | — | — | — | — | — | — | Throughput 60 t/s | Latency 0.41s | Release date— |
|
| Qwen3.5 Omni Flash | Context— | Input$0.100/M | Output$0.800/M | Providers +19 | — | 42.2±16.0P | 48.3±13.9P | — | — | — | — | — | Throughput — | Latency — | Release date— |
|
| Claude 2.0Anthropic | Context— | Input— | Output— | Providers +8 | — | 34.5±13.9P | 35.2±11.8E | — | 33.3±16.0P | — | — | — | Throughput — | Latency — | Release date— |
|
| Gemini 3.0 ProGoogle | Context— | Input— | Output— | Providers +1 | — | — | — | — | — | — | — | — | Throughput — | Latency — | 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.
