AI Model Benchmark Directory

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.

Newest Most tested Recently tested A–Z

Model	Context	Input	Output	Providers	Agents	Coding	Reasoning	Knowledge	Math	Multilingual	Multimodal	Instruction following	Throughput	Latency	Release date
Llama Nemotron Embed VL 1B V2NVIDIA	Context131.1K	Input—	Output—	Providers	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date2026-02-25	— — — — — — — —
Llama Nemotron Rerank VL 1B V2NVIDIA	Context10.2K	Input—	Output—	Providers—	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date2026-06-09	— — — — — — — —
Llama 3 8B InstructMeta	Context8.2K	Input—	Output—	Providers +1	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date—	— — — — — — — —
Llama 3.1 70B InstructMeta	Context131.1K	Input—	Output—	Providers +1	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date2024-07-23	— — — — — — — —
Reach model researchersAd spacePromote your API while developers browse models and pricing.Advertise here
Llama 3.1 8B InstructMeta	Context131.1K	Input—	Output—	Providers +2	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date2024-07-23	— — — — — — — —
Hermes 3 70B InstructNous	Context131.1K	Input$0.700/M	Output$0.700/M	Providers—	—	36.5±13.9P	37.7±11.1E	—	39.6±11.8E	—	—	—	Throughput —	Latency —	Release date2024-08-18	— 36.5 37.7 — 39.6 — — —
Llama 3.2 11B Vision InstructMeta	Context131.1K	Input—	Output—	Providers +4	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date2024-09-25	— — — — — — — —
Llama 3.2 1B InstructMeta	Context60K	Input—	Output—	Providers +4	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date2024-09-25	— — — — — — — —
Llama 3.2 3B InstructMeta	Context131.1K	Input—	Output—	Providers +8	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date2024-09-25	— — — — — — — —
Llama 3.3 70B InstructMeta	Context131.1K	Input—	Output—	Providers +6	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date2024-12-06	— — — — — — — —
R1 Distill Llama 70BDeepSeek	Context8.2K	Input$0.700/M	Output$1.10/M	Providers	—	42.6±13.9P	45.3±11.1E	—	55±11.8E	—	—	—	Throughput —	Latency —	Release date2025-01-23	— 42.6 45.3 — 55 — — —
Llama Guard 4 12BMeta	Context163.8K	Input—	Output—	Providers	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date2025-04-30	— — — — — — — —
Llama 3.3 Nemotron Super 49B V1.5NVIDIA	Context131.1K	Input—	Output—	Providers +1	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date2025-10-10	— — — — — — — —
MiniMax M3MiniMax	Context1.0M	Input$0.300/M	Output$1.20/M	Providers +93	53.7±7.3	52.7±6.6	59.2±10.8E	51.7±14.0P	—	—	46.9±12.0E	57.8±16.0P	Throughput 81 t/s	Latency 2.49s	Release date2026-05-31	53.7 52.7 59.2 51.7 — — 46.9 57.8
Aion RP Llama 3.1	Context32.8K	Input—	Output—	Providers +5	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date2025-02-04	— — — — — — — —
Hermes 3 Llama 3.1	Context131.1K	Input—	Output—	Providers +21	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date2024-08-18	— — — — — — — —
Llama 3.1Meta	Context—	Input—	Output—	Providers +24	37.5±16.0P	45.1±16.0P	36.9±10.8E	47.3±16.0P	—	—	—	43.1±16.0P	Throughput —	Latency —	Release date—	37.5 45.1 36.9 47.3 — — — 43.1
Llama 3.3Meta	Context—	Input—	Output—	Providers +13	—	—	—	—	—	—	—	—	Throughput 985 t/s	Latency 0.45s	Release date—	— — — — — — — —
Meta Llama 3.3 Instruct	Context—	Input—	Output—	Providers	—	—	—	—	—	—	—	—	Throughput 48 t/s	Latency 0.93s	Release date—	— — — — — — — —
Dracarys Llama 3.1 Instruct	Context—	Input—	Output—	Providers +24	—	—	—	—	—	—	—	—	Throughput 18 t/s	Latency 0.59s	Release date—	— — — — — — — —
Usdcode Llama 3.1 Instruct	Context—	Input—	Output—	Providers +5	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date—	— — — — — — — —
Meta Llama 3.1 InstructMeta	Context—	Input—	Output—	Providers +4	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date—	— — — — — — — —
Meta Llama 3.3 Instruct Turbo	Context—	Input—	Output—	Providers	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date—	— — — — — — — —
Meta Llama 3.1 Instruct TurboMeta	Context—	Input—	Output—	Providers +1	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date—	— — — — — — — —
Qwen3.5	Context262.1K	Input$0.030/M	Output$0.150/M	Providers +104	44.7±5.2	40.5±8.9	52.3±8.1	53.1±11.6E	41.4±11.5E	54.6±12.2E	50.2±6.5	53.7±11.9E	Throughput 51 t/s	Latency 10.34s	Release date2026-03-10	44.7 40.5 52.3 53.1 41.4 54.6 50.2 53.7
Llama 3.2 Nemoretriever 300m Embed v1Meta	Context—	Input—	Output—	Providers +14	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date—	— — — — — — — —
Llama 4 MaverickMeta	Context1.0M	Input$0.260/M	Output$0.910/M	Providers +19	33±11.8E	45.5±13.9P	46.8±8.7	41±16.0P	46.2±9.3E	—	—	44.3±16.0P	Throughput —	Latency —	Release date2025-04-05	33 45.5 46.8 41 46.2 — — 44.3
Kimi K2.5MoonshotAI	Context262.1K	Input$0.600/M	Output$3.00/M	Providers +196	39.1±5.1	48.4±7.8	55.6±8.3	47.1±16.3P	49.2±9.0E	44.2±12.2E	52.7±12.0E	54±11.9E	Throughput 144 t/s	Latency 11.93s	Release date2026-01-27	39.1 48.4 55.6 47.1 49.2 44.2 52.7 54
GLM-4.7 FlashZ.ai	Context202.8K	Input$0.070/M	Output$0.400/M	Providers +56	—	41.4±16.0P	40.3±13.9P	—	—	—	—	—	Throughput 56 t/s	Latency 22.72s	Release date2026-01-19	— 41.4 40.3 — — — — —
MiniMax M2.7MiniMax	Context204.8K	Input$0.300/M	Output$1.20/M	Providers +172	45±6.0	47.2±8.2	54.6±10.8E	51.9±16.0P	—	—	—	54.6±16.0P	Throughput 203 t/s	Latency 6.87s	Release date2026-03-18	45 47.2 54.6 51.9 — — — 54.6
Gemini 3 FlashGoogle	Context1.0M	Input$0.500/M	Output$3.00/M	Providers +185	43±8.9	53.7±11.2E	52.2±8.7	50.6±16.0P	51.9±16.1P	—	—	47.8±16.0P	Throughput 162 t/s	Latency 7.48s	Release date2025-12-17	43 53.7 52.2 50.6 51.9 — — 47.8
Llama 4 ScoutMeta	Context1.3M	Input$0.180/M	Output$0.660/M	Providers +39	32.7±11.8E	34.3±13.9P	41.8±8.7	38.4±16.0P	44.4±9.3E	—	—	43.2±16.0P	Throughput 75 t/s	Latency 1.62s	Release date2025-04-05	32.7 34.3 41.8 38.4 44.4 — — 43.2
DeepSeek R1DeepSeek	Context64K	Input$1.35/M	Output$3.00/M	Providers +149	41.2±16.0P	49.7±13.9P	50.2±8.7	44.7±16.0P	57±11.8E	—	—	43.3±16.0P	Throughput 52 t/s	Latency 10.36s	Release date2025-05-28	41.2 49.7 50.2 44.7 57 — — 43.3
GLM-5Z.ai	Context204.8K	Input$1.00/M	Output$3.20/M	Providers +187	41.1±5.6	51.5±8.1	48.9±8.1	43.3±16.3P	51.1±9.1E	43.8±12.2E	—	52.4±11.9E	Throughput 51 t/s	Latency 21.59s	Release date2026-02-11	41.1 51.5 48.9 43.3 51.1 43.8 — 52.4
MiniMax M2.5MiniMax	Context204.8K	Input$0.300/M	Output$1.20/M	Providers +187	—	50.2±11.8E	54.7±13.9P	—	—	—	—	—	Throughput 61 t/s	Latency 9.68s	Release date2026-02-12	— 50.2 54.7 — — — — —
GPT-OSS	Context131.1K	Input—	Output—	Providers +137	—	—	—	—	—	—	—	—	Throughput 374 t/s	Latency 3.23s	Release date2025-08-05	— — — — — — — —

How to read category scores

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.

Read the complete scoring methodology

What this directory shows

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.

API price: Compare input and output price per million tokens when it is available.
Speed and latency: Use throughput and first-token latency to compare response behavior.
Provider coverage: Open a model to review its listed providers and their current details.
Capability data: Use the capability columns when current model scores are available.

How to use the model directory

Start with the decision that matters most for your workload, then compare the current rows before you test an endpoint.

Find a model.Search by model name, slug, or description.
Sort the key metric.Sort by price, throughput, latency, provider count, or capability data.
Compare providers.Open a model page to review the provider options and current data.
Test your endpoint.Run a speed test before you use an endpoint in production.

Model pricing leaderboard Model speed leaderboard Latency leaderboard Provider directory LLM API speed test

Frequently Asked Questions

How does LMSpeed benchmark AI models?

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.

Which AI model has the lowest API latency?

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.

How to compare LLM API pricing across providers?

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.

What is an AI model directory?

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.

How do I choose a model and provider?

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.

Can model price and speed change?

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.