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
Qwen3	Context262.1K	Input$0.200/M	Output$0.800/M	Providers +126	—	45.7±13.9P	47.6±11.1E	36.9±16.3P	58.3±11.8E	36.7±16.4P	—	—	Throughput 100 t/s	Latency 12.55s	Release date2025-07-21	— 45.7 47.6 36.9 58.3 36.7 — —
Qwen3 VL	Context—	Input—	Output—	Providers +17	—	—	—	—	—	—	—	—	Throughput 206 t/s	Latency 6.63s	Release date—	— — — — — — — —
Qwen3 CoderQwen	Context262.1K	Input—	Output—	Providers +61	—	—	—	—	—	—	—	—	Throughput 243 t/s	Latency 5.28s	Release date2025-07-23	— — — — — — — —
Qwen3 Embedding	Context—	Input—	Output—	Providers +43	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date—	— — — — — — — —
Qwen3 Next	Context—	Input—	Output—	Providers +7	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date—	— — — — — — — —
Qwen Image	Context—	Input—	Output—	Providers +34	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date—	— — — — — — — —
Qwen3 Omni Flash	Context—	Input—	Output—	Providers +39	—	—	—	—	—	—	—	—	Throughput 62 t/s	Latency 5.13s	Release date—	— — — — — — — —
Qwen3 S2S Flash Realtime	Context—	Input—	Output—	Providers +13	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date—	— — — — — — — —
Qwen3.5 Plus Image	Context—	Input—	Output—	Providers +1	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date—	— — — — — — — —
Qwen3 TTS Flash Realtime	Context—	Input—	Output—	Providers +14	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date—	— — — — — — — —
Qwen PlusQwen	Context1M	Input—	Output—	Providers +35	—	—	—	—	—	—	—	—	Throughput 39 t/s	Latency 0.83s	Release date2025-09-08	— — — — — — — —
Qwen3 Coder PlusQwen	Context1M	Input—	Output—	Providers +73	—	—	—	—	—	—	—	—	Throughput 45 t/s	Latency 1.35s	Release date2025-09-23	— — — — — — — —
Qwen3 MaxQwen	Context262.1K	Input$1.20/M	Output$6.00/M	Providers +93	47.5±11.8E	45±11.2E	48.8±8.7	40.5±16.0P	51.4±16.1P	—	—	44.6±16.0P	Throughput 38 t/s	Latency 7.37s	Release date2025-09-23	47.5 45 48.8 40.5 51.4 — — 44.6
Qwen3.5 PlusAlibaba	Context1M	Input—	Output—	Providers +115	44.3±16.2P	46.5±16.1P	—	—	48.8±16.1P	—	—	—	Throughput 51 t/s	Latency 13.81s	Release date2026-04-27	44.3 46.5 — — 48.8 — — —
Qwen3 TTS Flash	Context—	Input—	Output—	Providers +29	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date—	— — — — — — — —
Qwen3.1Alibaba	Context—	Input—	Output—	Providers +11	—	—	—	—	—	—	—	—	Throughput 151 t/s	Latency 4.42s	Release date—	— — — — — — — —
Qwen3 Coder FlashQwen	Context1M	Input—	Output—	Providers +29	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date2025-09-17	— — — — — — — —
Qwen3.6 PlusQwen	Context1M	Input$0.500/M	Output$3.00/M	Providers +127	49.2±5.5	50.9±8.2	56.6±8.1	52±11.6E	52.2±9.1E	52.2±12.2E	50.7±6.5	55.7±11.9E	Throughput 49 t/s	Latency 24.59s	Release date2026-04-02	49.2 50.9 56.6 52 52.2 52.2 50.7 55.7
Qwen3.0Alibaba	Context—	Input—	Output—	Providers +12	—	—	—	—	—	—	—	—	Throughput 165 t/s	Latency 1.77s	Release date—	— — — — — — — —
Qwen3 Max ThinkingQwen	Context262.1K	Input$1.20/M	Output$6.00/M	Providers +6	—	51.8±13.9P	55±11.1E	—	51.7±16.1P	—	—	—	Throughput —	Latency —	Release date2026-02-09	— 51.8 55 — 51.7 — — —
Qwen3.5 Flash	Context1M	Input—	Output—	Providers +73	—	—	—	—	42.7±16.1P	—	—	—	Throughput 115 t/s	Latency 7.92s	Release date2026-02-25	— — — — 42.7 — — —
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—	— — — — — — — —
Qwen3 Coder NextQwen	Context262.1K	Input$0.350/M	Output$1.20/M	Providers +20	—	46.9±16.0P	48.6±13.9P	—	—	—	—	—	Throughput 147 t/s	Latency 0.97s	Release date2026-02-04	— 46.9 48.6 — — — — —
Qwen3.6 Plus Thinking	Context—	Input—	Output—	Providers +9	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date—	— — — — — — — —
Qwen3.5 Omni Plus	Context—	Input$0.400/M	Output$4.80/M	Providers +20	—	52.6±16.0P	52.5±13.9P	—	—	—	—	—	Throughput 36 t/s	Latency 2.15s	Release date—	— 52.6 52.5 — — — — —
Qwen3.5 Omni Flash	Context—	Input$0.100/M	Output$0.800/M	Providers +20	—	41.7±16.0P	47.7±13.9P	—	—	—	—	—	Throughput —	Latency —	Release date—	— 41.7 47.7 — — — — —
Qwen3.5 Plus Image Edit	Context—	Input—	Output—	Providers +1	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date—	— — — — — — — —
DeepSeek V3.2DeepSeek	Context163.8K	Input$0.280/M	Output$0.420/M	Providers +181	39±6.9	51.1±8.6	50.9±8.7	39.6±16.0P	49±16.1P	—	—	46±16.0P	Throughput 46 t/s	Latency 5.33s	Release date2025-12-01	39 51.1 50.9 39.6 49 — — 46
Qwen3.5	Context262.1K	Input$0.030/M	Output$0.150/M	Providers +105	44.6±5.2	40.3±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	44.6 40.3 52.3 53.1 41.4 54.6 50.2 53.7
FreeOpenrouter	Context200K	Input—	Output—	Providers +16	—	—	—	—	—	—	—	—	Throughput 24 t/s	Latency 25.61s	Release date2026-02-01	— — — — — — — —
DeepSeek R1 Distill Qwen 1.5BDeepSeek	Context—	Input—	Output—	Providers +21	—	25.7±13.9P	29.7±11.1E	—	45.5±11.8E	—	—	—	Throughput 126 t/s	Latency 4.28s	Release date—	— 25.7 29.7 — 45.5 — — —
DeepSeek R1 Distill QwenDeepSeek	Context128K	Input—	Output—	Providers +51	—	40.4±13.9P	39.1±8.9	54.3±16.0P	55.7±11.8E	—	—	37.5±16.0P	Throughput 50 t/s	Latency 19.88s	Release date2025-01-29	— 40.4 39.1 54.3 55.7 — — 37.5
Qwen1.8BAlibaba	Context—	Input—	Output—	Providers +14	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date—	— — — — — — — —
Qwen1.8B Long ContextAlibaba	Context—	Input—	Output—	Providers +14	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date—	— — — — — — — —
Qwen3.6 FlashQwen	Context1M	Input—	Output—	Providers +21	—	—	—	—	—	—	—	—	Throughput 106 t/s	Latency 8.21s	Release date2026-04-27	— — — — — — — —
Qwen3 InstantAlibaba	Context—	Input—	Output—	Providers	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date—	— — — — — — — —
Qwen3.7 MaxQwen	Context1M	Input$2.50/M	Output$7.50/M	Providers +60	56.8±5.8	56.6±6.0	59.5±8.7	55.8±12.2E	62.2±12.2E	58.1±11.7E	—	56.8±11.9E	Throughput 111 t/s	Latency 22.62s	Release date2026-05-21	56.8 56.6 59.5 55.8 62.2 58.1 — 56.8
Qwen3.7 PlusQwen	Context1M	Input$0.400/M	Output$1.60/M	Providers +55	53.5±5.7	52.5±6.0	57.3±8.7	48.6±12.2E	55.2±12.2E	51.1±11.7E	55.1±6.3	56.8±11.9E	Throughput 80 t/s	Latency 28.78s	Release date2026-06-03	53.5 52.5 57.3 48.6 55.2 51.1 55.1 56.8
Nex n2 ProNex AGI	Context262.1K	Input$0.500/M	Output$2.50/M	Providers +9	—	53.4±16.0P	58.6±13.9P	—	—	—	—	—	Throughput 83 t/s	Latency 1.16s	Release date2026-06-08	— 53.4 58.6 — — — — —
Qwen3.6 35B A3BQwen	Context262.1K	Input$0.375/M	Output$2.25/M	Providers +5	45.9±5.9	37.4±6.0	52.3±8.7	39.1±12.2E	34.6±11.5E	—	44.1±7.0	50.6±16.0P	Throughput —	Latency —	Release date2026-04-27	45.9 37.4 52.3 39.1 34.6 — 44.1 50.6
Qwen3.6 Max PreviewQwen	Context262.1K	Input$1.30/M	Output$7.80/M	Providers +15	53.6±11.8E	51.4±8.9	55.4±10.8E	55.1±16.3P	50.6±16.1P	—	—	54.9±16.0P	Throughput —	Latency —	Release date2026-04-27	53.6 51.4 55.4 55.1 50.6 — — 54.9
Qwen3.6 27BQwen	Context262.1K	Input$0.600/M	Output$3.60/M	Providers +3	55.4±6.6	46.6±6.0	54.3±8.7	37.3±11.6E	41.3±11.5E	—	46.3±6.5	51.7±16.0P	Throughput —	Latency —	Release date2026-04-27	55.4 46.6 54.3 37.3 41.3 — 46.3 51.7
Qwen3.5-9BQwen	Context262.1K	Input$0.170/M	Output$0.250/M	Providers—	—	43.3±16.0P	51.9±13.9P	—	—	—	—	—	Throughput —	Latency —	Release date2026-03-10	— 43.3 51.9 — — — — —
Qwen3.5-35B-A3BQwen	Context262.1K	Input$0.250/M	Output$2.00/M	Providers	42.7±8.7	41.8±11.2E	51.2±8.3	38±16.3P	—	41.6±16.4P	45.8±12.1E	51.5±11.9E	Throughput —	Latency —	Release date2026-02-25	42.7 41.8 51.2 38 — 41.6 45.8 51.5
Qwen3.5-27BQwen	Context262.1K	Input$0.300/M	Output$2.40/M	Providers	45.7±8.7	48.7±11.2E	53.5±8.3	41.4±16.3P	—	45.4±16.4P	49±12.1E	57.1±11.9E	Throughput —	Latency —	Release date2026-02-25	45.7 48.7 53.5 41.4 — 45.4 49 57.1
Qwen3.5-122B-A10BQwen	Context262.1K	Input$0.400/M	Output$3.20/M	Providers	47.9±10.6E	48.5±11.8E	53±8.3	43.7±16.3P	—	45.4±16.4P	47.7±9.4E	54.2±11.9E	Throughput —	Latency —	Release date2026-02-25	47.9 48.5 53 43.7 — 45.4 47.7 54.2
Qwen3.5 397B A17BQwen	Context262.1K	Input$0.600/M	Output$3.60/M	Providers	—	53.5±16.0P	58±13.9P	—	—	—	—	—	Throughput 366 t/s	Latency 9.72s	Release date2026-02-16	— 53.5 58 — — — — —
Qwen3 VL 32B InstructQwen	Context131.1K	Input$0.160/M	Output$0.640/M	Providers +2	—	45.5±13.9P	48.2±11.1E	—	49.1±16.1P	—	—	—	Throughput —	Latency —	Release date2025-10-23	— 45.5 48.2 — 49.1 — — —
Qwen3 VL 8B ThinkingQwen	Context131.1K	Input—	Output—	Providers	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date2025-10-14	— — — — — — — —
Qwen3 VL 8B InstructQwen	Context262.1K	Input$0.180/M	Output$0.700/M	Providers +2	—	35.5±13.9P	40.6±11.1E	—	41.5±16.1P	—	—	—	Throughput —	Latency —	Release date2025-10-14	— 35.5 40.6 — 41.5 — — —
Qwen3 VL 30B A3B ThinkingQwen	Context262.1K	Input—	Output—	Providers +2	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date2025-10-06	— — — — — — — —
Qwen3 VL 30B A3B InstructQwen	Context262.1K	Input$0.200/M	Output$0.800/M	Providers +1	—	45.4±13.9P	47.3±11.1E	—	49.8±16.1P	—	—	—	Throughput —	Latency —	Release date2025-10-06	— 45.4 47.3 — 49.8 — — —
Qwen3 VL 235B A22B ThinkingQwen	Context131.1K	Input—	Output—	Providers +5	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date2025-09-23	— — — — — — — —
Qwen3 VL 235B A22B InstructQwen	Context262.1K	Input$0.400/M	Output$1.60/M	Providers +5	—	49.4±13.9P	50±11.1E	—	49.5±16.1P	—	—	—	Throughput —	Latency —	Release date2025-09-23	— 49.4 50 — 49.5 — — —
Qwen3 Next 80B A3B ThinkingQwen	Context262.1K	Input—	Output—	Providers +5	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date2025-09-11	— — — — — — — —
Qwen3 Next 80B A3B InstructQwen	Context262.1K	Input$0.150/M	Output$1.20/M	Providers +17	—	48.2±13.9P	50.4±11.1E	—	48.7±16.1P	—	—	—	Throughput —	Latency —	Release date2025-09-11	— 48.2 50.4 — 48.7 — — —
Qwen3 30B A3B Thinking 2507Qwen	Context81.9K	Input—	Output—	Providers +4	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date2025-08-28	— — — — — — — —
Qwen3 Coder 30B A3B InstructQwen	Context262.1K	Input$0.450/M	Output$2.25/M	Providers	—	42.9±13.9P	42.6±11.1E	—	50.5±11.8E	—	—	—	Throughput —	Latency —	Release date2025-07-31	— 42.9 42.6 — 50.5 — — —
Qwen3 30B A3B Instruct 2507Qwen	Context262.1K	Input—	Output—	Providers +3	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date2025-07-29	— — — — — — — —

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.