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
GPT-5.6 Sol ProOpenAI	Context1.1M	Input—	Output—	Providers +2	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date2026-07-09	— — — — — — — —
GPT-5.6 Terra ProOpenAI	Context1.1M	Input—	Output—	Providers +2	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date2026-07-09	— — — — — — — —
GPT-5.6 Luna ProOpenAI	Context1.1M	Input—	Output—	Providers +3	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date2026-07-09	— — — — — — — —
GPT-3.5 Turbo 16kOpenAI	Context16.4K	Input—	Output—	Providers +1	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date2023-08-28	— — — — — — — —
GPT-4 Turbo PreviewOpenAI	Context128K	Input—	Output—	Providers	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date2024-01-25	— — — — — — — —
GPT-3.5 Turbo (older v0613)OpenAI	Context4.1K	Input—	Output—	Providers +1	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date2024-01-25	— — — — — — — —
GPT-4o (2024-05-13)OpenAI	Context128K	Input$5.00/M	Output$15.00/M	Providers	—	43.5±13.9P	42.6±11.1E	—	46±11.8E	—	—	—	Throughput —	Latency —	Release date2024-05-13	— 43.5 42.6 — 46 — — —
GPT-4o-mini (2024-07-18)OpenAI	Context128K	Input—	Output—	Providers	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date2024-07-18	— — — — — — — —
GPT-4o (2024-08-06)OpenAI	Context128K	Input$2.50/M	Output$10.00/M	Providers	—	44.3±13.9P	39±13.9P	—	46.2±11.8E	—	—	—	Throughput —	Latency —	Release date2024-08-06	— 44.3 39 — 46.2 — — —
GPT-4o (2024-11-20)OpenAI	Context128K	Input—	Output—	Providers	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date2024-11-20	— — — — — — — —
GPT-4o Search PreviewOpenAI	Context128K	Input—	Output—	Providers +2	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date2025-03-12	— — — — — — — —
GPT-4o-mini Search PreviewOpenAI	Context128K	Input—	Output—	Providers +2	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date2025-03-12	— — — — — — — —
gpt-oss-20bOpenAI	Context131.1K	Input$0.070/M	Output$0.200/M	Providers	37.8±9.3E	48±11.2E	44.1±8.7	35.5±16.0P	53±16.1P	—	—	50.8±16.0P	Throughput —	Latency —	Release date2025-08-05	37.8 48 44.1 35.5 53 — — 50.8
gpt-oss-120bOpenAI	Context131.1K	Input$0.150/M	Output$0.590/M	Providers +3	35±6.0	47.7±9.1	49.2±8.7	55.5±14.0P	53.7±16.1P	31.5±17.3P	—	52.1±16.0P	Throughput —	Latency —	Release date2025-08-05	35 47.7 49.2 55.5 53.7 31.5 — 52.1
GPT-5 ChatOpenAI	Context128K	Input—	Output—	Providers	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date2025-08-07	— — — — — — — —
GPT-5.1 ChatOpenAI	Context128K	Input—	Output—	Providers	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date2025-11-13	— — — — — — — —
GPT-5.2 ChatOpenAI	Context128K	Input—	Output—	Providers	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date2025-12-10	— — — — — — — —
GPT-5.3 ChatOpenAI	Context128K	Input—	Output—	Providers	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date2026-03-03	— — — — — — — —
GPT Chat LatestOpenAI	Context400K	Input—	Output—	Providers +6	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date2026-05-05	— — — — — — — —
GPT-5.6 TerraOpenAI	Context1.1M	Input$2.00/M	Output$12.00/M	Providers +137	61.5±7.2	58.5±9.3E	58.4±8.7	57±16.7P	64.5±16.1P	—	54.7±16.1P	52.9±16.0P	Throughput 148 t/s	Latency 3.70s	Release date2026-07-09	61.5 58.5 58.4 57 64.5 — 54.7 52.9
GPT-5.6 SolOpenAI	Context1.1M	Input$4.00/M	Output$20.00/M	Providers +137	66.7±7.3	61.3±9.3E	60.8±8.7	57.2±16.7P	67±16.1P	—	59.5±16.1P	53.4±16.0P	Throughput 54 t/s	Latency 4.05s	Release date2026-07-09	66.7 61.3 60.8 57.2 67 — 59.5 53.4
GPT-5.6 LunaOpenAI	Context1.1M	Input$0.200/M	Output$1.20/M	Providers +132	57.8±7.2	56.3±9.3E	54.2±8.7	56.5±16.7P	62.4±16.1P	—	50.3±16.1P	—	Throughput 564 t/s	Latency 6.16s	Release date2026-07-09	57.8 56.3 54.2 56.5 62.4 — 50.3 —
GPT-5.5 ProOpenAI	Context1.1M	Input—	Output—	Providers +31	61.1±16.1P	—	62.1±14.0P	59.6±16.1P	57.2±16.1P	—	—	—	Throughput —	Latency —	Release date2026-04-24	61.1 — 62.1 59.6 57.2 — — —
GPT-5.5OpenAI	Context1.1M	Input$5.00/M	Output$30.00/M	Providers +152	61.7±5.1	59.4±8.7	58.9±8.7	58.9±14.0P	56.9±16.1P	—	55.7±16.1P	54.6±16.0P	Throughput 46 t/s	Latency 4.95s	Release date2026-04-24	61.7 59.4 58.9 58.9 56.9 — 55.7 54.6
GPT Image 2OpenAI	Context400K	Input—	Output—	Providers +118	—	—	—	—	—	—	—	—	Throughput 51 t/s	Latency 3.62s	Release date2026-06-24	— — — — — — — —
GPT-4o StudyOpenAI	Context—	Input—	Output—	Providers +4	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date—	— — — — — — — —
GPT-5 ImageOpenAI	Context400K	Input—	Output—	Providers +7	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date2025-10-14	— — — — — — — —
GPT-4o DALL-EOpenAI	Context—	Input—	Output—	Providers	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date—	— — — — — — — —
GPT-4o TranscribeOpenAI	Context128K	Input—	Output—	Providers +40	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date2026-04-27	— — — — — — — —
GPT-3.5 NetOpenAI	Context—	Input—	Output—	Providers +1	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date—	— — — — — — — —
GPT Image 1 MiniOpenAI	Context400K	Input—	Output—	Providers +20	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date2026-06-24	— — — — — — — —
GPT-5.4 ProOpenAI	Context1.1M	Input$30.00/M	Output$180.00/M	Providers +71	60.2±16.1P	—	58.6±11.2E	60.8±16.1P	56.8±16.1P	—	73±16.1P	—	Throughput —	Latency —	Release date2026-03-05	60.2 — 58.6 60.8 56.8 — 73 —
GPT-4o Mini SearchOpenAI	Context128K	Input—	Output—	Providers +36	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date2025-03-12	— — — — — — — —
GPT-4OpenAI	Context8.2K	Input$30.00/M	Output$60.00/M	Providers +77	—	49.5±18.4P	36.9±11.8E	—	40.7±16.0P	—	—	—	Throughput 35 t/s	Latency 0.74s	Release date2023-05-28	— 49.5 36.9 — 40.7 — — —
GPT-5.3OpenAI	Context128K	Input—	Output—	Providers +75	—	—	—	—	—	—	—	—	Throughput 59 t/s	Latency 2.57s	Release date2026-03-03	— — — — — — — —
GPT Image 1OpenAI	Context400K	Input—	Output—	Providers +44	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date2026-06-24	— — — — — — — —
GPT-5 ProOpenAI	Context400K	Input—	Output—	Providers +72	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date2025-10-06	— — — — — — — —
GPT-4 DALL-EOpenAI	Context—	Input—	Output—	Providers +12	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date—	— — — — — — — —
GPT-4o AudioOpenAI	Context—	Input—	Output—	Providers +80	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date—	— — — — — — — —
GPT AudioOpenAI	Context128K	Input—	Output—	Providers +22	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date2026-01-19	— — — — — — — —
GPT-4o Mini AudioOpenAI	Context—	Input—	Output—	Providers +34	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date—	— — — — — — — —
GPT-5 CodexOpenAI	Context400K	Input$1.25/M	Output$10.00/M	Providers +124	—	55.8±13.9P	56.6±11.1E	—	54.7±16.1P	—	—	—	Throughput 154 t/s	Latency 2.76s	Release date2025-09-23	— 55.8 56.6 — 54.7 — — —
GPT-4o Mini RealtimeOpenAI	Context—	Input—	Output—	Providers +36	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date—	— — — — — — — —
GPT-5 NanoOpenAI	Context400K	Input$0.050/M	Output$0.400/M	Providers +111	—	51±13.9P	47.9±11.1E	—	50.9±16.1P	—	—	—	Throughput 123 t/s	Latency 10.60s	Release date2025-08-07	— 51 47.9 — 50.9 — — —
GPT-4o RealtimeOpenAI	Context—	Input—	Output—	Providers +73	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date—	— — — — — — — —
GPT-5.2OpenAI	Context400K	Input$1.75/M	Output$14.00/M	Providers +241	47.5±6.6	56±8.5	53.3±6.4	57.2±14.0P	55.9±16.1P	—	42.3±9.0E	54.4±16.0P	Throughput 56 t/s	Latency 3.43s	Release date2025-12-10	47.5 56 53.3 57.2 55.9 — 42.3 54.4
GPT-5.3 CodexOpenAI	Context400K	Input$1.75/M	Output$14.00/M	Providers +253	52.6±6.6	58±8.5	59.5±10.8E	54.3±16.0P	—	—	—	54.4±16.0P	Throughput 78 t/s	Latency 3.91s	Release date2026-02-24	52.6 58 59.5 54.3 — — — 54.4
GPT-5.4 NanoOpenAI	Context400K	Input$0.200/M	Output$1.25/M	Providers +97	44.7±8.1	49.6±11.8E	49.8±10.8E	42.6±14.0P	51.8±16.1P	—	31.2±16.1P	54.6±16.0P	Throughput 137 t/s	Latency 3.38s	Release date2026-03-17	44.7 49.6 49.8 42.6 51.8 — 31.2 54.6
GPT-4o Transcribe DiarizeOpenAI	Context—	Input—	Output—	Providers +18	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date—	— — — — — — — —
ChatGPT Image	Context—	Input—	Output—	Providers +17	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date—	— — — — — — — —
GPT-5 Codex MiniOpenAI	Context—	Input—	Output—	Providers +64	—	—	—	—	—	—	—	—	Throughput 38 t/s	Latency 3.35s	Release date—	— — — — — — — —
GPT-4o ImageOpenAI	Context—	Input—	Output—	Providers +29	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date—	— — — — — — — —
GPT-5.1 CodexOpenAI	Context400K	Input$1.25/M	Output$10.00/M	Providers +133	49.7±9.3E	50.5±11.2E	55.2±8.7	49.9±16.0P	54.1±16.1P	—	—	52.5±16.0P	Throughput —	Latency —	Release date2025-11-13	49.7 50.5 55.2 49.9 54.1 — — 52.5
GPT-5.2 ProOpenAI	Context400K	Input—	Output—	Providers +90	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date2025-12-10	— — — — — — — —
GPT-4 NetOpenAI	Context—	Input—	Output—	Providers +2	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date—	— — — — — — — —
GPT Image 1.5OpenAI	Context—	Input—	Output—	Providers +115	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date—	— — — — — — — —
GPT-4 GizmoOpenAI	Context—	Input—	Output—	Providers +24	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date—	— — — — — — — —
Net GPT-4o	Context—	Input—	Output—	Providers	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date—	— — — — — — — —
GPT-4o Mini TranscribeOpenAI	Context128K	Input—	Output—	Providers +38	—	—	—	—	—	—	—	—	Throughput —	Latency —	Release date2026-05-01	— — — — — — — —
ChatGPT-4oOpenAI	Context—	Input—	Output—	Providers +49	—	—	—	—	—	—	—	—	Throughput 78 t/s	Latency 4.56s	Release date—	— — — — — — — —

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.