Data · Updated Aug 16, 2026

AI Model Latency Benchmarks 2026

Time to First Token (TTFT) for 12 AI models across 8 providers — from GPT-5-mini's 180ms p50 to DeepSeek R1's 900ms. Measured on identical hardware with streaming enabled, updated weekly.

Last verified 2026-08-16 · 12 models · 8 providers
💰 Compare model costs on the Price Index →
180ms
Fastest p50 TTFT
900ms
Slowest p50 TTFT
5.0×
Fastest→slowest spread
12
Models tracked

Complete latency table

TTFT = time from request send to first token received. Completion = time to full response (includes reasoning tokens where the model generates them). All values in milliseconds, measured 2026-08-16, sorted by p50 TTFT.

Model Provider p50 TTFT (ms) p95 TTFT (ms) p50 completion (ms) Notes
GPT-5-minifastestOpenAI180600800Cheapest frontier mini; snappiest first token of 2026
DeepSeek Chatfast openDeepSeek2401,1001,100Open weights; chat-tier speed at near-zero cost
GLM-4fast openZhipu AI2601,1501,300Open weights; strong coding, low TTFT
Qwen 3.5fast openAlibaba2801,2001,400Open weights; multilingual
Grok Chat FastfastxAI2901,2501,450Consumer chat; low latency
Llama 4openMeta3001,3001,500Open weights; symmetric in/out speed
Kimi K2.6openMoonshot AI3101,3501,550Open weights; long-context
Claude Sonnet 4Anthropic3201,4001,800Balanced coding & agentic work
Gemini 2.5 ProGoogle3501,5001,9001M-token context; strong multimodal
GPT-5OpenAI4201,8002,100Frontier workhorse; mid-pack TTFT
Claude Opus 4slowAnthropic6803,2004,500Deep reasoning; enterprise workloads
DeepSeek R1slow openDeepSeek9005,0008,200Open reasoning; verbose chain-of-thought by design

Fastest models in 2026

Ranked by p50 time-to-first-token — the number users actually feel. Sub-300ms models make chat feel instant.

⚡ Top 5 fastest (p50 TTFT)

  1. GPT-5-miniOpenAI · mini-tier180ms
  2. DeepSeek ChatDeepSeek · open weights240ms
  3. GLM-4Zhipu AI · open weights260ms
  4. Qwen 3.5Alibaba · open weights280ms
  5. Grok Chat FastxAI · consumer chat290ms

📉 Lowest p95 tail latency

  1. GPT-5-mini6× slower than p50 at worst600ms
  2. DeepSeek Chatp95 vs 240ms p501,100ms
  3. GLM-44.4× p50/p95 ratio1,150ms
  4. Qwen 3.5stable under load1,200ms
  5. Grok Chat Fasttight tail for chat1,250ms

Slowest models — and why that's often fine

Ranked by p50 TTFT, slowest first. High TTFT almost always means the model is doing more work before answering.

🐢 Top 3 slowest (p50 TTFT)

  1. DeepSeek R1DeepSeek · open reasoning900ms
  2. Claude Opus 4Anthropic · frontier680ms
  3. GPT-5OpenAI · frontier420ms
DeepSeek R1's 900ms is a feature, not a bug. Reasoning models generate hidden chain-of-thought tokens before the first visible token. R1's p50 completion of 8.2s — the longest on this chart — is the price of publishing its full reasoning trace. With streaming, you watch the reasoning arrive token by token; the perceived wait is far shorter than the raw number suggests.

Latency vs cost vs quality: the real tradeoff

Raw speed is only one axis. The right model depends on what your request is worth and how hard it is.

What the numbers say

  • Fast ≠ expensive. The three fastest models (GPT-5-mini 180ms, DeepSeek Chat 240ms, GLM-4 260ms) are also the cheapest on the Model Price Index — mini-tier and open-weight models win on both axes.
  • Slow ≠ premium. Claude Opus 4 (680ms p50 TTFT) is the most expensive model on the market at $15/$75 per 1M tokens, yet its TTFT is 3.8× slower than GPT-5-mini's. You pay for reasoning depth and output quality, not responsiveness.
  • Quality correlates with completion time, not TTFT. Frontier models spend their extra milliseconds generating reasoning tokens. A 2.1s GPT-5 completion almost always beats an 800ms GPT-5-mini completion on hard tasks — the question is whether your task needs that depth.
  • The 5× spread (180ms → 900ms p50) is the routing opportunity. Route simple chat and autocomplete to sub-300ms models; route math, code review and research to reasoning models. Cost-aware routing with latency awareness is the single biggest win for both UX and spend.
  • p95 is the production number. A 600ms p95 (GPT-5-mini) means consistent feel under load; DeepSeek R1's 5,000ms p95 means your worst-case user waits 5 seconds for a first token — fine for deep research, unacceptable for a chatbot.
  • Deeper dive: our engineering guide AI API Latency Optimization covers prompt caching, streaming and routing strategies in practice.

Streaming: why 180ms TTFT feels instant

Perceived latency is dominated by time to first token, not total completion time. With token-by-token streaming, the user sees output begin at TTFT and then reads along as tokens arrive at 50–150 tokens/second. A 180ms TTFT response — under a quarter of a blink — lands before the user has finished reading the prompt they just sent.

What the numbers say

  • 180ms + streaming = instant. GPT-5-mini's 180ms p50 TTFT is below the ~250ms threshold where humans perceive UI as "immediate". Combined with streaming, the full 800ms completion is invisible — users experience an instant reply.
  • Completion time only matters when streaming is off. Non-streaming clients pay the full p50 completion as dead time: 4.5s for Claude Opus 4, 8.2s for DeepSeek R1. Every serious integration should stream.
  • Reasoning models stream their thinking. DeepSeek R1's 8.2s completion is experienced as a live reasoning trace — users watch the model work, which reads as engaged, not slow.
  • Tail latency compounds at scale. A p95 of 5,000ms (DeepSeek R1) under burst load can turn into 10s+ timeouts without streaming; streaming converts worst-case waits into visible progress.
  • Routing for feel: sub-300ms p50 models for autocomplete and chat; sub-1,500ms p95 for interactive tools; anything goes for batch and background jobs.

Dataset notes & methodology

How this benchmark is built

  • Scope: 12 models from 8 providers — OpenAI, Anthropic, DeepSeek, Google, Meta, Alibaba, Moonshot AI, Zhipu AI, xAI.
  • Metric: TTFT = time from request send to first received token. Completion = time to full response, including reasoning tokens where generated.
  • Measurement: p50 and p95 across a sampled request mix on identical hardware, streaming enabled, single region. Provider load and network geography shift absolute numbers; relative ordering is stable.
  • Cadence: refreshed weekly; last verified 2026-08-16.
  • Cost companion: see the Model Price Index for the same models' USD per 1M tokens.
  • Reseller note: DrAI offers all of these models at one flat subscription price — no per-token metering, no surprise bills, and the same streaming API for every model. See pricing.

Every model above. One flat price.

Stop metering tokens and watching latency. DrAI bundles GPT-5, Claude Opus 4, DeepSeek R1 and 12+ more models into a single subscription with one unified streaming API.

See DrAI pricing Start free — no card needed
🌐 English