Models / API speed

Compiled by Spring Prompt

LLM API speed

How long each model takes on a real task, how fast it writes, and how much it writes to get there. Seconds per task are measured on our own benchmarks; tokens per second are from Artificial Analysis. The pricing page does the same for cost.

Benchmarks timed
4
seconds per task, from our runs
Settings with tokens/s
137
model and reasoning setting
Speeds measured
9 Nov 2026

Seconds per task

Wall-clock time from sending the request to a usable answer, measured while running our own benchmarks, with the score the same run earned. It's what a model's speed means in practice: how long it thinks, how much it writes and how fast it writes, together. Each model is shown at its quickest setting. Times were measured through OpenRouter on the run date, so they also depend on the host and its load that day.

CatalogBench: turning a sparse product feed into a listing (36 models)

CatalogBench: score against time per listing

Further up scored better; further left finished sooner. The line joins the models no other model beats on both.

Best score for the waitOther models (hover for names)Best score at each wait

0%20%40%60%80%100% 1.0 s10 s100 s Seconds per listing (log scale) Reliably publish-ready Gemini 3.5 Flash-Lite GPT-6.2 Sol Gemini 4 Neon
#Model and settingSeconds per listingOutput tokens per listingReliably publish-ready
1Gemini 3.5 Flash-Lite3.3 snot yet17.9%
2Mistral Medium 3.54.9 snot yet17.9%
3GPT-6.2 Sol6.5 s44275.0%
4DeepSeek-V4.1-Flash-10176.7 s1,22621.4%
5Gemini 4 Argon7.3 snot yet60.7%
6Claude Haiku 4.58.1 snot yet1.8%
7Muse Ember8.1 s3,81653.6%
8GPT-6 Luna8.2 snot yet55.4%
9Mistral Large 48.2 snot yet7.1%
10GPT-6.2 Astra9.7 s42673.2%
11Claude Sonnet 5.59.9 snot yet32.1%
12GPT-6.1 Terra10 s45764.3%
13GPT-6.1 Sol10 snot yet75.0%
14Muse Wonder10 snot yet66.1%
15GPT-6 Sol11 snot yet66.1%
16Claude Haiku 5.511 snot yet26.8%
17GPT-6 Astra12 snot yet75.0%
18Claude Opus 5.517 snot yet55.4%
19Claude Fable 5.218 s1,44271.4%
20DeepSeek-V4.1-Flash18 snot yet41.1%
21Gemini 3.8 Flash19 snot yet35.7%
22Gemini 4 Hydrogen20 s2,41662.5%
23Qwen4-Max21 s1,22739.3%
24Claude Fable 5.122 snot yet26.8%
25Gemini 3.1 Pro Preview22 snot yet44.6%
26Particle-124 s2,1800.0%
27MiniMax M3.1 Flash25 s3,0140.0%
28GLM-5.3 FlashX Legal29 s3,6510.0%
29Gemini 4 Neon36 s3,93978.6%
30Grok 4.742 snot yet57.1%
31Gemini 4 Carbon45 s1,60053.6%
32Muse Spark 1.348 snot yet48.2%
33GLM-5V-Turbo62 snot yet1.8%
34Kimi K367 snot yet41.1%
35Qwen3.8-Max (0902)78 snot yet28.6%
36Kimi K3.1 Pro114 s3,996–

DeckBench: turning an analysis into a deck (36 models)

DeckBench: score against time per deck

Further up scored better; further left finished sooner. The line joins the models no other model beats on both.

Best score for the waitOther models (hover for names)Best score at each wait

05001,0001,5002,000 10 s100 s17 min167 min Seconds per deck (log scale) Deck rating Gemini 3.5 Flash-Lite Muse Wonder GPT-6.2 Sol GPT-6 Sol GPT-6 Astra Qwen4-Max
#Model and settingSeconds per deckOutput tokens per deckDeck rating
1Gemini 3.5 Flash-Lite15 snot yet605
2Mistral Medium 3.525 snot yet585
3Muse Wonder29 snot yet1,204
4Muse Ember30 s22,0941,143
5GPT-6.2 Astra44 s4,4531,188
6Claude Haiku 4.552 snot yet646
7Claude Haiku 5.562 snot yet1,120
8Gemini 4 Argon68 snot yet951
9DeepSeek-V4.1-Flash-101773 s21,0191,046
10Gemini 3.1 Pro Preview78 snot yet716
11GPT-6.2 Sol82 s7,3061,370
12Mercury 383 s32,448726
13Claude Sonnet 5.583 snot yet1,334
14Muse Spark 1.389 snot yet807
15Gemini 3.8 Flash93 snot yet771
16Claude Opus 5.598 snot yet1,323
17GPT-6 Luna101 snot yet1,252
18Mistral Large 4114 snot yet595
19GPT-6.1 Terra2.2 min12,0861,280
20Particle-12.6 min16,9521,086
21Claude Fable 5.12.6 minnot yet1,256
22GPT-6 Sol2.8 minnot yet1,438
23GLM-5.3 FlashX Legal2.9 min27,796809
24GPT-6.1 Sol3.0 minnot yet1,375
25Gemini 4 Hydrogen3.4 min31,3681,079
26MiniMax M3.1 Flash3.6 min33,7651,266
27Gemini 4 Carbon3.8 min15,626992
28Claude Fable 5.24.8 min33,2851,403
29GPT-6 Astra5.2 minnot yet1,551
30DeepSeek-V4-Pro (0423)5.5 minnot yet530
31Grok 4.76.2 minnot yet1,242
32Gemini 4 Neon7.1 min48,4621,013
33Kimi K37.3 minnot yet1,194
34Qwen4-Max8.1 min36,5721,563
35Qwen3.8-Max (0902)9.1 minnot yet1,025
36Kimi K3.1 Pro21 min51,7391,223

SurveyBench: planning a user survey and analysing its responses (27 models)

SurveyBench: score against time per survey (both steps)

Further up scored better; further left finished sooner. The line joins the models no other model beats on both.

Best score for the waitOther models (hover for names)Best score at each wait

05001,0001,5002,000 10 s100 s17 min167 min Seconds per survey (both steps) (log scale) Analysis rating Gemini 3.5 Flash-Lite Muse Ember Muse Wonder GPT-6.2 Astra Claude Fable 5.2
#Model and settingSeconds per survey (both steps)Output tokens per survey (both steps)Analysis rating
1Gemini 3.5 Flash-Lite16 snot yet637
2Mistral Medium 3.548 snot yet578
3Muse Ember73 s40,2981,344
4Gemini 4 Argon74 snot yet928
5Muse Wonder83 snot yet1,439
6GPT-6.2 Astra92 s5,8881,476
7GPT-6.1 Terra92 s8,1121,217
8Claude Haiku 4.593 snot yet560
9GPT-6.2 Sol104 s9,1871,362
10Gemini 3.8 Flash2.2 min21,981845
11DeepSeek-V4.1-Flash-10172.2 min30,8931,119
12GPT-6 Luna2.3 min14,3331,072
13Claude Haiku 5.52.5 minnot yet1,233
14Gemini 3.1 Pro Preview2.8 minnot yet744
15Claude Opus 5.53.0 minnot yet1,417
16Mercury 33.2 min57,343735
17GPT-6.1 Sol3.7 minnot yet1,429
18Particle-14.2 min26,6011,133
19Gemini 4 Hydrogen4.4 min41,5421,096
20Claude Fable 5.25.6 min33,9021,670
21MiniMax M3.1 Flash5.9 min63,237428
22Gemini 4 Carbon6.5 min27,7601,054
23GLM-5.3 FlashX Legal7.2 min51,553937
24Gemini 4 Neon7.3 min50,889629
25Mistral Large 47.3 minnot yet770
26Qwen4-Max12 min39,9991,381
27Kimi K3.1 Pro33 min70,935605

BulletBench: choosing a chess move on the Lightning 10+1 clock (45 models)

BulletBench: score against time per move (median)

Further up scored better; further left finished sooner. The line joins the models no other model beats on both.

Best score for the waitOther models (hover for names)Best score at each wait

-200300800 0.1 s1.0 s10 s Seconds per move (median) (log scale) Ladder Elo Seed-2.0-Mini (minimal reasoning) Mercury Decide Clef Omni Gemini Decision 1 Gemini 3.1 Flash-Lite (minimal reasoning) Gemini 3.5 Flash-Lite

Tokens per task. Some models solve a task in far fewer tokens than others, which can matter more than how fast they write. We record output tokens per task, thinking included, for every run from 14 October 2026; a benchmark shows them once its models have been run again. Earlier runs recorded only time and cost.

Tokens per second

How fast each model writes once it has started: the median output tokens a second on its usual API, measured by Artificial Analysis. A reasoning model thinks before it answers, and that wait isn't in tokens per second, so "first token" shows it: the median time before the answer starts. Each row is one model at one reasoning setting. Models with a shutdown date announced are left out.

Model and settingTokens/sFirst tokenIntelligence
Nemotron 3.5 Super VLNVIDIA · open weights 411 5.4 s 26.5
Gemini 3.5 Flash-LiteGoogle 398 4.7 s 22.2
DeepSeek-V4.1-Flash (no reasoning)DeepSeek · open weights 369 0.6 s 24.7
Trinity Large ThinkingArcee AI 362 6.6 s 10.8
Beam 1.0 501B A23BReflection · open weights 323 6.7 s 30.3
gpt-oss-20b (low reasoning)OpenAI · open weights 277 7.6 s 10.0
gpt-oss-20b (high reasoning)OpenAI · open weights 263 8.0 s 9.0
Nova Micro 1.0Amazon 260 0.5 s 5.9
gpt-oss-120b (high reasoning)OpenAI · open weights 259 8.2 s 11.6
gpt-oss-120b (low reasoning)OpenAI · open weights 258 8.3 s 10.2
Muse Spark 1.3 (xhigh reasoning)Meta 254 30 s 45.1
Claude Haiku 5.5 (max reasoning)Anthropic 240 4.7 min 43.4
Nemotron 3 Nano 30B A3B (thinking reasoning)NVIDIA · open weights 238 8.9 s 8.9
Nova 2 Lite (no reasoning)Amazon 233 0.7 s 8.7
Inkling (xhigh reasoning)Thinking Machines · open weights 232 11 s 25.0
Nemotron 3 Nano 30B A3B (no reasoning)NVIDIA · open weights 232 0.4 s 6.8
DeepSeek-V4.1-Flash (max reasoning)DeepSeek · open weights 231 9.4 s 39.5
Qwen3.5-Omni-FlashAlibaba 231 0.9 s 12.5
Nova 2 Lite (high reasoning)Amazon 220 24 s 13.4
DeepSeek-V4.1-Flash-1017 (max reasoning)DeepSeek · open weights 212 10 s 45.1
Ministral 3 3BMistral AI · open weights 209 0.4 s 4.8
Nova 2 Lite (medium reasoning)Amazon 200 27 s 12.5
Claude Haiku 5.5 (xhigh reasoning)Anthropic 192 46 s 41.2
DeepSeek-V4-Flash-Vision-Exp (max reasoning)DeepSeek · open weights 191 12 s 34.8
Inkling SmallThinking Machines · open weights 181 13 s 25.7
Nova 2 Lite (low reasoning)Amazon 177 16 s 11.8
Mistral Small 4Mistral AI · open weights 176 12 s 11.3
Claude Haiku 5.5 (high reasoning)Anthropic 169 16 s 37.8
Mistral Small 4 (no reasoning)Mistral AI · open weights 166 0.6 s 9.0
Qwen3-Next-80B-A3B-ThinkingAlibaba 163 13 s 11.2
MiniMax M3.1 FlashMiniMax · open weights 159 13 s 42.4
Mistral Medium 3.5Mistral AI 157 13 s 14.2
Claude Haiku 5.5 (low reasoning)Anthropic 157 6.4 s 29.5
Claude Haiku 5.5 (medium reasoning)Anthropic 155 8.9 s 34.5
o3OpenAI 155 4.6 s 20.2
Muse Wonder (max reasoning)Meta 153 48 s 52.4
GPT-5.5 Instant (2026-06-26)OpenAI 152 14 s 26.0
Gemma 4 12BGoogle 148 15 s 14.2
MiniMax-M3MiniMax · open weights 146 15 s 29.2
Gemma 4 12B (no reasoning)Google 145 1.1 s 9.4
Qwen3.5-122B-A10B (no reasoning)Alibaba · open weights 144 1.0 s 17.7
Muse Glimmer (high reasoning)Meta 142 14 s 17.5
Muse Spark Open (xhigh reasoning)Meta · open weights 142 15 s 38.9
Gemini 3.8 Flash (high reasoning)Google 141 16 s 40.9
GPT-5.6 Terra (max reasoning)OpenAI 140 3.3 min 42.1
Claude Sonnet 5.5 (max reasoning)Anthropic 137 5.4 min 56.0
Qwen3.6-35B-A3B (no reasoning)Alibaba · open weights 135 1.1 s 15.2
Qwen3.6-35B-A3BAlibaba · open weights 134 42 s 18.2
Llama 4 ScoutMeta · open weights 132 0.6 s 6.5
Qwen3.5-122B-A10BAlibaba · open weights 132 16 s 15.6
Gemini 3.1 Pro PreviewGoogle 130 15 s 29.7
GPT-6 Luna (max reasoning)OpenAI 127 116 s 38.1
GPT-6 Luna (high reasoning)OpenAI 122 17 s 32.9
Qwen3-Next-80B-A3B-InstructAlibaba · open weights 121 0.6 s 9.6
Muse Spark 1.3 (max reasoning)Meta 119 56 s 48.1
GPT-5.3-Codex (xhigh reasoning)OpenAI 119 45 s 32.5
Solar Pro 4Upstage 119 18 s 26.6
GPT-6 Luna (low reasoning)OpenAI 115 3.5 s 21.5
GPT-5.6 Terra (xhigh reasoning)OpenAI 114 21 s 38.0
GPT-6 Luna (no reasoning)OpenAI 113 0.7 s 18.5
GPT-6 Luna (xhigh reasoning)OpenAI 112 38 s 34.6
Qwen3.5-9B (no reasoning)Alibaba · open weights 110 0.4 s 13.3
Qwen3-Omni-30B-A3B-ThinkingAlibaba 108 19 s 7.8
Qwen3-Omni-30B-A3B-InstructAlibaba 107 0.9 s 6.0
GPT-5.6 Terra (high reasoning)OpenAI 106 6.3 s 34.2
Claude Sonnet 5.5 (xhigh reasoning)Anthropic 103 19 s 51.9
Claude Sonnet 5.5 (high reasoning)Anthropic 100 9.2 s 46.8
GPT-5.6 Terra (medium reasoning)OpenAI 100 1.9 s 30.1
Llama 3.3 70B InstructMeta · open weights 98 0.6 s 7.7
GPT-5.6 Terra (low reasoning)OpenAI 97 1.4 s 27.5
Qwen3.5-Omni-PlusAlibaba 97 1.1 s 20.4
Claude Opus 5.5 (max reasoning)Anthropic 96 10 min 57.6
DeepSeek-V4-Pro (0813, max reasoning)DeepSeek · open weights 96 22 s 36.0
GPT-5.6 Terra (no reasoning)OpenAI 96 0.7 s 20.8
Ministral 3 8BMistral AI · open weights 93 0.5 s 5.5
Claude Sonnet 5.5 (medium reasoning)Anthropic 93 0.9 s 40.8
DeepSeek-V4-Pro (0813, no reasoning)DeepSeek · open weights 93 1.2 s 20.4
Claude Sonnet 5.5 (low reasoning)Anthropic 93 0.7 s 35.9
GLM-5.3 (low reasoning)Z.ai · open weights 87 25 s 34.3
Hy3Tencent · open weights 83 26 s 25.3
Reka Flash 3Reka AI · open weights 83 25 s 5.6
Gemma 4 26B A4B (no reasoning)Google · open weights 82 0.6 s 13.1
Claude Opus 5.5 (xhigh reasoning)Anthropic 80 81 s 56.0
Ministral 3 14BMistral AI · open weights 79 0.5 s 6.0
GLM-5.3-FlashZ.ai · open weights 79 27 s 41.8
GLM-5.3 (max reasoning)Z.ai · open weights 78 28 s 44.8
Qwen3-Coder-NextAlibaba · open weights 77 0.7 s 9.2
Magistral Small 1.2Mistral AI 76 27 s 8.6
Claude Opus 5.5 (low reasoning)Anthropic 76 6.9 s 42.3
Claude Opus 5.5 (high reasoning)Anthropic 75 27 s 53.6
Grok 4.7 (xhigh reasoning)xAI 74 22 s 46.4
Claude Opus 5.5 (medium reasoning)Anthropic 74 14 s 51.2
Grok 4.7 (high reasoning)xAI 74 18 s 46.3
Claude Fable 5.1 (max reasoning)Anthropic 72 2.8 min 53.4
GPT-6 Astra (max reasoning)OpenAI 72 3.7 min 52.7
Qwen3.5-9BAlibaba · open weights 71 29 s 11.2
GPT-6 Astra (xhigh reasoning)OpenAI 67 118 s 52.4
Granite 4.2 8BIBM · open weights 65 31 s 11.1
Grok 4.7 (low reasoning)xAI 63 4.0 s 42.2
Mistral Large 4Mistral AI · open weights 60 34 s 38.4
Claude Fable 5.1 (xhigh reasoning)Anthropic 60 47 s 53.2
Command ACohere · open weights 59 0.4 s 7.0
GPT-6 Astra (high reasoning)OpenAI 59 51 s 50.9
GPT-6 Astra (low reasoning)OpenAI 56 1.4 s 45.8
Qwen3.7-PlusAlibaba 56 37 s 25.2
Qwen3.5-397B-A17B (no reasoning)Alibaba · open weights 56 1.5 s 21.4
Qwen3.8-Flash-NextAlibaba 55 38 s 39.8
GPT-6 Astra (medium reasoning)OpenAI 55 5.7 s 49.6
Qwen3.5-397B-A17BAlibaba · open weights 55 60 s 18.4
Claude Fable 5.1 (medium reasoning)Anthropic 54 6.0 s 48.9
Kimi K2.7 CodeMoonshot AI · open weights 54 43 s 25.8
Gemma 4 26B A4BGoogle · open weights 53 38 s 16.7
GPT-6.1 Sol (max reasoning)OpenAI 53 4.2 min 51.8
Claude Fable 5.1 (low reasoning)Anthropic 52 0.9 s 46.8
Claude Fable 5.1 (high reasoning)Anthropic 51 10.0 s 51.2
GPT-6.1 Sol (xhigh reasoning)OpenAI 50 110 s 51.0
GPT-6.1 Sol (high reasoning)OpenAI 49 41 s 50.2
Gemma 4 31B (no reasoning)Google · open weights 48 0.8 s 13.9
Qwen3.8-27B (low reasoning)Alibaba · open weights 46 44 s 26.2
Llama 4 MaverickMeta · open weights 46 0.6 s 9.3
MiMo-V2.6-FlashXiaomi · open weights 46 47 s 37.9
Phi-4Microsoft · open weights 45 1.0 s 5.9
GPT-6.1 Sol (low reasoning)OpenAI 45 1.7 s 42.1
GPT-6.1 Sol (medium reasoning)OpenAI 45 7.0 s 47.8
Qwen3.8-27B (medium reasoning)Alibaba · open weights 43 48 s 27.6
Qwen3.8-27B (no reasoning)Alibaba · open weights 43 1.3 s 20.2
MiMo-V2.6-ProXiaomi · open weights 43 50 s 46.3
Kimi K3 (max reasoning)Moonshot AI · open weights 41 52 s 43.6
Kimi K3 (low reasoning)Moonshot AI · open weights 40 53 s 30.1
Qwen3.8-27B (xhigh reasoning)Alibaba · open weights 39 52 s 33.7
Qwen3.8-Max (0902)Alibaba 37 56 s 45.4
Qwen3.8-2.4T-A95BAlibaba · open weights 36 58 s 39.9
Gemma 4 31BGoogle · open weights 35 50 s 14.7
Gemma 4 E4B (no reasoning)Google 32 0.4 s 7.5
Gemma 4 E4BGoogle 28 72 s 8.9
Qwen3.5-4B (thinking reasoning)Alibaba 10 3.4 min 13.1
Qwen3.5-4B (no reasoning)Alibaba 9 0.7 s 10.8

Tokens per second against intelligence

How fast each model writes for what it can do

Further up is more capable; further right writes faster. Green settings write fastest for their intelligence: none is beaten on both.

Fastest for their intelligenceOther settings (hover for names)

020406080 1101001,000 Output tokens per second (log scale) Intelligence Index Nemotron 3.5 Super VL Beam 1.0 501B A23B Muse Spark 1.3 (xhigh reasoning) Muse Wonder (max reasoning) Claude Sonnet 5.5 (max reasoning) Claude Opus 5.5 (max reasoning)

Each dot is one model at one reasoning setting. Green dots write fastest for their intelligence: for each, no other setting writes faster and is more capable. Tokens per second is on a log scale. It leaves out thinking time, so a high reasoning setting can write quickly and still take minutes per task.

The fastest writer at each level

Grouped by the Artificial Analysis Intelligence Index.

IntelligenceFastest writerTokens/sMost capableTokens/s
Frontier: 50 or more Muse Wonder (max reasoning)Meta · 52.4153 Claude Opus 5.5 (max reasoning)Anthropic · 57.696
Strong: 40–50 Muse Spark 1.3 (xhigh reasoning)Meta · 45.1254 GPT-6 Astra (medium reasoning)OpenAI · 49.655
Capable: 30–40 Beam 1.0 501B A23BReflection · 30.3323 Qwen3.8-2.4T-A95BAlibaba · 39.936
Everyday: 20–30 Nemotron 3.5 Super VLNVIDIA · 26.5411 Gemini 3.1 Pro PreviewGoogle · 29.7130
Light: under 20 Trinity Large ThinkingArcee AI · 10.8362 GPT-6 Luna (no reasoning)OpenAI · 18.5113

How to get answers faster

Time your own task

Tokens per second is only part of it. A model that thinks for longer, or writes three times as much, takes longer whatever its writing speed. Time a few real requests on two or three candidates.

Set the reasoning effort deliberately

The setting matters as much as the model: the same model can start answering in two seconds or eight minutes. Try the lowest setting that passes your task.

Stream the answer

For chat, people judge speed by when words appear. Streaming shows the answer from the first token.

Ask for less

Writing time grows with every output token. Ask for structured output, cap the length, and leave out what you won't use.

Run independent calls in parallel

Ten separate extractions sent at once finish in the time of the slowest, not of all ten in a row.

Check the host

Open-weights models run on many hosts at very different speeds; some sell a faster tier. The tokens per second here are on each model's usual API.

Quick answers

What is the fastest LLM API?

Nemotron 3.5 Super VL writes fastest, at 411 output tokens a second on its usual API, measured by Artificial Analysis.

What is the fastest capable LLM?

Muse Spark 1.3 (xhigh reasoning) writes fastest of the settings scoring 40 to 50 on the Intelligence Index, at 254 tokens a second.

How fast is the most capable model?

Claude Opus 5.5 (max reasoning) scores highest on the Intelligence Index (57.6). It writes 96 tokens a second, but thinks first: its answers typically start after 10 min.

How long does an LLM take for a real task?

On CatalogBench, turning a sparse product feed into a listing, Gemini 3.5 Flash-Lite took 3.3 s per product and Kimi K3.1 Pro 114 s, measured on our own runs.

Why isn't tokens per second the same as speed on a task?

Tokens per second is how fast a model writes once it has started. The time a task takes also depends on how long it thinks first and how many tokens it writes in all: a slower writer that solves the task in fewer tokens can finish first.

Which model is quick enough for your task?

Run the models you're considering side by side on your own prompt. See how long each answer takes, whether it passes your checks, and what it costs.

Sources and method

  • Seconds and tokens per task: recorded while running our own benchmarks (CatalogBench, DeckBench, SurveyBench, BulletBench), averaged over the same tasks as their cost, including any retry needed for a usable answer. SurveyBench adds its two steps together. BulletBench is the median time per chess move. Output tokens include hidden thinking; tokenizers differ between developers, so token counts compare effort only roughly.
  • Tokens per second, first token and intelligence: Artificial Analysis (data sourced from Artificial Analysis), fetched 9 Nov 2026. Medians over recent weeks on each model's usual API. Each row's Intelligence Index is for the same setting as its speed.