Llama Models

53 modelsGeneral models from $0.2/M inputUp to 1.05M context

Usage

Last 30 days · 2026-09-06 to 2026-10-05

Tokens

1.5B

Requests

200K

Models in use

28 of 53

Tokens per day, stacked by model

0145M289M09-0609-1309-2009-2710-042026-09-06 — 19,971,790 tokens llama-4-scout: 19,776,165 llama-3.3-70b-instruct: 193,020 llama-4-maverick: 1,215 2 more models: 440 deepinfra-llama-3.3-70b-instant-turbo: 290 llama-3.3-70b: 195 llama3.1-8b: 190 llama-3.1-70b: 145 deepinfra-llama-4-maverick-17b-128e-instruct: 1302026-09-07 — 132,025 tokens llama-4-maverick: 93,765 llama-4-scout: 33,200 llama-3.3-70b: 4,915 llama-3.3-70b-instruct: 1452026-09-08 — 1,713,535 tokens llama-3.3-70b-instruct: 1,401,415 llama-4-scout: 171,625 llama-4-maverick: 140,190 llama-3.3-70b: 160 deepinfra-llama-4-maverick-17b-128e-instruct: 1452026-09-09 — 458,030 tokens llama-4-maverick: 344,320 llama-4-scout: 95,820 llama-3.1-70b: 17,670 deepinfra-llama-4-maverick-17b-128e-instruct: 145 llama-3.3-70b-instruct: 752026-09-10 — 389,030 tokens llama-4-maverick: 386,350 2 more models: 565 llama-3.3-70b-instruct: 435 llama-4-scout: 355 deepinfra-llama-3.3-70b-instant-turbo: 355 deepinfra-llama-4-maverick-17b-128e-instruct: 265 llama-3.1-70b: 260 llama-3.3-70b: 255 llama3.1-8b: 1902026-09-11 — 633,060 tokens llama-4-maverick: 620,860 llama-4-scout: 12,2002026-09-12 — 306,575 tokens llama-4-scout: 306,150 llama-4-maverick: 285 llama-3.3-70b-instruct: 1402026-09-13 — 13,113,900 tokens llama-3.3-70b: 6,813,240 deepinfra-llama-3.3-70b-instant-turbo: 5,866,120 llama-3.3-70b-instruct: 434,125 llama-4-scout: 180 llama-4-maverick: 165 2 more models: 702026-09-14 — 14,668,985 tokens llama-4-scout: 6,570,835 llama-4-maverick: 5,299,845 llama-3.3-70b: 1,744,025 deepinfra-llama-3.3-70b-instant-turbo: 1,054,2802026-09-15 — 0 tokens2026-09-16 — 150,335 tokens llama-4-scout: 82,930 llama-4-maverick: 66,710 llama-3.3-70b-instruct: 6952026-09-17 — 160,895,190 tokens llama-3.3-70b: 146,980,255 llama-4-scout: 13,907,380 llama-4-maverick: 7,5552026-09-18 — 16,050 tokens llama-4-maverick: 8,050 llama-4-scout: 8,0002026-09-19 — 0 tokens2026-09-20 — 25,514,860 tokens llama-4-scout: 25,514,015 llama-4-maverick: 770 2 more models: 752026-09-21 — 330,240 tokens llama-3.3-70b: 283,360 llama-4-scout: 46,8802026-09-22 — 2,076,995 tokens llama-3.3-70b: 1,926,550 llama-4-scout: 142,680 llama-4-maverick: 7,7652026-09-23 — 6,148,140 tokens llama-3.3-70b: 5,156,490 llama-4-scout: 742,780 llama-4-maverick: 248,590 deepinfra-llama-4-maverick-17b-128e-instruct: 145 2 more models: 1352026-09-24 — 6,791,085 tokens llama-4-scout: 5,483,535 llama-3.3-70b-instruct: 1,307,265 llama-4-maverick: 2852026-09-25 — 87,969,380 tokens llama-3.3-70b-instruct: 57,929,765 llama-3.3-70b: 19,999,265 llama-4-maverick: 7,983,270 llama-4-scout: 2,057,0802026-09-26 — 213,941,720 tokens llama-3.3-70b-instruct: 82,625,145 llama-4-scout: 78,398,265 llama-4-maverick: 51,814,665 llama-3.3-70b: 1,103,6452026-09-27 — 1,001,580 tokens llama-4-scout: 522,035 llama-4-maverick: 479,5452026-09-28 — 69,494,840 tokens llama-3.3-70b-instruct: 37,079,905 llama-4-scout: 27,343,950 llama-4-maverick: 5,068,015 llama-3.1-70b: 1,000 2 more models: 605 deepinfra-llama-3.3-70b-instant-turbo: 460 llama3.1-8b: 380 deepinfra-llama-4-maverick-17b-128e-instruct: 265 llama-3.3-70b: 2602026-09-29 — 75,499,760 tokens llama-4-scout: 67,118,270 llama-3.3-70b-instruct: 8,381,140 llama-4-maverick: 220 2 more models: 1302026-09-30 — 222,096,460 tokens llama-4-scout: 124,039,875 llama-3.3-70b-instruct: 57,676,875 llama-3.3-70b: 40,379,550 llama-4-maverick: 1602026-10-01 — 289,235,810 tokens llama-3.3-70b-instruct: 242,220,860 llama-4-scout: 46,480,005 llama-4-maverick: 534,9452026-10-02 — 239,881,070 tokens llama-3.3-70b-instruct: 221,530,685 llama-4-scout: 18,350,3852026-10-03 — 11,224,295 tokens llama-4-scout: 10,796,285 llama-4-maverick: 426,555 llama-3.3-70b-instruct: 1,370 llama-3.3-70b: 852026-10-04 — 14,620,620 tokens llama-4-scout: 14,129,710 llama-4-maverick: 490,9102026-10-05 — 53,675,075 tokens llama-4-maverick: 26,587,490 llama-4-scout: 24,356,630 llama3.1-8b: 2,728,220 llama-3.3-70b-instruct: 1,715 2 more models: 405 llama-3.3-70b: 190 deepinfra-llama-4-maverick-17b-128e-instruct: 155 deepinfra-llama-3.3-70b-instant-turbo: 135 llama-3.1-70b: 135
  • llama-3.3-70b-instruct
  • llama-4-scout
  • llama-3.3-70b
  • llama-4-maverick
  • deepinfra-llama-3.3-70b-instant-turbo
  • llama3.1-8b
  • llama-3.1-70b
  • deepinfra-llama-4-maverick-17b-128e-instruct
  • 2 more models

Which models that traffic went to

  1. Llama 3.3 70B Instruct46.4%711M
  2. Llama 4 Scout31.8%486M
  3. Llama 3.3 70B14.6%224M
  4. Llama 4 Maverick6.6%101M
  5. Deepinfra Llama 3.3 70B Instant Turbo0.5%6.9M
  6. Llama3.1 8B0.2%2.7M
  7. Llama 3.1 70B<0.1%19.2K
  8. Deepinfra Llama 4 Maverick 17B 128e Instruct<0.1%1.3K
  9. 2 more models<0.1%2.4K

Share of 1.5B tokens. 18 models with traffic report no token counts and cannot be ranked here, including groq-llama-3.3-70b-versatile and aihubmix-Llama-3-1-8B-Instruct — they are in the request view.

The two views disagree on purpose: a model can take a large share of the calls and a small share of the tokens — many short requests — or the reverse. Which one matters depends on whether your cost is driven by call volume or by prompt length. Measured on AIHubMix over the last 30 days, counting the 53 model IDs listed on this page; traffic routed through upstream-specific IDs that are not in the public catalog is not included.

All 53 Llama Models

Open in model list
Llama models on AIHubMix with input and output modalities, context length, maximum output, price per million tokens including cache read and cache write rates, and measured throughput and latency.
Modalities
llama-4-maverickTakes text, vision, returns text.1.05M32K$0.2$0.2/M98 tok/s0.23 s
llama-4-scoutTakes text, vision, returns text.131K131K$0.2$0.2/M148 tok/s0.81 s
llama-3.3-70b-instructTakes text, returns text.131K—$0.6$1.2/M——
llama-3.3-70b66K8K$0.6$0.6/M3250 tok/s0.25 s
llama3-groq-8b-8192-tool-use-preview——$0.00019$0.00019/M——
llama3-groq-70b-8192-tool-use-preview——$0.00089$0.00089/M——
meta-llama/llama-3.1-405b-instruct:free——$0.02$0.02/M——
meta-llama/llama-3.1-70b-instruct:free——$0.02$0.02/M——
meta-llama/llama-3.1-8b-instruct:free——$0.02$0.02/M——
meta-llama/llama-3.2-11b-vision-instruct:free——$0.02$0.02/M——
meta-llama/llama-3.2-3b-instruct:free——$0.02$0.02/M——
deepinfra-llama-3.1-8b-instant——$0.033$0.055/M——
groq-llama-3.1-8b-instant——$0.055$0.088/M——
llama3-8b-8192——$0.06$0.12/M——
deepinfra-llama-4-scout-17b-16e-instruct——$0.088$0.33/M18 tok/s0.81 s
llama2-7b-2048——$0.1$0.1/M——
deepinfra-llama-3.3-70b-instant-turbo——$0.11$0.352/M5 tok/s5.62 s
groq-llama-4-scout-17b-16e-instruct——$0.122$0.366/M——
deepseek-r1-distill-qianfan-llama-8b——$0.137$0.548/M——
llama-3.2-11b-vision-preview——$0.2$0.2/M——
llama-3.2-1b-preview——$0.2$0.2/M——
llama-3.2-3b-preview——$0.2$0.2/M——
groq-llama-4-maverick-17b-128e-instruct——$0.22$0.66/M——
qianfan-llama-vl-8b——$0.274$0.685/M——
aihubmix-Llama-3-1-8B-Instruct——$0.3$0.6/M——
llama-3.1-8b-instant——$0.3$0.6/M——
llama3-8b-8192(33)——$0.3$0.3/M——
llama3.1-8b——$0.3$0.6/M——
meta/llama3-8B-chat——$0.3$0.3/M——
deepinfra-llama-4-maverick-17b-128e-instruct——$0.33$1.32/M82 tok/s0.93 s
aihubmix-Llama-3-2-11B-Vision——$0.4$0.4/M——
Gryphe/MythoMax-L2-13b——$0.4$0.4/M——
llama-3.1-70b——$0.44$0.44/M——
llama2-70b-4096Takes , returns text.——$0.5$0.5/M——
llama2-70b-40960Takes , returns text.——$0.5$0.5/M——
meta-llama/Llama-3.2-90B-Vision-Instruct——$0.5$0.5/M——
meta-llama-3-8b——$0.548$0.548/M——
aihubmix-Llama-3-1-70B-Instruct——$0.6$0.78/M——
cerebras-llama-3.3-70b——$0.6$0.6/M——
llama-3.1-70b-versatile——$0.6$0.6/M——
groq-llama-3.3-70b-versatile——$0.649$0.869/M——
aihubmix-Llama-3-70B-Instruct——$0.7$0.7/M——
llama3-70b-8192——$0.7$0.9373/M——
qianfan-chinese-llama-2-13b——$0.822$0.822/M——
WizardLM/WizardCoder-Python-34B-V1.0——$0.9$0.9/M——
aihubmix-Llama-3-2-90B-Vision——$2.4$2.4/M——
llama-3.2-90b-vision-preview——$2.4$2.4/M——
llama3-70b-8192(33)——$2.65$2.65/M——
llama-3.1-405b-instruct——$4$4/M——
llama-3.1-405b-reasoning——$4$4/M——
meta-llama-3-70b——$4.795$4.795/M——
aihubmix-Llama-3-1-405B-Instruct——$5$15/M——
meta/llama-3.1-405b-instruct——$5$5/M——

Prices are USD per million tokens; cache read and cache write are the rates for prompt-cache hits and for writing a prompt into the cache. Throughput and latency are measured on AIHubMix — the same figures the model detail page shows — not vendor claims. A dash means the catalog does not publish that field for that model, which is not the same as the model not supporting it.

Common Comparisons

llama-3.3-70b-instruct vs llama-4-maverickllama-3.3-70b-instruct vs llama-4-scoutllama-3.3-70b-instruct vs llama2-70b-4096llama-3.3-70b-instruct vs qwen3.8-max-previewkimi-k3 vs llama-3.3-70b-instruct

Llama on AIHubMix

Which Llama model should I start with?

llama-4-maverick at $0.2/M input — the cheapest entry here that declares tool calling, and it carries a 1.05M context. Move up to aihubmix-Llama-3-1-405B-Instruct when answer quality matters more than cost.

Why are there several entries for the same model?

Because each row is a route you can call, not a model release. Some IDs name an upstream (azure-, alicloud-, cc-), some are the open-weight repository form (meta-llama/…), and some differ only in capitalisation, kept so older integrations keep working.

The catalog does not carry a field saying which of those a given row is, so this page does not sort them into buckets it would have to invent. Every row shows that route’s own price, context and speed — compare those directly, and open a model to see the upstreams that serve it.

Do I need a separate Llama account?

No. One AIHubMix key covers every model on this page, and switching between them is a change to the model string — billing, rate limits, and logs stay in one place.

Other Model Authors

See all model authors →
Qwen
149 modelsOpenAI
142 modelsGoogle
87 modelsZ.AI
71 modelsByteDance
48 models

Start calling Llama in one line

One key, one endpoint, 912 models across 42 model authors.

Get API keyRead the docs

© 2023 - 2026 AIHubMix, LLC

Product

Developer

Connect

Terms & Policies