Llama Models

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

Usage

Last 30 days · 2026-10-02 to 2026-10-31

Tokens

2.3B

Requests

190K

Models in use

53 of 53

Tokens per day, stacked by model

0228M456M10-0210-0910-1610-2310-302026-10-02 — 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: 340 deepinfra-llama-3.1-8b-instant: 200 llama-3.3-70b: 190 deepinfra-llama-4-maverick-17b-128e-instruct: 155 deepinfra-llama-3.3-70b-instant-turbo: 1352026-10-06 — 34,824,320 tokens llama-4-maverick: 20,249,505 llama-3.3-70b-instruct: 14,514,320 llama-4-scout: 60,4952026-10-07 — 14,334,785 tokens llama-4-maverick: 14,309,765 llama-4-scout: 24,920 llama-3.3-70b-instruct: 1002026-10-08 — 7,951,030 tokens llama-4-maverick: 7,815,270 llama-4-scout: 132,895 llama-3.3-70b-instruct: 2,8652026-10-09 — 28,694,165 tokens llama-4-maverick: 20,902,065 llama-3.3-70b-instruct: 7,709,710 llama-4-scout: 82,3902026-10-10 — 21,400,915 tokens llama-3.3-70b-instruct: 14,483,960 llama-4-scout: 6,654,535 llama-4-maverick: 262,4202026-10-11 — 39,184,075 tokens llama-4-maverick: 23,973,010 llama-3.3-70b-instruct: 15,184,875 llama-4-scout: 25,790 2 more models: 245 deepinfra-llama-4-maverick-17b-128e-instruct: 1552026-10-12 — 23,984,025 tokens llama-4-scout: 15,980,375 llama-3.3-70b-instruct: 8,002,675 llama-4-maverick: 9752026-10-13 — 65,339,070 tokens llama-4-scout: 40,741,305 llama-4-maverick: 23,686,340 deepinfra-llama-3.1-8b-instant: 911,4252026-10-14 — 40,364,160 tokens llama-4-scout: 39,967,005 llama-3.3-70b-instruct: 361,735 llama-3.3-70b: 29,735 llama-4-maverick: 5,6852026-10-15 — 22,266,090 tokens deepinfra-llama-3.3-70b-instant-turbo: 12,534,115 llama-4-maverick: 6,805,995 deepinfra-llama-4-maverick-17b-128e-instruct: 1,864,965 llama-3.3-70b-instruct: 1,000,730 llama-4-scout: 60,2852026-10-16 — 69,808,975 tokens llama-4-scout: 30,499,700 llama-4-maverick: 24,366,860 llama-3.3-70b-instruct: 14,941,435 deepinfra-llama-3.3-70b-instant-turbo: 710 deepinfra-llama-4-maverick-17b-128e-instruct: 100 deepinfra-llama-3.1-8b-instant: 85 2 more models: 852026-10-17 — 2,050,725 tokens llama-4-scout: 2,046,795 deepinfra-llama-3.1-8b-instant: 2,110 llama-4-maverick: 1,8202026-10-18 — 11,122,510 tokens llama-3.3-70b: 9,544,545 deepinfra-llama-3.1-8b-instant: 998,850 llama-4-maverick: 571,170 deepinfra-llama-4-maverick-17b-128e-instruct: 7,565 llama-4-scout: 3802026-10-19 — 12,934,970 tokens llama-4-maverick: 11,255,630 llama-4-scout: 1,551,380 deepinfra-llama-3.1-8b-instant: 125,490 2 more models: 615 llama3.1-8b: 565 deepinfra-llama-4-maverick-17b-128e-instruct: 360 llama-3.3-70b: 315 deepinfra-llama-3.3-70b-instant-turbo: 315 llama-3.3-70b-instruct: 3002026-10-20 — 70,292,845 tokens llama-4-maverick: 30,482,590 deepinfra-llama-3.1-8b-instant: 29,355,665 llama-4-scout: 10,425,330 llama-3.3-70b: 27,620 2 more models: 540 deepinfra-llama-4-maverick-17b-128e-instruct: 340 deepinfra-llama-3.3-70b-instant-turbo: 265 llama3.1-8b: 250 llama-3.3-70b-instruct: 2452026-10-21 — 251,878,805 tokens llama-4-maverick: 234,170,590 llama-3.3-70b-instruct: 15,342,895 llama-4-scout: 2,364,755 deepinfra-llama-4-maverick-17b-128e-instruct: 105 deepinfra-llama-3.1-8b-instant: 95 llama3.1-8b: 95 llama-3.3-70b: 90 deepinfra-llama-3.3-70b-instant-turbo: 90 2 more models: 902026-10-22 — 281,081,260 tokens llama-3.3-70b: 167,810,285 llama-4-maverick: 113,266,480 2 more models: 1,475 deepinfra-llama-4-maverick-17b-128e-instruct: 690 deepinfra-llama-3.1-8b-instant: 650 deepinfra-llama-3.3-70b-instant-turbo: 650 llama3.1-8b: 650 llama-4-scout: 3802026-10-23 — 456,206,545 tokens llama-3.3-70b: 445,062,835 llama-4-maverick: 11,138,565 llama-4-scout: 2,110 2 more models: 820 deepinfra-llama-3.1-8b-instant: 480 deepinfra-llama-3.3-70b-instant-turbo: 465 llama-3.3-70b-instruct: 450 llama3.1-8b: 410 deepinfra-llama-4-maverick-17b-128e-instruct: 4102026-10-24 — 256,943,380 tokens llama-3.3-70b: 249,519,680 llama-4-maverick: 6,786,035 llama-3.3-70b-instruct: 637,175 llama-4-scout: 380 2 more models: 1102026-10-25 — 51,585,580 tokens llama-3.3-70b-instruct: 23,444,025 llama-4-maverick: 20,069,950 deepinfra-llama-3.3-70b-instant-turbo: 8,067,280 2 more models: 1,055 deepinfra-llama-4-maverick-17b-128e-instruct: 690 llama-3.3-70b: 650 deepinfra-llama-3.1-8b-instant: 650 llama3.1-8b: 650 llama-4-scout: 6302026-10-26 — 62,182,875 tokens llama-4-maverick: 61,783,925 llama-4-scout: 396,220 2 more models: 750 llama-3.3-70b-instruct: 670 deepinfra-llama-4-maverick-17b-128e-instruct: 290 llama-3.3-70b: 255 deepinfra-llama-3.1-8b-instant: 255 deepinfra-llama-3.3-70b-instant-turbo: 255 llama3.1-8b: 2552026-10-27 — 47,707,015 tokens llama-4-maverick: 45,869,900 llama-4-scout: 1,333,605 llama3.1-8b: 354,770 2 more models: 65,045 deepinfra-llama-3.1-8b-instant: 29,980 deepinfra-llama-3.3-70b-instant-turbo: 29,980 llama-3.3-70b: 14,795 deepinfra-llama-4-maverick-17b-128e-instruct: 8,290 llama-3.3-70b-instruct: 6502026-10-28 — 24,989,645 tokens llama-4-maverick: 12,811,135 llama-3.3-70b-instruct: 12,109,735 llama-4-scout: 66,920 2 more models: 545 llama-3.3-70b: 350 deepinfra-llama-3.3-70b-instant-turbo: 270 deepinfra-llama-3.1-8b-instant: 240 deepinfra-llama-4-maverick-17b-128e-instruct: 240 llama3.1-8b: 2102026-10-29 — 12,921,690 tokens llama-3.3-70b-instruct: 8,395,285 llama-4-maverick: 4,174,175 2 more models: 218,710 llama-4-scout: 133,300 deepinfra-llama-3.1-8b-instant: 2202026-10-30 — 22,058,000 tokens llama-3.3-70b-instruct: 11,555,260 llama-4-maverick: 5,953,225 deepinfra-llama-3.1-8b-instant: 4,480,935 llama-4-scout: 67,135 2 more models: 575 llama3.1-8b: 400 deepinfra-llama-3.3-70b-instant-turbo: 190 deepinfra-llama-4-maverick-17b-128e-instruct: 155 llama-3.3-70b: 1252026-10-31 — 45,374,380 tokens deepinfra-llama-3.1-8b-instant: 20,332,065 llama-3.3-70b-instruct: 20,200,975 llama-4-maverick: 4,706,680 llama-4-scout: 134,660
  • llama-3.3-70b
  • llama-4-maverick
  • llama-3.3-70b-instruct
  • llama-4-scout
  • deepinfra-llama-3.1-8b-instant
  • deepinfra-llama-3.3-70b-instant-turbo
  • llama3.1-8b
  • deepinfra-llama-4-maverick-17b-128e-instruct
  • 2 more models

Which models that traffic went to

  1. Llama 3.3 70B38.0%872M
  2. Llama 4 Maverick31.9%733M
  3. Llama 3.3 70B Instruct17.0%389M
  4. Llama 4 Scout9.6%220M
  5. Deepinfra Llama 3.1 8B Instant2.4%56.2M
  6. Deepinfra Llama 3.3 70B Instant Turbo0.9%20.6M
  7. Llama3.1 8B0.1%3.1M
  8. Deepinfra Llama 4 Maverick 17B 128e Instruct0.1%1.9M
  9. 2 more models<0.1%291K

Share of 2.3B tokens. 43 models with traffic report no token counts and cannot be ranked here, including llama-3.1-8b-instant 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/s0.41 s
llama-3.3-70b-instructTakes text, returns text.131K—$0.6$1.2/M——
llama-3.3-70bTakes , returns text.66K8K$0.6$0.6/M3250 tok/s0.25 s
llama3-groq-8b-8192-tool-use-previewTakes , returns text.——$0.00019$0.00019/M——
llama3-groq-70b-8192-tool-use-previewTakes , returns text.——$0.00089$0.00089/M——
meta-llama/llama-3.1-405b-instruct:freeTakes , returns text.——$0.02$0.02/M——
meta-llama/llama-3.1-70b-instruct:freeTakes , returns text.——$0.02$0.02/M——
meta-llama/llama-3.1-8b-instruct:freeTakes , returns text.——$0.02$0.02/M——
meta-llama/llama-3.2-11b-vision-instruct:freeTakes , returns text.——$0.02$0.02/M——
meta-llama/llama-3.2-3b-instruct:freeTakes , returns text.——$0.02$0.02/M——
deepinfra-llama-3.1-8b-instantTakes , returns text.——$0.033$0.055/M5 tok/s0.47 s
groq-llama-3.1-8b-instantTakes , returns text.——$0.055$0.088/M——
llama3-8b-8192Takes , returns text.——$0.06$0.12/M——
deepinfra-llama-4-scout-17b-16e-instructTakes , returns text.——$0.088$0.33/M6 tok/s0.41 s
llama2-7b-2048Takes , returns text.——$0.1$0.1/M——
deepinfra-llama-3.3-70b-instant-turboTakes , returns text.——$0.11$0.352/M4 tok/s0.59 s
groq-llama-4-scout-17b-16e-instructTakes , returns text.——$0.122$0.366/M——
deepseek-r1-distill-qianfan-llama-8bTakes , returns text.——$0.137$0.548/M——
llama-3.2-11b-vision-previewTakes , returns text.——$0.2$0.2/M——
llama-3.2-1b-previewTakes , returns text.——$0.2$0.2/M——
llama-3.2-3b-previewTakes , returns text.——$0.2$0.2/M——
groq-llama-4-maverick-17b-128e-instructTakes , returns text.——$0.22$0.66/M——
qianfan-llama-vl-8bTakes , returns text.——$0.274$0.685/M——
aihubmix-Llama-3-1-8B-InstructTakes , returns text.——$0.3$0.6/M——
llama-3.1-8b-instantTakes , returns text.——$0.3$0.6/M——
llama3-8b-8192(33)Takes , returns text.——$0.3$0.3/M——
llama3.1-8bTakes , returns text.——$0.3$0.6/M5 tok/s0.47 s
meta/llama3-8B-chatTakes , returns text.——$0.3$0.3/M——
deepinfra-llama-4-maverick-17b-128e-instructTakes , returns text.——$0.33$1.32/M18 tok/s0.49 s
aihubmix-Llama-3-2-11B-VisionTakes , returns text.——$0.4$0.4/M——
Gryphe/MythoMax-L2-13bTakes , returns text.——$0.4$0.4/M——
llama-3.1-70bTakes , returns text.——$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-InstructTakes , returns text.——$0.5$0.5/M——
meta-llama-3-8bTakes , returns text.——$0.548$0.548/M——
aihubmix-Llama-3-1-70B-InstructTakes , returns text.——$0.6$0.78/M——
cerebras-llama-3.3-70bTakes , returns text.——$0.6$0.6/M——
llama-3.1-70b-versatileTakes , returns text.——$0.6$0.6/M——
groq-llama-3.3-70b-versatileTakes , returns text.——$0.649$0.869/M——
aihubmix-Llama-3-70B-InstructTakes , returns text.——$0.7$0.7/M——
llama3-70b-8192Takes , returns text.——$0.7$0.9373/M——
qianfan-chinese-llama-2-13bTakes , returns text.——$0.822$0.822/M——
WizardLM/WizardCoder-Python-34B-V1.0Takes , returns text.——$0.9$0.9/M——
aihubmix-Llama-3-2-90B-VisionTakes , returns text.——$2.4$2.4/M——
llama-3.2-90b-vision-previewTakes , returns text.——$2.4$2.4/M——
llama3-70b-8192(33)Takes , returns text.——$2.65$2.65/M——
llama-3.1-405b-instructTakes , returns text.——$4$4/M——
llama-3.1-405b-reasoningTakes , returns text.——$4$4/M——
meta-llama-3-70bTakes , returns text.——$4.795$4.795/M——
aihubmix-Llama-3-1-405B-InstructTakes , returns text.——$5$15/M——
meta/llama-3.1-405b-instructTakes , returns text.——$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

Gryphe/MythoMax-L2-13b vs WizardLM/WizardCoder-Python-34B-V1.0Gryphe/MythoMax-L2-13b vs aihubmix-Llama-3-1-405B-InstructGryphe/MythoMax-L2-13b vs aihubmix-Llama-3-1-70B-InstructGryphe/MythoMax-L2-13b vs qwen3.8-max-previewGryphe/MythoMax-L2-13b vs kimi-k3

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
154 modelsOpenAI
144 modelsGoogle
90 modelsZ.AI
72 modelsByteDance
47 models

Start calling Llama in one line

One key, one endpoint, 941 models across 46 model authors.

Get API keyRead the docs

© 2023 - 2026 AIHubMix, LLC

Product

Developer

Company

Terms & Policies