AIHubMixAIHubMix

Llama Models

52 modelsGeneral models from $0.20/M inputUp to 1.05M context

Usage

Last 30 days · 2026-07-22 to 2026-08-20

Tokens

3.8B

Requests

263K

Models in use

22 of 52

Tokens per day, stacked by model

0368M736M07-2207-2908-0508-1208-192026-07-22 — 22,687,225 tokens llama-4-scout: 17,442,800 llama-4-maverick: 5,244,4252026-07-23 — 538,646,785 tokens llama-3.3-70b: 482,613,375 llama-4-scout: 38,709,675 deepinfra-llama-3.3-70b-instant-turbo: 11,513,945 llama-4-maverick: 5,809,7902026-07-24 — 660,609,890 tokens llama-3.3-70b: 506,860,205 llama3.1-8b: 89,316,565 llama-3.1-70b: 45,727,970 llama-4-scout: 18,248,425 llama-4-maverick: 391,115 deepinfra-llama-3.3-70b-instant-turbo: 65,6102026-07-25 — 83,448,230 tokens llama-3.3-70b: 83,157,070 llama-4-maverick: 260,965 llama-4-scout: 30,1952026-07-26 — 242,035,100 tokens llama-3.3-70b: 188,099,780 llama-4-scout: 53,933,425 llama-4-maverick: 1,8952026-07-27 — 460,952,540 tokens llama-3.3-70b: 408,449,930 llama-4-scout: 41,321,765 llama-4-maverick: 11,180,8452026-07-28 — 116,410,250 tokens llama-4-scout: 90,003,720 llama-4-maverick: 26,179,650 llama-3.3-70b: 224,890 5 more models: 985 groq-llama-3.3-70b-versatile: 300 llama3.1-8b: 190 deepinfra-llama-3.1-8b-instant: 190 deepinfra-llama-3.3-70b-instant-turbo: 190 llama-3.1-70b: 1352026-07-29 — 2,297,060 tokens llama-4-maverick: 2,160,085 5 more models: 121,475 llama-4-scout: 15,5002026-07-30 — 5,155 tokens llama-4-maverick: 2,930 5 more models: 980 groq-llama-3.3-70b-versatile: 300 llama3.1-8b: 225 deepinfra-llama-3.1-8b-instant: 190 llama-4-scout: 135 llama-3.1-70b: 135 deepinfra-llama-3.3-70b-instant-turbo: 135 llama-3.3-70b: 1252026-07-31 — 123,854,515 tokens llama-4-maverick: 123,854,100 5 more models: 290 llama-4-scout: 1252026-08-01 — 2,264,410 tokens llama-4-maverick: 2,249,100 llama-4-scout: 15,240 5 more models: 702026-08-02 — 12,233,855 tokens llama-4-maverick: 11,974,810 llama-4-scout: 259,0452026-08-03 — 20,380 tokens llama-4-maverick: 16,300 llama-4-scout: 3,895 llama3.1-8b: 115 5 more models: 702026-08-04 — 16,735 tokens llama-4-scout: 16,595 llama-4-maverick: 70 5 more models: 702026-08-05 — 72,780 tokens llama-4-maverick: 37,325 llama-4-scout: 35,385 5 more models: 702026-08-06 — 57,706,600 tokens deepinfra-llama-3.1-8b-instant: 57,678,060 llama-4-maverick: 22,795 llama-4-scout: 5,570 llama-3.3-70b: 105 5 more models: 702026-08-07 — 3,574,285 tokens llama-4-scout: 3,516,590 deepinfra-llama-3.1-8b-instant: 40,765 5 more models: 5,775 llama-3.1-70b: 5,195 llama-3.3-70b: 5,175 groq-llama-3.3-70b-versatile: 300 llama3.1-8b: 225 deepinfra-llama-3.3-70b-instant-turbo: 190 llama-4-maverick: 702026-08-08 — 197,236,570 tokens llama-3.1-70b: 195,200,420 llama-4-scout: 2,030,335 llama-4-maverick: 5,745 5 more models: 702026-08-09 — 736,064,095 tokens llama-4-maverick: 736,036,010 llama-4-scout: 28,015 5 more models: 702026-08-10 — 524,070,090 tokens llama-4-maverick: 523,920,695 llama-4-scout: 132,535 5 more models: 5,665 llama-3.1-70b: 5,285 llama-3.3-70b: 5,075 groq-llama-3.3-70b-versatile: 300 deepinfra-llama-3.3-70b-instant-turbo: 210 llama3.1-8b: 190 deepinfra-llama-3.1-8b-instant: 1352026-08-11 — 1,530,430 tokens groq-llama-3.3-70b-versatile: 1,516,465 llama-4-maverick: 8,020 llama-4-scout: 5,875 5 more models: 702026-08-12 — 496,225 tokens llama-4-scout: 495,880 llama-4-maverick: 275 5 more models: 702026-08-13 — 140 tokens llama-4-maverick: 70 5 more models: 702026-08-14 — 445 tokens llama-4-scout: 210 llama-4-maverick: 165 5 more models: 702026-08-15 — 1,865,825 tokens llama-3.1-70b: 1,037,115 llama-4-maverick: 385,325 5 more models: 316,075 llama-4-scout: 126,325 groq-llama-3.3-70b-versatile: 235 deepinfra-llama-3.3-70b-instant-turbo: 225 llama-3.3-70b: 200 llama3.1-8b: 190 deepinfra-llama-3.1-8b-instant: 1352026-08-16 — 545,425 tokens llama-3.1-70b: 531,420 llama-4-scout: 14,0052026-08-17 — 46,345 tokens llama-4-maverick: 46,260 llama-4-scout: 852026-08-18 — 216,615 tokens llama-4-maverick: 202,925 llama-4-scout: 13,6902026-08-19 — 39,160 tokens llama-4-scout: 38,830 llama-4-maverick: 3302026-08-20 — 63,550 tokens llama-4-scout: 62,945 llama-4-maverick: 370 5 more models: 235
  • llama-3.3-70b
  • llama-4-maverick
  • llama-4-scout
  • llama-3.1-70b
  • llama3.1-8b
  • deepinfra-llama-3.1-8b-instant
  • deepinfra-llama-3.3-70b-instant-turbo
  • groq-llama-3.3-70b-versatile
  • 5 more models

Which models that traffic went to

  1. Llama 3.3 70B44.1%1.7B
  2. Llama 4 Maverick38.3%1.4B
  3. Llama 4 Scout7.0%267M
  4. Llama 3.1 70B6.4%243M
  5. Llama3.1 8B2.4%89.3M
  6. Deepinfra Llama 3.1 8B Instant1.5%57.7M
  7. Deepinfra Llama 3.3 70B Instant Turbo0.3%11.6M
  8. Groq Llama 3.3 70B Versatile<0.1%1.5M
  9. 5 more models<0.1%452K

Share of 3.8B tokens. 9 models with traffic report no token counts and cannot be ranked here, including deepseek-r1-distill-qianfan-llama-8b and meta-llama-3-70b — 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 52 model IDs listed on this page; traffic routed through upstream-specific IDs that are not in the public catalog is not included.

All 52 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$0.20$0.20/M98 tok/s0.23 s
llama-4-scoutTakes text, vision, returns text.131K—$0.20$0.20/M2637 tok/s0.29 s
llama-3.3-70b66K8K$0.60$0.60/M3250 tok/s0.25 s
llama3-groq-8b-8192-tool-use-preview——$0.0002$0.0002/M——
llama3-groq-70b-8192-tool-use-preview——$0.0009$0.0009/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——$0.03$0.05/M——
groq-llama-3.1-8b-instant——$0.06$0.09/M——
llama3-8b-8192——$0.06$0.12/M——
deepinfra-llama-4-scout-17b-16e-instruct——$0.09$0.33/M——
llama2-7b-2048——$0.10$0.10/M——
deepinfra-llama-3.3-70b-instant-turbo——$0.11$0.35/M——
groq-llama-4-scout-17b-16e-instruct——$0.12$0.37/M——
deepseek-r1-distill-qianfan-llama-8b——$0.14$0.55/M——
llama-3.2-11b-vision-preview——$0.20$0.20/M——
llama-3.2-1b-preview——$0.20$0.20/M——
llama-3.2-3b-preview——$0.20$0.20/M——
groq-llama-4-maverick-17b-128e-instruct——$0.22$0.66/M——
qianfan-llama-vl-8b——$0.27$0.69/M——
aihubmix-Llama-3-1-8B-Instruct——$0.30$0.60/M——
llama-3.1-8b-instant——$0.30$0.60/M——
llama3-8b-8192(33)——$0.30$0.30/M——
llama3.1-8b——$0.30$0.60/M107 tok/s0.17 s
meta/llama3-8B-chat——$0.30$0.30/M——
deepinfra-llama-4-maverick-17b-128e-instruct——$0.33$1.32/M——
aihubmix-Llama-3-2-11B-Vision——$0.40$0.40/M——
Gryphe/MythoMax-L2-13b——$0.40$0.40/M——
llama-3.1-70b——$0.44$0.44/M12 tok/s0.30 s
llama2-70b-4096Takes , returns text.——$0.50$0.50/M——
llama2-70b-40960Takes , returns text.——$0.50$0.50/M——
meta-llama/Llama-3.2-90B-Vision-Instruct——$0.50$0.50/M——
meta-llama-3-8b——$0.55$0.55/M——
aihubmix-Llama-3-1-70B-Instruct——$0.60$0.78/M——
cerebras-llama-3.3-70b——$0.60$0.60/M——
llama-3.1-70b-versatile——$0.60$0.60/M——
groq-llama-3.3-70b-versatile——$0.65$0.87/M——
aihubmix-Llama-3-70B-Instruct——$0.70$0.70/M——
llama3-70b-8192——$0.70$0.94/M——
qianfan-chinese-llama-2-13b——$0.82$0.82/M——
WizardLM/WizardCoder-Python-34B-V1.0——$0.90$0.90/M——
aihubmix-Llama-3-2-90B-Vision——$2.40$2.40/M——
llama-3.2-90b-vision-preview——$2.40$2.40/M——
llama3-70b-8192(33)——$2.65$2.65/M——
llama-3.1-405b-instruct——$4.00$4.00/M——
llama-3.1-405b-reasoning——$4.00$4.00/M——
meta-llama-3-70b——$4.79$4.79/M——
aihubmix-Llama-3-1-405B-Instruct——$5.00$15.00/M——
meta/llama-3.1-405b-instruct——$5.00$5.00/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-4-maverick vs llama-4-scoutllama-4-maverick vs llama2-70b-4096llama-4-maverick vs llama2-70b-40960llama-4-maverick vs qwen3.8-max-previewkimi-k3 vs llama-4-maverick

Llama on AIHubMix

Which Llama model should I start with?

llama-4-maverick at $0.20/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
141 modelsOpenAI
133 modelsGoogle
83 modelsZ.AI
66 modelsByteDance
46 models

Start calling Llama in one line

One key, one endpoint, 859 models across 37 model authors.

Get API keyRead the docs
AIHubMix

© 2023 - 2026 AIHubMix, LLC

Product

Company

Developer

Connect