BroadRouter

Presyo ng LLM API ayon sa model

Na-update

Presyo ng 428 na model mula sa 41 na provider, 1,671 na presyo lahat, bawat isa binasa sa sariling pricing page ng provider, may source link at petsa (pinakabago: Nobyembre 15, 2026). Nasa bawat page ng model ang input, cached input at output price ng bawat provider, ang sariling presyo ng gumawa, mga service tier at ang buwanang gastos ng tatlong totoong workload.

Naka-presyo ang LLM API kada milyong token, na may hiwalay na presyo para sa input, cached input at output. Para sa mga open-weight model gaya ng DeepSeek, Qwen, GLM, Kimi at Llama, maraming provider ang nagse-serve ng parehong weights sa presyong malaki ang pagkakaiba. May presyo sa sariling API ng gumawa ang 160 sa 428 na model. Nasa table sa ibaba ang 198 na model na may standard na presyo mula sa 2 o higit pang provider. Iisa lang ang provider ng natitirang 230; nasa maikling listahan ng mga model na iisa ang provider (Ingles) sila, at hindi isinasama sa search results ang mga page nila hanggang may pangalawang provider na maglista sa kanila.

Hinahanap ang pinakamababang presyo? Ang pinakamurang LLM API ngayon: nira-rank ang mga model sa iisang blended na presyo, sa kabuuan at ayon sa laki. Log ng pagbabago ng presyo (Ingles): bawat presyong gumalaw sa pagitan ng mga pagsuri namin. Presyo ayon sa provider (Ingles): ang buong price list at mga tier ng bawat provider; sa presyo ayon sa gumawa ng model, naka-grupo ang mga model ayon sa kompanyang gumawa sa kanila. Mga open-weight model ayon sa use case (Ingles): inaayos ang mga model ayon sa nailathalang benchmark score, iisang source at setting kada table, katabi ng mga presyong ito.

Presyo ng LLM API kada 1M token, ayon sa model
ModelGumawaMga providerPinakamurang inputPinakamurang outputPinakamurang blended 3:1Median in / outPresyo ng gumawa in / outMax context
Qwen · 35 na model
Qwen 2.5 7B (Ingles)Qwen3US$0.05US$0.05US$0.05US$0.05 / US$0.13—32,768
Qwen3-8B (Ingles)Qwen2US$0.06US$0.06US$0.06US$0.0885 / US$0.2575—131,072
Qwen3.5 9B (Ingles)Qwen4US$0.10US$0.15US$0.1125US$0.135 / US$0.20—262,144
Qwen3 30B A3B (fp8) (Ingles)Qwen3US$0.051US$0.25US$0.122US$0.08 / US$0.335—40,960
Qwen3 Coder 30B A3B (Ingles)Qwen3US$0.07US$0.28US$0.1225US$0.125 / US$0.45—262,144
Qwen3-14B (Ingles)Qwen3US$0.07US$0.24US$0.1225US$0.12 / US$0.24—131,072
Qwen3 32B FP8 (Ingles)Qwen5US$0.08US$0.28US$0.13US$0.102 / US$0.57—131,072
Qwen3-30B-A3B-Instruct-2507 (Ingles)Qwen2US$0.09US$0.30US$0.1425US$0.1075 / US$0.375—262,144
Qwen3 235B A22B Instruct 2507 FP8 (Ingles)Qwen5US$0.0875US$0.35US$0.1531US$0.14 / US$0.75—262,144
Qwen3.8 Flash (Ingles)Qwen5US$0.113US$0.382US$0.1803US$0.15 / US$0.47US$0.15 / US$0.471,048,575
Qwen3 VL 30B A3B Instruct (Ingles)Qwen4US$0.15US$0.50US$0.2375US$0.175 / US$0.65—262,144
Qwen3 Coder Next (Ingles)Qwen3US$0.12US$0.80US$0.29US$0.16 / US$1.15—32,768
Qwen3.6 35B A3BQwen10US$0.10US$0.89US$0.2975US$0.168 / US$1.0569US$0.375 / US$2.25262,144
Qwen3-VL 8B (Ingles)Qwen2US$0.18US$0.68US$0.305US$0.215 / US$0.715—262,144
Qwen3.8 27B · nasa BroadNet Inference dinQwen15US$0.039US$1.25US$0.3417US$0.40 / US$3US$0.50 / US$31,000,000
Qwen3 Next 80B A3B Instruct (Ingles)Qwen5US$0.09US$1.10US$0.3425US$0.125 / US$1.15—262,144
Qwen3.5 35B A3BQwen7US$0.14US$1US$0.355US$0.24 / US$1.80US$0.25 / US$2262,144
Qwen2.5-72B-Instruct (Ingles)Qwen3US$0.36US$0.40US$0.37US$0.37 / US$0.40—32,768
Qwen3 VL 235B A22B (Ingles)Qwen3US$0.20US$0.88US$0.37US$0.21 / US$1.90—262,144
Qwen-MT Plus (Ingles)Qwen2US$0.25US$0.75US$0.375US$1.355 / US$4.06US$2.46 / US$7.3716,384
Qwen3 235B A22B FP8 (Ingles)Qwen2US$0.17US$1.09US$0.40US$0.3125 / US$1.455—32,768
Qwen3 Next 80B A3B Thinking (Ingles)Qwen2US$0.15US$1.20US$0.4125US$0.15 / US$1.35—262,144
Qwen3 Coder 480B A35BQwen6US$0.22US$1US$0.4375US$0.325 / US$1.525—262,144
Qwen3.7 Plus (Ingles)Qwen2US$0.32US$1.28US$0.56US$0.36 / US$1.44US$0.40 / US$1.60—
Qwen3.5 27BQwen7US$0.20US$1.75US$0.5875US$0.30 / US$2.40US$0.30 / US$2.40262,144
Qwen3.6 27BQwen7US$0.25US$2US$0.6875US$0.32 / US$3.20US$0.60 / US$3.60262,144
Qwen3.5 122B A10B (Ingles)Qwen4US$0.26US$2.08US$0.715US$0.40 / US$3.20US$0.40 / US$3.20262,144
Qwen2.5 Coder 32B Instruct (Ingles)Qwen2US$0.66US$1US$0.745US$0.67 / US$1.10—32,768
Qwen3.5 397B A17BQwen7US$0.45US$3US$1.087US$0.55 / US$3.60US$0.60 / US$3.60262,144
Qwen3.6 Plus (Ingles)Qwen3US$0.50US$3US$1.125US$0.50 / US$3US$0.50 / US$3262,144
Qwen3 235B A22B Thinking 2507 FP8 (Ingles)Qwen3US$0.35US$3.50US$1.212US$0.45 / US$3.50—131,072
Qwen3.8 2.4T A95BQwen6US$1US$4US$1.75US$2 / US$6US$2 / US$61,048,576
Qwen3.7 Max (Ingles)Qwen5US$1.25US$3.75US$1.875US$2.50 / US$7.50US$2.50 / US$7.501,000,000
Qwen3.8 MaxQwen6US$1.65US$4.951US$2.475US$2 / US$6US$2 / US$61,000,000
Qwen3.8 Max (0902) (Ingles)Qwen3US$1.65US$4.951US$2.475US$2 / US$6US$2 / US$61,000,000
OpenAI · 30 na model
GPT OSS 20BOpenAI10US$0.018US$0.09US$0.036US$0.04 / US$0.19—131,072
OpenAI GPT OSS 120BOpenAI21US$0.03US$0.17US$0.065US$0.10 / US$0.60—131,072
GPT OSS Safeguard 20B (Ingles)OpenAI3US$0.07US$0.20US$0.1025US$0.075 / US$0.30—131,072
GPT-5 Nano (Ingles)OpenAI3US$0.05US$0.40US$0.1375US$0.05 / US$0.40US$0.05 / US$0.40—
GPT-6 LunaOpenAI6US$0.10US$0.50US$0.20US$0.10 / US$0.50US$0.10 / US$0.501,050,000
GPT-4o mini (Ingles)OpenAI3US$0.15US$0.60US$0.2625US$0.15 / US$0.60US$0.15 / US$0.60—
GPT-5.6 LunaOpenAI6US$0.20US$1.20US$0.45US$0.20 / US$1.20US$0.20 / US$1.201,050,000
GPT-5.4 Nano (Ingles)OpenAI3US$0.20US$1.25US$0.4625US$0.20 / US$1.25US$0.20 / US$1.25—
GPT-5 Mini (Ingles)OpenAI3US$0.25US$2US$0.6875US$0.25 / US$2US$0.25 / US$2—
GPT-4.1 Mini (Ingles)OpenAI2US$0.40US$1.60US$0.70US$0.40 / US$1.60US$0.40 / US$1.60—
GPT-5.4 Mini (Ingles)OpenAI3US$0.75US$4.50US$1.688US$0.75 / US$4.50US$0.75 / US$4.50—
GPT-6.1 Terra (Ingles)OpenAI4US$1US$5US$2US$1 / US$5US$1 / US$51,050,000
GPT-5 (2025-08-07) (Ingles)OpenAI3US$1.25US$10US$3.438US$1.25 / US$10US$1.25 / US$10—
GPT-5.1 (Ingles)OpenAI2US$1.25US$10US$3.438US$1.25 / US$10US$1.25 / US$10—
GPT-4.1 (2025-04-14) (Ingles)OpenAI3US$2US$8US$3.50US$2 / US$8US$2 / US$8—
o3 (2025-04-16) (Ingles)OpenAI3US$2US$8US$3.50US$2 / US$8US$2 / US$8—
GPT-6 SolOpenAI6US$2US$10US$4US$2 / US$10US$2 / US$101,050,000
GPT-6.1 SolOpenAI6US$2US$10US$4US$2 / US$10US$2 / US$101,050,000
GPT-4o (Ingles)OpenAI2US$2.50US$10US$4.375US$2.50 / US$10US$2.50 / US$10—
GPT-5.6 TerraOpenAI6US$2US$12US$4.50US$2 / US$12US$2 / US$121,050,000
GPT-5.2 (Ingles)OpenAI3US$1.75US$14US$4.813US$1.75 / US$14US$1.75 / US$14—
GPT-5.3 Codex (Ingles)OpenAI3US$1.75US$14US$4.813US$1.75 / US$14US$1.75 / US$14—
GPT-5.4 (Ingles)OpenAI4US$2.50US$15US$5.625US$2.50 / US$15US$2.50 / US$151,050,000
GPT-5.6 SolOpenAI6US$4US$20US$8US$4 / US$20US$4 / US$201,050,000
GPT Chat Latest (Ingles)OpenAI2US$5US$30US$11.25US$5 / US$30US$5 / US$30—
GPT-5.5OpenAI6US$5US$30US$11.25US$5 / US$30US$5 / US$301,050,000
GPT-6 AstraOpenAI6US$10US$50US$20US$10 / US$50US$10 / US$501,050,000
GPT-5 Pro (Ingles)OpenAI2US$15US$120US$41.25US$15 / US$120US$15 / US$120—
GPT-5.2 Pro (Ingles)OpenAI2US$21US$168US$57.75US$21 / US$168US$21 / US$168—
GPT-5.4 Pro (Ingles)OpenAI3US$30US$180US$67.50US$30 / US$180US$30 / US$180—
DeepSeek · 20 na model
DeepSeek V4 Flash 0731DeepSeek15US$0.06US$0.18US$0.09US$0.22 / US$0.66—1,048,576
DeepSeek V4 FlashDeepSeek8US$0.09US$0.18US$0.1125US$0.139 / US$0.28—1,048,576
DeepSeek R1 Distill Qwen 7B (Ingles)DeepSeek2US$0.10US$0.20US$0.125US$0.39 / US$0.50—131,072
DeepSeek V4.1 Flash 1017DeepSeek16US$0.098US$0.294US$0.147US$0.30 / US$1.20US$0.30 / US$1.201,048,576
DeepSeek R1 Distill Qwen 14B (Ingles)DeepSeek2US$0.20US$0.20US$0.20US$0.3155 / US$0.66—131,072
DeepSeek R1 Distill Llama 8B (Ingles)DeepSeek2US$0.14US$0.32US$0.2025US$0.17 / US$0.355—131,072
DeepSeek V4.1 Flash · nasa BroadNet Inference dinDeepSeek16US$0.13US$0.42US$0.21US$0.30 / US$1.20US$0.30 / US$1.201,048,576
DeepSeek V3.2DeepSeek11US$0.2088US$0.3096US$0.234US$0.33 / US$0.48—163,840
DeepSeek-V3.2-Exp (Ingles)DeepSeek2US$0.27US$0.41US$0.305US$0.27 / US$0.41—163,840
DeepSeek-V4-Flash-Vision-Exp (Ingles)DeepSeek3US$0.2156US$0.6468US$0.3234US$0.44 / US$1.32—1,048,576
DeepSeek R1 Distill Llama 70B (Ingles)DeepSeek2US$0.25US$0.75US$0.375US$1.425 / US$1.875—131,072
DeepSeek V3.1DeepSeek7US$0.25US$0.95US$0.425US$0.285 / US$1—163,840
DeepSeek V3 (Ingles)DeepSeek3US$0.25US$0.89US$0.4375US$0.32 / US$1—163,840
DeepSeek-V3.1-Terminus (Ingles)DeepSeek3US$0.27US$1US$0.4525US$0.27 / US$1—163,840
DeepSeek V3 0324 (Ingles)DeepSeek3US$0.29US$1.14US$0.5025US$0.385 / US$1.625—131,072
DeepSeek R1 Distill Qwen 32B (Ingles)DeepSeek3US$0.497US$0.90US$0.60US$0.50 / US$4.80—131,072
DeepSeek R1 0528 (Ingles)DeepSeek5US$0.385US$1.625US$0.695US$0.57 / US$2.29—163,840
DeepSeek R1 (Ingles)DeepSeek4US$0.50US$2.18US$0.92US$0.925 / US$3.79—163,840
DeepSeek V4 ProDeepSeek11US$0.957US$1.914US$1.196US$1.65 / US$3.301US$1.32 / US$3.961,048,576
DeepSeek V4 Pro 0813DeepSeek15US$0.85US$2.60US$1.30US$1.32 / US$3.96US$1.32 / US$3.961,048,576
Google · 19 na model
Gemma 3 4B (Ingles)Google3US$0.04US$0.08US$0.05US$0.05 / US$0.10—131,072
Gemma 3 12B (Ingles)Google4US$0.05US$0.15US$0.075US$0.07 / US$0.22—131,072
Gemma 3 27BGoogle6US$0.08US$0.16US$0.10US$0.1095 / US$0.25—198,000
Gemma 4 26B A4B · nasa BroadNet Inference dinGoogle11US$0.07US$0.30US$0.1375US$0.13 / US$0.40—262,144
gemma-4-31B-it-turbo (Ingles)Google2US$0.09US$0.34US$0.1525US$0.105 / US$0.355—262,144
Gemma 4 31BGoogle12US$0.10US$0.34US$0.16US$0.14 / US$0.40—262,144
Gemini 2.5 Flash-Lite (Ingles)Google2US$0.10US$0.40US$0.175US$0.10 / US$0.40US$0.10 / US$0.40—
Gemini 3.1 Flash-Lite (gemini-3.1-flash-lite) (Ingles)Google3US$0.25US$1.50US$0.5625US$0.25 / US$1.50US$0.25 / US$1.501,000,000
Gemini 2.5 Flash (Ingles)Google3US$0.30US$2.50US$0.85US$0.30 / US$2.50US$0.30 / US$2.501,000,000
Gemini 3.5 Flash-Lite (Ingles)Google3US$0.30US$2.50US$0.85US$0.30 / US$2.50US$0.30 / US$2.501,048,576
Gemini 3.6 Flash (Ingles)Google3US$0.75US$3.75US$1.50US$0.75 / US$3.75US$0.75 / US$3.751,048,576
Gemini 3.7 Flash (Ingles)Google3US$0.75US$3.75US$1.50US$0.75 / US$3.75—1,048,576
Gemini 3.8 Flash (Ingles)Google3US$0.75US$3.75US$1.50US$0.75 / US$3.75US$0.75 / US$3.751,048,576
Gemini 4 Hydrogen (Ingles)Google3US$1.50US$7.50US$3US$1.50 / US$7.50US$1.50 / US$7.50—
Gemini 3.5 Flash (Ingles)Google3US$1.50US$9US$3.375US$1.50 / US$9—1,048,576
Gemini 2.5 Pro (Ingles)Google3US$1.25US$10US$3.438US$1.25 / US$10US$1.25 / US$101,000,000
Gemini 4 Argon (Ingles)Google4US$2US$10US$4US$2 / US$10US$2 / US$101,048,576
Gemini 4 Carbon (Ingles)Google4US$2US$10US$4US$2 / US$10US$2 / US$101,048,576
Gemini 3.1 Pro Preview (Ingles)Google3US$2US$12US$4.50US$2 / US$12US$2 / US$121,048,576
Anthropic · 15 na model
Claude Haiku 5.5 (Ingles)Anthropic4US$0.10US$0.50US$0.20US$0.10 / US$0.50US$0.10 / US$0.50—
Claude Haiku 4.5Anthropic5US$1US$5US$2US$1 / US$5US$1 / US$5200,000
Claude Sonnet 5 (Ingles)Anthropic5US$2US$10US$4US$2 / US$10US$2 / US$101,000,000
Claude Sonnet 5.5Anthropic6US$2US$10US$4US$2 / US$10US$2 / US$101,000,000
Claude Sonnet 4.5 (Ingles)Anthropic4US$3US$15US$6US$3 / US$15US$3 / US$15—
Claude Sonnet 4.6 (Ingles)Anthropic5US$3US$15US$6US$3 / US$15US$3 / US$151,000,000
Claude Opus 5.5Anthropic6US$4US$20US$8US$4 / US$20US$4 / US$201,000,000
Claude Opus 4.5 (Ingles)Anthropic4US$5US$25US$10US$5 / US$25US$5 / US$25—
Claude Opus 4.6 (Ingles)Anthropic4US$5US$25US$10US$5 / US$25US$5 / US$251,000,000
Claude Opus 4.7 (Ingles)Anthropic5US$5US$25US$10US$5 / US$25US$5 / US$251,000,000
Claude Opus 4.8 (Ingles)Anthropic5US$5US$25US$10US$5 / US$25US$5 / US$251,000,000
Claude Opus 5 (Ingles)Anthropic5US$5US$25US$10US$5 / US$25US$5 / US$251,000,000
Claude Fable 5.2 (Ingles)Anthropic4US$8US$40US$16US$8 / US$40US$8 / US$401,000,000
Claude Fable 5Anthropic5US$10US$50US$20US$10 / US$50US$10 / US$501,000,000
Claude Fable 5.1 (Ingles)Anthropic4US$10US$50US$20US$10 / US$50US$10 / US$501,000,000
Z.ai · 13 na model
GLM 5.3 FlashZ.ai20US$0.075US$0.25US$0.1187US$0.15 / US$0.50US$0.15 / US$0.501,048,576
GLM 4.7 FlashZ.ai6US$0.06US$0.40US$0.145US$0.07 / US$0.40libre202,752
GLM 4.5 Air (Ingles)Z.ai4US$0.13US$0.85US$0.31US$0.17 / US$0.98US$0.20 / US$1.10131,076
GLM 4.6V (Ingles)Z.ai2US$0.30US$0.90US$0.45US$0.30 / US$0.90US$0.30 / US$0.90131,072
GLM 5.3 FlashX (Ingles)Z.ai2US$0.37US$1.25US$0.59US$0.37 / US$1.25US$0.37 / US$1.251,048,576
GLM 4.7Z.ai8US$0.40US$1.75US$0.7375US$0.60 / US$2.20US$0.60 / US$2.20204,800
GLM 4.6Z.ai6US$0.43US$1.75US$0.76US$0.55 / US$2.10US$0.60 / US$2.20204,800
GLM 5.2Z.ai19US$0.5625US$1.80US$0.8719US$1.40 / US$4.40US$1.40 / US$4.401,048,576
GLM 4.5V (Ingles)Z.ai2US$0.60US$1.80US$0.90US$0.60 / US$1.80US$0.60 / US$1.8065,536
GLM 5Z.ai10US$0.60US$1.92US$0.93US$1 / US$3.20US$1 / US$3.20204,800
GLM-4.5-FP8 (Ingles)Z.ai2US$0.60US$2.20US$1US$0.60 / US$2.20US$0.60 / US$2.20131,072
GLM 5.3 · nasa BroadNet Inference dinZ.ai24US$0.19US$2.20US$1.047US$1.40 / US$4.40US$1.40 / US$4.401,048,576
GLM 5.1Z.ai12US$0.90US$2.90US$1.40US$1.40 / US$4.40US$1.40 / US$4.40204,800
Meta · 12 na model
Llama 3.1 8B InstructMeta6US$0.02US$0.04US$0.025US$0.21 / US$0.22—131,072
Llama 3.2 1B Instruct (Ingles)Meta3US$0.027US$0.10US$0.0705US$0.027 / US$0.201—32,768
Llama 3 8B Instruct (Ingles)Meta3US$0.0925US$0.095US$0.09312US$0.282 / US$0.60—8,192
Llama 3.2 3B Instruct (Ingles)Meta4US$0.0509US$0.15US$0.1219US$0.1005 / US$0.335—128,000
Llama 4 Scout 17B 16E InstructMeta6US$0.08US$0.30US$0.15US$0.175 / US$0.625—1,048,576
Llama 3.3 70BMeta14US$0.10US$0.32US$0.155US$0.625 / US$0.72—131,072
Llama 3.2 11B Vision Instruct (Ingles)Meta3US$0.049US$0.16US$0.16US$0.16 / US$0.371——
Llama 4 Maverick 17B 128E Instruct FP8Meta7US$0.24US$0.80US$0.3875US$0.27 / US$1—1,048,576
Muse Glimmer 30B (Ingles)Meta3US$0.30US$1.10US$0.50US$0.30 / US$1.20—131,072
Llama 3.1 Instruct (70B) (Ingles)Meta3US$0.293US$0.72US$0.72US$0.72 / US$2.253—32,768
Muse Spark Open (Ingles)Meta4US$1.25US$4.25US$2US$1.25 / US$4.25—1,048,576
Llama 3 Instruct (70B) (Ingles)Meta2US$2.65US$3.50US$2.862US$3.075 / US$5.90—8,192
Mistral AI · 9 na model
Mistral-Nemo-Instruct-2407 (Ingles)Mistral AI2US$0.029US$0.03US$0.02925US$0.12325 / US$0.13875—131,072
Mistral-Small-24B-Instruct-2501 (Ingles)Mistral AI2US$0.05US$0.08US$0.0575US$0.1125 / US$0.185—32,768
Ministral 3 3B (Ingles)Mistral AI2US$0.10US$0.10US$0.10US$0.10 / US$0.10US$0.10 / US$0.10262,144
Mistral Small 3.2 24B Instruct (Ingles)Mistral AI4US$0.075US$0.20US$0.1062US$0.091875 / US$0.275—256,000
Ministral 3 8B (Ingles)Mistral AI2US$0.15US$0.15US$0.15US$0.15 / US$0.15US$0.15 / US$0.15262,144
Mistral Small 3.1 24B Instruct (Ingles)Mistral AI4US$0.10US$0.30US$0.15US$0.1614 / US$0.36025—32,768
Ministral 3 14B (Ingles)Mistral AI3US$0.20US$0.20US$0.20US$0.20 / US$0.20US$0.20 / US$0.20262,144
Mistral Large 3 (Ingles)Mistral AI3US$0.50US$1.50US$0.75US$0.636 / US$1.908——
Mistral Medium 3 (Ingles)Mistral AI2US$0.40US$2US$0.80US$1.79 / US$5.75——
Moonshot AI · 8 na model
Kimi K2.6Moonshot AI13US$0.39US$1.80US$0.7425US$0.80 / US$3.50US$0.95 / US$4262,144
Kimi K2.5Moonshot AI8US$0.45US$2.25US$0.90US$0.60 / US$3—262,144
Kimi K2 ThinkingMoonshot AI6US$0.60US$1.20US$0.90US$0.60 / US$2.50—262,144
Kimi K2 Instruct (Ingles)Moonshot AI2US$0.57US$2.30US$1.002US$0.585 / US$2.40—131,072
Kimi K2 Instruct 0905 (Ingles)Moonshot AI2US$0.60US$2.50US$1.075US$0.60 / US$2.50—262,144
Kimi K2.7 CodeMoonshot AI12US$0.60US$3US$1.20US$0.90458 / US$3.90US$0.95 / US$4262,144
Kimi K3Moonshot AI18US$1.85US$9.50US$3.763US$3 / US$15US$3 / US$151,048,576
Kimi K3.1 ProMoonshot AI13US$1.75US$9.50US$3.80US$2 / US$10US$2 / US$101,048,576
MiniMax · 6 na model
MiniMax M3.1 FlashMiniMax9US$0.15US$0.60US$0.2625US$0.15 / US$0.60US$0.15 / US$0.601,048,576
MiniMax M2.7 (Ingles)MiniMax3US$0.21US$0.84US$0.3675US$0.30 / US$1.20—204,800
MiniMax M3MiniMax10US$0.23US$0.96US$0.4125US$0.30 / US$1.20US$0.30 / US$1.201,048,576
MiniMax M2.5MiniMax6US$0.27US$0.95US$0.44US$0.30 / US$1.20—204,800
MiniMax M2 (Ingles)MiniMax4US$0.2775US$1.11US$0.4856US$0.30 / US$1.20—204,800
Minimax M2.1 (Ingles)MiniMax3US$0.30US$1.20US$0.525US$0.30 / US$1.20—204,800
xAI · 6 na model
Grok 4.20 (non-reasoning) (Ingles)xAI2US$1.25US$2.50US$1.563US$1.25 / US$2.50US$1.25 / US$2.501,000,000
Grok 4.20 (reasoning) (Ingles)xAI3US$1.25US$2.50US$1.563US$1.25 / US$2.50US$1.25 / US$2.501,000,000
Grok 4.3 (Ingles)xAI4US$1.25US$2.50US$1.563US$1.25 / US$2.50US$1.25 / US$2.501,000,000
Grok 4.5 (Ingles)xAI3US$2US$6US$3US$2 / US$6US$2 / US$62,000,000
Grok 4.6xAI6US$2US$6US$3US$2 / US$6US$2 / US$62,000,000
Grok 4.7xAI6US$2US$6US$3US$2 / US$6US$2 / US$6524,288
NVIDIA · 5 na model
NVIDIA Nemotron 3.5 Lightning 30B A3B (Ingles)NVIDIA5US$0.05US$0.16US$0.085US$0.06 / US$0.20—1,048,576
NVIDIA Nemotron 3 Nano 30B A3B (Ingles)NVIDIA3US$0.05US$0.20US$0.0875US$0.06 / US$0.24—262,144
NVIDIA Nemotron 3 Super 120B A12B (Ingles)NVIDIA3US$0.075US$0.40US$0.1563US$0.15 / US$0.65—262,144
NVIDIA Nemotron 3.5 Super VLNVIDIA6US$0.10US$0.40US$0.175US$0.175 / US$0.50—1,000,000
NVIDIA Nemotron 3 UltraNVIDIA9US$0.50US$2.15US$0.9125US$0.60 / US$2.40—262,144
StepFun · 3 na model
Step-3.5-Flash (Ingles)StepFun2US$0.10US$0.30US$0.15US$0.10 / US$0.30—262,144
Step 3.7 Flash (Ingles)StepFun3US$0.20US$1.15US$0.4375US$0.20 / US$1.15—262,144
Step 5 Preview (Ingles)StepFun4US$1US$2.70US$1.425US$1 / US$2.70—1,048,576
Tencent · 3 na model
Hy3 (Ingles)Tencent4US$0.132US$0.528US$0.231US$0.14 / US$0.58—262,144
Hy4 (Ingles)Tencent3US$0.417US$1.2505US$0.6254US$0.417 / US$1.2505—1,048,576
Hy4 PreviewTencent6US$0.834US$2.501US$1.251US$0.834 / US$2.501—1,048,576
Xiaomi · 3 na model
MiMo V2.6 Flash (Ingles)Xiaomi5US$0.112US$0.224US$0.14US$0.14 / US$0.28—1,050,000
MiMo v2.5 (Ingles)Xiaomi4US$0.14US$0.28US$0.175US$0.1445 / US$0.3865—1,048,576
MiMo V2.6 Pro (Ingles)Xiaomi3US$0.32625US$0.6525US$0.4078US$0.387 / US$0.783—1,050,000
Cohere · 2 na model
Command R (Ingles)Cohere2US$0.15US$0.60US$0.2625US$0.325 / US$1.05US$0.15 / US$0.60128,000
Command A+ (Ingles)Cohere2US$0.80US$3.20US$1.40—libre—
inclusionAI · 2 na model
Ling 3.0 Flash (Ingles)inclusionAI2US$0.06US$0.18US$0.09US$0.06 / US$0.18—262,144
Ling 3.0 Flash VL (Ingles)inclusionAI2US$0.06US$0.18US$0.09US$0.0675 / US$0.20—262,144
Sao10K · 2 na model
Llama 3 8B Stheno V3.2 (Ingles)Sao10K2US$0.05US$0.05US$0.05US$0.21 / US$0.215—8,192
L3.1-70B-Euryale-v2.2 (Ingles)Sao10K2US$0.72US$0.72US$0.72US$0.785 / US$0.785—131,072
IBM · 1 na model
IBM Granite 4.2 8B (Ingles)IBM2US$0.06US$0.15US$0.0825US$0.06 / US$0.20—131,072
Microsoft · 1 na model
Phi-4 (Ingles)Microsoft3US$0.07US$0.14US$0.0875US$0.07 / US$0.14—131,072
Reflection AI · 1 na model
Beam 1.0 501B A23B (Ingles)Reflection AI3US$0.40US$1.20US$0.60US$0.40 / US$1.20——
Ricursive AI · 1 na model
Ripple-65B Preview (Ingles)Ricursive AI2US$0.20US$0.60US$0.30US$0.20 / US$0.60—1,000,000
Thinking Machines · 1 na model
Inkling 2 Small (Ingles)Thinking Machines3US$0.285US$0.95US$0.4512US$0.30 / US$1—1,048,576

198 na model na may 2+ provider; hiwalay na nakalista ang 230 na model na iisa ang provider (Ingles). USD kada 1M token, standard tier. Ang "pinakamura" ay ang pinakamababang standard na presyo para sa model sa mga provider na sinuri namin, hindi sa buong market; puwedeng magmula sa magkaibang provider ang minimum na input at output. Nasa bawat page ng model ang batch, flex, priority at fast tier, at ang mga libreng row, pero hindi sila kailanman nagtatakda ng "pinakamura". Binibilang ang mga promotional na presyo at may tag ang mga ito sa page ng model. Ang "Presyo ng gumawa" ay ang sariling API ng gumawa ng model, kung nagbebenta ito ng API (DeepSeek: presyo sa peak hours). 1,218 na standard na presyo lahat; pinakabagong pagsuri: Nobyembre 15, 2026. Papunta sa sariling mga page ng model ng BroadNet Inference ang mga link ng BroadNet. Sariling site ng BroadNet ang BroadRouter.

I-report ang maling presyo o numero (email sa info@broadnet.ai, nakalagay na ang link ng page na ito).

Paano ihambing ang presyo ng LLM API?

  1. I-presyo ang workload mo, hindi ang model. Mabigat sa input ang chatbot; mabigat sa output ang reasoning agent. Tinatanggap ng cost calculator (Ingles) ang traffic at cache rate mo.
  2. Tingnan ang cached input. Ipinapadala muli ng mga agent ang parehong prefix; puwedeng mas sulit ang murang cache price kaysa murang input price. Mga cached input token.
  3. Tingnan ang context, precision at tier. Puwedeng mas mababa ang context cap ng pinakamurang row, mag-serve ito ng FP4, o maging best-effort na tier. Ipinapakita ng bawat page ng model ang tatlong ito.
  4. Bilangin ang token kada model. Magkakaiba ang tokenizer, kaya magkaiba ang bilang ng token ng parehong prompt. Gamitin ang token counter (Ingles).

Ang parehong data bilang open dataset (CSV at JSON; CC BY 4.0 ang compilation namin, at kinikilala ang provider ng bawat presyo), may agwat ng presyo sa pagitan ng mga provider, presyo ng gumawa laban sa host at cached pricing kada model: ang LLM API price index (Ingles). Bawat indibidwal na presyo, may source URL, petsa at quote: i-download ang lahat ng presyo (Ingles).

Tingnan din ang paghahambing ng model laban sa model (Ingles) at ang presyo at plan ng BroadNet Inference.

Mga tanong

Aling LLM API ang pinakamura kada token?

Sa 198 na model na may dalawa o higit pang provider sa data namin (sariling pricing page ng 41 na provider, binasa Nobyembre 14, 2026 hanggang Nobyembre 15, 2026), ang Llama 3.1 8B Instruct ang may pinakamababang nakalistang standard na presyo: US$0.02 input at US$0.04 output kada 1M token sa DeepInfra. Gumagamit ang ranking ng pinakamurang LLM API ng nakasaad na quality filter, kaya puwedeng iba ang nangunguna roon. Bihirang ang pinakamurang model ang pinakaangkop sa isang task, kaya i-presyo ang workload mo.

Bakit iba-iba ang presyo ng parehong model?

Sine-serve ang mga open-weight model ng maraming kompanya sa magkakaibang hardware, precision (FP4, FP8, BF16) at service tier. May standard na presyo ang GLM 5.3 mula sa 24 na provider. Sa 197 na model na may dalawa o higit pang may-bayad na standard na presyo, ang pinakamahal ay median na 1.3× ng pinakamura sa 3:1 blend.

Saan galing ang mga presyong ito?

Mula sa sariling pricing page ng bawat provider. Binasa namin ang 1,671 na presyo mula sa 41 na provider sa tulong ng AI at ng page renderer, at iniimbak namin ang bawat isa kasama ang source URL nito, ang petsa ng pagsuri at isang quote mula sa page. Walang aggregator o router feed na ginagamit. Nasa methodology page ang buong patakaran. Galing sa sariling rate card ng BroadNet Inference ang mga row ng BroadNet at hindi naka-rank ang mga ito.

Ano ang ibig sabihin ng presyo kada token kung kada milyon ang presyo?

USD kada 1M token ang presyo ng mga provider. Hatiin sa 1,000,000 para makuha ang presyo ng isang token: ang US$0.30 kada 1M ay US$0.0000003 kada token. Magkahiwalay ang presyo ng input, cached input at output, at sinisingil bilang output ang mga reasoning token.

Paano ko tatantiyahin ang buwanang bill?

Gamitin ang LLM API cost calculator (Ingles): pumili ng workload, saka magdagdag ng alinman sa 428 na model sa pinakamurang standard na presyo nito. Bilangin muna ang totoong laki ng mga prompt mo gamit ang token counter (Ingles).

Basahin bilang MarkdownTanungin ang ChatGPTTanungin ang ClaudeTanungin ang Perplexity

Mga source