LLM API Pricing Comparison

LLMPrices compares API prices for 461 large language models from 67 providers, normalized to US dollars per 1M tokens. As of October 22, 2026, input prices range from free to $150 per 1M tokens; the cheapest paid model is IBM: Granite 4.0 Micro at $0.017 input and $0.112 output per 1M tokens, and the median input price is $0.475. Prices are refreshed daily — see how we collect them.
Models tracked
461
from 67 providers
Cheapest paid input
$0.017
IBM: Granite 4.0 Micro
Free models
21
$0 in / $0 out
Largest context
2M
SpaceXAI: Grok 4.20 Multi-Agent
Last updated
October 22, 2026
refreshed daily

Cheapest input (per 1M)

See the full ranking →

Cheapest output (per 1M)

See the full ranking →

Official prices, verified

For 78 flagship models from OpenAI, Anthropic, Google, DeepSeek, xAI, Mistral, MiniMax and Moonshot, prices were checked against each provider's own pricing page (2026-10-21): 72 match the catalog, 6 differ.

See the official prices table →

All LLM API prices

ModelProviderInput /1MOutput /1MCached in /1MContext
Recursive: Flint (free)recursiveFreeFree—262,144
MiniMax: MiniMax M3.1 Flash (free)minimaxFreeFree—1,000,000
XingChen: Xing4.0 29B A4B (free)xingchen-agiFreeFree—262,144
NVIDIA: Nemotron 3.5 Super VL (free)nvidiaFreeFree—1,000,000
Dots Studio: Dots3-Note Preview (free)dots-studioFreeFree—512,000
LiquidAI: LFM2.5-2.6B (free)liquidFreeFree—65,536
NVIDIA: Nemotron 3.5 Lightning (free)nvidiaFreeFree—1,000,000
Thinking Machines: Inkling Small (free)thinkingmachinesFreeFree—1,048,576
Poolside: Laguna S 2.1 (free)poolsideFreeFree—262,144
Thinking Machines: Inkling (free)thinkingmachinesFreeFree—1,048,576
Poolside: Laguna XS 2.1 (free)poolsideFreeFree—262,144
Cohere: North Mini Code (free)cohereFreeFree—256,000
NVIDIA: Nemotron 3.5 Content Safety (free)nvidiaFreeFree—128,000
NVIDIA: Nemotron 3 Ultra (free)nvidiaFreeFree—1,000,000
NVIDIA: Nemotron 3 Nano Omni (free)nvidiaFreeFree—256,000
Google: Gemma 4 26B A4B (free)googleFreeFree—262,144
Google: Gemma 4 31B (free)googleFreeFree—262,144
Google: Lyria 3 Pro PreviewgoogleFreeFree—1,048,576
Google: Lyria 3 Clip PreviewgoogleFreeFree—1,048,576
NVIDIA: Nemotron 3 Super (free)nvidiaFreeFree—262,144
Free Models RouteropenrouterFreeFree—200,000
ScaleDown: Summarizescaledown$0.04Free—1,000,000
ScaleDown: Extractscaledown$0.04Free—1,000,000
Mistral: Mistral Nemomistralai$0.029$0.03—131,072
inclusionAI: Ling 3.0 Flashinclusionai$0.021$0.063$0.0042262,144
Google: Gemma 3 4Bgoogle$0.04$0.05$0.02131,072
Sao10K: Llama 3 8B Lunarissao10k$0.04$0.05—8,192
OpenAI: gpt-oss-20bopenai$0.018$0.09$0.009131,072
Z.ai: GLM Flash Latest~z-ai$0.0413$0.0773$0.031,048,576
Nex AGI: Nex-N2.5-Mininex-agi$0.025$0.1$0.0025262,144
IBM: Granite 4.0 Microibm-granite$0.017$0.112—131,000
Mistral: Mistral Small 3mistralai$0.05$0.08—32,768
Meta: Llama 3.1 8B Instructmeta-llama$0.05$0.08$0.025131,072
OpenAI: gpt-oss-20b (batch)openai$0.024$0.112—131,072
Mistral: Ministral 3 8B 2512 (batch)mistralai$0.075$0.075$0.0075262,144
Qwen: Qwen3.7 Flashqwen$0.03$0.13$0.0061,000,000
OpenAI: gpt-oss-120b (batch)openai$0.0296$0.136—131,072
DeepSeek: DeepSeek V4.1 Flashdeepseek$0.0342$0.1368$0.0006841,048,576
Amazon: Nova Micro 1.0amazon$0.035$0.14—128,000
DeepSeek: DeepSeek V4 Flash 0731deepseek$0.04444$0.1333$0.0014141,048,576
Inference.net: Schematron V2 Turboinference-net$0.03$0.15$0.03128,000
Poolside: Laguna XS 2.1poolside$0.06$0.12$0.03262,144
Cohere: Command R7B (12-2024)cohere$0.0375$0.15—128,000
Inception: Mercury 2.5inception$0.04$0.15$0.004260,000
MythoMax 13Bgryphe$0.08$0.11—8,192
DeepSeek: DeepSeek V4.1 Flash (batch)deepseek$0.05$0.15$0.0041,048,576
Reka Edgerekaai$0.1$0.1—16,384
Mistral: Ministral 3 3B 2512mistralai$0.1$0.1$0.01131,072
Google: Gemma 3 12Bgoogle$0.05$0.15—131,072
Qwen: Qwen3.5-9Bqwen$0.08$0.13$0.04262,144
Microsoft: Phi 4microsoft$0.07$0.14—16,384
DeepSeek: DeepSeek V4 Flash Latest~deepseek$0.0422$0.1729$0.02751,048,576
Tencent: Hy-MT2-1.8Btencent$0.044$0.177—8,192
OpenAI: GPT-5 Nano (batch)openai$0.025$0.2$0.0025400,000
Meta: Llama 3.2 1B Instructmeta-llama$0.027$0.201—60,000
Z.ai: GLM 5.3 Flash (batch)z-ai$0.05$0.18$0.011,048,576
inclusionAI: Ling 3.0 Flash VLinclusionai$0.06$0.18$0.012131,072
Upstage: Solar Mini 4upstage$0.05$0.2$0.005524,288
OpenAI: GPT-4.1 Nano (batch)openai$0.05$0.2$0.01251,047,576
NVIDIA: Nemotron 3.5 Lightningnvidia$0.07$0.2$0.04262,144
Poolside: Laguna S 2.1poolside$0.09$0.18$0.0091,048,576
DeepSeek: DeepSeek V4 Flash 0423deepseek$0.091$0.182$0.01821,048,576
Inference.net: Schematron V2 Smallinference-net$0.05$0.23$0.05128,000
Anthropic: Claude Haiku 5.5 (batch)anthropic$0.05$0.25$0.0051,000,000
inclusionAI: Ling 3.1 Flashinclusionai$0.075$0.225$0.015262,144
OpenAI: GPT-6 Luna Pro (batch)openai$0.05$0.25$0.0051,050,000
OpenAI: GPT-6 Luna (batch)openai$0.05$0.25$0.0051,050,000
Meta: Muse Spark 1.3 Contributormeta$0.1$0.2$0.0021,048,576
Meta: Muse Spark 1.2 Contributormeta$0.1$0.2$0.0021,048,576
NVIDIA: Nemotron 3 Nano 30B A3Bnvidia$0.06$0.24—262,144
Mistral: Ministral 3 8B 2512mistralai$0.15$0.15$0.015262,144
ByteDance: UI-TARS 7B bytedance$0.1$0.2$0.1128,000
Reka Flash 3rekaai$0.1$0.2—65,536
Amazon: Nova Lite 1.0amazon$0.06$0.24—300,000
Qwen: Qwen2.5 7B Instructqwen$0.1$0.2—32,768
IBM: Granite 4.2 8Bibm-granite$0.06$0.25$0.015131,072
Nex AGI: Nex-N2.5-Pronex-agi$0.075$0.25$0.015262,144
Qwen: Qwen3.5-Flashqwen$0.065$0.26—1,000,000
Google: Gemma 4 26B A4B google$0.0765$0.255$0.0425262,144
Mistral: Mistral Small 3.2 24Bmistralai$0.09375$0.25—256,000
Qwen: Qwen3 Coder 30B A3B Instructqwen$0.07$0.28—262,144
Xiaomi: MiMo-V2.5xiaomi$0.119$0.238$0.002551,050,000
Meta: Llama Guard 4 12Bmeta-llama$0.18$0.18—163,840
Qwen: Qwen3 14Bqwen$0.12$0.24—40,960
Qwen: Qwen3 32Bqwen$0.08$0.28—131,072
Tencent: Hy-MT2-30B-A3Btencent$0.074$0.295—8,192
Tencent: Hy-MT2-7Btencent$0.074$0.295—8,192
Mistral: Mistral Small 4 (batch)mistralai$0.075$0.3$0.0075262,144
ByteDance Seed: Seed 1.6 Flashbytedance-seed$0.075$0.3—262,144
OpenAI: gpt-oss-safeguard-20bopenai$0.075$0.3$0.0375131,072
OpenAI: GPT-4o-mini (batch)openai$0.075$0.3$0.0375128,000
Meta: Llama 3.2 3B Instructmeta-llama$0.0509$0.335—131,072
Qwen: Qwen3 30B A3B Instruct 2507qwen$0.09$0.3—262,144
NVIDIA: Nemotron 3.5 Content Safetynvidia$0.2$0.2—131,072
StepFun: Step 3.5 Flashstepfun$0.1$0.3—262,144
Mistral: Ministral 3 14B 2512mistralai$0.2$0.2$0.02262,144
Mistral: Voxtral Small 24B 2507mistralai$0.1$0.3$0.0132,768
Meta: Llama 4 Scoutmeta-llama$0.1$0.3—1,310,720
Tencent: Hy3tencent$0.0825$0.33$0.02063262,144
Meta: Llama 3.3 70B Instructmeta-llama$0.1$0.32—131,072
Xiaomi: MiMo-V2.6-Flashxiaomi$0.14$0.28$0.00281,050,000
Google: Gemma 3 27Bgoogle$0.08$0.35$0.04131,072
Inception: Mercury 3inception$0.1$0.35$0.011,000,000
OpenAI: GPT-5 Nanoopenai$0.05$0.4$0.005400,000
Z.ai: GLM 4.7 Flashz-ai$0.0605$0.4—200,000
ByteDance Seed: Seed-2.0-Minibytedance-seed$0.1$0.4—262,144
Google: Gemini 2.5 Flash Litegoogle$0.1$0.4$0.011,048,576
OpenAI: GPT-4.1 Nanoopenai$0.1$0.4$0.0251,047,576
DeepSeek: DeepSeek Flash Latest~deepseek$0.07$0.5$0.0081,048,576
PrismML: Ternary Bonsai 2 27Bprism-ml$0.075$0.5$0.0375262,144
Anthropic: Claude Haiku 5.5anthropic$0.1$0.5$0.011,000,000
OpenAI: GPT-6 Luna Proopenai$0.1$0.5$0.011,050,000
OpenAI: GPT-6 Lunaopenai$0.1$0.5$0.011,050,000
OpenAI: GPT Luna Latest~openai$0.1$0.5$0.011,050,000
Anthropic: Claude Haiku Latest~anthropic$0.1$0.5$0.011,000,000
Google: Gemma 4 31Bgoogle$0.2$0.4—262,144
Mistral: Codestral 2508 (batch)mistralai$0.15$0.45$0.015256,000
Qwen: Qwen3.8 Omni Flashqwen$0.15$0.47$0.0161,000,000
Qwen: Qwen3.8 Flashqwen$0.15$0.47$0.0161,000,000
Qwen: Qwen3 30B A3Bqwen$0.12$0.5—40,960
Qwen: Qwen3 235B A22B Instruct 2507qwen$0.09$0.55—262,144
NVIDIA: Nemotron 3.5 Super VLnvidia$0.15$0.5$0.021,048,576
Z.ai: GLM 5.3 Flashz-ai$0.15$0.5$0.031,048,576
DeepSeek: DeepSeek V3.2 Expdeepseek$0.27$0.41—163,840
OpenAI: GPT-5.6 Luna Pro (batch)openai$0.1$0.6$0.011,050,000
OpenAI: GPT-5.6 Luna (batch)openai$0.1$0.6$0.011,050,000
DeepSeek: DeepSeek V3.2deepseek$0.28$0.42$0.028163,840
Tencent: Hunyuan A13B Instructtencent$0.14$0.57—131,072
OpenAI: GPT-5.4 Nano (batch)openai$0.1$0.625$0.01400,000
DeepSeek: DeepSeek V4.1 Flash 1017deepseek$0.15$0.6$0.0031,048,576
LiquidAI: LFM2.5-24B-A2Bliquid$0.05$0.7$0.025128,000
Upstage: Solar Pro 4upstage$0.15$0.6$0.03524,288
Mistral: Mistral Small 4mistralai$0.15$0.6$0.015262,144
Upstage: Solar Pro 3upstage$0.15$0.6$0.015131,072
Qwen: Qwen3 VL 30B A3B Instructqwen$0.15$0.6—262,144
OpenAI: gpt-oss-120bopenai$0.15$0.6$0.075131,072
Cohere: Command R (08-2024)cohere$0.15$0.6—128,000
OpenAI: GPT-4o-miniopenai$0.15$0.6$0.075128,000
OpenAI: GPT-4o-mini (2024-07-18)openai$0.15$0.6$0.075128,000
Qwen2.5 72B Instructqwen$0.36$0.4—32,768
Tencent: Hy3 previewtencent$0.18$0.6$0.06262,144
Mistral: Sabamistralai$0.2$0.6$0.0232,768
TheDrummer: UnslopNemo 12Bthedrummer$0.4$0.4—1,024,000
Meta: Llama 3.1 70B Instructmeta-llama$0.4$0.4—131,072
TheDrummer: Cydonia 24B V4.1thedrummer$0.3$0.5$0.15131,072
Meta: Llama 4 Maverickmeta-llama$0.1875$0.6525$0.05524,288
DeepSeek: DeepSeek V4 Flash Vision Expdeepseek$0.2156$0.6468$0.006861,048,576
Google: Gemini 3.1 Flash Lite (batch)google$0.125$0.75$0.01251,048,576
Mistral: Mistral Small 3.1 24Bmistralai$0.351$0.555—128,000
Xiaomi: MiMo-V2.5-Proxiaomi$0.3045$0.609$0.00281,050,000
Qwen: Qwen3 Coder Nextqwen$0.12$0.8$0.07262,144
Z.ai: GLM 4.5 Airz-ai$0.13$0.85$0.025131,072
OpenAI: GPT-4.1 Mini (batch)openai$0.2$0.8$0.051,047,576
Inception: Mercury 2inception$0.25$0.75$0.025128,000
Mistral: Mistral Large 3 2512 (batch)mistralai$0.25$0.75$0.025262,144
Qwen: Qwen3 VL 8B Instructqwen$0.25$0.75$0.12262,144
ReMM SLERP 13Bundi95$0.35$0.65—6,144
OpenAI: GPT-3.5 Turbo (batch)openai$0.25$0.75—16,385
Qwen: Qwen-Plusqwen$0.26$0.78$0.0521,000,000
Arcee AI: Trinity Large Thinkingarcee-ai$0.25$0.8$0.06262,144
Qwen: Qwen3.6 35B A3Bqwen$0.1$0.95$0.05262,144
Venice: Uncensoredcognitivecomputations$0.2$0.9—128,000
OpenAI: GPT-5 Mini (batch)openai$0.125$1$0.0125400,000
Qwen: Qwen3.5-35B-A3Bqwen$0.14$1$0.05262,144
Qwen: Qwen3.7 Plus (batch)qwen$0.23$0.92—262,144
Mancer: Weaver (alpha)mancer$0.4$0.75—8,000
DeepSeek: DeepSeek V4 Pro 0423deepseek$0.3835$0.767$0.031961,048,576
Qwen: Qwen3 Coder Flashqwen$0.195$0.975$0.0391,000,000
Qwen: Qwen3 Next 80B A3B Instructqwen$0.09$1.1—262,144
Z.ai: GLM 4.6Vz-ai$0.3$0.9$0.055131,072
DeepSeek: DeepSeek V3.1deepseek$0.25$0.95$0.13163,840
Mistral: Mistral Medium 3.1 (batch)mistralai$0.2$1$0.02131,072
Mistral: Codestral 2508mistralai$0.3$0.9$0.03256,000
MiniMax: MiniMax M2.5minimax$0.27$0.95$0.03204,800
DeepSeek: DeepSeek V3.1 Terminusdeepseek$0.27$1—163,840
MiniMax: MiniMax M2minimax$0.255$1.02—204,800
DeepSeek: DeepSeek V3deepseek$0.2574$1.029—163,840
Qwen: Qwen3 VL 30B A3B Thinkingqwen$0.29$1—262,144
Reflection: Beam 1.0 501B A23Breflection$0.3$1$0.041,048,576
Qwen: Qwen3 Coder 480B A35Bqwen$0.3$1$0.1262,144
MiniMax: MiniMax-01minimax$0.2$1.1—1,000,192
Google: Gemma 2 27Bgoogle$0.65$0.65—8,192
Xiaomi: MiMo-V2.6-Proxiaomi$0.435$0.87$0.00361,050,000
Qwen: Qwen3.6 Flashqwen$0.1875$1.125—1,000,000
StepFun: Step 3.7 Flashstepfun$0.2$1.15$0.04262,144
Qwen: Qwen3 Next 80B A3B Thinkingqwen$0.15$1.2—262,144
TheDrummer: Skyfall 36B V2thedrummer$0.55$0.8$0.2532,768
Qwen: Qwen3.8 27Bqwen$0.04$1.35$0.0181,000,000
Google: Gemini 3.5 Flash Lite (batch)google$0.15$1.25$0.0151,048,576
OpenAI: GPT-5.6 Luna Proopenai$0.2$1.2$0.021,050,000
OpenAI: GPT-5.6 Lunaopenai$0.2$1.2$0.021,050,000
Nous: Hermes 3 70B Instructnousresearch$0.7$0.7—131,072
DeepSeek: DeepSeek V3 0324deepseek$0.29$1.14$0.11163,840
OpenAI: GPT-5.4 Nanoopenai$0.2$1.25$0.02400,000
Z.ai: GLM Latest~z-ai$0.079$1.4$0.0781,048,576
Meta: Muse Glimmer 30Bmeta$0.3$1.2$0.04131,072
Meituan: LongCat 2.0meituan$0.3$1.2$0.0061,048,756
MiniMax: MiniMax M3minimax$0.3$1.2$0.061,048,576
MiniMax: MiniMax M2.7minimax$0.3$1.2$0.06204,800
MiniMax: MiniMax M2-herminimax$0.3$1.2$0.0365,536
MiniMax: MiniMax M2.1minimax$0.3$1.2$0.03204,800
Qwen: Qwen3.7 Plusqwen$0.32$1.28$0.0641,000,000
Z.ai: GLM 5.3 FlashXz-ai$0.37$1.25$0.091,048,576
Perceptron: Perceptron Mk1.5perceptron$0.15$1.5—36,864
Thinking Machines: Inkling Smallthinkingmachines$0.45$1.2$0.1524,288
Perceptron: Perceptron Mk1perceptron$0.15$1.5—32,768
Qwen2.5 Coder 32B Instructqwen$0.66$1—32,768
Sao10K: Llama 3.1 Euryale 70B v2.2sao10k$0.85$0.85—131,072
Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)google$0.25$1.5—65,536
Google: Gemini 3.1 Flash Litegoogle$0.25$1.5$0.0251,048,576
Google: Gemini 3.1 Flash Lite Previewgoogle$0.25$1.5$0.0251,048,576
Google: Gemini 3 Flash Preview (batch)google$0.25$1.5—1,048,576
Qwen: Qwen2.5 VL 72B Instructqwen$0.8$1$0.4128,000
Cohere: Command A+cohere$0.3$1.5$0.15192,000
Qwen: Qwen3.5 Plus 2026-02-15qwen$0.26$1.56—1,000,000
OpenAI: GPT-4.1 Miniopenai$0.4$1.6$0.11,047,576
Mistral: Mistral Large 3 2512mistralai$0.5$1.5$0.05262,144
Morph: Morph V3 Fastmorph$0.8$1.2—262,144
Perplexity: Sonarperplexity$1$1—127,072
Nous: Hermes 3 405B Instructnousresearch$1$1—131,072
OpenAI: GPT-3.5 Turboopenai$0.5$1.5—16,385
AionLabs: Aion 3.5 Miniaion-labs$0.7$1.4$0.18262,144
AionLabs: Aion-3.0-Miniaion-labs$0.7$1.4$0.18131,072
Qwen: Qwen3.5 Plus 2026-04-20qwen$0.3$1.8—1,000,000
Relace: Relace Apply 3relace$0.85$1.25—256,000
Qwen: Qwen3 VL 235B A22B Instructqwen$0.21$1.9$0.1262,144
Google: Gemini 3.8 Flash (batch)google$0.375$1.875$0.03751,048,576
Google: Gemini 3.7 Flash (batch)google$0.375$1.875$0.03751,048,576
Google: Gemini 3.6 Flash (batch)google$0.375$1.875$0.03751,048,576
Qwen: Qwen3.6 27Bqwen$0.25$2$0.025262,144
ByteDance Seed: Seed-2.0-Litebytedance-seed$0.25$2—262,144
ByteDance Seed: Seed 1.6bytedance-seed$0.25$2—262,144
OpenAI: GPT-5.1-Codex-Miniopenai$0.25$2$0.03400,000
OpenAI: GPT-5 Miniopenai$0.25$2$0.025400,000
Qwen: Qwen3.6 Plusqwen$0.325$1.95—1,000,000
Qwen: Qwen3.5-122B-A10Bqwen$0.26$2.08—262,144
AionLabs: Aion-2.0aion-labs$0.8$1.6$0.2131,072
Mistral: Devstral 2 2512mistralai$0.4$2$0.04262,144
Mistral: Mistral Medium 3.1mistralai$0.4$2$0.04131,072
Z.ai: GLM 4.5Vz-ai$0.6$1.8$0.1165,536
Mistral: Mistral Medium 3mistralai$0.4$2$0.04131,072
AionLabs: Aion-RP 1.0 (8B)aion-labs$0.8$1.6—32,768
Qwen: Qwen3.5-27Bqwen$0.27$2.16$0.27262,144
Z.ai: GLM 5.3 (batch)z-ai$0.45$2$0.11,048,576
Z.ai: GLM 4.7z-ai$0.54$1.98$0.099204,800
OpenAI: GPT-5.4 Mini (batch)openai$0.375$2.25$0.0375400,000
DeepSeek: DeepSeek V4 Pro 0813deepseek$0.66$1.98$0.0221,048,576
DeepSeek: R1 0528deepseek$0.5$2.15$0.35163,840
NVIDIA: Nemotron 3 Supernvidia$0.3$2.4$0.15262,144
Qwen: Qwen3.5 397B A17Bqwen$0.39$2.34—262,144
Z.ai: GLM 4.6z-ai$0.55$2.2$0.11204,800
MiniMax: MiniMax M1minimax$0.55$2.2—1,000,000
OpenAI: o4 Mini (batch)openai$0.55$2.2$0.1375200,000
OpenAI: o3 Mini (batch)openai$0.55$2.2$0.275200,000
Moondream: Moondream 3 Previewmoondream$0.3$2.5—32,000
Moondream: Moondream 3.1moondream$0.3$2.5—32,000
Google: Gemini 3.5 Flash Litegoogle$0.3$2.5$0.031,048,576
Amazon: Nova 2 Liteamazon$0.3$2.5—1,000,000
Google: Nano Banana (Gemini 2.5 Flash Image)google$0.3$2.5$0.0332,768
Morph: Morph V3 Largemorph$0.9$1.9—262,144
Google: Gemini 2.5 Flashgoogle$0.3$2.5$0.031,048,576
Z.ai: GLM 4.5z-ai$0.6$2.2$0.11131,072
MoonshotAI: Kimi K2 0711moonshotai$0.57$2.3—131,072
Z.ai: GLM 5.3z-ai$0.7$2.2$0.131,048,576
ByteDance Seed: Seed 2.1 Turbobytedance-seed$0.5$2.5—262,144
NVIDIA: Nemotron 3 Ultranvidia$0.6$2.4$0.12262,144
SpaceXAI: Grok Build 0.1x-ai$1$2$0.2256,000
SpaceXAI: Grok 4.3 (batch)x-ai$1$2$0.161,000,000
MoonshotAI: Kimi K2.5moonshotai$0.5$2.5$0.15262,144
OpenAI: GPT Audio Miniopenai$0.6$2.4—128,000
Anthropic: Claude Haiku 4.5 (batch)anthropic$0.5$2.5$0.05200,000
OpenAI: GPT-3.5 Turbo (older v0613)openai$1$2—4,095
Tencent: Hy4 previewtencent$0.7506$2.251$0.03781,048,576
MoonshotAI: Kimi K2 Thinkingmoonshotai$0.6$2.5$0.15262,144
MoonshotAI: Kimi K2 0905moonshotai$0.6$2.5—262,144
ByteDance Seed: Seed-2.0-Codebytedance-seed$0.5$3—262,144
Google: Nano Banana 2 (Gemini 3.1 Flash Image)google$0.5$3—131,072
Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)google$0.5$3—65,536
Google: Gemini 3 Flash Previewgoogle$0.5$3$0.051,048,576
OpenAI: GPT-3.5 Turbo Instructopenai$1.5$2—4,095
Elorian: Glimpseelorian$0.6$3$0.06262,144
StepFun: Step 5 Previewstepfun$1$2.7$0.11,048,576
SpaceXAI: Grok 4.3x-ai$1.25$2.5$0.21,000,000
SpaceXAI: Grok 4.20 Multi-Agentx-ai$1.25$2.5$0.22,000,000
SpaceXAI: Grok 4.20x-ai$1.25$2.5$0.22,000,000
Qwen: Qwen3 235B A22B Thinking 2507qwen$0.45$3.5—128,000
Pareto 26.10unbiased$0.8$3.2$0.031,048,576
Pareto Latest~unbiased$0.8$3.2$0.031,048,576
Amazon: Nova Pro 1.0amazon$0.8$3.2—300,000
Relace: Relace Searchrelace$1$3—256,000
Nous: Hermes 4 405Bnousresearch$1$3—131,072
MoonshotAI: Kimi K2.7 Codemoonshotai$0.6712$3.35$0.18262,144
MoonshotAI: Kimi K2.6moonshotai$0.65$3.41$0.15262,144
Z.ai: GLM 5z-ai$1$3.2$0.2204,800
Google: Gemini 3.7 Flashgoogle$0.75$3.75$0.0751,048,576
Google: Gemini 3.6 Flashgoogle$0.75$3.75$0.0751,048,576
Mistral: Mistral Medium 3.5 (batch)mistralai$0.75$3.75—262,144
Google: Gemini Flash Latest~google$0.75$3.75$0.0751,048,576
OpenAI: GPT-5 Image Miniopenai$2.5$2$0.25400,000
Google: Gemini 3.8 Flashgoogle$0.825$4.125$0.08251,048,576
Sakana: Sakana Namazusakana$0.95$4$0.15262,144
OpenAI: o3 (batch)openai$1$4$0.25200,000
OpenAI: GPT-4.1 (batch)openai$1$4$0.251,047,576
Thinking Machines: Inklingthinkingmachines$1$4.05$0.17524,288
Z.ai: GLM 5V Turboz-ai$1.2$4$0.24202,752
Z.ai: GLM 5 Turboz-ai$1.2$4$0.24202,752
Google: Gemini 3.5 Flash (batch)google$0.75$4.5$0.0751,048,576
OpenAI: GPT Mini Latest~openai$0.75$4.5$0.075400,000
OpenAI: GPT-5.4 Miniopenai$0.75$4.5$0.075400,000
Meta: Muse Spark Openmeta$1.25$4.25$0.151,048,576
Meta: Muse Spark 1.3meta$1.25$4.25$0.151,048,576
Meta: Muse Spark 1.2meta$1.25$4.25$0.151,048,576
Meta: Muse Spark 1.1meta$1.25$4.25$0.151,048,576
OpenAI: o4 Mini Highopenai$1.1$4.4$0.275200,000
OpenAI: o4 Miniopenai$1.1$4.4$0.275200,000
OpenAI: o3 Mini Highopenai$1.1$4.4$0.55200,000
OpenAI: o3 Miniopenai$1.1$4.4$0.55200,000
Mistral: Mistral Large 4mistralai$1.36$4.18$0.141,048,576
OpenAI: GPT-5.1 (batch)openai$0.625$5$0.0625400,000
OpenAI: GPT-5 (batch)openai$0.625$5$0.0625400,000
Z.ai: GLM 5.1z-ai$1.4$4.4$0.26204,800
Qwen: Qwen3.7 Maxqwen$1.475$4.425$0.2951,000,000
Google: Gemini 4 Argon (batch)google$1$5$0.051,048,576
OpenAI: GPT-6.1 Sol Pro (batch)openai$1$5$0.051,050,000
OpenAI: GPT-6.1 Sol (batch)openai$1$5$0.051,050,000
Anthropic: Claude Sonnet 5.5 (batch)anthropic$1$5$0.051,000,000
OpenAI: GPT-6 Sol Pro (batch)openai$1$5$0.11,050,000
OpenAI: GPT-6 Sol (batch)openai$1$5$0.11,050,000
Anthropic: Claude Sonnet 5 (batch)anthropic$1$5$0.11,000,000
Anthropic: Claude Haiku 4.5anthropic$1$5$0.1200,000
OpenAI: GPT-4o (batch)openai$1.25$5$0.625128,000
Writer: Palmyra X5writer$0.6$6—1,040,000
OpenAI: GPT-5.6 Terra Pro (batch)openai$1$6$0.11,050,000
OpenAI: GPT-5.6 Terra (batch)openai$1$6$0.11,050,000
Google: Gemini 3.1 Pro Preview (batch)google$1$6—1,048,576
OpenAI: GPT-3.5 Turbo 16kopenai$3$4—16,385
Z.ai: GLM 5.2z-ai$0.0341$7$0.0331,048,576
Magnum v4 72Banthracite-org$2.5$5—32,768
OpenAI: GPT-5.2 (batch)openai$0.875$7$0.0875400,000
SpaceXAI: Grok 4.7x-ai$2$6$0.5500,000
Sakana: Fugu Maxsakana$2$6$0.251,000,000
Qwen: Qwen3.8 Max (0902)qwen$2$6$0.251,000,000
Qwen: Qwen3.8 2.4T A95Bqwen$2$6$0.251,048,576
SpaceXAI: Grok 4.6x-ai$2$6$0.5500,000
SpaceXAI: Grok 4.5x-ai$2$6$0.3500,000
xAI: Grok Latest~x-ai$2$6$0.5500,000
Mistral Large 2407mistralai$2$6$0.2131,072
Mistral: Mixtral 8x22B Instructmistralai$2$6$0.265,536
Mistral Largemistralai$2$6$0.2128,000
DeepSeek: DeepSeek Pro Latest~deepseek$0.1307$8$0.131,048,576
OpenAI: GPT-5.4 (batch)openai$1.25$7.5$0.1251,050,000
Google: Nano Banana 2.1google$1.5$7.5—65,536
AionLabs: Aion 3.5aion-labs$3$6$0.75262,144
AionLabs: Aion-3.0aion-labs$3$6$0.75131,072
Mistral: Mistral Medium 3.5mistralai$1.5$7.5—262,144
Anthropic: Claude Sonnet 4.6 (batch)anthropic$1.5$7.5$0.151,000,000
Anthropic: Claude Sonnet 4.5 (batch)anthropic$1.5$7.5$0.151,000,000
Pareto 26.9unbiased$2.5$7.5$0.25262,144
OpenAI: o3openai$2$8$0.5200,000
OpenAI: GPT-4.1openai$2$8$0.51,047,576
Perplexity: Sonar Reasoning Properplexity$2$8—128,000
Perplexity: Sonar Deep Researchperplexity$2$8—128,000
Google: Gemini 3.5 Flashgoogle$1.5$9$0.151,048,576
OpenAI: GPT-5.1-Codex-Maxopenai$1.25$10$0.125400,000
OpenAI: GPT-5.1openai$1.25$10$0.125400,000
OpenAI: GPT-5.1-Codexopenai$1.25$10$0.13400,000
OpenAI: GPT-5openai$1.25$10$0.125400,000
Google: Gemini 2.5 Progoogle$1.25$10$0.1251,048,576
Google: Gemini 2.5 Pro Preview 06-05google$1.25$10$0.1251,048,576
Z.ai: GLM 5.3 Primez-ai$2.8$8.8$0.561,000,000
Google: Gemini 4 Argongoogle$2$10$0.11,048,576
OpenAI: GPT-6.1 Sol Proopenai$2$10$0.11,050,000
OpenAI: GPT-6.1 Solopenai$2$10$0.11,050,000
Anthropic: Claude Sonnet 5.5anthropic$2$10$0.11,000,000
OpenAI: GPT-6 Sol Proopenai$2$10$0.21,050,000
OpenAI: GPT-6 Solopenai$2$10$0.21,050,000
Anthropic: Claude Opus 5.5 (batch)anthropic$2$10$0.11,000,000
OpenAI: GPT Sol Latest~openai$2$10$0.11,050,000
OpenAI: GPT-5.6 Sol Pro (batch)openai$2$10$0.21,050,000
OpenAI: GPT-5.6 Sol (batch)openai$2$10$0.21,050,000
Anthropic: Claude Sonnet 5anthropic$2$10$0.21,000,000
Google: Gemini Pro Latest~google$2$10$0.11,048,576
Anthropic: Claude Sonnet Latest~anthropic$2$10$0.11,000,000
MoonshotAI: Kimi K3moonshotai$0.239$11.94$0.211,048,576
OpenAI: GPT Audioopenai$2.5$10—128,000
Cohere: Command Acohere$2.5$10—256,000
OpenAI: GPT-4o (2024-11-20)openai$2.5$10$1.25128,000
Cohere: Command R+ (08-2024)cohere$2.5$10—128,000
OpenAI: GPT-4o (2024-08-06)openai$2.5$10$1.25128,000
OpenAI: GPT-4oopenai$2.5$10$1.25128,000
Xiaomi: MiMo-V2.6-Pro-UltraSpeedxiaomi$4.35$8.7$0.0361,048,576
MoonshotAI: Kimi K3 (batch)moonshotai$2.28$11.4$0.2281,048,576
OpenAI: GPT Terra Latest~openai$2$12$0.21,050,000
OpenAI: GPT-5.6 Terra Proopenai$2$12$0.21,050,000
OpenAI: GPT-5.6 Terraopenai$2$12$0.21,050,000
Google: Nano Banana Pro (Gemini 3 Pro Image)google$2$12$0.2131,072
Google: Gemini 3.1 Pro Preview Custom Toolsgoogle$2$12$0.21,048,576
Google: Gemini 3.1 Pro Previewgoogle$2$12$0.21,048,576
Google: Nano Banana Pro (Gemini 3 Pro Image Preview)google$2$12$0.265,536
Anthropic: Claude Opus 5 (batch)anthropic$2.5$12.5$0.251,000,000
Anthropic: Claude Opus 4.8 (batch)anthropic$2.5$12.5$0.251,000,000
Anthropic: Claude Opus 4.7 (batch)anthropic$2.5$12.5$0.251,000,000
Anthropic: Claude Opus 4.6 (batch)anthropic$2.5$12.5$0.251,000,000
Anthropic: Claude Opus 4.5 (batch)anthropic$2.5$12.5$0.25200,000
Amazon: Nova Premier 1.0amazon$2.5$12.5$0.6251,000,000
OpenAI: GPT-5.3-Codexopenai$1.75$14$0.175400,000
OpenAI: GPT-5.2-Codexopenai$1.75$14$0.175400,000
OpenAI: GPT-5.2 Chatopenai$1.75$14$0.175128,000
OpenAI: GPT-5.2openai$1.75$14$0.175400,000
Qwen: Qwen3.8 Max Primeqwen$4$12$0.51,000,000
MoonshotAI: Kimi Latest~moonshotai$0.238$16$0.2281,048,576
OpenAI: GPT-5.5 (batch)openai$2.5$15$0.251,050,000
OpenAI: GPT-5.4openai$2.5$15$0.251,050,000
Fireworks: Ember-1fireworks$3$15$0.31,048,576
Anthropic: Claude Sonnet 4.6anthropic$3$15$0.31,000,000
Perplexity: Sonar Pro Searchperplexity$3$15—200,000
Anthropic: Claude Sonnet 4.5anthropic$3$15$0.31,000,000
Perplexity: Sonar Properplexity$3$15—200,000
OpenAI: GPT-5 Imageopenai$10$10$1.25400,000
OpenAI: GPT-4o (2024-05-13)openai$5$15—128,000
OpenAI: GPT-4 Turbo (batch)openai$5$15—128,000
OpenAI: GPT-5.4 Image 2openai$8$15$2272,000
Meta: Muse Wondermeta$4$20$0.21,048,576
Anthropic: Claude Opus 5.5anthropic$4$20$0.21,000,000
OpenAI: GPT-5.6 Sol Proopenai$4$20$0.41,050,000
OpenAI: GPT-5.6 Solopenai$4$20$0.41,050,000
Anthropic: Claude Opus Latest~anthropic$4$20$0.21,000,000
OpenAI: GPT-6 Astra (batch)openai$5$25$0.51,050,000
OpenAI: GPT-6 Astra Pro (batch)openai$5$25$0.51,050,000
Anthropic: Claude Fable 5.1 (batch)anthropic$5$25$0.1251,000,000
Anthropic: Claude Opus 5anthropic$5$25$0.51,000,000
Anthropic: Claude Fable 5 (batch)anthropic$5$25$0.51,000,000
Anthropic: Claude Opus 4.8anthropic$5$25$0.51,000,000
Anthropic: Claude Opus 4.7anthropic$5$25$0.51,000,000
Anthropic: Claude Opus 4.6anthropic$5$25$0.51,000,000
Anthropic: Claude Opus 4.5anthropic$5$25$0.5200,000
Sakana: Fugu Ultra v2sakana$5$30$0.51,000,000
Sakana: Fugu Ultrasakana$5$30$0.51,000,000
OpenAI: GPT Chat Latestopenai$5$30$0.5400,000
OpenAI: GPT-5.5openai$5$30$0.51,050,000
OpenAI: GPT-4 Turboopenai$10$30—128,000
Anthropic: Claude Opus 4.1 (batch)anthropic$7.5$37.5$0.75200,000
OpenAI: GPT Astra Latest~openai$10$50$11,050,000
OpenAI: GPT-6 Astraopenai$10$50$11,050,000
OpenAI: GPT-6 Astra Proopenai$10$50$11,050,000
Anthropic: Claude Fable 5.1anthropic$10$50$0.251,000,000
Anthropic: Claude Fable Latest~anthropic$10$50$0.251,000,000
Anthropic: Claude Fable 5anthropic$10$50$11,000,000
OpenAI: GPT-5 Pro (batch)openai$7.5$60—400,000
OpenAI: o1openai$15$60$7.5200,000
Anthropic: Claude Opus 4.1anthropic$15$75$1.5200,000
OpenAI: GPT-4openai$30$60—8,191
OpenAI: GPT-5.2 Pro (batch)openai$10.5$84—400,000
OpenAI: o3 Proopenai$20$80—200,000
OpenAI: GPT-5.5 Pro (batch)openai$15$90—1,050,000
OpenAI: GPT-5.4 Pro (batch)openai$15$90—1,050,000
OpenAI: GPT-5 Proopenai$15$120—400,000
OpenAI: GPT-5.2 Proopenai$21$168—400,000
OpenAI: GPT-5.5 Proopenai$30$180—1,050,000
OpenAI: GPT-5.4 Proopenai$30$180—1,050,000
OpenAI: o1-proopenai$150$600—200,000

Click any column header to sort. Prices are list prices per 1M tokens in USD. Methodology and data sources →

Frequently asked questions

What is the cheapest LLM API?

As of October 22, 2026, the cheapest paid LLM API on LLMPrices is IBM: Granite 4.0 Micro at $0.017 per 1M input tokens and $0.112 per 1M output tokens. 21 models are completely free. See the cheapest LLM APIs ranking.

How are LLM API prices compared here?

Every price is normalized to US dollars per 1M tokens (input, output and cached input), taken from OpenRouter's public catalog and refreshed daily. Most providers bill the same unit, so rates are directly comparable.

What is cached input pricing?

Many providers discount input tokens that repeat across requests (for example a long system prompt). The cached-input column shows that discounted rate per 1M tokens; it can cut input costs by 50–90% on repetitive workloads.

How often do LLM API prices change?

Providers adjust list prices every few weeks, and new cheaper models launch constantly. This page is regenerated from a fresh catalog snapshot every day, and each model page shows its snapshot date.