LLMprices.dev - Compare LLM Pricing

4 min read Original article ↗

Meta: Llama 3.2 3B Instruct

$0.02$0.02131,072

Meta: Llama 3.1 8B Instruct

$0.02$0.03131,072$0.02$0.0432,768$0.04$0.04131,072$0.02$0.04131,072

Meta: Llama 3.2 11B Vision Instruct

$0.049$0.049131,072

Sao10K: Llama 3 8B Lunaris

$0.04$0.058,192

Mistral: Mistral 7B Instruct

$0.028$0.05432,768$0.02$0.06131,072

Meta: Llama 3 8B Instruct

$0.03$0.068,192$0.06$0.064,096$0.01703012$0.068153696,000

NousResearch: Hermes 2 Pro - Llama-3 8B

$0.025$0.088,192

Qwen: Qwen2.5 Coder 7B Instruct

$0.03$0.0932,768$0.03$0.098,192

Mistral: Ministral 3 3B 2512

$0.10$0.10131,072$0.05$0.1032,768$0.05$0.1032,768$0.10$0.10128,000

DeepSeek: DeepSeek R1 0528 Qwen3 8B

$0.02$0.1032,768

Nous: DeepHermes 3 Mistral 24B Preview

$0.02$0.1032,768$0.03$0.10131,072

Microsoft: Phi 4 Multimodal Instruct

$0.05$0.10131,072$0.10$0.10131,072

Qwen: Qwen2.5 7B Instruct

$0.04$0.1032,768$0.10$0.1032,768

Microsoft: Phi-3.5 Mini 128K Instruct

$0.10$0.10128,000

Microsoft: Phi-3 Mini 128K Instruct

$0.10$0.10128,000$0.017$0.11131,000$0.03$0.1132,768

Mistral: Mistral Small 3.1 24B

$0.03$0.11131,072$0.03$0.1132,768

DeepSeek: R1 Distill Llama 70B

$0.03$0.11131,072

Qwen2.5 Coder 32B Instruct

$0.03$0.1132,768

THUDM: GLM 4.1V 9B Thinking

$0.028$0.110465,536$0.028$0.1104128,000

Mistral: Devstral Small 2505

$0.06$0.12128,000

DeepSeek: R1 Distill Qwen 14B

$0.12$0.1232,768$0.03$0.14131,072$0.06$0.1416,384$0.035$0.14128,000

EssentialAI: Rnj 1 Instruct

$0.15$0.1532,768

Mistral: Ministral 3 8B 2512

$0.15$0.15262,144$0.045$0.15131,072$0.04$0.1596,000

Cohere: Command R7B (12-2024)

$0.0375$0.15128,000

NVIDIA: Nemotron Nano 9B V2

$0.04$0.16131,072

Mistral: Mistral Small 3.2 24B

$0.06$0.18131,072$0.18$0.18131,072$0.18$0.18163,840$0.039$0.19131,072

OpenAI: gpt-oss-120b (exacto)

$0.039$0.19131,072

Mistral: Mistral 7B Instruct v0.1

$0.11$0.192,824

Mistral: Ministral 3 14B 2512

$0.20$0.20262,144

AllenAI: Olmo 3 7B Instruct

$0.10$0.2065,536$0.12$0.2065,536$0.10$0.20128,000

AllenAI: Olmo 2 32B Instruct

$0.05$0.20128,000$0.05$0.201,000,000

Meta: Llama 3.2 1B Instruct

$0.027$0.2060,000

Qwen: Qwen2.5-VL 7B Instruct

$0.20$0.2032,768

Mistral: Mistral 7B Instruct v0.3

$0.20$0.2032,768$0.20$0.208,192

Mistral: Mistral 7B Instruct v0.2

$0.20$0.2032,768$0.05$0.22262,144$0.06$0.2240,960$0.05$0.2240,960

Qwen: Qwen2.5 VL 32B Instruct

$0.05$0.2216,384

Baidu: ERNIE 4.5 21B A3B Thinking

$0.056$0.224131,072$0.056$0.224120,000

NVIDIA: Nemotron 3 Nano 30B A3B

$0.06$0.24262,144$0.08$0.2440,960

DeepSeek: R1 Distill Qwen 32B

$0.24$0.2464,000$0.06$0.24300,000$0.25$0.2532,768

Qwen: Qwen2.5 VL 72B Instruct

$0.07$0.2632,768

Qwen: Qwen3 Coder 30B A3B Instruct

$0.07$0.27160,000

Mistral: Devstral Small 1.1

$0.07$0.28128,000

ByteDance Seed: Seed 1.6 Flash

$0.075$0.30262,144

Mistral: Mistral Small Creative

$0.10$0.3032,768

Mistral: Voxtral Small 24B 2507

$0.10$0.3032,000

OpenAI: gpt-oss-safeguard-20b

$0.075$0.30131,072$0.08$0.30327,680

Google: Gemini 2.0 Flash Lite

$0.075$0.301,048,576

Nous: Hermes 3 70B Instruct

$0.30$0.3065,536$0.224$0.32163,840

DeepSeek: DeepSeek V3.2 Exp

$0.21$0.32163,840

Meta: Llama 3.3 70B Instruct

$0.10$0.32131,072

Qwen: Qwen3 30B A3B Instruct 2507

$0.08$0.33262,144

Qwen: Qwen3 30B A3B Thinking 2507

$0.051$0.3432,768

Microsoft: Phi 4 Reasoning Plus

$0.07$0.3532,768$0.11$0.38131,072$0.10$0.3932,768$0.12$0.3932,768

Qwen: Qwen3 VL 8B Instruct

$0.064$0.40131,072

NVIDIA: Llama 3.3 Nemotron Super 49B V1.5

$0.10$0.40131,072

Google: Gemini 2.5 Flash Lite Preview 09-2025

$0.10$0.401,048,576

Tongyi DeepResearch 30B A3B

$0.09$0.40131,072$0.20$0.40256,000$0.05$0.40400,000

Google: Gemini 2.5 Flash Lite

$0.10$0.401,048,576$0.10$0.401,047,576$0.15$0.4032,768$0.10$0.401,048,576

TheDrummer: UnslopNemo 12B

$0.40$0.4032,768

Meta: Llama 3.2 90B Vision Instruct

$0.35$0.4032,768

Meta: Llama 3.1 70B Instruct

$0.40$0.40131,072

Meta: Llama 3 70B Instruct

$0.30$0.408,192

DeepSeek: DeepSeek V3.2 Speciale

$0.27$0.41163,840

TheDrummer: Rocinante 12B

$0.17$0.4332,768

Baidu: ERNIE 4.5 VL 28B A3B

$0.112$0.44830,000

Qwen: Qwen3 235B A22B Instruct 2507

$0.071$0.463262,144$0.48$0.4865,536$0.20$0.502,000,000

TheDrummer: Cydonia 24B V4.1

$0.30$0.50131,072$0.20$0.502,000,000$0.30$0.50131,072$0.30$0.50131,072$0.18$0.5440,960

Mistral: Mixtral 8x7B Instruct

$0.54$0.5432,768

Tencent: Hunyuan A13B Instruct

$0.14$0.57131,072

Cogito V2 Preview Llama 109B

$0.18$0.5932,767

NVIDIA: Nemotron Nano 12B 2 VL

$0.20$0.60131,072

Qwen: Qwen3 VL 30B A3B Instruct

$0.15$0.60262,144

Qwen: Qwen3 235B A22B Thinking 2507

$0.11$0.60262,144$0.15$0.601,048,576

OpenAI: GPT-4o-mini Search Preview

$0.15$0.60128,000$0.20$0.6032,768

NeverSleep: Lumimaid v0.2 8B

$0.09$0.6032,768

Cohere: Command R (08-2024)

$0.15$0.60128,000

OpenAI: GPT-4o-mini (2024-07-18)

$0.15$0.60128,000$0.15$0.60128,000$0.21$0.637,500$0.65$0.658,192$0.45$0.656,144$0.104$0.68131,072$0.15$0.7532,768

Sao10K: Llama 3.3 Euryale 70B

$0.65$0.75131,072

Sao10K: Llama 3.1 Euryale 70B v2.2

$0.65$0.7532,768

DeepSeek: DeepSeek V3.1 Terminus (exacto)

$0.21$0.79163,840

DeepSeek: DeepSeek V3.1 Terminus

$0.21$0.79163,840

Qwen: Qwen3 VL 30B A3B Thinking

$0.16$0.80131,072

Meituan: LongCat Flash Chat

$0.20$0.80131,072$0.50$0.8032,768

TheDrummer: Skyfall 36B V2

$0.55$0.8032,768

Deep Cogito: Cogito V2 Preview Llama 70B

$0.88$0.8832,768

Baidu: ERNIE 4.5 300B A47B

$0.224$0.88123,000

DeepSeek: DeepSeek V3 0324

$0.20$0.88163,840$0.30$0.90131,072$0.30$0.90256,000

Qwen: Qwen3 Coder 480B A35B

$0.22$0.95262,144$0.20$1.00196,608

Baidu: ERNIE 4.5 VL 424B A47B

$0.336$1.00123,000$0.25$1.00128,000$0.25$1.00128,000$1.00$1.00127,072

Nous: Hermes 3 405B Instruct

$1.00$1.00131,072

Microsoft: Phi-3 Medium 128K Instruct

$1.00$1.00128,000$0.75$1.008,000

Prime Intellect: INTELLECT-3

$0.20$1.10131,072

Qwen: Qwen3 Next 80B A3B Instruct

$0.09$1.10262,144$0.20$1.101,000,192$0.29$1.15131,072$0.30$1.20204,800$0.30$1.20163,840

Qwen: Qwen3 VL 235B A22B Thinking

$0.30$1.20262,144

Qwen: Qwen3 VL 235B A22B Instruct

$0.20$1.20262,144

Qwen: Qwen3 Next 80B A3B Thinking

$0.12$1.20131,072$0.40$1.201,000,000$0.30$1.20131,072

TNG: DeepSeek R1T2 Chimera

$0.30$1.20163,840$0.80$1.2081,920$0.75$1.20131,072

TNG: DeepSeek R1T Chimera

$0.30$1.20163,840$0.80$1.204,096

AlfredPros: CodeLLaMa 7B Instruct Solidity

$0.80$1.204,096$0.40$1.20131,072$0.30$1.20163,840$0.30$1.20163,840

NVIDIA: Llama 3.1 Nemotron 70B Instruct

$1.20$1.20131,072

Deep Cogito: Cogito v2.1 671B

$1.25$1.25128,000$0.85$1.25256,000

Anthropic: Claude 3 Haiku

$0.25$1.25200,000$0.70$1.40131,072$0.57$1.4265,536$0.48$1.4465,536

Sao10k: Llama 3 Euryale 70B v2.1

$1.48$1.488,192$0.40$1.50202,752

Mistral: Mistral Large 3 2512

$0.50$1.50262,144

Qwen: Qwen3 VL 32B Instruct

$0.50$1.50262,144$0.30$1.50128,000$0.20$1.50256,000$0.50$1.5016,385$0.35$1.55131,072$0.40$1.601,047,576

AionLabs: Aion-RP 1.0 (8B)

$0.80$1.6032,768

MoonshotAI: Kimi K2 Thinking

$0.40$1.75262,144$0.40$1.75163,840$1.00$1.754,096$0.44$1.76204,800

Qwen: Qwen3 Coder 480B A35B (exacto)

$0.22$1.80262,144

NVIDIA: Llama 3.1 Nemotron Ultra 253B v1

$0.60$1.80131,072$0.456$1.84131,072$0.39$1.90204,800$0.39$1.90262,144$0.90$1.90262,144$0.25$2.00262,144

OpenAI: GPT-5.1-Codex-Mini

$0.25$2.00400,000$2.50$2.00400,000

Mistral: Mistral Medium 3.1

$0.40$2.00131,072$0.25$2.00400,000$0.40$2.00131,072

Mistral: Mistral Medium 3

$0.40$2.00131,072

OpenAI: GPT-3.5 Turbo (older v0613)

$1.00$2.004,095

OpenAI: GPT-3.5 Turbo Instruct

$1.50$2.004,095

Qwen: Qwen3 VL 8B Thinking

$0.18$2.10256,000

DeepSeek: DeepSeek Prover V2

$0.50$2.18163,840$0.40$2.201,000,000$0.30$2.501,000,000

Google: Gemini 2.5 Flash Image (Nano Banana)

$0.30$2.5032,768

Google: Gemini 2.5 Flash Preview 09-2025

$0.30$2.501,048,576

MoonshotAI: Kimi K2 0905 (exacto)

$0.60$2.50262,144

Google: Gemini 2.5 Flash Image Preview (Nano Banana)

$0.30$2.5032,768$0.30$2.501,048,576

Google: Gemini 3 Flash Preview

$0.50$3.001,048,576$1.00$3.00256,000

Sao10K: Llama 3.1 70B Hanami x1

$3.00$3.0016,000$0.80$3.20131,072$0.80$3.20300,000

Arcee AI: Maestro Reasoning

$0.90$3.30131,072$0.85$3.40131,072

Deep Cogito: Cogito V2 Preview Llama 405B

$3.50$3.5032,768

Meta: Llama 3.1 405B Instruct

$3.50$3.5010,000

Qwen: Qwen Plus 0728 (thinking)

$0.40$4.001,000,000

Anthropic: Claude 3.5 Haiku

$0.80$4.00200,000

Anthropic: Claude 3.5 Haiku (2024-10-22)

$0.80$4.00200,000

Meta: Llama 3.1 405B (base)

$4.00$4.0032,768

OpenAI: GPT-3.5 Turbo 16k

$3.00$4.0016,385$1.10$4.40200,000$1.10$4.40200,000$1.10$4.40200,000$1.10$4.40200,000$4.50$4.5016,000

Anthropic: Claude Haiku 4.5

$1.00$5.00200,000$1.00$5.00128,000

Perplexity: Sonar Reasoning

$1.00$5.00127,000$3.00$5.0016,384$1.20$6.00256,000$1.50$6.00200,000$2.00$6.00131,072$2.00$6.00131,072

Mistral: Pixtral Large 2411

$2.00$6.00131,072

Mistral: Mixtral 8x22B Instruct

$2.00$6.0065,536$2.00$6.00128,000$1.60$6.4032,768

OpenAI: o4 Mini Deep Research

$2.00$8.00200,000$2.00$8.00256,000$2.00$8.00200,000$2.00$8.001,047,576

Perplexity: Sonar Reasoning Pro

$2.00$8.00128,000

Perplexity: Sonar Deep Research

$2.00$8.00128,000$4.00$8.00131,072$6.00$8.006,144

OpenAI: GPT-5.1-Codex-Max

$1.25$10.00400,000$1.25$10.00400,000$1.25$10.00128,000$1.25$10.00400,000$10.00$10.00400,000$1.25$10.00400,000$2.50$10.00128,000$1.25$10.00128,000$1.25$10.00400,000$1.25$10.001,048,576

Google: Gemini 2.5 Pro Preview 06-05

$1.25$10.001,048,576

Google: Gemini 2.5 Pro Preview 05-06

$1.25$10.001,048,576$2.50$10.00256,000

OpenAI: GPT-4o Search Preview

$2.50$10.00128,000

OpenAI: GPT-4o (2024-11-20)

$2.50$10.00128,000

Inflection: Inflection 3 Pi

$2.50$10.008,000

Inflection: Inflection 3 Productivity

$2.50$10.008,000

Cohere: Command R+ (08-2024)

$2.50$10.00128,000

OpenAI: GPT-4o (2024-08-06)

$2.50$10.00128,000$2.50$10.00128,000

Google: Nano Banana Pro (Gemini 3 Pro Image Preview)

$2.00$12.0065,536

Google: Gemini 3 Pro Preview

$2.00$12.001,048,576$2.50$12.501,000,000$1.75$14.00128,000$1.75$14.00400,000

Perplexity: Sonar Pro Search

$3.00$15.00200,000

Anthropic: Claude Sonnet 4.5

$3.00$15.001,000,000$3.00$15.00256,000$3.00$15.00131,072

Anthropic: Claude Sonnet 4

$3.00$15.001,000,000$3.00$15.00131,072$3.00$15.00200,000

Anthropic: Claude 3.7 Sonnet (thinking)

$3.00$15.00200,000

Anthropic: Claude 3.7 Sonnet

$3.00$15.00200,000$5.00$15.00128,000

OpenAI: GPT-4o (2024-05-13)

$5.00$15.00128,000

OpenAI: GPT-4o (extended)

$6.00$18.00128,000

Anthropic: Claude Opus 4.5

$5.00$25.00200,000

Anthropic: Claude 3.5 Sonnet

$6.00$30.00200,000$10.00$30.00128,000

OpenAI: GPT-4 Turbo Preview

$10.00$30.00128,000

OpenAI: GPT-4 Turbo (older v1106)

$10.00$30.00128,000$10.00$40.00200,000$15.00$60.00200,000

OpenAI: GPT-4 (older v0314)

$30.00$60.008,191$30.00$60.008,191

Anthropic: Claude Opus 4.1

$15.00$75.00200,000$15.00$75.00200,000$15.00$75.00200,000$20.00$80.00200,000$15.00$120.00400,000$21.00$168.00400,000$150.00$600.00200,000