LLM API Pricing Comparison
We currently track pricing for 412 models: 19 are free, the cheapest paid model is inclusionAI: Ling-2.6-flash at $0.01 per 1M input tokens, and the most expensive is OpenAI: o1-pro at $150. Refreshed weekly.
All 412 models — cheapest input first
| Model | Author | Input $/1M | Output $/1M | Context |
|---|---|---|---|---|
| OpenRouter: Fusion | openrouter | $-1000000.00 | $-1000000.00 | 1M |
| Auto Router | openrouter | $-1000000.00 | $-1000000.00 | 2M |
| Body Builder (beta) | openrouter | $-1000000.00 | $-1000000.00 | 128K |
| Auto Router (Beta) | openrouter | $-1000000.00 | $-1000000.00 | 2M |
| Pareto Code Router | openrouter | $-1000000.00 | $-1000000.00 | 2M |
| Poolside: Laguna XS 2.1 (free) | poolside | Free | Free | 262K |
| Cohere: North Mini Code (free) | cohere | Free | Free | 256K |
| NVIDIA: Nemotron 3.5 Content Safety (free) | nvidia | Free | Free | 128K |
| NVIDIA: Nemotron 3 Ultra (free) | nvidia | Free | Free | 1M |
| Google: Gemma 4 26B A4B (free) | Free | Free | 262K | |
| Google: Gemma 4 31B (free) | Free | Free | 262K | |
| Google: Lyria 3 Clip Preview | Free | Free | 1M | |
| NVIDIA: Nemotron 3 Super (free) | nvidia | Free | Free | 262K |
| Free Models Router | openrouter | Free | Free | 200K |
| NVIDIA: Nemotron 3 Nano 30B A3B (free) | nvidia | Free | Free | 256K |
| NVIDIA: Nemotron Nano 9B V2 (free) | nvidia | Free | Free | 128K |
| OpenAI: gpt-oss-20b (free) | openai | Free | Free | 131K |
| NVIDIA: Nemotron 3 Nano Omni (free) | nvidia | Free | Free | 256K |
| NVIDIA: Nemotron Nano 12B 2 VL (free) | nvidia | Free | Free | 128K |
| Google: Lyria 3 Pro Preview | Free | Free | 1M | |
| Poolside: Laguna S 2.1 (free) | poolside | Free | Free | 262K |
| Dots Studio: Dots3-Note Preview (free) | dots-studio | Free | Free | 512K |
| LiquidAI: LFM2.5-2.6B (free) | liquid | Free | Free | 128K |
| NVIDIA: Nemotron 3.5 Lightning (free) | nvidia | Free | Free | 1M |
| inclusionAI: Ling-2.6-flash | inclusionai | $0.01 | $0.03 | 262K |
| IBM: Granite 4.0 Micro | ibm-granite | $0.02 | $0.11 | 131K |
| Mistral: Mistral Nemo | mistralai | $0.02 | $0.03 | 131K |
| Ling-3.0-flash | inclusionai | $0.02 | $0.06 | 262K |
| Nex AGI: Nex-N2-Mini | nex-agi | $0.03 | $0.10 | 262K |
| OpenAI: GPT-5 Nano (batch) | openai | $0.03 | $0.20 | 400K |
| Meta: Llama 3.2 1B Instruct | meta-llama | $0.03 | $0.20 | 60K |
| OpenAI: gpt-oss-120b | openai | $0.03 | $0.17 | 131K |
| OpenAI: gpt-oss-20b | openai | $0.03 | $0.13 | 131K |
| Qwen: Qwen3.7 Flash | qwen | $0.03 | $0.13 | 1M |
| Upstage: Solar Pro 4 | upstage | $0.03 | $0.12 | 524K |
| Amazon: Nova Micro 1.0 | amazon | $0.04 | $0.14 | 128K |
| Cohere: Command R7B (12-2024) | cohere | $0.04 | $0.15 | 128K |
| Sao10K: Llama 3 8B Lunaris | sao10k | $0.04 | $0.05 | 8K |
| Qwen: Qwen3 30B A3B Instruct 2507 | qwen | $0.05 | $0.19 | 262K |
| IBM: Granite 4.1 8B | ibm-granite | $0.05 | $0.10 | 131K |
| NVIDIA: Nemotron 3 Nano 30B A3B | nvidia | $0.05 | $0.20 | 262K |
| OpenAI: GPT-5 Nano | openai | $0.05 | $0.40 | 400K |
| Mistral: Mistral Small 3 | mistralai | $0.05 | $0.08 | 33K |
| Google: Gemma 3 12B | $0.05 | $0.15 | 131K | |
| Meta: Llama 3.1 8B Instruct | meta-llama | $0.05 | $0.08 | 131K |
| Meta: Llama 3.2 3B Instruct | meta-llama | $0.05 | $0.33 | 131K |
| Google: Gemma 3 4B | $0.05 | $0.10 | 131K | |
| Google: Gemini 2.5 Flash Lite (batch) | $0.05 | $0.20 | 1M | |
| OpenAI: GPT-4.1 Nano (batch) | openai | $0.05 | $0.20 | 1M |
| Poolside: Laguna XS 2.1 | poolside | $0.06 | $0.12 | 262K |
| Z.ai: GLM 4.7 Flash | z-ai | $0.06 | $0.40 | 203K |
| Google: Gemma 3n 4B | $0.06 | $0.12 | 33K | |
| Amazon: Nova Lite 1.0 | amazon | $0.06 | $0.24 | 300K |
| MythoMax 13B | gryphe | $0.06 | $0.06 | 8K |
| Tencent: Hy3 preview | tencent | $0.06 | $0.21 | 262K |
| Qwen: Qwen3.5-Flash | qwen | $0.07 | $0.26 | 1M |
| Qwen: Qwen3 Coder 30B A3B Instruct | qwen | $0.07 | $0.28 | 262K |
| Microsoft: Phi 4 | microsoft | $0.07 | $0.14 | 16K |
| inclusionAI: Ring-2.6-1T | inclusionai | $0.07 | $0.63 | 262K |
| ByteDance Seed: Seed 1.6 Flash | bytedance-seed | $0.07 | $0.30 | 262K |
| OpenAI: gpt-oss-safeguard-20b | openai | $0.07 | $0.30 | 131K |
| inclusionAI: Ling-2.6-1T | inclusionai | $0.07 | $0.63 | 262K |
| OpenAI: GPT-4o-mini (batch) | openai | $0.07 | $0.30 | 128K |
| DeepSeek V4 Flash Latest | ~deepseek | $0.08 | $0.25 | 1M |
| Qwen: Qwen3 32B | qwen | $0.08 | $0.28 | 131K |
| Google: Gemma 3 27B | $0.08 | $0.45 | 262K | |
| NVIDIA: Nemotron 3 Super | nvidia | $0.08 | $0.40 | 1M |
| Qwen: Qwen3 235B A22B Instruct 2507 | qwen | $0.09 | $0.55 | 262K |
| Poolside: Laguna S 2.1 | poolside | $0.09 | $0.18 | 1M |
| Mistral: Mistral Small 3.2 24B | mistralai | $0.09 | $0.25 | 256K |
| OpenAI: GPT-5.6 Luna | openai | $0.10 | $0.60 | 1.1M |
| Google: Gemma 4 31B | $0.10 | $0.34 | 262K | |
| Reka Edge | rekaai | $0.10 | $0.10 | 16K |
| Qwen: Qwen3.5-9B | qwen | $0.10 | $0.15 | 262K |
| StepFun: Step 3.5 Flash | stepfun | $0.10 | $0.30 | 262K |
| Mistral: Voxtral Small 24B 2507 | mistralai | $0.10 | $0.30 | 32K |
| Mistral: Ministral 3 3B 2512 | mistralai | $0.10 | $0.10 | 131K |
| Qwen: Qwen3 Next 80B A3B Instruct | qwen | $0.10 | $1.10 | 262K |
| ByteDance: UI-TARS 7B | bytedance | $0.10 | $0.20 | 128K |
| OpenAI: GPT-4.1 Nano | openai | $0.10 | $0.40 | 1M |
| Meta: Llama 4 Scout | meta-llama | $0.10 | $0.30 | 1.3M |
| Reka Flash 3 | rekaai | $0.10 | $0.20 | 66K |
| Qwen: Qwen2.5 7B Instruct | qwen | $0.10 | $0.20 | 33K |
| Meta: Llama 3.3 70B Instruct | meta-llama | $0.10 | $0.32 | 131K |
| OpenAI: GPT-5.6 Luna Pro | openai | $0.10 | $0.60 | 1.1M |
| Google: Gemini 2.5 Flash Lite | $0.10 | $0.40 | 1M | |
| ByteDance Seed: Seed-2.0-Mini | bytedance-seed | $0.10 | $0.40 | 262K |
| OpenAI: GPT-5.6 Luna Pro (batch) | openai | $0.10 | $0.60 | 1.1M |
| OpenAI: GPT-5.6 Luna (batch) | openai | $0.10 | $0.60 | 1.1M |
| OpenAI: GPT-5.4 Nano (batch) | openai | $0.10 | $0.63 | 400K |
| NVIDIA: Nemotron 3.5 Lightning | nvidia | $0.10 | $0.25 | 1M |
| Qwen: Qwen3 VL 32B Instruct | qwen | $0.10 | $0.42 | 131K |
| Qwen: Qwen3 VL 8B Instruct | qwen | $0.12 | $0.46 | 262K |
| Qwen: Qwen3 8B | qwen | $0.12 | $0.46 | 131K |
| Google: Gemma 4 26B A4B | $0.12 | $0.40 | 262K | |
| Qwen: Qwen3 Coder Next | qwen | $0.12 | $0.80 | 262K |
| Qwen: Qwen3 14B | qwen | $0.12 | $0.24 | 131K |
| Qwen: Qwen3 30B A3B | qwen | $0.12 | $0.50 | 131K |
| Google: Gemini 3.1 Flash Lite (batch) | $0.13 | $0.75 | 1M | |
| OpenAI: GPT-5 Mini (batch) | openai | $0.13 | $1 | 400K |
| Qwen: Qwen3 VL 30B A3B Instruct | qwen | $0.13 | $0.52 | 262K |
| Nous: Hermes 4 70B | nousresearch | $0.13 | $0.40 | 131K |
| Z.ai: GLM 4.5 Air | z-ai | $0.13 | $0.85 | 131K |
| Tencent: Hy3 | tencent | $0.13 | $0.53 | 262K |
| DeepSeek: DeepSeek V4 Flash 0423 | deepseek | $0.14 | $0.28 | 1M |
| Xiaomi: MiMo-V2.5 | xiaomi | $0.14 | $0.28 | 1.1M |
| Tencent: Hunyuan A13B Instruct | tencent | $0.14 | $0.57 | 131K |
| DeepSeek: DeepSeek V4 Flash 0731 | deepseek | $0.14 | $0.28 | 1M |
| Perceptron: Perceptron Mk1 | perceptron | $0.15 | $1.50 | 33K |
| Qwen: Qwen3.6 35B A3B | qwen | $0.15 | $1 | 262K |
| Mistral: Mistral Small 4 | mistralai | $0.15 | $0.60 | 262K |
| Upstage: Solar Pro 3 | upstage | $0.15 | $0.60 | 131K |
| AllenAI: Olmo 3 32B Think | allenai | $0.15 | $0.50 | 66K |
| Mistral: Ministral 3 8B 2512 | mistralai | $0.15 | $0.15 | 262K |
| Qwen: Qwen3 Next 80B A3B Thinking | qwen | $0.15 | $1.20 | 262K |
| OpenAI: GPT-4o-mini | openai | $0.15 | $0.60 | 128K |
| OpenAI: GPT-4o-mini (2024-07-18) | openai | $0.15 | $0.60 | 128K |
| Cohere: Command R (08-2024) | cohere | $0.15 | $0.60 | 128K |
| Kwaipilot: KAT-Coder-Air V2.5 | kwaipilot | $0.15 | $0.60 | 256K |
| Google: Gemini 3.5 Flash Lite (batch) | $0.15 | $1.25 | 1M | |
| MiniMax: MiniMax M3 (batch) | minimax | $0.15 | $0.60 | 524K |
| Google: Gemini 2.5 Flash (batch) | $0.15 | $1.25 | 1M | |
| Qwen: Qwen3 VL 8B Thinking | qwen | $0.18 | $2.10 | 131K |
| Meta: Llama Guard 4 12B | meta-llama | $0.18 | $0.18 | 1M |
| Qwen: Qwen3.6 Flash | qwen | $0.19 | $1.13 | 1M |
| Google: Gemini 3.7 Flash (batch) | $0.19 | $0.94 | 1M | |
| Qwen: Qwen3.5-27B | qwen | $0.20 | $1.56 | 262K |
| Qwen: Qwen3 Coder Flash | qwen | $0.20 | $0.97 | 1M |
| StepFun: Step 3.7 Flash | stepfun | $0.20 | $1.15 | 262K |
| OpenAI: GPT-5.4 Nano | openai | $0.20 | $1.25 | 400K |
| Mistral: Ministral 3 14B 2512 | mistralai | $0.20 | $0.20 | 262K |
| Qwen: Qwen3 VL 30B A3B Thinking | qwen | $0.20 | $2.40 | 262K |
| Qwen: Qwen3 30B A3B Thinking 2507 | qwen | $0.20 | $2.40 | 82K |
| Venice: Uncensored | cognitivecomputations | $0.20 | $0.90 | 128K |
| Meta: Llama 4 Maverick | meta-llama | $0.20 | $0.70 | 1M |
| Mistral: Saba | mistralai | $0.20 | $0.60 | 33K |
| MiniMax: MiniMax-01 | minimax | $0.20 | $1.10 | 1M |
| OpenAI: GPT-4.1 Mini (batch) | openai | $0.20 | $0.80 | 1M |
| Arcee AI: Trinity Large Thinking | arcee-ai | $0.22 | $0.85 | 262K |
| MiniMax: MiniMax M2.5 | minimax | $0.22 | $0.90 | 205K |
| Qwen: Qwen3 235B A22B Thinking 2507 | qwen | $0.23 | $2.30 | 262K |
| Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) | $0.25 | $1.50 | 66K | |
| Nex AGI: Nex-N2-Pro | nex-agi | $0.25 | $1 | 262K |
| Google: Gemini 3.1 Flash Lite | $0.25 | $1.50 | 1M | |
| ByteDance Seed: Seed-2.0-Lite | bytedance-seed | $0.25 | $2 | 262K |
| Google: Gemini 3.1 Flash Lite Preview | $0.25 | $1.50 | 1M | |
| Inception: Mercury 2 | inception | $0.25 | $0.75 | 128K |
| ByteDance Seed: Seed 1.6 | bytedance-seed | $0.25 | $2 | 262K |
| OpenAI: GPT-5.1-Codex-Mini | openai | $0.25 | $2 | 400K |
| DeepSeek: DeepSeek V3.1 | deepseek | $0.25 | $0.95 | 164K |
| OpenAI: GPT-5 Mini | openai | $0.25 | $2 | 400K |
| Qwen: Qwen2.5 VL 72B Instruct | qwen | $0.25 | $0.75 | 128K |
| Anthropic: Claude 3 Haiku | anthropic | $0.25 | $1.25 | 200K |
| TheDrummer: Rocinante 12B | thedrummer | $0.25 | $0.50 | 66K |
| Qwen: Qwen3.5-35B-A3B | qwen | $0.25 | $1.25 | 262K |
| Google: Gemini 3 Flash Preview (batch) | $0.25 | $1.50 | 1M | |
| OpenAI: GPT-3.5 Turbo (batch) | openai | $0.25 | $0.75 | 16K |
| MiniMax: MiniMax M2 | minimax | $0.26 | $1.02 | 205K |
| DeepSeek: DeepSeek V3 | deepseek | $0.26 | $1.03 | 164K |
| Qwen: Qwen3.5 Plus 2026-02-15 | qwen | $0.26 | $1.56 | 1M |
| Qwen: Qwen3 VL 235B A22B Instruct | qwen | $0.26 | $1.04 | 262K |
| Qwen: Qwen Plus 0728 | qwen | $0.26 | $0.78 | 1M |
| Qwen: Qwen-Plus | qwen | $0.26 | $0.78 | 1M |
| DeepSeek: DeepSeek V3.2 | deepseek | $0.27 | $0.40 | 164K |
| DeepSeek: DeepSeek V3.2 Exp | deepseek | $0.27 | $0.41 | 164K |
| DeepSeek: DeepSeek V3 0324 | deepseek | $0.27 | $1.12 | 164K |
| DeepSeek: DeepSeek V3.1 Terminus | deepseek | $0.27 | $0.95 | 164K |
| Qwen: Qwen3.5-122B-A10B | qwen | $0.29 | $2.40 | 262K |
| MiniMax: MiniMax M3 | minimax | $0.30 | $1.20 | 1M |
| Qwen: Qwen3.5 Plus 2026-04-20 | qwen | $0.30 | $1.80 | 1M |
| Kwaipilot: KAT-Coder-Pro V2 | kwaipilot | $0.30 | $1.20 | 262K |
| MiniMax: MiniMax M2.7 | minimax | $0.30 | $1.20 | 205K |
| Z.ai: GLM 4.6V | z-ai | $0.30 | $0.90 | 131K |
| MiniMax: MiniMax M2.1 | minimax | $0.30 | $1.20 | 205K |
| Amazon: Nova 2 Lite | amazon | $0.30 | $2.50 | 1M |
| Google: Nano Banana (Gemini 2.5 Flash Image) | $0.30 | $2.50 | 33K | |
| Mistral: Codestral 2508 | mistralai | $0.30 | $0.90 | 256K |
| Qwen: Qwen3 Coder 480B A35B | qwen | $0.30 | $1 | 262K |
| Google: Gemini 2.5 Flash | $0.30 | $2.50 | 1M | |
| MiniMax: MiniMax M2-her | minimax | $0.30 | $1.20 | 66K |
| TheDrummer: Cydonia 24B V4.1 | thedrummer | $0.30 | $0.50 | 131K |
| Meituan: LongCat 2.0 | meituan | $0.30 | $1.20 | 1M |
| Google: Gemini 3.5 Flash Lite | $0.30 | $2.50 | 1M | |
| NVIDIA: Nemotron 3 Ultra (batch) | nvidia | $0.30 | $1.80 | 512K |
| Qwen: Qwen3.7 Plus | qwen | $0.32 | $1.28 | 1M |
| Qwen: Qwen3.6 Plus | qwen | $0.33 | $1.95 | 1M |
| Meta: Muse Glimmer 30B | meta | $0.35 | $1.50 | 131K |
| Mistral: Mistral Small 3.1 24B | mistralai | $0.35 | $0.55 | 128K |
| Qwen2.5 72B Instruct | qwen | $0.36 | $0.40 | 33K |
| Google Gemini Flash Latest | $0.38 | $1.88 | 1M | |
| Google: Gemini 3.6 Flash (batch) | $0.38 | $1.88 | 1M | |
| OpenAI: GPT-5.4 Mini (batch) | openai | $0.38 | $2.25 | 400K |
| Google: Gemini 3.7 Flash | $0.38 | $1.88 | 1M | |
| Z.ai: GLM 4.7 | z-ai | $0.40 | $1.75 | 205K |
| Qwen: Qwen Plus 0728 (thinking) | qwen | $0.40 | $1.20 | 1M |
| Qwen: Qwen3 VL 235B A22B Thinking | qwen | $0.40 | $4 | 131K |
| Mistral: Mistral Medium 3.1 | mistralai | $0.40 | $2 | 131K |
| OpenAI: GPT-4.1 Mini | openai | $0.40 | $1.60 | 1M |
| TheDrummer: UnslopNemo 12B | thedrummer | $0.40 | $0.40 | 1M |
| Meta: Llama 3.1 70B Instruct | meta-llama | $0.40 | $0.40 | 131K |
| Mistral: Mistral Medium 3 | mistralai | $0.40 | $2 | 131K |
| Baidu: ERNIE 4.5 VL 424B A47B | baidu | $0.42 | $1.25 | 123K |
| Xiaomi: MiMo-V2.5-Pro | xiaomi | $0.43 | $0.87 | 1.1M |
| DeepSeek: DeepSeek V4 Pro 0813 | deepseek | $0.43 | $0.87 | 1M |
| ReMM SLERP 13B | undi95 | $0.45 | $0.65 | 6K |
| Thinking Machines: Inkling Small | thinkingmachines | $0.45 | $1.20 | 524K |
| Qwen: Qwen3 235B A22B | qwen | $0.46 | $1.82 | 131K |
| MoonshotAI: Kimi K2.7 Code (batch) | moonshotai | $0.47 | $2 | 262K |
| Google: Nano Banana 2 (Gemini 3.1 Flash Image) | $0.50 | $3 | 131K | |
| Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview) | $0.50 | $3 | 66K | |
| Qwen: Qwen3.5 397B A17B | qwen | $0.50 | $3.60 | 262K |
| Google: Gemini 3 Flash Preview | $0.50 | $3 | 1M | |
| Mistral: Mistral Large 3 2512 | mistralai | $0.50 | $1.50 | 262K |
| Z.ai: GLM 4.6 | z-ai | $0.50 | $2 | 205K |
| DeepSeek: R1 0528 | deepseek | $0.50 | $2.15 | 164K |
| Mancer: Weaver (alpha) | mancer | $0.50 | $0.75 | 8K |
| OpenAI: GPT-3.5 Turbo | openai | $0.50 | $1.50 | 16K |
| Thinking Machines: Inkling (batch) | thinkingmachines | $0.50 | $2.02 | 524K |
| ByteDance Seed: Seed 2.1 Turbo | bytedance-seed | $0.50 | $2.50 | 262K |
| ByteDance Seed: Seed-2.0-Code | bytedance-seed | $0.50 | $3 | 262K |
| Anthropic: Claude Haiku 4.5 (batch) | anthropic | $0.50 | $2.50 | 200K |
| MiniMax: MiniMax M1 | minimax | $0.55 | $2.20 | 1M |
| TheDrummer: Skyfall 36B V2 | thedrummer | $0.55 | $0.80 | 33K |
| OpenAI: o4 Mini High (batch) | openai | $0.55 | $2.20 | 200K |
| OpenAI: o4 Mini (batch) | openai | $0.55 | $2.20 | 200K |
| OpenAI: o3 Mini High (batch) | openai | $0.55 | $2.20 | 200K |
| OpenAI: o3 Mini (batch) | openai | $0.55 | $2.20 | 200K |
| MoonshotAI: Kimi K2.5 | moonshotai | $0.57 | $2.85 | 262K |
| MoonshotAI: Kimi K2 0711 | moonshotai | $0.57 | $2.30 | 131K |
| NVIDIA: Nemotron 3 Ultra | nvidia | $0.60 | $3.60 | 512K |
| Qwen: Qwen3.6 27B | qwen | $0.60 | $3.60 | 262K |
| Writer: Palmyra X5 | writer | $0.60 | $6 | 1M |
| OpenAI: GPT Audio Mini | openai | $0.60 | $2.40 | 128K |
| MoonshotAI: Kimi K2 Thinking | moonshotai | $0.60 | $2.50 | 262K |
| MoonshotAI: Kimi K2 0905 | moonshotai | $0.60 | $2.50 | 262K |
| Z.ai: GLM 4.5 | z-ai | $0.60 | $2.20 | 131K |
| Z.ai: GLM 4.5V | z-ai | $0.60 | $1.80 | 66K |
| WizardLM-2 8x22B | microsoft | $0.62 | $0.62 | 66K |
| OpenAI: GPT-5.1 (batch) | openai | $0.63 | $5 | 400K |
| OpenAI: GPT-5 Codex (batch) | openai | $0.63 | $5 | 400K |
| OpenAI: GPT-5 (batch) | openai | $0.63 | $5 | 400K |
| Google: Gemini 2.5 Pro (batch) | $0.63 | $5 | 1M | |
| Z.ai: GLM 5.2 | z-ai | $0.63 | $1.98 | 1M |
| Qwen: Qwen3 Coder Plus | qwen | $0.65 | $3.25 | 1M |
| Sao10K: Llama 3.3 Euryale 70B | sao10k | $0.65 | $0.75 | 131K |
| Google: Gemma 2 27B | $0.65 | $0.65 | 8K | |
| Qwen2.5 Coder 32B Instruct | qwen | $0.66 | $1 | 33K |
| MoonshotAI: Kimi K2.7 Code | moonshotai | $0.67 | $3.40 | 262K |
| AionLabs: Aion-3.0-Mini | aion-labs | $0.70 | $1.40 | 131K |
| DeepSeek: R1 | deepseek | $0.70 | $2.50 | 64K |
| Nous: Hermes 3 70B Instruct | nousresearch | $0.70 | $0.70 | 131K |
| Z.ai: GLM 5.2 (batch) | z-ai | $0.70 | $2.20 | 512K |
| Kwaipilot: KAT-Coder-Pro V2.5 | kwaipilot | $0.74 | $2.96 | 256K |
| OpenAI GPT Mini Latest | ~openai | $0.75 | $4.50 | 400K |
| OpenAI: GPT-5.4 Mini | openai | $0.75 | $4.50 | 400K |
| Arcee AI: Virtuoso Large | arcee-ai | $0.75 | $1.20 | 131K |
| Google: Gemini 3.6 Flash | $0.75 | $3.75 | 1M | |
| Google: Gemini 3.5 Flash (batch) | $0.75 | $4.50 | 1M | |
| Qwen: Qwen3 Max Thinking | qwen | $0.78 | $3.90 | 262K |
| Qwen: Qwen3 Max | qwen | $0.78 | $3.90 | 262K |
| AionLabs: Aion-2.0 | aion-labs | $0.80 | $1.60 | 131K |
| Morph: Morph V3 Fast | morph | $0.80 | $1.20 | 82K |
| AionLabs: Aion-RP 1.0 (8B) | aion-labs | $0.80 | $1.60 | 33K |
| Amazon: Nova Pro 1.0 | amazon | $0.80 | $3.20 | 300K |
| DeepSeek: R1 Distill Llama 70B | deepseek | $0.80 | $0.80 | 8K |
| Sao10K: Llama 3.1 Euryale 70B v2.2 | sao10k | $0.85 | $0.85 | 131K |
| Relace: Relace Apply 3 | relace | $0.85 | $1.25 | 256K |
| OpenAI: GPT-5.2 (batch) | openai | $0.88 | $7 | 400K |
| Morph: Morph V3 Large | morph | $0.90 | $1.90 | 262K |
| MoonshotAI: Kimi K2.6 | moonshotai | $0.95 | $4 | 262K |
| Z.ai: GLM 5 | z-ai | $0.95 | $2.55 | 205K |
| Thinking Machines: Inkling | thinkingmachines | $0.95 | $4.05 | 1M |
| Sakana: Sakana Namazu | sakana | $0.95 | $4 | 262K |
| OpenAI: GPT-5.6 Terra | openai | $1 | $6 | 1.1M |
| SpaceXAI: Grok Build 0.1 | x-ai | $1 | $2 | 256K |
| Anthropic Claude Haiku Latest | ~anthropic | $1 | $5 | 200K |
| Relace: Relace Search | relace | $1 | $3 | 256K |
| Anthropic: Claude Haiku 4.5 | anthropic | $1 | $5 | 200K |
| Nous: Hermes 4 405B | nousresearch | $1 | $3 | 131K |
| Perplexity: Sonar | perplexity | $1 | $1 | 127K |
| Nous: Hermes 3 405B Instruct | nousresearch | $1 | $1 | 131K |
| OpenAI: GPT-3.5 Turbo (older v0613) | openai | $1 | $2 | 4K |
| OpenAI: GPT-5.6 Terra Pro | openai | $1 | $6 | 1.1M |
| OpenAI: GPT-5.6 Terra Pro (batch) | openai | $1 | $6 | 1.1M |
| OpenAI: GPT-5.6 Terra (batch) | openai | $1 | $6 | 1.1M |
| Anthropic: Claude Sonnet 5 (batch) | anthropic | $1 | $5 | 1M |
| Google: Gemini 3.1 Pro Preview (batch) | $1 | $6 | 1M | |
| OpenAI: o3 (batch) | openai | $1 | $4 | 200K |
| OpenAI: GPT-4.1 (batch) | openai | $1 | $4 | 1M |
| Qwen: Qwen3.6 Max Preview | qwen | $1.03 | $6.16 | 262K |
| OpenAI: o4 Mini | openai | $1.10 | $4.40 | 200K |
| OpenAI: o4 Mini High | openai | $1.10 | $4.40 | 200K |
| OpenAI: o3 Mini | openai | $1.10 | $4.40 | 200K |
| OpenAI: o3 Mini High | openai | $1.10 | $4.40 | 200K |
| DeepSeek: DeepSeek V4 Pro | deepseek | $1.17 | $2.34 | 1M |
| Z.ai: GLM 5V Turbo | z-ai | $1.20 | $4 | 203K |
| Z.ai: GLM 5 Turbo | z-ai | $1.20 | $4 | 203K |
| SpaceXAI: Grok 4.3 | x-ai | $1.25 | $2.50 | 1M |
| SpaceXAI: Grok 4.20 Multi-Agent | x-ai | $1.25 | $2.50 | 2M |
| SpaceXAI: Grok 4.20 | x-ai | $1.25 | $2.50 | 2M |
| Deep Cogito: Cogito v2.1 671B | deepcogito | $1.25 | $1.25 | 128K |
| OpenAI: GPT-5.1 | openai | $1.25 | $10 | 400K |
| OpenAI: GPT-5.1-Codex-Max | openai | $1.25 | $10 | 400K |
| OpenAI: GPT-5.1-Codex | openai | $1.25 | $10 | 400K |
| OpenAI: GPT-5 | openai | $1.25 | $10 | 400K |
| Google: Gemini 2.5 Pro | $1.25 | $10 | 1M | |
| Google: Gemini 2.5 Pro Preview 05-06 | $1.25 | $10 | 1M | |
| Google: Gemini 2.5 Pro Preview 06-05 | $1.25 | $10 | 1M | |
| Meta: Muse Spark 1.1 | meta | $1.25 | $4.25 | 1M |
| Meta: Muse Spark 1.2 | meta | $1.25 | $4.25 | 1M |
| OpenAI: GPT-5.4 (batch) | openai | $1.25 | $7.50 | 1.1M |
| OpenAI: GPT-4o (batch) | openai | $1.25 | $5 | 128K |
| Z.ai: GLM 5.1 | z-ai | $1.40 | $4.40 | 205K |
| Qwen: Qwen3.7 Max | qwen | $1.48 | $4.42 | 1M |
| Google: Gemini 3.5 Flash | $1.50 | $9 | 1M | |
| Mistral: Mistral Medium 3.5 | mistralai | $1.50 | $7.50 | 262K |
| OpenAI: GPT-3.5 Turbo Instruct | openai | $1.50 | $2 | 4K |
| Anthropic: Claude Sonnet 4.6 (batch) | anthropic | $1.50 | $7.50 | 1M |
| Anthropic: Claude Sonnet 4.5 (batch) | anthropic | $1.50 | $7.50 | 1M |
| OpenAI: GPT-5.2 Chat | openai | $1.75 | $14 | 128K |
| OpenAI: GPT-5.2 | openai | $1.75 | $14 | 400K |
| OpenAI: GPT-5.2-Codex | openai | $1.75 | $14 | 400K |
| OpenAI: GPT-5.3-Codex | openai | $1.75 | $14 | 400K |
| Google: Nano Banana Pro (Gemini 3 Pro Image) | $2 | $12 | 131K | |
| SpaceXAI: Grok 4.5 | x-ai | $2 | $6 | 500K |
| xAI: Grok Latest | ~x-ai | $2 | $6 | 500K |
| Anthropic: Claude Sonnet 5 | anthropic | $2 | $10 | 1M |
| Anthropic Claude Sonnet Latest | ~anthropic | $2 | $10 | 1M |
| Google Gemini Pro Latest | $2 | $12 | 1M | |
| Google: Gemini 3.1 Pro Preview | $2 | $12 | 1M | |
| Google: Gemini 3.1 Pro Preview Custom Tools | $2 | $12 | 1M | |
| Google: Nano Banana Pro (Gemini 3 Pro Image Preview) | $2 | $12 | 66K | |
| AI21: Jamba Large 1.7 | ai21 | $2 | $8 | 256K |
| OpenAI: o3 | openai | $2 | $8 | 200K |
| OpenAI: GPT-4.1 | openai | $2 | $8 | 1M |
| Perplexity: Sonar Deep Research | perplexity | $2 | $8 | 128K |
| Perplexity: Sonar Reasoning Pro | perplexity | $2 | $8 | 128K |
| Mistral Large 2407 | mistralai | $2 | $6 | 131K |
| Mistral: Mixtral 8x22B Instruct | mistralai | $2 | $6 | 66K |
| Mistral Large | mistralai | $2 | $6 | 128K |
| Qwen: Qwen3.8 Max | qwen | $2 | $6 | 1M |
| Qwen: Qwen3.8 2.4T A95B | qwen | $2 | $6 | 1M |
| SpaceXAI: Grok 4.6 | x-ai | $2 | $6 | 500K |
| OpenAI: GPT-5.4 | openai | $2.50 | $15 | 1.1M |
| OpenAI: GPT Audio | openai | $2.50 | $10 | 128K |
| Amazon: Nova Premier 1.0 | amazon | $2.50 | $12.50 | 1M |
| OpenAI: GPT-5 Image Mini | openai | $2.50 | $2 | 400K |
| Cohere: Command A | cohere | $2.50 | $10 | 256K |
| OpenAI: GPT-4o (2024-11-20) | openai | $2.50 | $10 | 128K |
| OpenAI: GPT-4o (2024-08-06) | openai | $2.50 | $10 | 128K |
| Cohere: Command R+ (08-2024) | cohere | $2.50 | $10 | 128K |
| OpenAI: GPT-4o | openai | $2.50 | $10 | 128K |
| Claude Opus 5 (batch) | anthropic | $2.50 | $12.50 | 1M |
| OpenAI: GPT-5.6 Sol Pro (batch) | openai | $2.50 | $15 | 1.1M |
| OpenAI: GPT-5.6 Sol (batch) | openai | $2.50 | $15 | 1.1M |
| Anthropic: Claude Opus 4.8 (batch) | anthropic | $2.50 | $12.50 | 1M |
| OpenAI: GPT-5.5 (batch) | openai | $2.50 | $15 | 1.1M |
| Anthropic: Claude Opus 4.7 (batch) | anthropic | $2.50 | $12.50 | 1M |
| Anthropic: Claude Opus 4.6 (batch) | anthropic | $2.50 | $12.50 | 1M |
| Anthropic: Claude Opus 4.5 (batch) | anthropic | $2.50 | $12.50 | 200K |
| MoonshotAI Kimi Latest | ~moonshotai | $2.80 | $14 | 1M |
| AionLabs: Aion-3.0 | aion-labs | $3 | $6 | 131K |
| Anthropic: Claude Sonnet 4.6 | anthropic | $3 | $15 | 1M |
| Perplexity: Sonar Pro Search | perplexity | $3 | $15 | 200K |
| Anthropic: Claude Sonnet 4.5 | anthropic | $3 | $15 | 1M |
| Anthropic: Claude Sonnet 4 | anthropic | $3 | $15 | 1M |
| Perplexity: Sonar Pro | perplexity | $3 | $15 | 200K |
| OpenAI: GPT-3.5 Turbo 16k | openai | $3 | $4 | 16K |
| MoonshotAI: Kimi K3 | moonshotai | $3 | $15 | 1M |
| Magnum v4 72B | anthracite-org | $3 | $5 | 33K |
| Sakana: Fugu Ultra | sakana | $5 | $30 | 1M |
| OpenAI: GPT-5.6 Sol | openai | $5 | $30 | 1.1M |
| OpenAI: GPT-5.6 Sol Pro | openai | $5 | $30 | 1.1M |
| Anthropic: Claude Opus 4.8 | anthropic | $5 | $25 | 1M |
| OpenAI GPT Latest | ~openai | $5 | $30 | 1.1M |
| OpenAI: GPT-5.5 | openai | $5 | $30 | 1.1M |
| Anthropic: Claude Opus Latest | ~anthropic | $5 | $25 | 1M |
| Anthropic: Claude Opus 4.7 | anthropic | $5 | $25 | 1M |
| Anthropic: Claude Opus 4.6 | anthropic | $5 | $25 | 1M |
| OpenAI: GPT Chat Latest | openai | $5 | $30 | 400K |
| OpenAI: GPT-4o (2024-05-13) | openai | $5 | $15 | 128K |
| Anthropic: Claude Opus 4.5 | anthropic | $5 | $25 | 200K |
| Claude Opus 5 | anthropic | $5 | $25 | 1M |
| OpenAI: GPT-4 Turbo (batch) | openai | $5 | $15 | 128K |
| Anthropic: Claude Fable 5 (batch) | anthropic | $5 | $25 | 1M |
| OpenAI: GPT-5 Pro (batch) | openai | $7.50 | $60 | 400K |
| Anthropic: Claude Opus 4.1 (batch) | anthropic | $7.50 | $37.50 | 200K |
| OpenAI: o1 (batch) | openai | $7.50 | $30 | 200K |
| OpenAI: GPT-5.4 Image 2 | openai | $8 | $15 | 272K |
| Anthropic: Claude Fable 5 | anthropic | $10 | $50 | 1M |
| Anthropic: Claude Fable Latest | ~anthropic | $10 | $50 | 1M |
| OpenAI: GPT-5 Image | openai | $10 | $10 | 400K |
| OpenAI: GPT-4 Turbo | openai | $10 | $30 | 128K |
| OpenAI: GPT-4 Turbo Preview | openai | $10 | $30 | 128K |
| Anthropic: Claude Opus 4.8 (Fast) | anthropic | $10 | $50 | 1M |
| Claude Opus 5 (Fast) | anthropic | $10 | $50 | 1M |
| OpenAI: o3 Pro (batch) | openai | $10 | $40 | 200K |
| OpenAI: GPT-5.2 Pro (batch) | openai | $10.50 | $84 | 400K |
| OpenAI: GPT-5 Pro | openai | $15 | $120 | 400K |
| Anthropic: Claude Opus 4.1 | anthropic | $15 | $75 | 200K |
| Anthropic: Claude Opus 4 | anthropic | $15 | $75 | 200K |
| OpenAI: o1 | openai | $15 | $60 | 200K |
| OpenAI: GPT-5.5 Pro (batch) | openai | $15 | $90 | 1.1M |
| OpenAI: GPT-5.4 Pro (batch) | openai | $15 | $90 | 1.1M |
| OpenAI: o3 Pro | openai | $20 | $80 | 200K |
| OpenAI: GPT-5.2 Pro | openai | $21 | $168 | 400K |
| Anthropic: Claude Opus 4.7 (Fast) | anthropic | $30 | $150 | 1M |
| OpenAI: GPT-5.5 Pro | openai | $30 | $180 | 1.1M |
| OpenAI: GPT-5.4 Pro | openai | $30 | $180 | 1.1M |
| OpenAI: GPT-4 | openai | $30 | $60 | 8K |
| OpenAI: o1-pro (batch) | openai | $75 | $300 | 200K |
| OpenAI: o1-pro | openai | $150 | $600 | 200K |
Get notified when LLM prices change
This table refreshes weekly. We email you when prices move — once a week, no spam.
FAQ
Which LLM is cheapest per 1M input tokens?
As of the week of 2026-08-10, inclusionAI: Ling-2.6-flash is the cheapest paid model at $0.01 per 1M input tokens; the priciest is OpenAI: o1-pro at $150 — a gap of roughly 15000x. 19 models are free to use.
Which LLM has the cheapest output tokens?
inclusionAI: Ling-2.6-flash, at $0.03 per 1M output tokens. For generation-heavy jobs this number matters more than the input price.
Which LLM has the largest context window?
Auto Router, at 2M tokens among the models we track. If you feed whole documents in, check this column alongside price.
How is LLM API pricing calculated?
Most LLM APIs charge per token, with separate rates for input (prompt) and output (completion) tokens — output is usually pricier. Prices on this page are USD per 1M tokens.
Pricing data comes from the OpenRouter catalog and refreshes weekly.