LLM API pricing by model
Updated
Prices for 428 models from 41 providers, 1,671 prices in all, each read from the provider's own pricing page with a source link and date (newest check 2026-11-15). Each model page lists every provider's input, cached-input and output price, the maker's own price, service tiers and the monthly cost of three real workloads.
An LLM API is priced per million tokens, with separate prices for input, cached input and output. For open-weight models such as DeepSeek, Qwen, GLM, Kimi and Llama, many providers serve the same weights at very different prices. 160 of the 428 models have a price on their maker's own API. The table below lists the 198 models with a standard price from 2 or more providers. The other 230 have a single provider; they are in a compact list of single-provider models, and their pages are kept out of search results until a second provider lists them.
Looking for the lowest price? The cheapest LLM APIs right now ranks the models on one blended price, overall and by size. The price change log lists every price that moved between our checks. Prices by provider lists each provider's full price list and tiers, and prices by model maker groups the models by the company that made them.
| Model | Maker | Providers | Cheapest input | Cheapest output | Cheapest blended 3:1 | Median in / out | Maker's price in / out | Max context |
|---|---|---|---|---|---|---|---|---|
| Qwen · 35 models | ||||||||
| Qwen 2.5 7B | Qwen | 3 | USD 0.05 | USD 0.05 | USD 0.05 | USD 0.05 / USD 0.13 | — | 32,768 |
| Qwen3-8B | Qwen | 2 | USD 0.06 | USD 0.06 | USD 0.06 | USD 0.0885 / USD 0.2575 | — | 131,072 |
| Qwen3.5 9B | Qwen | 4 | USD 0.10 | USD 0.15 | USD 0.1125 | USD 0.135 / USD 0.20 | — | 262,144 |
| Qwen3 30B A3B (fp8) | Qwen | 3 | USD 0.051 | USD 0.25 | USD 0.122 | USD 0.08 / USD 0.335 | — | 40,960 |
| Qwen3 Coder 30B A3B | Qwen | 3 | USD 0.07 | USD 0.28 | USD 0.1225 | USD 0.125 / USD 0.45 | — | 262,144 |
| Qwen3-14B | Qwen | 3 | USD 0.07 | USD 0.24 | USD 0.1225 | USD 0.12 / USD 0.24 | — | 131,072 |
| Qwen3 32B FP8 | Qwen | 5 | USD 0.08 | USD 0.28 | USD 0.13 | USD 0.102 / USD 0.57 | — | 131,072 |
| Qwen3-30B-A3B-Instruct-2507 | Qwen | 2 | USD 0.09 | USD 0.30 | USD 0.1425 | USD 0.1075 / USD 0.375 | — | 262,144 |
| Qwen3 235B A22B Instruct 2507 FP8 | Qwen | 5 | USD 0.0875 | USD 0.35 | USD 0.1531 | USD 0.14 / USD 0.75 | — | 262,144 |
| Qwen3.8 Flash | Qwen | 5 | USD 0.113 | USD 0.382 | USD 0.1803 | USD 0.15 / USD 0.47 | USD 0.15 / USD 0.47 | 1,048,575 |
| Qwen3 VL 30B A3B Instruct | Qwen | 4 | USD 0.15 | USD 0.50 | USD 0.2375 | USD 0.175 / USD 0.65 | — | 262,144 |
| Qwen3 Coder Next | Qwen | 3 | USD 0.12 | USD 0.80 | USD 0.29 | USD 0.16 / USD 1.15 | — | 32,768 |
| Qwen3.6 35B A3B | Qwen | 10 | USD 0.10 | USD 0.89 | USD 0.2975 | USD 0.168 / USD 1.0569 | USD 0.375 / USD 2.25 | 262,144 |
| Qwen3-VL 8B | Qwen | 2 | USD 0.18 | USD 0.68 | USD 0.305 | USD 0.215 / USD 0.715 | — | 262,144 |
| Qwen3.8 27B · also on BroadNet | Qwen | 15 | USD 0.039 | USD 1.25 | USD 0.3417 | USD 0.40 / USD 3 | USD 0.50 / USD 3 | 1,000,000 |
| Qwen3 Next 80B A3B Instruct | Qwen | 5 | USD 0.09 | USD 1.10 | USD 0.3425 | USD 0.125 / USD 1.15 | — | 262,144 |
| Qwen3.5 35B A3B | Qwen | 7 | USD 0.14 | USD 1 | USD 0.355 | USD 0.24 / USD 1.80 | USD 0.25 / USD 2 | 262,144 |
| Qwen2.5-72B-Instruct | Qwen | 3 | USD 0.36 | USD 0.40 | USD 0.37 | USD 0.37 / USD 0.40 | — | 32,768 |
| Qwen3 VL 235B A22B | Qwen | 3 | USD 0.20 | USD 0.88 | USD 0.37 | USD 0.21 / USD 1.90 | — | 262,144 |
| Qwen-MT Plus | Qwen | 2 | USD 0.25 | USD 0.75 | USD 0.375 | USD 1.355 / USD 4.06 | USD 2.46 / USD 7.37 | 16,384 |
| Qwen3 235B A22B FP8 | Qwen | 2 | USD 0.17 | USD 1.09 | USD 0.40 | USD 0.3125 / USD 1.455 | — | 32,768 |
| Qwen3 Next 80B A3B Thinking | Qwen | 2 | USD 0.15 | USD 1.20 | USD 0.4125 | USD 0.15 / USD 1.35 | — | 262,144 |
| Qwen3 Coder 480B A35B | Qwen | 6 | USD 0.22 | USD 1 | USD 0.4375 | USD 0.325 / USD 1.525 | — | 262,144 |
| Qwen3.7 Plus | Qwen | 2 | USD 0.32 | USD 1.28 | USD 0.56 | USD 0.36 / USD 1.44 | USD 0.40 / USD 1.60 | — |
| Qwen3.5 27B | Qwen | 7 | USD 0.20 | USD 1.75 | USD 0.5875 | USD 0.30 / USD 2.40 | USD 0.30 / USD 2.40 | 262,144 |
| Qwen3.6 27B | Qwen | 7 | USD 0.25 | USD 2 | USD 0.6875 | USD 0.32 / USD 3.20 | USD 0.60 / USD 3.60 | 262,144 |
| Qwen3.5 122B A10B | Qwen | 4 | USD 0.26 | USD 2.08 | USD 0.715 | USD 0.40 / USD 3.20 | USD 0.40 / USD 3.20 | 262,144 |
| Qwen2.5 Coder 32B Instruct | Qwen | 2 | USD 0.66 | USD 1 | USD 0.745 | USD 0.67 / USD 1.10 | — | 32,768 |
| Qwen3.5 397B A17B | Qwen | 7 | USD 0.45 | USD 3 | USD 1.087 | USD 0.55 / USD 3.60 | USD 0.60 / USD 3.60 | 262,144 |
| Qwen3.6 Plus | Qwen | 3 | USD 0.50 | USD 3 | USD 1.125 | USD 0.50 / USD 3 | USD 0.50 / USD 3 | 262,144 |
| Qwen3 235B A22B Thinking 2507 FP8 | Qwen | 3 | USD 0.35 | USD 3.50 | USD 1.212 | USD 0.45 / USD 3.50 | — | 131,072 |
| Qwen3.8 2.4T A95B | Qwen | 6 | USD 1 | USD 4 | USD 1.75 | USD 2 / USD 6 | USD 2 / USD 6 | 1,048,576 |
| Qwen3.7 Max | Qwen | 5 | USD 1.25 | USD 3.75 | USD 1.875 | USD 2.50 / USD 7.50 | USD 2.50 / USD 7.50 | 1,000,000 |
| Qwen3.8 Max | Qwen | 6 | USD 1.65 | USD 4.951 | USD 2.475 | USD 2 / USD 6 | USD 2 / USD 6 | 1,000,000 |
| Qwen3.8 Max (0902) | Qwen | 3 | USD 1.65 | USD 4.951 | USD 2.475 | USD 2 / USD 6 | USD 2 / USD 6 | 1,000,000 |
| OpenAI · 30 models | ||||||||
| GPT OSS 20B | OpenAI | 10 | USD 0.018 | USD 0.09 | USD 0.036 | USD 0.04 / USD 0.19 | — | 131,072 |
| OpenAI GPT OSS 120B | OpenAI | 21 | USD 0.03 | USD 0.17 | USD 0.065 | USD 0.10 / USD 0.60 | — | 131,072 |
| GPT OSS Safeguard 20B | OpenAI | 3 | USD 0.07 | USD 0.20 | USD 0.1025 | USD 0.075 / USD 0.30 | — | 131,072 |
| GPT-5 Nano | OpenAI | 3 | USD 0.05 | USD 0.40 | USD 0.1375 | USD 0.05 / USD 0.40 | USD 0.05 / USD 0.40 | — |
| GPT-6 Luna | OpenAI | 6 | USD 0.10 | USD 0.50 | USD 0.20 | USD 0.10 / USD 0.50 | USD 0.10 / USD 0.50 | 1,050,000 |
| GPT-4o mini | OpenAI | 3 | USD 0.15 | USD 0.60 | USD 0.2625 | USD 0.15 / USD 0.60 | USD 0.15 / USD 0.60 | — |
| GPT-5.6 Luna | OpenAI | 6 | USD 0.20 | USD 1.20 | USD 0.45 | USD 0.20 / USD 1.20 | USD 0.20 / USD 1.20 | 1,050,000 |
| GPT-5.4 Nano | OpenAI | 3 | USD 0.20 | USD 1.25 | USD 0.4625 | USD 0.20 / USD 1.25 | USD 0.20 / USD 1.25 | — |
| GPT-5 Mini | OpenAI | 3 | USD 0.25 | USD 2 | USD 0.6875 | USD 0.25 / USD 2 | USD 0.25 / USD 2 | — |
| GPT-4.1 Mini | OpenAI | 2 | USD 0.40 | USD 1.60 | USD 0.70 | USD 0.40 / USD 1.60 | USD 0.40 / USD 1.60 | — |
| GPT-5.4 Mini | OpenAI | 3 | USD 0.75 | USD 4.50 | USD 1.688 | USD 0.75 / USD 4.50 | USD 0.75 / USD 4.50 | — |
| GPT-6.1 Terra | OpenAI | 4 | USD 1 | USD 5 | USD 2 | USD 1 / USD 5 | USD 1 / USD 5 | 1,050,000 |
| GPT-5 (2025-08-07) | OpenAI | 3 | USD 1.25 | USD 10 | USD 3.438 | USD 1.25 / USD 10 | USD 1.25 / USD 10 | — |
| GPT-5.1 | OpenAI | 2 | USD 1.25 | USD 10 | USD 3.438 | USD 1.25 / USD 10 | USD 1.25 / USD 10 | — |
| GPT-4.1 (2025-04-14) | OpenAI | 3 | USD 2 | USD 8 | USD 3.50 | USD 2 / USD 8 | USD 2 / USD 8 | — |
| o3 (2025-04-16) | OpenAI | 3 | USD 2 | USD 8 | USD 3.50 | USD 2 / USD 8 | USD 2 / USD 8 | — |
| GPT-6 Sol | OpenAI | 6 | USD 2 | USD 10 | USD 4 | USD 2 / USD 10 | USD 2 / USD 10 | 1,050,000 |
| GPT-6.1 Sol | OpenAI | 6 | USD 2 | USD 10 | USD 4 | USD 2 / USD 10 | USD 2 / USD 10 | 1,050,000 |
| GPT-4o | OpenAI | 2 | USD 2.50 | USD 10 | USD 4.375 | USD 2.50 / USD 10 | USD 2.50 / USD 10 | — |
| GPT-5.6 Terra | OpenAI | 6 | USD 2 | USD 12 | USD 4.50 | USD 2 / USD 12 | USD 2 / USD 12 | 1,050,000 |
| GPT-5.2 | OpenAI | 3 | USD 1.75 | USD 14 | USD 4.813 | USD 1.75 / USD 14 | USD 1.75 / USD 14 | — |
| GPT-5.3 Codex | OpenAI | 3 | USD 1.75 | USD 14 | USD 4.813 | USD 1.75 / USD 14 | USD 1.75 / USD 14 | — |
| GPT-5.4 | OpenAI | 4 | USD 2.50 | USD 15 | USD 5.625 | USD 2.50 / USD 15 | USD 2.50 / USD 15 | 1,050,000 |
| GPT-5.6 Sol | OpenAI | 6 | USD 4 | USD 20 | USD 8 | USD 4 / USD 20 | USD 4 / USD 20 | 1,050,000 |
| GPT Chat Latest | OpenAI | 2 | USD 5 | USD 30 | USD 11.25 | USD 5 / USD 30 | USD 5 / USD 30 | — |
| GPT-5.5 | OpenAI | 6 | USD 5 | USD 30 | USD 11.25 | USD 5 / USD 30 | USD 5 / USD 30 | 1,050,000 |
| GPT-6 Astra | OpenAI | 6 | USD 10 | USD 50 | USD 20 | USD 10 / USD 50 | USD 10 / USD 50 | 1,050,000 |
| GPT-5 Pro | OpenAI | 2 | USD 15 | USD 120 | USD 41.25 | USD 15 / USD 120 | USD 15 / USD 120 | — |
| GPT-5.2 Pro | OpenAI | 2 | USD 21 | USD 168 | USD 57.75 | USD 21 / USD 168 | USD 21 / USD 168 | — |
| GPT-5.4 Pro | OpenAI | 3 | USD 30 | USD 180 | USD 67.50 | USD 30 / USD 180 | USD 30 / USD 180 | — |
| DeepSeek · 20 models | ||||||||
| DeepSeek V4 Flash 0731 | DeepSeek | 15 | USD 0.06 | USD 0.18 | USD 0.09 | USD 0.22 / USD 0.66 | — | 1,048,576 |
| DeepSeek V4 Flash | DeepSeek | 8 | USD 0.09 | USD 0.18 | USD 0.1125 | USD 0.139 / USD 0.28 | — | 1,048,576 |
| DeepSeek R1 Distill Qwen 7B | DeepSeek | 2 | USD 0.10 | USD 0.20 | USD 0.125 | USD 0.39 / USD 0.50 | — | 131,072 |
| DeepSeek V4.1 Flash 1017 | DeepSeek | 16 | USD 0.098 | USD 0.294 | USD 0.147 | USD 0.30 / USD 1.20 | USD 0.30 / USD 1.20 | 1,048,576 |
| DeepSeek R1 Distill Qwen 14B | DeepSeek | 2 | USD 0.20 | USD 0.20 | USD 0.20 | USD 0.3155 / USD 0.66 | — | 131,072 |
| DeepSeek R1 Distill Llama 8B | DeepSeek | 2 | USD 0.14 | USD 0.32 | USD 0.2025 | USD 0.17 / USD 0.355 | — | 131,072 |
| DeepSeek V4.1 Flash · also on BroadNet | DeepSeek | 16 | USD 0.13 | USD 0.42 | USD 0.21 | USD 0.30 / USD 1.20 | USD 0.30 / USD 1.20 | 1,048,576 |
| DeepSeek V3.2 | DeepSeek | 11 | USD 0.2088 | USD 0.3096 | USD 0.234 | USD 0.33 / USD 0.48 | — | 163,840 |
| DeepSeek-V3.2-Exp | DeepSeek | 2 | USD 0.27 | USD 0.41 | USD 0.305 | USD 0.27 / USD 0.41 | — | 163,840 |
| DeepSeek-V4-Flash-Vision-Exp | DeepSeek | 3 | USD 0.2156 | USD 0.6468 | USD 0.3234 | USD 0.44 / USD 1.32 | — | 1,048,576 |
| DeepSeek R1 Distill Llama 70B | DeepSeek | 2 | USD 0.25 | USD 0.75 | USD 0.375 | USD 1.425 / USD 1.875 | — | 131,072 |
| DeepSeek V3.1 | DeepSeek | 7 | USD 0.25 | USD 0.95 | USD 0.425 | USD 0.285 / USD 1 | — | 163,840 |
| DeepSeek V3 | DeepSeek | 3 | USD 0.25 | USD 0.89 | USD 0.4375 | USD 0.32 / USD 1 | — | 163,840 |
| DeepSeek-V3.1-Terminus | DeepSeek | 3 | USD 0.27 | USD 1 | USD 0.4525 | USD 0.27 / USD 1 | — | 163,840 |
| DeepSeek V3 0324 | DeepSeek | 3 | USD 0.29 | USD 1.14 | USD 0.5025 | USD 0.385 / USD 1.625 | — | 131,072 |
| DeepSeek R1 Distill Qwen 32B | DeepSeek | 3 | USD 0.497 | USD 0.90 | USD 0.60 | USD 0.50 / USD 4.80 | — | 131,072 |
| DeepSeek R1 0528 | DeepSeek | 5 | USD 0.385 | USD 1.625 | USD 0.695 | USD 0.57 / USD 2.29 | — | 163,840 |
| DeepSeek R1 | DeepSeek | 4 | USD 0.50 | USD 2.18 | USD 0.92 | USD 0.925 / USD 3.79 | — | 163,840 |
| DeepSeek V4 Pro | DeepSeek | 11 | USD 0.957 | USD 1.914 | USD 1.196 | USD 1.65 / USD 3.301 | USD 1.32 / USD 3.96 | 1,048,576 |
| DeepSeek V4 Pro 0813 | DeepSeek | 15 | USD 0.85 | USD 2.60 | USD 1.30 | USD 1.32 / USD 3.96 | USD 1.32 / USD 3.96 | 1,048,576 |
| Google · 19 models | ||||||||
| Gemma 3 4B | 3 | USD 0.04 | USD 0.08 | USD 0.05 | USD 0.05 / USD 0.10 | — | 131,072 | |
| Gemma 3 12B | 4 | USD 0.05 | USD 0.15 | USD 0.075 | USD 0.07 / USD 0.22 | — | 131,072 | |
| Gemma 3 27B | 6 | USD 0.08 | USD 0.16 | USD 0.10 | USD 0.1095 / USD 0.25 | — | 198,000 | |
| Gemma 4 26B A4B · also on BroadNet | 11 | USD 0.07 | USD 0.30 | USD 0.1375 | USD 0.13 / USD 0.40 | — | 262,144 | |
| gemma-4-31B-it-turbo | 2 | USD 0.09 | USD 0.34 | USD 0.1525 | USD 0.105 / USD 0.355 | — | 262,144 | |
| Gemma 4 31B | 12 | USD 0.10 | USD 0.34 | USD 0.16 | USD 0.14 / USD 0.40 | — | 262,144 | |
| Gemini 2.5 Flash-Lite | 2 | USD 0.10 | USD 0.40 | USD 0.175 | USD 0.10 / USD 0.40 | USD 0.10 / USD 0.40 | — | |
| Gemini 3.1 Flash-Lite (gemini-3.1-flash-lite) | 3 | USD 0.25 | USD 1.50 | USD 0.5625 | USD 0.25 / USD 1.50 | USD 0.25 / USD 1.50 | 1,000,000 | |
| Gemini 2.5 Flash | 3 | USD 0.30 | USD 2.50 | USD 0.85 | USD 0.30 / USD 2.50 | USD 0.30 / USD 2.50 | 1,000,000 | |
| Gemini 3.5 Flash-Lite | 3 | USD 0.30 | USD 2.50 | USD 0.85 | USD 0.30 / USD 2.50 | USD 0.30 / USD 2.50 | 1,048,576 | |
| Gemini 3.6 Flash | 3 | USD 0.75 | USD 3.75 | USD 1.50 | USD 0.75 / USD 3.75 | USD 0.75 / USD 3.75 | 1,048,576 | |
| Gemini 3.7 Flash | 3 | USD 0.75 | USD 3.75 | USD 1.50 | USD 0.75 / USD 3.75 | — | 1,048,576 | |
| Gemini 3.8 Flash | 3 | USD 0.75 | USD 3.75 | USD 1.50 | USD 0.75 / USD 3.75 | USD 0.75 / USD 3.75 | 1,048,576 | |
| Gemini 4 Hydrogen | 3 | USD 1.50 | USD 7.50 | USD 3 | USD 1.50 / USD 7.50 | USD 1.50 / USD 7.50 | — | |
| Gemini 3.5 Flash | 3 | USD 1.50 | USD 9 | USD 3.375 | USD 1.50 / USD 9 | — | 1,048,576 | |
| Gemini 2.5 Pro | 3 | USD 1.25 | USD 10 | USD 3.438 | USD 1.25 / USD 10 | USD 1.25 / USD 10 | 1,000,000 | |
| Gemini 4 Argon | 4 | USD 2 | USD 10 | USD 4 | USD 2 / USD 10 | USD 2 / USD 10 | 1,048,576 | |
| Gemini 4 Carbon | 4 | USD 2 | USD 10 | USD 4 | USD 2 / USD 10 | USD 2 / USD 10 | 1,048,576 | |
| Gemini 3.1 Pro Preview | 3 | USD 2 | USD 12 | USD 4.50 | USD 2 / USD 12 | USD 2 / USD 12 | 1,048,576 | |
| Anthropic · 15 models | ||||||||
| Claude Haiku 5.5 | Anthropic | 4 | USD 0.10 | USD 0.50 | USD 0.20 | USD 0.10 / USD 0.50 | USD 0.10 / USD 0.50 | — |
| Claude Haiku 4.5 | Anthropic | 5 | USD 1 | USD 5 | USD 2 | USD 1 / USD 5 | USD 1 / USD 5 | 200,000 |
| Claude Sonnet 5 | Anthropic | 5 | USD 2 | USD 10 | USD 4 | USD 2 / USD 10 | USD 2 / USD 10 | 1,000,000 |
| Claude Sonnet 5.5 | Anthropic | 6 | USD 2 | USD 10 | USD 4 | USD 2 / USD 10 | USD 2 / USD 10 | 1,000,000 |
| Claude Sonnet 4.5 | Anthropic | 4 | USD 3 | USD 15 | USD 6 | USD 3 / USD 15 | USD 3 / USD 15 | — |
| Claude Sonnet 4.6 | Anthropic | 5 | USD 3 | USD 15 | USD 6 | USD 3 / USD 15 | USD 3 / USD 15 | 1,000,000 |
| Claude Opus 5.5 | Anthropic | 6 | USD 4 | USD 20 | USD 8 | USD 4 / USD 20 | USD 4 / USD 20 | 1,000,000 |
| Claude Opus 4.5 | Anthropic | 4 | USD 5 | USD 25 | USD 10 | USD 5 / USD 25 | USD 5 / USD 25 | — |
| Claude Opus 4.6 | Anthropic | 4 | USD 5 | USD 25 | USD 10 | USD 5 / USD 25 | USD 5 / USD 25 | 1,000,000 |
| Claude Opus 4.7 | Anthropic | 5 | USD 5 | USD 25 | USD 10 | USD 5 / USD 25 | USD 5 / USD 25 | 1,000,000 |
| Claude Opus 4.8 | Anthropic | 5 | USD 5 | USD 25 | USD 10 | USD 5 / USD 25 | USD 5 / USD 25 | 1,000,000 |
| Claude Opus 5 | Anthropic | 5 | USD 5 | USD 25 | USD 10 | USD 5 / USD 25 | USD 5 / USD 25 | 1,000,000 |
| Claude Fable 5.2 | Anthropic | 4 | USD 8 | USD 40 | USD 16 | USD 8 / USD 40 | USD 8 / USD 40 | 1,000,000 |
| Claude Fable 5 | Anthropic | 5 | USD 10 | USD 50 | USD 20 | USD 10 / USD 50 | USD 10 / USD 50 | 1,000,000 |
| Claude Fable 5.1 | Anthropic | 4 | USD 10 | USD 50 | USD 20 | USD 10 / USD 50 | USD 10 / USD 50 | 1,000,000 |
| Z.ai · 13 models | ||||||||
| GLM 5.3 Flash | Z.ai | 20 | USD 0.075 | USD 0.25 | USD 0.1187 | USD 0.15 / USD 0.50 | USD 0.15 / USD 0.50 | 1,048,576 |
| GLM 4.7 Flash | Z.ai | 6 | USD 0.06 | USD 0.40 | USD 0.145 | USD 0.07 / USD 0.40 | free | 202,752 |
| GLM 4.5 Air | Z.ai | 4 | USD 0.13 | USD 0.85 | USD 0.31 | USD 0.17 / USD 0.98 | USD 0.20 / USD 1.10 | 131,076 |
| GLM 4.6V | Z.ai | 2 | USD 0.30 | USD 0.90 | USD 0.45 | USD 0.30 / USD 0.90 | USD 0.30 / USD 0.90 | 131,072 |
| GLM 5.3 FlashX | Z.ai | 2 | USD 0.37 | USD 1.25 | USD 0.59 | USD 0.37 / USD 1.25 | USD 0.37 / USD 1.25 | 1,048,576 |
| GLM 4.7 | Z.ai | 8 | USD 0.40 | USD 1.75 | USD 0.7375 | USD 0.60 / USD 2.20 | USD 0.60 / USD 2.20 | 204,800 |
| GLM 4.6 | Z.ai | 6 | USD 0.43 | USD 1.75 | USD 0.76 | USD 0.55 / USD 2.10 | USD 0.60 / USD 2.20 | 204,800 |
| GLM 5.2 | Z.ai | 19 | USD 0.5625 | USD 1.80 | USD 0.8719 | USD 1.40 / USD 4.40 | USD 1.40 / USD 4.40 | 1,048,576 |
| GLM 4.5V | Z.ai | 2 | USD 0.60 | USD 1.80 | USD 0.90 | USD 0.60 / USD 1.80 | USD 0.60 / USD 1.80 | 65,536 |
| GLM 5 | Z.ai | 10 | USD 0.60 | USD 1.92 | USD 0.93 | USD 1 / USD 3.20 | USD 1 / USD 3.20 | 204,800 |
| GLM-4.5-FP8 | Z.ai | 2 | USD 0.60 | USD 2.20 | USD 1 | USD 0.60 / USD 2.20 | USD 0.60 / USD 2.20 | 131,072 |
| GLM 5.3 · also on BroadNet | Z.ai | 24 | USD 0.19 | USD 2.20 | USD 1.047 | USD 1.40 / USD 4.40 | USD 1.40 / USD 4.40 | 1,048,576 |
| GLM 5.1 | Z.ai | 12 | USD 0.90 | USD 2.90 | USD 1.40 | USD 1.40 / USD 4.40 | USD 1.40 / USD 4.40 | 204,800 |
| Meta · 12 models | ||||||||
| Llama 3.1 8B Instruct | Meta | 6 | USD 0.02 | USD 0.04 | USD 0.025 | USD 0.21 / USD 0.22 | — | 131,072 |
| Llama 3.2 1B Instruct | Meta | 3 | USD 0.027 | USD 0.10 | USD 0.0705 | USD 0.027 / USD 0.201 | — | 32,768 |
| Llama 3 8B Instruct | Meta | 3 | USD 0.0925 | USD 0.095 | USD 0.09312 | USD 0.282 / USD 0.60 | — | 8,192 |
| Llama 3.2 3B Instruct | Meta | 4 | USD 0.0509 | USD 0.15 | USD 0.1219 | USD 0.1005 / USD 0.335 | — | 128,000 |
| Llama 4 Scout 17B 16E Instruct | Meta | 6 | USD 0.08 | USD 0.30 | USD 0.15 | USD 0.175 / USD 0.625 | — | 1,048,576 |
| Llama 3.3 70B | Meta | 14 | USD 0.10 | USD 0.32 | USD 0.155 | USD 0.625 / USD 0.72 | — | 131,072 |
| Llama 3.2 11B Vision Instruct | Meta | 3 | USD 0.049 | USD 0.16 | USD 0.16 | USD 0.16 / USD 0.371 | — | — |
| Llama 4 Maverick 17B 128E Instruct FP8 | Meta | 7 | USD 0.24 | USD 0.80 | USD 0.3875 | USD 0.27 / USD 1 | — | 1,048,576 |
| Muse Glimmer 30B | Meta | 3 | USD 0.30 | USD 1.10 | USD 0.50 | USD 0.30 / USD 1.20 | — | 131,072 |
| Llama 3.1 Instruct (70B) | Meta | 3 | USD 0.293 | USD 0.72 | USD 0.72 | USD 0.72 / USD 2.253 | — | 32,768 |
| Muse Spark Open | Meta | 4 | USD 1.25 | USD 4.25 | USD 2 | USD 1.25 / USD 4.25 | — | 1,048,576 |
| Llama 3 Instruct (70B) | Meta | 2 | USD 2.65 | USD 3.50 | USD 2.862 | USD 3.075 / USD 5.90 | — | 8,192 |
| Mistral AI · 9 models | ||||||||
| Mistral-Nemo-Instruct-2407 | Mistral AI | 2 | USD 0.029 | USD 0.03 | USD 0.02925 | USD 0.12325 / USD 0.13875 | — | 131,072 |
| Mistral-Small-24B-Instruct-2501 | Mistral AI | 2 | USD 0.05 | USD 0.08 | USD 0.0575 | USD 0.1125 / USD 0.185 | — | 32,768 |
| Ministral 3 3B | Mistral AI | 2 | USD 0.10 | USD 0.10 | USD 0.10 | USD 0.10 / USD 0.10 | USD 0.10 / USD 0.10 | 262,144 |
| Mistral Small 3.2 24B Instruct | Mistral AI | 4 | USD 0.075 | USD 0.20 | USD 0.1062 | USD 0.091875 / USD 0.275 | — | 256,000 |
| Ministral 3 8B | Mistral AI | 2 | USD 0.15 | USD 0.15 | USD 0.15 | USD 0.15 / USD 0.15 | USD 0.15 / USD 0.15 | 262,144 |
| Mistral Small 3.1 24B Instruct | Mistral AI | 4 | USD 0.10 | USD 0.30 | USD 0.15 | USD 0.1614 / USD 0.36025 | — | 32,768 |
| Ministral 3 14B | Mistral AI | 3 | USD 0.20 | USD 0.20 | USD 0.20 | USD 0.20 / USD 0.20 | USD 0.20 / USD 0.20 | 262,144 |
| Mistral Large 3 | Mistral AI | 3 | USD 0.50 | USD 1.50 | USD 0.75 | USD 0.636 / USD 1.908 | — | — |
| Mistral Medium 3 | Mistral AI | 2 | USD 0.40 | USD 2 | USD 0.80 | USD 1.79 / USD 5.75 | — | — |
| Moonshot AI · 8 models | ||||||||
| Kimi K2.6 | Moonshot AI | 13 | USD 0.39 | USD 1.80 | USD 0.7425 | USD 0.80 / USD 3.50 | USD 0.95 / USD 4 | 262,144 |
| Kimi K2.5 | Moonshot AI | 8 | USD 0.45 | USD 2.25 | USD 0.90 | USD 0.60 / USD 3 | — | 262,144 |
| Kimi K2 Thinking | Moonshot AI | 6 | USD 0.60 | USD 1.20 | USD 0.90 | USD 0.60 / USD 2.50 | — | 262,144 |
| Kimi K2 Instruct | Moonshot AI | 2 | USD 0.57 | USD 2.30 | USD 1.002 | USD 0.585 / USD 2.40 | — | 131,072 |
| Kimi K2 Instruct 0905 | Moonshot AI | 2 | USD 0.60 | USD 2.50 | USD 1.075 | USD 0.60 / USD 2.50 | — | 262,144 |
| Kimi K2.7 Code | Moonshot AI | 12 | USD 0.60 | USD 3 | USD 1.20 | USD 0.90458 / USD 3.90 | USD 0.95 / USD 4 | 262,144 |
| Kimi K3 | Moonshot AI | 18 | USD 1.85 | USD 9.50 | USD 3.763 | USD 3 / USD 15 | USD 3 / USD 15 | 1,048,576 |
| Kimi K3.1 Pro | Moonshot AI | 13 | USD 1.75 | USD 9.50 | USD 3.80 | USD 2 / USD 10 | USD 2 / USD 10 | 1,048,576 |
| MiniMax · 6 models | ||||||||
| MiniMax M3.1 Flash | MiniMax | 9 | USD 0.15 | USD 0.60 | USD 0.2625 | USD 0.15 / USD 0.60 | USD 0.15 / USD 0.60 | 1,048,576 |
| MiniMax M2.7 | MiniMax | 3 | USD 0.21 | USD 0.84 | USD 0.3675 | USD 0.30 / USD 1.20 | — | 204,800 |
| MiniMax M3 | MiniMax | 10 | USD 0.23 | USD 0.96 | USD 0.4125 | USD 0.30 / USD 1.20 | USD 0.30 / USD 1.20 | 1,048,576 |
| MiniMax M2.5 | MiniMax | 6 | USD 0.27 | USD 0.95 | USD 0.44 | USD 0.30 / USD 1.20 | — | 204,800 |
| MiniMax M2 | MiniMax | 4 | USD 0.2775 | USD 1.11 | USD 0.4856 | USD 0.30 / USD 1.20 | — | 204,800 |
| Minimax M2.1 | MiniMax | 3 | USD 0.30 | USD 1.20 | USD 0.525 | USD 0.30 / USD 1.20 | — | 204,800 |
| xAI · 6 models | ||||||||
| Grok 4.20 (non-reasoning) | xAI | 2 | USD 1.25 | USD 2.50 | USD 1.563 | USD 1.25 / USD 2.50 | USD 1.25 / USD 2.50 | 1,000,000 |
| Grok 4.20 (reasoning) | xAI | 3 | USD 1.25 | USD 2.50 | USD 1.563 | USD 1.25 / USD 2.50 | USD 1.25 / USD 2.50 | 1,000,000 |
| Grok 4.3 | xAI | 4 | USD 1.25 | USD 2.50 | USD 1.563 | USD 1.25 / USD 2.50 | USD 1.25 / USD 2.50 | 1,000,000 |
| Grok 4.5 | xAI | 3 | USD 2 | USD 6 | USD 3 | USD 2 / USD 6 | USD 2 / USD 6 | 2,000,000 |
| Grok 4.6 | xAI | 6 | USD 2 | USD 6 | USD 3 | USD 2 / USD 6 | USD 2 / USD 6 | 2,000,000 |
| Grok 4.7 | xAI | 6 | USD 2 | USD 6 | USD 3 | USD 2 / USD 6 | USD 2 / USD 6 | 524,288 |
| NVIDIA · 5 models | ||||||||
| NVIDIA Nemotron 3.5 Lightning 30B A3B | NVIDIA | 5 | USD 0.05 | USD 0.16 | USD 0.085 | USD 0.06 / USD 0.20 | — | 1,048,576 |
| NVIDIA Nemotron 3 Nano 30B A3B | NVIDIA | 3 | USD 0.05 | USD 0.20 | USD 0.0875 | USD 0.06 / USD 0.24 | — | 262,144 |
| NVIDIA Nemotron 3 Super 120B A12B | NVIDIA | 3 | USD 0.075 | USD 0.40 | USD 0.1563 | USD 0.15 / USD 0.65 | — | 262,144 |
| NVIDIA Nemotron 3.5 Super VL | NVIDIA | 6 | USD 0.10 | USD 0.40 | USD 0.175 | USD 0.175 / USD 0.50 | — | 1,000,000 |
| NVIDIA Nemotron 3 Ultra | NVIDIA | 9 | USD 0.50 | USD 2.15 | USD 0.9125 | USD 0.60 / USD 2.40 | — | 262,144 |
| StepFun · 3 models | ||||||||
| Step-3.5-Flash | StepFun | 2 | USD 0.10 | USD 0.30 | USD 0.15 | USD 0.10 / USD 0.30 | — | 262,144 |
| Step 3.7 Flash | StepFun | 3 | USD 0.20 | USD 1.15 | USD 0.4375 | USD 0.20 / USD 1.15 | — | 262,144 |
| Step 5 Preview | StepFun | 4 | USD 1 | USD 2.70 | USD 1.425 | USD 1 / USD 2.70 | — | 1,048,576 |
| Tencent · 3 models | ||||||||
| Hy3 | Tencent | 4 | USD 0.132 | USD 0.528 | USD 0.231 | USD 0.14 / USD 0.58 | — | 262,144 |
| Hy4 | Tencent | 3 | USD 0.417 | USD 1.2505 | USD 0.6254 | USD 0.417 / USD 1.2505 | — | 1,048,576 |
| Hy4 Preview | Tencent | 6 | USD 0.834 | USD 2.501 | USD 1.251 | USD 0.834 / USD 2.501 | — | 1,048,576 |
| Xiaomi · 3 models | ||||||||
| MiMo V2.6 Flash | Xiaomi | 5 | USD 0.112 | USD 0.224 | USD 0.14 | USD 0.14 / USD 0.28 | — | 1,050,000 |
| MiMo v2.5 | Xiaomi | 4 | USD 0.14 | USD 0.28 | USD 0.175 | USD 0.1445 / USD 0.3865 | — | 1,048,576 |
| MiMo V2.6 Pro | Xiaomi | 3 | USD 0.32625 | USD 0.6525 | USD 0.4078 | USD 0.387 / USD 0.783 | — | 1,050,000 |
| Cohere · 2 models | ||||||||
| Command R | Cohere | 2 | USD 0.15 | USD 0.60 | USD 0.2625 | USD 0.325 / USD 1.05 | USD 0.15 / USD 0.60 | 128,000 |
| Command A+ | Cohere | 2 | USD 0.80 | USD 3.20 | USD 1.40 | — | free | — |
| inclusionAI · 2 models | ||||||||
| Ling 3.0 Flash | inclusionAI | 2 | USD 0.06 | USD 0.18 | USD 0.09 | USD 0.06 / USD 0.18 | — | 262,144 |
| Ling 3.0 Flash VL | inclusionAI | 2 | USD 0.06 | USD 0.18 | USD 0.09 | USD 0.0675 / USD 0.20 | — | 262,144 |
| Sao10K · 2 models | ||||||||
| Llama 3 8B Stheno V3.2 | Sao10K | 2 | USD 0.05 | USD 0.05 | USD 0.05 | USD 0.21 / USD 0.215 | — | 8,192 |
| L3.1-70B-Euryale-v2.2 | Sao10K | 2 | USD 0.72 | USD 0.72 | USD 0.72 | USD 0.785 / USD 0.785 | — | 131,072 |
| IBM · 1 model | ||||||||
| IBM Granite 4.2 8B | IBM | 2 | USD 0.06 | USD 0.15 | USD 0.0825 | USD 0.06 / USD 0.20 | — | 131,072 |
| Microsoft · 1 model | ||||||||
| Phi-4 | Microsoft | 3 | USD 0.07 | USD 0.14 | USD 0.0875 | USD 0.07 / USD 0.14 | — | 131,072 |
| Reflection AI · 1 model | ||||||||
| Beam 1.0 501B A23B | Reflection AI | 3 | USD 0.40 | USD 1.20 | USD 0.60 | USD 0.40 / USD 1.20 | — | — |
| Ricursive AI · 1 model | ||||||||
| Ripple-65B Preview | Ricursive AI | 2 | USD 0.20 | USD 0.60 | USD 0.30 | USD 0.20 / USD 0.60 | — | 1,000,000 |
| Thinking Machines · 1 model | ||||||||
| Inkling 2 Small | Thinking Machines | 3 | USD 0.285 | USD 0.95 | USD 0.4512 | USD 0.30 / USD 1 | — | 1,048,576 |
198 models with 2+ providers; 230 single-provider models are listed separately. USD per 1M tokens, standard tier. "Cheapest" is the lowest standard price for the model; input and output minimums can come from different providers. Batch, flex, priority and fast tiers, and free rows, are on each model page but never set "cheapest". Promotional prices count and are tagged on the model page. "Maker's price" is the model maker's own API, where it sells one (DeepSeek: peak-hour price). 1,218 standard prices in all; newest check 2026-11-15. BroadNet links go to BroadNet Inference's own model pages.
Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).
How do you compare LLM API prices?
- Price your workload, not the model. A chatbot is input-heavy, a reasoning agent is output-heavy. The cost calculator takes your traffic and cache rate.
- Check cached input. Agents resend the same prefix; a cheap cache price can beat a cheap input price. Cached input tokens.
- Check context, precision and tier. The cheapest row may cap context lower, serve FP4, or be a best-effort tier. Each model page shows all three.
- Count tokens per model. Tokenizers differ, so the same prompt costs a different number of tokens. Use the token counter.
The same data as an open dataset (CSV and JSON; our compilation CC BY 4.0, each price credited to its provider), with provider spread, maker versus host prices and cached pricing per model: the LLM API price index. Every individual price, with its source URL, date and quote: download all prices.
Also see model vs model comparisons and BroadNet Inference prices and plans.
Questions
Which LLM API is cheapest per token?
Among the 198 models with two or more providers, Llama 3.1 8B Instruct has the lowest standard price: USD 0.02 input and USD 0.04 output per 1M tokens at DeepInfra. The cheapest LLM APIs ranking applies a stated quality filter, so its top pick can differ. The cheapest model is rarely the best one for a task, so price your workload.
Why does the same model have different prices?
Open-weight models are served by many companies on different hardware, precision (FP4, FP8, BF16) and service tiers. GLM 5.3 has standard prices from 24 providers. Across 197 models with two or more paid standard prices, the dearest costs a median 1.3× the cheapest on the 3:1 blend.
Where do these prices come from?
From each provider's own pricing page. We read 1,671 prices from 41 providers with AI assistance and a page renderer, and store each one with its source URL, the date checked and a quote from the page. No aggregator or router feed is used. The methodology page has the full rules. BroadNet rows come from BroadNet Inference's own rate card and are not ranked.
What does price per token mean if prices are per million?
Providers quote USD per 1M tokens. Divide by 1,000,000 for the price of one token: USD 0.30 per 1M is USD 0.0000003 per token. Input, cached input and output are priced separately, and reasoning tokens bill as output.
How do I estimate a monthly bill?
Use the LLM API cost calculator: pick a workload, then add any of 428 models at its cheapest standard price. Count your real prompt sizes with the token counter first.
Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity
Sources
- AI21 Labs: pricing (checked 2026-11-15)
- AkashML: pricing (checked 2026-11-15)
- Alibaba Cloud Model Studio: pricing (checked 2026-11-14)
- Amazon Bedrock: pricing (checked 2026-11-14)
- Amazon Nova (Bedrock): pricing (checked 2026-11-14)
- Anthropic: pricing (checked 2026-11-14)
- Baidu: pricing (checked 2026-11-15)
- Baseten: pricing (checked 2026-11-14)
- Cerebras: pricing (checked 2026-11-14)
- Chutes: pricing (checked 2026-11-15)
- Cloudflare Workers AI: pricing (checked 2026-11-14)
- Cohere: pricing (checked 2026-11-14)
- CoreWeave Forge (formerly W&B Inference): pricing (checked 2026-11-15)
- Crusoe Cloud: pricing (checked 2026-11-15)
- DeepInfra: pricing (checked 2026-11-14)
- DeepSeek: pricing (checked 2026-11-14)
- DigitalOcean Gradient (Serverless Inference): pricing (checked 2026-11-14)
- Featherless: pricing (checked 2026-11-15)
- Fireworks AI: pricing (checked 2026-11-14)
- FriendliAI: pricing (checked 2026-11-15)
- GMI Cloud: pricing (checked 2026-11-15)
- Google (Gemini API): pricing (checked 2026-11-14)
- Google Cloud Vertex AI: pricing (checked 2026-11-14)
- Groq: pricing (checked 2026-11-14)
- Hyperbolic: pricing (checked 2026-11-14)
- IBM watsonx.ai: pricing (checked 2026-11-15)
- Microsoft Azure (Azure OpenAI + Foundry Models): pricing (checked 2026-11-14)
- MiniMax: pricing (checked 2026-11-14)
- Mistral AI: pricing (checked 2026-11-14)
- Moonshot AI (Kimi): pricing (checked 2026-11-14)
- Novita AI: pricing (checked 2026-11-14)
- Nscale: pricing (checked 2026-11-15)
- OpenAI: pricing (checked 2026-11-14)
- Parasail: pricing (checked 2026-11-14)
- Perplexity: pricing (checked 2026-11-15)
- SambaNova Cloud: pricing (checked 2026-11-14)
- SiliconFlow: pricing (checked 2026-11-14)
- Together AI: pricing (checked 2026-11-14)
- Venice: pricing (checked 2026-11-15)
- xAI: pricing (checked 2026-11-14)
- Z.ai: pricing (checked 2026-11-14)
- BroadNet Inference rate card, pricing.json (synced 2026-11-14)