API cost calculator
Estimate what a workload costs across 525 models, then sort by price, intelligence index, or value (index per dollar) to find the cheapest model that meets your bar.
Presets:
525 models · cost for 1M in + 1M out
| Developer | Context | In $/M | Out $/M | ||||
|---|---|---|---|---|---|---|---|
| MiniCPM5-1B | OpenBMB | 26.9 | — | $0 | $0 | $0 | — |
| Gemini 2.5 Flash | 78.3 | — | $0 | $0 | $0 | — | |
| Qwen Chat 72B | Alibaba | — | — | $0 | $0 | $0 | — |
| Qwen3 4B 2507 | Alibaba | 71.9 | — | $0 | $0 | $0 | — |
| Qwen3 4B 2507 Instruct | Alibaba | 52.2 | — | $0 | $0 | $0 | — |
| Qwen1.5 Chat 110B | Alibaba | 28.9 | — | $0 | $0 | $0 | — |
| Qwen3 VL 4B Instruct | Alibaba | 41.6 | — | $0 | $0 | $0 | — |
| Qwen3 VL 4B | Alibaba | 44.3 | — | $0 | $0 | $0 | — |
| Arctic Instruct | Snowflake | — | — | $0 | $0 | $0 | — |
| Apriel-v1.5-15B-Thinker | ServiceNow | 77.2 | — | $0 | $0 | $0 | — |
| Sarvam M | Sarvam | 56.4 | — | $0 | $0 | $0 | — |
| OLMo 2 7B | Allen Institute for AI | 15.5 | — | $0 | $0 | $0 | — |
| OLMo 2 32B | Allen Institute for AI | 23.5 | — | $0 | $0 | $0 | — |
| Llama 3.1 Tulu3 405B | Allen Institute for AI | 57.5 | — | $0 | $0 | $0 | — |
| MiniMax M1 40k | MiniMax | 67.6 | — | $0 | $0 | $0 | — |
| DBRX Instruct | Databricks | 27.5 | — | $0 | $0 | $0 | — |
| LFM2 1.2B | Liquid AI | 13.5 | — | $0 | $0 | $0 | — |
| LFM 40B | Liquid AI | 33.2 | — | $0 | $0 | $0 | — |
| Phi-3 Mini Instruct 3.8B | Microsoft | 27.5 | — | $0 | $0 | $0 | — |
| OpenChat 3.5 | OpenChat | 24.1 | — | $0 | $0 | $0 | — |
| Grok 3 Reasoning | xAI | — | — | $0 | $0 | $0 | — |
| Grok | xAI | 53.8 | — | $0 | $0 | $0 | — |
| Sonar Reasoning | Perplexity | 77.2 | — | $0 | $0 | $0 | — |
| DeepSeek-V2-Chat | DeepSeek | — | — | $0 | $0 | $0 | — |
| DeepSeek R1 0528 Qwen3 8B | DeepSeek | 66.2 | — | $0 | $0 | $0 | — |
| DeepSeek Coder V2 Lite Instruct | DeepSeek | 30.2 | — | $0 | $0 | $0 | — |
| DeepSeek LLM 67B Chat | DeepSeek | — | — | $0 | $0 | $0 | — |
| DeepSeek-Coder-V2 | DeepSeek | 74.3 | — | $0 | $0 | $0 | — |
| Mistral Saba | Mistral AI | 57.1 | — | $0 | $0 | $0 | — |
| Magistral Small 1 | Mistral AI | 64.7 | — | $0 | $0 | $0 | — |
| Magistral Medium 1 | Mistral AI | 65.5 | — | $0 | $0 | $0 | — |
| Claude 2.1 | Anthropic | 34.6 | — | $0 | $0 | $0 | — |
| Claude Instant | Anthropic | 28.4 | — | $0 | $0 | $0 | — |
| Gemma 3n E2B Instruct | 27.5 | — | $0 | $0 | $0 | — | |
| Gemma 3n E4B Instruct | 34.7 | — | $0 | $0 | $0 | — | |
| Gemini 1.0 Ultra | — | — | $0 | $0 | $0 | — | |
| Gemma 3 1B Instruct | 16.2 | — | $0 | $0 | $0 | — | |
| Gemini 2.0 Pro | 67.4 | — | $0 | $0 | $0 | — | |
| Llama 2 Chat 13B | Meta | 28.9 | — | $0 | $0 | $0 | — |
| Llama 2 Chat 70B | Meta | 28.9 | — | $0 | $0 | $0 | — |
| GPT-4o Realtime | OpenAI | — | — | $0 | $0 | $0 | — |
| GPT-4o mini Realtime | OpenAI | — | — | $0 | $0 | $0 | — |
| Doubao Seed Code | ByteDance | 79.4 | — | $0 | $0 | $0 | — |
| Ling-mini-2.0 | InclusionAI | 53.9 | — | $0 | $0 | $0 | — |
| Ring-1T | InclusionAI | 77.9 | — | $0 | $0 | $0 | — |
| Ling-1T | InclusionAI | 73.3 | — | $0 | $0 | $0 | — |
| Jamba Reasoning 3B | AI21 Labs | 30.7 | — | $0 | $0 | $0 | — |
| Jamba 1.7 Mini | AI21 Labs | 22.5 | — | $0 | $0 | $0 | — |
| Apriel-v1.6-15B-Thinker | ServiceNow | 80.3 | — | $0 | $0 | $0 | — |
| Tiny Aya Global | Cohere | 30.5 | — | $0 | $0 | $0 | — |
| JT-MINI | China Mobile | 67.6 | — | $0 | $0 | $0 | — |
| JT-35B-Flash | China Mobile | 82.9 | — | $0 | $0 | $0 | — |
| MiniCPM-V 4.6 1.3B | OpenBMB | 30.5 | — | $0 | $0 | $0 | — |
| Nanbeige4.1-3B | Nanbeige | 84.9 | — | $0 | $0 | $0 | — |
| Tri-21B-Think | Trillion Labs | 60.1 | — | $0 | $0 | $0 | — |
| LongCat Flash Lite | LongCat | 63.6 | — | $0 | $0 | $0 | — |
| HyperCLOVA X SEED Think | Naver | 65.5 | — | $0 | $0 | $0 | — |
| Mi:dm K 2.5 Pro | Korea Telecom | 74.4 | — | $0 | $0 | $0 | — |
| K2 Think V2 | MBZUAI Institute of Foundation Models | 71.3 | — | $0 | $0 | $0 | — |
| K2-V2 | MBZUAI Institute of Foundation Models | 73.6 | — | $0 | $0 | $0 | — |
| Motif-2-12.7B-Reasoning | Motif Technologies | 73.6 | — | $0 | $0 | $0 | — |
| Sarvam 30B | Sarvam | 63.3 | — | $0 | $0 | $0 | — |
| Sarvam 105B | Sarvam | 73.8 | — | $0 | $0 | $0 | — |
| ERNIE 5.0 Thinking | Baidu | 81.7 | — | $0 | $0 | $0 | — |
| Qwen Chat 14B | Alibaba | — | — | $0 | $0 | $0 | — |
| K-EXAONE | LG AI Research | 82.3 | — | $0 | $0 | $0 | — |
| EXAONE 4.0 32B | LG AI Research | 79.8 | — | $0 | $0 | $0 | — |
| Exaone 4.0 1.2B | LG AI Research | 53.1 | — | $0 | $0 | $0 | — |
| EXAONE 4.5 33B | LG AI Research | 79.4 | — | $0 | $0 | $0 | — |
| DeepHermes 3 - Llama-3.1 8B | Nous Research | 23.5 | — | $0 | $0 | $0 | — |
| DeepHermes 3 - Mistral 24B | Nous Research | 43.8 | — | $0 | $0 | $0 | — |
| Granite 4.0 H 1B | IBM | 18 | — | $0 | $0 | $0 | — |
| Granite 4.0 1B | IBM | 17.9 | — | $0 | $0 | $0 | — |
| Granite 4.0 350M | IBM | 10.2 | — | $0 | $0 | $0 | — |
| Granite 4.1 30B | IBM | 48.1 | — | $0 | $0 | $0 | — |
| Granite 4.1 3B | IBM | 31.4 | — | $0 | $0 | $0 | — |
| Granite 4.0 H 350M | IBM | 10.4 | — | $0 | $0 | $0 | — |
| Olmo 3.1 32B Think | Allen Institute for AI | 70.6 | — | $0 | $0 | $0 | — |
| Molmo2-8B | Allen Institute for AI | 42.5 | — | $0 | $0 | $0 | — |
| Olmo 3.1 32B Instruct | Allen Institute for AI | 53.9 | — | $0 | $0 | $0 | — |
| Olmo 3 7B Think | Allen Institute for AI | 62.4 | — | $0 | $0 | $0 | — |
| Molmo 7B-D | Allen Institute for AI | 16.3 | — | $0 | $0 | $0 | — |
| Step3 VL 10B | StepFun | 69 | — | $0 | $0 | $0 | — |
| Step 3.5 Flash 2603 | StepFun | 82.6 | — | $0 | $0 | $0 | — |
| Llama 65B | Meta | — | — | $0 | $0 | $0 | — |
| Kimi Linear 48B A3B Instruct | Moonshot AI | 43.5 | — | $0 | $0 | $0 | — |
| NVIDIA Nemotron 3 Nano 4B | NVIDIA | 51.3 | — | $0 | $0 | $0 | — |
| Nemotron Cascade 2 30B A3B | NVIDIA | 75.8 | — | $0 | $0 | $0 | — |
| Llama 3.1 Nemotron Nano 4B v1.1 | NVIDIA | 54.5 | — | $0 | $0 | $0 | — |
| Solar Pro 2 | Upstage | 72.5 | — | $0 | $0 | $0 | — |
| Solar Open 100B | Upstage | 65.7 | — | $0 | $0 | $0 | — |
| LFM2.5-VL-1.6B | Liquid AI | 28.9 | — | $0 | $0 | $0 | — |
| LFM2.5-1.2B-Thinking | Liquid AI | 33.9 | — | $0 | $0 | $0 | — |
| LFM2 2.6B | Liquid AI | 19.2 | — | $0 | $0 | $0 | — |
| LFM2.5-1.2B-Instruct | Liquid AI | 32.6 | — | $0 | $0 | $0 | — |
| LFM2 8B A1B | Liquid AI | 31.3 | — | $0 | $0 | $0 | — |
| Grok Code Fast 1 | xAI | 65.3 | — | $0 | $0 | $0 | — |
| Grok 4.1 Fast | xAI | 85.6 | — | $0 | $0 | $0 | — |
| Falcon-H1R-7B | TII UAE | 72.8 | — | $0 | $0 | $0 | — |
| R1 1776 | Perplexity | 95.4 | — | $0 | $0 | $0 | — |
| Devstral Small 2 | Mistral AI | 47.5 | — | $0 | $0 | $0 | — |
| Gemma 3 270M | 7.6 | — | $0 | $0 | $0 | — | |
| Gemma 4 E2B | 43.3 | — | $0 | $0 | $0 | — | |
| Gemma 4 E4B | 57.6 | — | $0 | $0 | $0 | — | |
| Muse Spark | Meta | 88.4 | — | $0 | $0 | $0 | — |
| Qwen2.5-Coder 7B Instruct | Alibaba | 39.6 | — | $0 | $0 | $0 | — |
| Qwen2.5 32B Instruct | Alibaba | 66.7 | — | $0 | $0 | $0 | — |
| Qwen2 72B Instruct | Alibaba | 59.9 | — | $0 | $0 | $0 | — |
| Llama-3.3 Nemotron Super 49B v1 | NVIDIA | 63.9 | — | $0 | $0 | $0 | — |
| Gemini 2.0 Flash Thinking | 69.1 | — | $0 | $0 | $0 | — | |
| DeepSeek R1 Distill Qwen 14B | DeepSeek | 65.7 | — | $0 | $0 | $0 | — |
| DeepSeek R1 Distill Qwen 1.5B | DeepSeek | 32.6 | — | $0 | $0 | $0 | — |
| DeepSeek R1 Distill Llama 8B | DeepSeek | 53.3 | — | $0 | $0 | $0 | — |
| Gemini 3 Deep Think | 69.5 | 1M | $0 | $0 | $0 | — | |
| Grok-1 | xAI | — | — | $0 | $0 | $0 | — |
| Claude 2 | Anthropic | 33.4 | 100K | $0 | $0 | $0 | — |
| PaLM 2 | — | — | $0 | $0 | $0 | — | |
| Ling-2.6-flash | InclusionAI | 59.3 | 262K | $0.01 | $0.03 | $0.0400 | 1483 |
| Mistral Nemo | Mistral AI | — | 131K | $0.02 | $0.03 | $0.0500 | — |
| Llama 3.1 8B Instruct | Meta | 45 | 131K | $0.02 | $0.05 | $0.0700 | 643 |
| Llama 3 8B Instruct | Meta | 32.4 | 8K | $0.04 | $0.04 | $0.0800 | 405 |
| Gemma 3 4B Instruct | 31.7 | — | $0 | $0.1 | $0.1000 | 317 | |
| Qwen3.5 2B | Alibaba | 45.6 | — | $0 | $0.1 | $0.1000 | 456 |
| Qwen3.5 0.8B | Alibaba | 23.6 | — | $0 | $0.1 | $0.1000 | 236 |
| Llama 3.2 11B Instruct | Meta | 36.7 | 128K | $0.05 | $0.05 | $0.1000 | 367 |
| Gemma 3 4B | 45.8 | 131K | $0.04 | $0.08 | $0.1200 | 382 | |
| Granite 4.0 Micro | IBM | 25.6 | 131K | $0.017 | $0.112 | $0.1290 | 198 |
| Mistral Small 3 | Mistral AI | 43.6 | 33K | $0.05 | $0.08 | $0.1300 | 335 |
| Qwen2.5 7B Instruct | Alibaba | 46.6 | 131K | $0.04 | $0.1 | $0.1400 | 333 |
| LFM2-24B-A2B | Liquid AI | 47.4 | 128K | $0.03 | $0.12 | $0.1500 | 316 |
| Phi-4-multimodal-instruct | Microsoft | 46.2 | 128K | $0.05 | $0.1 | $0.1500 | 308 |
| Granite 4.1 8B | IBM | 43.3 | 131K | $0.05 | $0.1 | $0.1500 | 289 |
| Nova Micro | Amazon | 49 | 128K | $0.03 | $0.14 | $0.1700 | 288 |
| Gemma 3 12B | 55.5 | 131K | $0.04 | $0.13 | $0.1700 | 326 | |
| gpt-oss-20b | OpenAI | 73.6 | 131K | $0.03 | $0.14 | $0.1700 | 433 |
| Qwen3 235B A22B Instruct | Alibaba | — | 262K | $0.071 | $0.1 | $0.1710 | — |
| Nova Micro 1.0 | Amazon | — | 128K | $0.035 | $0.14 | $0.1750 | — |
| Gemma 3n 4B | — | 33K | $0.06 | $0.12 | $0.1800 | — | |
| Command R7B | Cohere | — | 128K | $0.038 | $0.15 | $0.1880 | — |
| Qwen3.5-9B | Alibaba | 80.6 | 262K | $0.04 | $0.15 | $0.1900 | 424 |
| Trinity Mini | Arcee AI | — | 131K | $0.045 | $0.15 | $0.1950 | — |
| Qwen3.5 4B | Alibaba | 77.1 | — | $0 | $0.2 | $0.2000 | 385 |
| NVIDIA Nemotron Nano 9B V2 | NVIDIA | 68.3 | — | $0 | $0.2 | $0.2000 | 341 |
| Reka Edge | Reka AI | — | 16K | $0.1 | $0.1 | $0.2000 | — |
| Phi-3.5-mini-instruct | Microsoft | 46 | 128K | $0.1 | $0.1 | $0.2000 | 230 |
| Ministral 8B Instruct | Mistral AI | 70.9 | 128K | $0.1 | $0.1 | $0.2000 | 355 |
| GLM 4 32B | Zhipu AI | — | 128K | $0.1 | $0.1 | $0.2000 | — |
| Nemotron Nano 9B V2 | NVIDIA | 77.6 | 131K | $0.04 | $0.16 | $0.2000 | 388 |
| Ministral 3 3B | Mistral AI | 33.7 | 131K | $0.1 | $0.1 | $0.2000 | 169 |
| Phi 4 | Microsoft | 47.6 | 16K | $0.065 | $0.14 | $0.2050 | 232 |
| gpt-oss-120b | OpenAI | 79.6 | 131K | $0.039 | $0.18 | $0.2190 | 363 |
| Llama 3.2 1B Instruct | Meta | 12.1 | 131K | $0.027 | $0.201 | $0.2280 | 53.1 |
| Gemma 3 27B | 58.4 | 131K | $0.08 | $0.16 | $0.2400 | 243 | |
| Nemotron 3 Nano 30B A3B | NVIDIA | — | 262K | $0.05 | $0.2 | $0.2500 | — |
| Mistral Small 3.2 24B | Mistral AI | — | 128K | $0.075 | $0.2 | $0.2750 | — |
| Hermes 2 Pro - Llama-3 8B | Nous Research | — | 8K | $0.14 | $0.14 | $0.2800 | — |
| Granite 3.3 8B | IBM | 32.5 | — | $0 | $0.3 | $0.3000 | 108 |
| Rnj 1 Instruct | Essential AI | — | 33K | $0.15 | $0.15 | $0.3000 | — |
| Pixtral-12B | Mistral AI | 66.1 | 128K | $0.15 | $0.15 | $0.3000 | 220 |
| Nova Lite | Amazon | 57.7 | 300K | $0.06 | $0.24 | $0.3000 | 192 |
| Mistral NeMo Instruct | Mistral AI | — | 128K | $0.15 | $0.15 | $0.3000 | — |
| DeepSeek R1 Distill Qwen 32B | DeepSeek | 68.4 | 128K | $0.12 | $0.18 | $0.3000 | 228 |
| Mistral 7B Instruct v0.1 | Mistral AI | — | 4K | $0.11 | $0.19 | $0.3000 | — |
| Nova Lite 1.0 | Amazon | — | 300K | $0.06 | $0.24 | $0.3000 | — |
| Ministral 3 8B | Mistral AI | 43.3 | 262K | $0.15 | $0.15 | $0.3000 | 144 |
| Qwen2.5 Turbo | Alibaba | 50.3 | — | $0.1 | $0.2 | $0.3000 | 168 |
| Mistral Small 3.1 | Mistral AI | 42.4 | — | $0.1 | $0.2 | $0.3000 | 141 |
| Apertus 8B Instruct | Swiss AI Initiative | 25.6 | — | $0.1 | $0.2 | $0.3000 | 85.3 |
| Olmo 3 7B Instruct | Allen Institute for AI | 40 | — | $0.1 | $0.2 | $0.3000 | 133 |
| NVIDIA Nemotron 3 Nano 30B A3B | NVIDIA | 80.1 | — | $0.1 | $0.2 | $0.3000 | 267 |
| Reka Flash 3 | Reka AI | 56.2 | 66K | $0.1 | $0.2 | $0.3000 | 187 |
| UI-TARS 7B | ByteDance | — | 128K | $0.1 | $0.2 | $0.3000 | — |
| DeepSeek-V4-Flash | DeepSeek | 89.4 | 1M | $0.1 | $0.2 | $0.3000 | 298 |
| Qwen3.5-Flash | Alibaba | — | 1M | $0.065 | $0.26 | $0.3250 | — |
| Hy3 | Tencent | 86.7 | 262K | $0.066 | $0.26 | $0.3260 | 266 |
| Qwen3 14B | Alibaba | 66.8 | 132K | $0.1 | $0.24 | $0.3400 | 196 |
| Qwen3 Coder 30B A3B Instruct | Alibaba | 55.4 | 160K | $0.07 | $0.27 | $0.3400 | 163 |
| ERNIE 4.5 21B A3B | Baidu | — | 131K | $0.07 | $0.28 | $0.3500 | — |
| ERNIE 4.5 21B A3B Thinking | Baidu | — | 131K | $0.07 | $0.28 | $0.3500 | — |
| Spotlight | Arcee AI | — | 131K | $0.18 | $0.18 | $0.3600 | — |
| Llama Guard 4 12B | Meta | — | 164K | $0.18 | $0.18 | $0.3600 | — |
| Qwen3 32B | Alibaba | 73.8 | 131K | $0.08 | $0.28 | $0.3600 | 205 |
| Gemini 1.5 Flash 8B | 48.4 | 1M | $0.07 | $0.3 | $0.3700 | 131 | |
| Seed 1.6 Flash | ByteDance | — | 262K | $0.075 | $0.3 | $0.3750 | — |
| Gemini 2.0 Flash Lite | 54.4 | 1M | $0.075 | $0.3 | $0.3750 | 145 | |
| gpt-oss-safeguard-20b | OpenAI | — | 131K | $0.075 | $0.3 | $0.3750 | — |
| Llama 4 Scout | Meta | 58.9 | 10M | $0.08 | $0.3 | $0.3800 | 155 |
| Llama 3.2 3B Instruct | Meta | 30.8 | 131K | $0.051 | $0.335 | $0.3860 | 79.8 |
| Qwen3 30B A3B Instruct | Alibaba | — | 262K | $0.09 | $0.3 | $0.3900 | — |
| Step 3.5 Flash | StepFun | 83.1 | 262K | $0.09 | $0.3 | $0.3900 | 213 |
| Gemma 4 26B A4B | 79.2 | 262K | $0.06 | $0.33 | $0.3900 | 203 | |
| Solar Mini | Upstage | 33.1 | — | $0.2 | $0.2 | $0.4000 | 82.8 |
| Mistral Small 3.2 | Mistral AI | 51 | — | $0.1 | $0.3 | $0.4000 | 128 |
| Devstral Small | Mistral AI | 45.3 | — | $0.1 | $0.3 | $0.4000 | 113 |
| Mistral 7B Instruct | Mistral AI | 14.7 | — | $0.2 | $0.2 | $0.4000 | 36.7 |
| Gemma 3 12B Instruct | 40 | — | $0.1 | $0.3 | $0.4000 | 100 | |
| Gemma 3 27B Instruct | 44.5 | — | $0.1 | $0.3 | $0.4000 | 111 | |
| Llama 2 Chat 7B | Meta | 11.3 | — | $0.1 | $0.3 | $0.4000 | 28.3 |
| Granite 4.0 H Small | IBM | 35.7 | — | $0.1 | $0.3 | $0.4000 | 89.3 |
| Nemotron 3 Nano Omni 30B A3B Reasoning | NVIDIA | 46.9 | — | $0.1 | $0.3 | $0.4000 | 117 |
| Devstral Small 1.1 | Mistral AI | — | 131K | $0.1 | $0.3 | $0.4000 | — |
| MiMo-V2-Flash | Xiaomi | 88 | 262K | $0.1 | $0.3 | $0.4000 | 220 |
| Mistral Small 3.1 24B Base | Mistral AI | 50.9 | 128K | $0.1 | $0.3 | $0.4000 | 127 |
| Mistral Small 3 24B Instruct | Mistral AI | 62.1 | 32K | $0.1 | $0.3 | $0.4000 | 155 |
| Voxtral Small 24B | Mistral AI | — | 32K | $0.1 | $0.3 | $0.4000 | — |
| Ministral 3 14B | Mistral AI | 47.9 | 262K | $0.2 | $0.2 | $0.4000 | 120 |
| DeepSeek-V2.5 | DeepSeek | 63.4 | 8K | $0.14 | $0.28 | $0.4200 | 151 |
| Llama 3.3 70B Instruct | Meta | 50.6 | 131K | $0.1 | $0.32 | $0.4200 | 120 |
| Phi 4 Mini Instruct | Microsoft | 32.6 | 131K | $0.08 | $0.35 | $0.4300 | 75.8 |
| Qwen3 8B | Alibaba | 57.8 | 131K | $0.05 | $0.4 | $0.4500 | 128 |
| GPT-5 nano | OpenAI | 71.2 | 400K | $0.05 | $0.4 | $0.4500 | 158 |
| GLM 4.7 Flash | Zhipu AI | 58.1 | 203K | $0.06 | $0.4 | $0.4600 | 126 |
| Qwen3 30B A3B Thinking | Alibaba | — | 131K | $0.08 | $0.4 | $0.4800 | — |
| Llama 3.2 11B Vision Instruct | Meta | — | 131K | $0.245 | $0.245 | $0.4900 | — |
| Gemma 4 31B | 85.7 | 262K | $0.12 | $0.37 | $0.4900 | 175 | |
| Gemini 2.5 Flash-Lite | 72.3 | — | $0.1 | $0.4 | $0.5000 | 145 | |
| Qwen3 4B | Alibaba | 56.5 | — | $0.1 | $0.4 | $0.5000 | 113 |
| Qwen3 1.7B | Alibaba | 46.9 | — | $0.1 | $0.4 | $0.5000 | 93.8 |
| Hermes 4 - Llama-3.1 70B | Nous Research | 71.3 | — | $0.1 | $0.4 | $0.5000 | 143 |
| Llama Nemotron Super 49B v1.5 | NVIDIA | 79.4 | — | $0.1 | $0.4 | $0.5000 | 159 |
| Seed-2.0-Mini | ByteDance | — | 262K | $0.1 | $0.4 | $0.5000 | — |
| DeepSeek R1 Distill Llama 70B | DeepSeek | 70.1 | 128K | $0.1 | $0.4 | $0.5000 | 140 |
| GPT-4.1 Nano | OpenAI | 42.1 | 1M | $0.1 | $0.4 | $0.5000 | 84.2 |
| Gemini 2.5 Flash Lite | 57 | 1M | $0.1 | $0.4 | $0.5000 | 114 | |
| Gemini 2.5 Flash Lite 09- | — | 1M | $0.1 | $0.4 | $0.5000 | — | |
| Llama 3.3 Nemotron Super 49B V1.5 | NVIDIA | — | 131K | $0.1 | $0.4 | $0.5000 | — |
| Gemini 2.0 Flash | 60.3 | 1M | $0.1 | $0.4 | $0.5000 | 121 | |
| Llama Guard 3 8B | Meta | — | 131K | $0.484 | $0.03 | $0.5140 | — |
| Qwen3 VL 32B Instruct | Alibaba | 66.5 | 262K | $0.104 | $0.416 | $0.5200 | 128 |
| Hermes 4 70B | Nous Research | — | 131K | $0.13 | $0.4 | $0.5300 | — |
| Qwen3 30B A3B | Alibaba | 71.7 | 131K | $0.09 | $0.45 | $0.5400 | 133 |
| Tongyi DeepResearch 30B A3B | Alibaba | — | 131K | $0.09 | $0.45 | $0.5400 | — |
| Nemotron 3 Super | NVIDIA | — | 1M | $0.09 | $0.45 | $0.5400 | — |
| R1 Distill Qwen 32B | DeepSeek | — | 128K | $0.29 | $0.29 | $0.5800 | — |
| Qwen3 VL 8B Instruct | Alibaba | 43 | 256K | $0.08 | $0.5 | $0.5800 | 74.1 |
| Hermes 3 - Llama-3.1 70B | Nous Research | 42.5 | — | $0.3 | $0.3 | $0.6000 | 70.8 |
| Hermes 3 70B Instruct | Nous Research | — | 131K | $0.3 | $0.3 | $0.6000 | — |
| Qwen3 30B A3B 2507 Instruct | Alibaba | 69.3 | — | $0.2 | $0.4 | $0.6000 | 115 |
| Jamba 1.6 Mini | AI21 Labs | 24.9 | — | $0.2 | $0.4 | $0.6000 | 41.5 |
| Jamba 1.5 Mini | AI21 Labs | 29.6 | 256K | $0.2 | $0.4 | $0.6000 | 49.3 |
| DeepSeek-V3.2 | DeepSeek | 87.1 | 131K | $0.252 | $0.378 | $0.6300 | 138 |
| DeepSeek V3.1 Nex N1 | Nex Agi | — | 131K | $0.135 | $0.5 | $0.6350 | — |
| Qwen3 VL 30B A3B Instruct | Alibaba | 66.5 | 262K | $0.13 | $0.52 | $0.6500 | 102 |
| Olmo 3 32B Think | Allen Institute for AI | 69.5 | 66K | $0.15 | $0.5 | $0.6500 | 107 |
| DeepSeek V3.2 Exp | DeepSeek | 72.2 | 164K | $0.27 | $0.41 | $0.6800 | 106 |
| Ring-flash-2.0 | InclusionAI | 74.6 | — | $0.1 | $0.6 | $0.7000 | 107 |
| Ling-flash-2.0 | InclusionAI | 66.9 | — | $0.1 | $0.6 | $0.7000 | 95.6 |
| Ling-2.6-1T | InclusionAI | 75.2 | 262K | $0.075 | $0.625 | $0.7000 | 107 |
| Ring-2.6-1T | InclusionAI | 85.7 | 262K | $0.075 | $0.625 | $0.7000 | 122 |
| Grok 4 Fast | xAI | 78.7 | 2M | $0.2 | $0.5 | $0.7000 | 112 |
| ERNIE 4.5 VL 28B A3B | Baidu | — | 131K | $0.14 | $0.56 | $0.7000 | — |
| Hunyuan A13B Instruct | Tencent | — | 131K | $0.14 | $0.57 | $0.7100 | — |
| DeepSeek V3.2 Speciale | DeepSeek | 89.9 | 164K | $0.287 | $0.431 | $0.7180 | 125 |
| Solar Pro 3 | Upstage | 72.4 | 128K | $0.15 | $0.6 | $0.7500 | 96.5 |
| QwQ-32B-Preview | Alibaba | 62.6 | 33K | $0.15 | $0.6 | $0.7500 | 83.5 |
| Llama 3.2 90B Instruct | Meta | 54 | 128K | $0.35 | $0.4 | $0.7500 | 72.0 |
| Gemini 1.5 Flash | 61.9 | 1M | $0.15 | $0.6 | $0.7500 | 82.5 | |
| GPT-4o-mini | OpenAI | 49.1 | 128K | $0.15 | $0.6 | $0.7500 | 65.5 |
| GPT-4o-mini Search | OpenAI | — | 128K | $0.15 | $0.6 | $0.7500 | — |
| Mistral Small 4 | Mistral AI | 76.9 | 262K | $0.15 | $0.6 | $0.7500 | 103 |
| Command R+ | Cohere | 28.9 | 128K | $0.15 | $0.6 | $0.7500 | 38.5 |
| Llama 4 Maverick | Meta | 63.9 | 1M | $0.15 | $0.6 | $0.7500 | 85.2 |
| Qwen2.5 72B Instruct | Alibaba | 59.1 | 131K | $0.36 | $0.4 | $0.7600 | 77.8 |
| Seed-OSS-36B-Instruct | ByteDance | 78.8 | — | $0.2 | $0.6 | $0.8000 | 98.5 |
| Mistral Small | Mistral AI | 40.3 | — | $0.2 | $0.6 | $0.8000 | 50.4 |
| NVIDIA Nemotron Nano 12B v2 VL | NVIDIA | 69.4 | — | $0.2 | $0.6 | $0.8000 | 86.8 |
| Grok 3 mini Reasoning | xAI | 80.9 | — | $0.3 | $0.5 | $0.8000 | 101 |
| Saba | Mistral AI | — | 33K | $0.2 | $0.6 | $0.8000 | — |
| Grok-3 Mini | xAI | 85.9 | 128K | $0.3 | $0.5 | $0.8000 | 107 |
| Llama 3.1 70B Instruct | Meta | 56 | 131K | $0.4 | $0.4 | $0.8000 | 70.0 |
| Qwen3 Next 80B A3B Thinking | Alibaba | 77.5 | 262K | $0.098 | $0.78 | $0.8780 | 88.3 |
| Qwen3.5 Omni Flash | Alibaba | 74.2 | — | $0.1 | $0.8 | $0.9000 | 82.4 |
| Mistral Small 3.1 24B | Mistral AI | — | 128K | $0.351 | $0.555 | $0.9060 | — |
| Qwen3 Coder Next | Alibaba | 73.7 | 262K | $0.11 | $0.8 | $0.9100 | 81.0 |
| Qwen3-235B-A22B-Instruct-2507 | Alibaba | 72.2 | 131K | $0.15 | $0.8 | $0.9500 | 76.0 |
| GLM 4.5 Air | Zhipu AI | 70.4 | 131K | $0.13 | $0.85 | $0.9800 | 71.8 |
| Qwen3 VL 30B A3B | Alibaba | 76.2 | — | $0.2 | $0.8 | $1.00 | 76.2 |
| Reka Flash | Reka AI | 52.9 | — | $0.2 | $0.8 | $1.00 | 52.9 |
| Mercury 2 | Inception | 77 | 128K | $0.25 | $0.75 | $1.00 | 77.0 |
| Qwen2.5 VL 72B Instruct | Alibaba | 79.1 | 131K | $0.25 | $0.75 | $1.00 | 79.1 |
| DeepSeek-V3.1 | DeepSeek | 59.8 | 164K | $0.21 | $0.79 | $1.00 | 59.8 |
| Qwen Plus | Alibaba | — | 1M | $0.26 | $0.78 | $1.04 | — |
| Trinity Large Thinking | Arcee AI | 75.2 | 262K | $0.22 | $0.85 | $1.07 | 70.3 |
| Qwen3 VL 235B A22B Instruct | Alibaba | 70.9 | 262K | $0.2 | $0.88 | $1.08 | 65.6 |
| NVIDIA Nemotron 3 Super 120B A12B | NVIDIA | 80 | — | $0.3 | $0.8 | $1.10 | 72.7 |
| Qwen3.5-35B-A3B | Alibaba | 84.5 | 262K | $0.139 | $1 | $1.14 | 74.2 |
| DeepSeek-V3 | DeepSeek | 58.1 | 131K | $0.229 | $0.914 | $1.14 | 50.8 |
| Qwen3.6 35B A3B | Alibaba | 84.1 | 262K | $0.15 | $1 | $1.15 | 73.1 |
| Qwen3 Coder Flash | Alibaba | — | 1M | $0.195 | $0.975 | $1.17 | — |
| Qwen3 Next 80B A3B Instruct | Alibaba | 68.9 | 262K | $0.09 | $1.1 | $1.19 | 57.9 |
| Mixtral 8x7B Instruct | Mistral AI | 26.1 | — | $0.5 | $0.7 | $1.20 | 21.8 |
| Codestral | Mistral AI | — | 256K | $0.3 | $0.9 | $1.20 | — |
| GLM 4.6V | Zhipu AI | 69.6 | 131K | $0.3 | $0.9 | $1.20 | 58.0 |
| DeepSeek V3.1 Terminus | DeepSeek | 83.5 | 164K | $0.27 | $0.95 | $1.22 | 68.4 |
| WizardLM-2 8x22B | Microsoft | — | 66K | $0.62 | $0.62 | $1.24 | — |
| MiniMax M2.1 | MiniMax | 83.6 | 205K | $0.29 | $0.95 | $1.24 | 67.4 |
| Llama 3 70B Instruct | Meta | 40.8 | 8K | $0.51 | $0.74 | $1.25 | 32.6 |
| MiniMax-M2 | MiniMax | 76 | 205K | $0.255 | $1 | $1.26 | 60.6 |
| MiniMax M2.5 | MiniMax | 84.8 | 205K | $0.15 | $1.15 | $1.30 | 65.2 |
| Qwen3 Omni 30B A3B Instruct | Alibaba | 57.3 | — | $0.3 | $1 | $1.30 | 44.1 |
| Qwen3 Omni 30B A3B | Alibaba | 73.4 | — | $0.3 | $1 | $1.30 | 56.5 |
| Coder Large | Arcee AI | — | 33K | $0.5 | $0.8 | $1.30 | — |
| INTELLECT-3 | Prime Intellect | 81 | 131K | $0.2 | $1.1 | $1.30 | 62.3 |
| Gemma 2 27B | — | 8K | $0.65 | $0.65 | $1.30 | — | |
| MiniMax-01 | MiniMax | — | 1M | $0.2 | $1.1 | $1.30 | — |
| DeepSeek-V4-Pro | DeepSeek | 88.2 | 1M | $0.435 | $0.87 | $1.31 | 67.6 |
| Qwen3.6 Flash | Alibaba | — | 1M | $0.188 | $1.125 | $1.31 | — |
| ERNIE 4.5 300B A47B | Baidu | 68.2 | 131K | $0.28 | $1.1 | $1.38 | 49.4 |
| Qwen3 0.6B | Alibaba | 29.3 | — | $0.1 | $1.3 | $1.40 | 20.9 |
| DeepSeek-V3 0324 | DeepSeek | 65.9 | 164K | $0.28 | $1.14 | $1.42 | 46.4 |
| GPT-5.4 nano | OpenAI | 81.7 | 400K | $0.2 | $1.25 | $1.45 | 56.3 |
| MiniMax M2.7 | MiniMax | 87.4 | 205K | $0.279 | $1.2 | $1.48 | 59.1 |
| Qwen3 VL 8B Thinking | Alibaba | — | 256K | $0.117 | $1.365 | $1.48 | — |
| KAT-Coder-Pro V1 | Kuaishou | 81.8 | — | $0.3 | $1.2 | $1.50 | 54.5 |
| KAT-Coder-Pro V2 | Kuaishou | 85.5 | 256K | $0.3 | $1.2 | $1.50 | 57.0 |
| Claude 3 Haiku | Anthropic | 38.9 | 200K | $0.25 | $1.25 | $1.50 | 25.9 |
| R1 Distill Llama 70B | DeepSeek | — | 131K | $0.7 | $0.8 | $1.50 | — |
| MiniMax M2-her | MiniMax | — | 66K | $0.3 | $1.2 | $1.50 | — |
| Qwen3 235B A22B Thinking | Alibaba | — | 262K | $0.15 | $1.495 | $1.65 | — |
| Perceptron Mk1 | Perceptron | — | 33K | $0.15 | $1.5 | $1.65 | — |
| Qwen2.5 Coder 32B Instruct | Alibaba | 50.1 | 128K | $0.66 | $1 | $1.66 | 30.2 |
| ERNIE 4.5 VL 424B A47B | Baidu | — | 131K | $0.42 | $1.25 | $1.67 | — |
| Qwen3 VL 30B A3B Thinking | Alibaba | — | 131K | $0.13 | $1.56 | $1.69 | — |
| QwQ-32B | Alibaba | 67.8 | — | $0.7 | $1 | $1.70 | 39.9 |
| Gemini 3.1 Flash Lite | 82.2 | 1M | $0.25 | $1.5 | $1.75 | 47.0 | |
| Qwen3.5-27B | Alibaba | 85.8 | 262K | $0.195 | $1.56 | $1.76 | 48.9 |
| Llama 3.1 405B Instruct | Meta | 60.9 | 128K | $0.89 | $0.89 | $1.78 | 34.2 |
| Qwen3.5 Plus | Alibaba | — | 1M | $0.26 | $1.56 | $1.82 | — |
| Virtuoso Large | Arcee AI | — | 131K | $0.75 | $1.2 | $1.95 | — |
| Magistral Small 1.2 | Mistral AI | 73.9 | — | $0.5 | $1.5 | $2.00 | 37.0 |
| Hermes 3 405B Instruct | Nous Research | — | 131K | $1 | $1 | $2.00 | — |
| Sonar | Perplexity | 56.8 | 127K | $1 | $1 | $2.00 | 28.4 |
| Morph V3 Fast | Morph | — | 82K | $0.8 | $1.2 | $2.00 | — |
| Gemini 1.0 Pro | 34 | 33K | $0.5 | $1.5 | $2.00 | 17.0 | |
| GPT-4.1 Mini | OpenAI | 58.2 | 1M | $0.4 | $1.6 | $2.00 | 29.1 |
| Mistral Large 3 | Mistral AI | 58.3 | 262K | $0.5 | $1.5 | $2.00 | 29.1 |
| GPT-3.5 Turbo | OpenAI | 35.2 | 16K | $0.5 | $1.5 | $2.00 | 17.6 |
| Qwen3 Coder 480B A35B | Alibaba | — | 1M | $0.22 | $1.8 | $2.02 | — |
| Aion-1.0-Mini | Aion Labs | — | 131K | $0.7 | $1.4 | $2.10 | — |
| Qwen3 Coder 480B A35B Instruct | Alibaba | 66.5 | — | $0.3 | $1.8 | $2.10 | 31.7 |
| Relace Apply 3 | Relace | — | 256K | $0.85 | $1.25 | $2.10 | — |
| GLM 4.7 | Zhipu AI | 89 | 203K | $0.4 | $1.75 | $2.15 | 41.4 |
| GLM-4.6 | Zhipu AI | 72.4 | 203K | $0.43 | $1.74 | $2.17 | 33.4 |
| Qwen3 30B A3B 2507 | Alibaba | 74.7 | — | $0.3 | $1.9 | $2.20 | 34.0 |
| Seed 1.6 | ByteDance | — | 262K | $0.25 | $2 | $2.25 | — |
| Seed-2.0-Lite | ByteDance | — | 262K | $0.25 | $2 | $2.25 | — |
| GPT-5.1-Codex-Mini | OpenAI | 84.7 | 400K | $0.25 | $2 | $2.25 | 37.6 |
| GPT-5 mini | OpenAI | 79.2 | 400K | $0.25 | $2 | $2.25 | 35.2 |
| Qwen3 235B A22B | Alibaba | 74.9 | 131K | $0.455 | $1.82 | $2.28 | 32.9 |
| Qwen3.6 Plus | Alibaba | 88.2 | 1M | $0.325 | $1.95 | $2.28 | 38.8 |
| Kimi K2.5 | Moonshot AI | 87.9 | 262K | $0.4 | $1.9 | $2.30 | 38.2 |
| Qwen3 VL 8B | Alibaba | 49.7 | — | $0.2 | $2.1 | $2.30 | 21.6 |
| Qwen3.5-122B-A10B | Alibaba | 85.7 | 262K | $0.26 | $2.08 | $2.34 | 36.6 |
| MiMo-V2-Omni-0327 | Xiaomi | 85.5 | — | $0.4 | $2 | $2.40 | 35.6 |
| Devstral Medium | Mistral AI | 47.8 | 131K | $0.4 | $2 | $2.40 | 19.9 |
| MiMo-V2-Omni | Xiaomi | 82.8 | 262K | $0.4 | $2 | $2.40 | 34.5 |
| MiMo-V2.5 | Xiaomi | 84.9 | 1M | $0.4 | $2 | $2.40 | 35.4 |
| Llama 3.1 Nemotron Ultra 253B v1 | NVIDIA | 78.3 | — | $0.6 | $1.8 | $2.40 | 32.6 |
| Llama 3.1 Nemotron 70B Instruct | NVIDIA | 43.7 | — | $1.2 | $1.2 | $2.40 | 18.2 |
| Mistral Medium 3 | Mistral AI | 58.6 | 131K | $0.4 | $2 | $2.40 | 24.4 |
| GLM 4.5V | Zhipu AI | 70.1 | 66K | $0.6 | $1.8 | $2.40 | 29.2 |
| Mistral Medium 3.1 | Mistral AI | 51.5 | 131K | $0.4 | $2 | $2.40 | 21.5 |
| Devstral 2 | Mistral AI | 54.3 | 262K | $0.4 | $2 | $2.40 | 22.6 |
| Aion-RP 1.0 | Aion Labs | — | 33K | $0.8 | $1.6 | $2.40 | — |
| Aion-2.0 | Aion Labs | — | 131K | $0.8 | $1.6 | $2.40 | — |
| Cogito v2.1 671B | Deep Cogito | — | 128K | $1.25 | $1.25 | $2.50 | — |
| GLM-5 | Zhipu AI | 81.9 | 203K | $0.6 | $1.92 | $2.52 | 32.5 |
| Qwen3 235B A22B 2507 | Alibaba | 84.2 | — | $0.4 | $2.2 | $2.60 | 32.4 |
| Cogito v2.1 | Deep Cogito | 75.8 | — | $1.3 | $1.3 | $2.60 | 29.2 |
| MiniMax-M1 | MiniMax | 61.5 | 1M | $0.4 | $2.2 | $2.60 | 23.7 |
| Qwen3.5 397B A17B | Alibaba | 89.3 | 262K | $0.39 | $2.34 | $2.73 | 32.7 |
| DeepSeek-R1-0528 | DeepSeek | 63.3 | 131K | $0.55 | $2.19 | $2.74 | 23.1 |
| DeepSeek-R1 | DeepSeek | 75 | 128K | $0.55 | $2.19 | $2.74 | 27.4 |
| Nova 2.0 Omni | Amazon | 78.2 | — | $0.3 | $2.5 | $2.80 | 27.9 |
| Morph V3 Large | Morph | — | 262K | $0.9 | $1.9 | $2.80 | — |
| Nano Banana | — | 33K | $0.3 | $2.5 | $2.80 | — | |
| Nova 2 Lite | Amazon | 82.1 | 1M | $0.3 | $2.5 | $2.80 | 29.3 |
| Gemini 2.5 Flash | 73.1 | 1M | $0.3 | $2.5 | $2.80 | 26.1 | |
| MiniMax M1 80k | MiniMax | 75.5 | — | $0.6 | $2.2 | $2.80 | 27.0 |
| GLM-4.5 | Zhipu AI | 73 | 131K | $0.6 | $2.2 | $2.80 | 26.1 |
| Qwen3 VL 235B A22B Thinking | Alibaba | — | 131K | $0.26 | $2.6 | $2.86 | — |
| Kimi K2 Instruct | Moonshot AI | 66.5 | 131K | $0.57 | $2.3 | $2.87 | 23.2 |
| Kimi K2 | Moonshot AI | 73.6 | 131K | $0.57 | $2.3 | $2.87 | 25.6 |
| GPT Audio Mini | OpenAI | — | 128K | $0.6 | $2.4 | $3.00 | — |
| Grok Build 0.1 | xAI | — | 256K | $1 | $2 | $3.00 | — |
| Kimi K2 0905 | Moonshot AI | 71 | 262K | $0.6 | $2.5 | $3.10 | 22.9 |
| Kimi K2 Thinking | Moonshot AI | 85.6 | 262K | $0.6 | $2.5 | $3.10 | 27.6 |
| R1 | DeepSeek | — | 164K | $0.7 | $2.5 | $3.20 | — |
| Qwen3-235B-A22B-Thinking-2507 | Alibaba | 79.6 | 256K | $0.3 | $3 | $3.30 | 24.1 |
| Qianfan-OCR-Fast | Baidu | — | 66K | $0.68 | $2.81 | $3.49 | — |
| GPT-3.5 Turbo Instruct | OpenAI | — | 4K | $1.5 | $2 | $3.50 | — |
| Nano Banana 2 | — | 131K | $0.5 | $3 | $3.50 | — | |
| Qwen3.6 27B | Alibaba | 84.2 | 262K | $0.3 | $3.2 | $3.50 | 24.1 |
| Gemini 3 Flash | 90.2 | 1M | $0.5 | $3 | $3.50 | 25.8 | |
| Apertus 70B Instruct | Swiss AI Initiative | 27.2 | — | $0.8 | $2.9 | $3.70 | 7.4 |
| Grok 4.3 | xAI | 90.1 | 1M | $1.25 | $2.5 | $3.75 | 24.0 |
| Grok 4.20 | xAI | — | 2M | $1.25 | $2.5 | $3.75 | — |
| Qwen3 Coder Plus | Alibaba | — | 1M | $0.65 | $3.25 | $3.90 | — |
| Hermes 4 - Llama-3.1 405B | Nous Research | 73.5 | — | $1 | $3 | $4.00 | 18.4 |
| Hermes 4 405B | Nous Research | — | 131K | $1 | $3 | $4.00 | — |
| Relace Search | Relace | — | 256K | $1 | $3 | $4.00 | — |
| MiMo-V2-Pro | Xiaomi | 87 | 1M | $1 | $3 | $4.00 | 21.8 |
| MiMo-V2.5-Pro | Xiaomi | 86.6 | 1M | $1 | $3 | $4.00 | 21.6 |
| Nova Pro | Amazon | 61.6 | 300K | $0.8 | $3.2 | $4.00 | 15.4 |
| Nova Pro 1.0 | Amazon | — | 300K | $0.8 | $3.2 | $4.00 | — |
| GLM 5.1 | Zhipu AI | 86.8 | 203K | $0.98 | $3.08 | $4.06 | 21.4 |
| Maestro Reasoning | Arcee AI | — | 131K | $0.9 | $3.3 | $4.20 | — |
| MoonshotAI Kimi | Moonshot AI | — | 262K | $0.73 | $3.49 | $4.22 | — |
| Kimi K2.6 | Moonshot AI | 74.9 | 262K | $0.73 | $3.49 | $4.22 | 17.7 |
| Switchpoint Router | Switchpoint | — | 131K | $0.85 | $3.4 | $4.25 | — |
| GPT-5 Image Mini | OpenAI | — | 400K | $2.5 | $2 | $4.50 | — |
| Qwen3 Max | Alibaba | 79.5 | 262K | $0.78 | $3.9 | $4.68 | 17.0 |
| Qwen3 Max Thinking | Alibaba | 76.1 | 262K | $0.78 | $3.9 | $4.68 | 16.3 |
| Claude 3.5 Haiku | Anthropic | 54.5 | 200K | $0.8 | $4 | $4.80 | 11.4 |
| Qwen3.5 Omni Plus | Alibaba | 82.6 | — | $0.4 | $4.8 | $5.20 | 15.9 |
| GLM 5 Turbo | Zhipu AI | 84.7 | 203K | $1.2 | $4 | $5.20 | 16.3 |
| GLM 5V Turbo | Zhipu AI | 80.9 | 203K | $1.2 | $4 | $5.20 | 15.6 |
| OpenAI GPT Mini | OpenAI | — | 400K | $0.75 | $4.5 | $5.25 | — |
| GPT-5.4 mini | OpenAI | 87.5 | 400K | $0.75 | $4.5 | $5.25 | 16.7 |
| o3 Mini High | OpenAI | — | 200K | $1.1 | $4.4 | $5.50 | — |
| o4 Mini High | OpenAI | — | 200K | $1.1 | $4.4 | $5.50 | — |
| o4-mini | OpenAI | 78.4 | 200K | $1.1 | $4.4 | $5.50 | 14.3 |
| o3-mini | OpenAI | 64.1 | 200K | $1.1 | $4.4 | $5.50 | 11.7 |
| Anthropic Claude Haiku | Anthropic | — | 200K | $1 | $5 | $6.00 | — |
| Claude Haiku 4.5 | Anthropic | 75.3 | 200K | $1 | $5 | $6.00 | 12.5 |
| Gemini 1.5 Pro | 67.3 | 2M | $1.25 | $5 | $6.25 | 10.8 | |
| Qwen3-Next-80B-A3B | Alibaba | 80.3 | 262K | $0.5 | $6 | $6.50 | 12.4 |
| Palmyra X5 | Writer | — | 1M | $0.6 | $6 | $6.60 | — |
| Qwen3 VL 235B A22B | Alibaba | 78.4 | — | $0.8 | $6.2 | $7.00 | 11.2 |
| Magistral Medium 1.2 | Mistral AI | 78.1 | — | $2 | $5 | $7.00 | 11.2 |
| GPT-3.5 Turbo 16k | OpenAI | — | 16K | $3 | $4 | $7.00 | — |
| Qwen3.6 Max | Alibaba | 88.8 | 262K | $1.04 | $6.24 | $7.28 | 12.2 |
| Qwen2.5 Max | Alibaba | 63.6 | — | $1.6 | $6.4 | $8.00 | 8.0 |
| Grok 4.20 0309 | xAI | 88.5 | — | $2 | $6 | $8.00 | 11.1 |
| Grok 4.20 0309 v2 | xAI | 91.1 | — | $2 | $6 | $8.00 | 11.4 |
| Mixtral 8x22B Instruct | Mistral AI | 39.1 | 66K | $2 | $6 | $8.00 | 4.9 |
| Pixtral Large | Mistral AI | 53.1 | 131K | $2 | $6 | $8.00 | 6.6 |
| Mistral Large | Mistral AI | 39.3 | 128K | $2 | $6 | $8.00 | 4.9 |
| Grok 4.20 Multi-Agent | xAI | — | 2M | $2 | $6 | $8.00 | — |
| Mistral Large 2 | Mistral AI | 47.9 | 128K | $2 | $6 | $8.00 | 6.0 |
| Mistral Medium 3.5 | Mistral AI | 74.8 | 262K | $1.5 | $7.5 | $9.00 | 8.3 |
| Qwen3 VL 32B | Alibaba | 78.4 | — | $0.7 | $8.4 | $9.10 | 8.6 |
| Jamba 1.6 Large | AI21 Labs | 42.6 | — | $2 | $8 | $10.00 | 4.3 |
| Sonar Deep Research | Perplexity | — | 128K | $2 | $8 | $10.00 | — |
| Sonar Reasoning Pro | Perplexity | 95.7 | 128K | $2 | $8 | $10.00 | 9.6 |
| Qwen3.7 Max | Alibaba | 92.3 | 1M | $2.5 | $7.5 | $10.00 | 9.2 |
| Jamba 1.5 Large | AI21 Labs | 42.8 | 256K | $2 | $8 | $10.00 | 4.3 |
| Jamba Large 1.7 | AI21 Labs | 36.5 | 256K | $2 | $8 | $10.00 | 3.6 |
| o4 Mini Deep Research | OpenAI | — | 200K | $2 | $8 | $10.00 | — |
| GPT-4.1 | OpenAI | 63.8 | 1M | $2 | $8 | $10.00 | 6.4 |
| o3 | OpenAI | 71.6 | 200K | $2 | $8 | $10.00 | 7.2 |
| Google Gemini Flash | — | 1M | $1.5 | $9 | $10.50 | — | |
| Gemini 3.5 Flash | 92.2 | 1M | $1.5 | $9 | $10.50 | 8.8 | |
| Mistral Medium | Mistral AI | 33.6 | — | $2.8 | $8.1 | $10.90 | 3.1 |
| Gemini 2.5 Pro Preview 06-05 | 76.6 | 1M | $1.25 | $10 | $11.25 | 6.8 | |
| GPT-5 Chat | OpenAI | — | 128K | $1.25 | $10 | $11.25 | — |
| GPT-5 Codex | OpenAI | 87.1 | 400K | $1.25 | $10 | $11.25 | 7.7 |
| GPT-5.1-Codex | OpenAI | 88.2 | 400K | $1.25 | $10 | $11.25 | 7.8 |
| GPT-5.1 Chat | OpenAI | — | 128K | $1.25 | $10 | $11.25 | — |
| GPT-5.1-Codex-Max | OpenAI | — | 400K | $1.25 | $10 | $11.25 | — |
| GPT-5.1 | OpenAI | 89 | 400K | $1.25 | $10 | $11.25 | 7.9 |
| GPT-5 | OpenAI | 80.5 | 400K | $1.25 | $10 | $11.25 | 7.2 |
| Gemini 2.5 Pro | 71.6 | 1M | $1.25 | $10 | $11.25 | 6.4 | |
| Nova 2.0 Pro | Amazon | 80.9 | — | $1.3 | $10 | $11.30 | 7.2 |
| Aion-1.0 | Aion Labs | — | 131K | $4 | $8 | $12.00 | — |
| Grok-2 | xAI | 62.4 | 128K | $2 | $10 | $12.00 | 5.2 |
| Inflection 3 Pi | Inflection | — | 8K | $2.5 | $10 | $12.50 | — |
| Inflection 3 Productivity | Inflection | — | 8K | $2.5 | $10 | $12.50 | — |
| Command A | Cohere | 55.9 | 256K | $2.5 | $10 | $12.50 | 4.5 |
| GPT Audio | OpenAI | — | 128K | $2.5 | $10 | $12.50 | — |
| GPT-4o Search | OpenAI | — | 128K | $2.5 | $10 | $12.50 | — |
| GPT-4o Audio | OpenAI | — | 128K | $2.5 | $10 | $12.50 | — |
| GPT-4o | OpenAI | 56.4 | 128K | $2.5 | $10 | $12.50 | 4.5 |
| Google Gemini Pro | — | 1M | $2 | $12 | $14.00 | — | |
| Nano Banana Pro | — | 66K | $2 | $12 | $14.00 | — | |
| Gemini 3.1 Pro Custom Tools | — | 1M | $2 | $12 | $14.00 | — | |
| Gemini 3.1 Pro | 83.2 | 1M | $2 | $12 | $14.00 | 5.9 | |
| Gemini 3 Pro | 82.8 | 1M | $2 | $12 | $14.00 | 5.9 | |
| Nova Premier | Amazon | 53.1 | — | $2.5 | $12.5 | $15.00 | 3.5 |
| o1-mini | OpenAI | 70.5 | 128K | $3 | $12 | $15.00 | 4.7 |
| Nova Premier 1.0 | Amazon | — | 1M | $2.5 | $12.5 | $15.00 | — |
| GPT-5.2 Chat | OpenAI | — | 128K | $1.75 | $14 | $15.75 | — |
| GPT-5.2-Codex | OpenAI | 89.9 | 400K | $1.75 | $14 | $15.75 | 5.7 |
| GPT-5.3-Codex | OpenAI | 91.5 | 400K | $1.75 | $14 | $15.75 | 5.8 |
| GPT-5.3 Chat | OpenAI | — | 128K | $1.75 | $14 | $15.75 | — |
| GPT-5.2 | OpenAI | 86.2 | 400K | $1.75 | $14 | $15.75 | 5.5 |
| GPT-5.4 | OpenAI | 74.9 | 1.1M | $2.5 | $15 | $17.50 | 4.3 |
| Anthropic Claude Sonnet | Anthropic | — | 1M | $3 | $15 | $18.00 | — |
| Sonar Pro | Perplexity | 58.8 | 200K | $3 | $15 | $18.00 | 3.3 |
| Sonar Pro Search | Perplexity | — | 200K | $3 | $15 | $18.00 | — |
| Claude 3 Sonnet | Anthropic | 45.8 | 200K | $3 | $15 | $18.00 | 2.5 |
| Grok 4 | xAI | 78.2 | 256K | $3 | $15 | $18.00 | 4.3 |
| Claude Sonnet 4.6 | Anthropic | 76.3 | 1M | $3 | $15 | $18.00 | 4.2 |
| Claude Sonnet 4.5 | Anthropic | 80.4 | 1M | $3 | $15 | $18.00 | 4.5 |
| Claude Sonnet 4 | Anthropic | 74.5 | 1M | $3 | $15 | $18.00 | 4.1 |
| Grok-3 | xAI | 82.6 | 128K | $3 | $15 | $18.00 | 4.6 |
| Claude 3.7 Sonnet | Anthropic | 74.7 | 200K | $3 | $15 | $18.00 | 4.2 |
| Claude 3.5 Sonnet | Anthropic | 70.3 | 200K | $3 | $15 | $18.00 | 3.9 |
| GPT-5 Image | OpenAI | — | 400K | $10 | $10 | $20.00 | — |
| GPT-5.4 Image 2 | OpenAI | — | 272K | $8 | $15 | $23.00 | — |
| Claude Opus | Anthropic | — | 1M | $5 | $25 | $30.00 | — |
| Claude Opus 4.7 | Anthropic | 90.9 | 1M | $5 | $25 | $30.00 | 3.0 |
| Claude Opus 4.6 | Anthropic | 79.4 | 1M | $5 | $25 | $30.00 | 2.6 |
| Claude Opus 4.5 | Anthropic | 88 | 200K | $5 | $25 | $30.00 | 2.9 |
| OpenAI GPT | OpenAI | — | 1.1M | $5 | $30 | $35.00 | — |
| GPT-5.5 Instant | OpenAI | — | — | $5 | $30 | $35.00 | — |
| GPT Chat | OpenAI | — | 400K | $5 | $30 | $35.00 | — |
| GPT-5.5 | OpenAI | 76.1 | 1.1M | $5 | $30 | $35.00 | 2.2 |
| GPT-4 Turbo | OpenAI | 59.8 | 128K | $10 | $30 | $40.00 | 1.5 |
| o3 Deep Research | OpenAI | — | 200K | $10 | $40 | $50.00 | — |
| Gemma 3n E4B Instructed | 24.8 | 32K | $20 | $40 | $60.00 | 0.4 | |
| o1-preview | OpenAI | 57.3 | 128K | $15 | $60 | $75.00 | 0.8 |
| o1 | OpenAI | 65.4 | 200K | $15 | $60 | $75.00 | 0.9 |
| Claude Opus 4.1 | Anthropic | 75.4 | 200K | $15 | $75 | $90.00 | 0.8 |
| Claude Opus 4 | Anthropic | 69.4 | 200K | $15 | $75 | $90.00 | 0.8 |
| GPT-4 | OpenAI | 58.3 | 8K | $30 | $60 | $90.00 | 0.6 |
| Claude 3 Opus | Anthropic | 58.5 | 200K | $15 | $75 | $90.00 | 0.7 |
| o3 Pro | OpenAI | 84.5 | 200K | $20 | $80 | $100.00 | 0.8 |
| GPT-5 Pro | OpenAI | 88.4 | 400K | $15 | $120 | $135.00 | 0.7 |
| GPT-5.2 Pro | OpenAI | — | 400K | $21 | $168 | $189.00 | — |
| GPT-5.4 Pro | OpenAI | — | 1.1M | $30 | $180 | $210.00 | — |
| GPT-5.5 Pro | OpenAI | — | 1.1M | $30 | $180 | $210.00 | — |
| GPT-4.5 | OpenAI | 59.4 | 128K | $75 | $150 | $225.00 | 0.3 |
| o1-pro | OpenAI | 82.5 | 200K | $150 | $600 | $750.00 | 0.1 |
| DeepSeek VL2 | DeepSeek | 74.9 | 129K | $9.5 | $4800 | $4,809.50 | 0.0 |
Estimates use list API pricing per million tokens; actual cost varies with caching, batching, and provider. Open-weights / self-hosted models are excluded (no per-token API price).