AI Model Capacity & Efficiency Comparison
Compare context windows, output capacity, and cost efficiency across 459+ models. Data sourced live from upstream provider APIs.
Note: This page shows capacity specs and pricing aggregated from upstream provider APIs. Real-world latency and tokens-per-second vary by load, prompt length, and provider infrastructure. For speed benchmarks, see Artificial Analysis or the model provider's own documentation.
Largest Context
2M
Grok 4.20 Multi-Agent
Largest Output
1.8M
Grok 4.20 Multi-Agent
Cheapest (non-free)
$0.02/1M in
Granite 4.0 Micro
Best Output Ratio
100%
ALLaM 7B Instruct (preview)
Coding & LLM Models
| Model | Provider | Context Window | Max Output | Output Ratio | Input $/1M | Output $/1M | Efficiency (derived) | Capabilities |
|---|---|---|---|---|---|---|---|---|
| Grok 4.20 Multi-Agent | xAI | 2M | 1.8M | 90% | $1.25 | $2.50 | 48 | |
| Grok 4.20 | xAI | 2M | 1.8M | 90% | $1.25 | $2.50 | 48 | |
| GLM Flash Latest | ~z-ai | 1.3M | 944K | 72% | $0.07 | $0.25 | 92 | |
| GLM 5.3 Flash | Zhipu AI | 1.3M | 944K | 72% | $0.15 | $0.50 | 85 | |
| GLM Latest | ~z-ai | 1.3M | 131K | 10% | $0.65 | $2.05 | 59 | |
| GLM 5.3 | Zhipu AI | 1.3M | 131K | 10% | $0.65 | $2.05 | 59 | |
| DeepSeek V4 Flash Latest | ~deepseek | 1.3M | 944K | 72% | $0.03 | $0.80 | 97 | |
| DeepSeek V4 Flash 0731 | DeepSeek | 1.3M | 944K | 72% | $0.04 | $0.64 | 96 | |
| Llama 4 Scout | Meta | 1.3M | 16K | 1% | $0.10 | $0.30 | 89 | |
| GPT-6 Luna Pro | OpenAI | 1.1M | 128K | 12% | $0.10 | $0.50 | 88 | |
| GPT-6 Luna Pro (batch) | OpenAI | 1.1M | 128K | 12% | $0.05 | $0.25 | 93 | |
| GPT-6 Luna | OpenAI | 1.1M | 128K | 12% | $0.10 | $0.50 | 88 | |
| GPT-6 Luna (batch) | OpenAI | 1.1M | 128K | 12% | $0.05 | $0.25 | 93 | |
| GPT-6 Sol Pro | OpenAI | 1.1M | 128K | 12% | $2.00 | $10.00 | 39 | |
| GPT-6 Sol Pro (batch) | OpenAI | 1.1M | 128K | 12% | $1.00 | $5.00 | 50 | |
| GPT-6 Sol | OpenAI | 1.1M | 128K | 12% | $2.00 | $10.00 | 39 | |
| GPT-6 Sol (batch) | OpenAI | 1.1M | 128K | 12% | $1.00 | $5.00 | 50 | |
| GPT Astra Latest | ~openai | 1.1M | 128K | 12% | $10.00 | $50.00 | 22 | |
| GPT Sol Latest | ~openai | 1.1M | 128K | 12% | $2.00 | $10.00 | 39 | |
| GPT Terra Latest | ~openai | 1.1M | 128K | 12% | $2.00 | $12.00 | 39 | |
| GPT Luna Latest | ~openai | 1.1M | 128K | 12% | $0.10 | $0.50 | 88 | |
| GPT-6 Astra | OpenAI | 1.1M | 128K | 12% | $10.00 | $50.00 | 22 | |
| GPT-6 Astra (batch) | OpenAI | 1.1M | 128K | 12% | $5.00 | $25.00 | 28 | |
| GPT-6 Astra Pro | OpenAI | 1.1M | 128K | 12% | $10.00 | $50.00 | 22 | |
| GPT-6 Astra Pro (batch) | OpenAI | 1.1M | 128K | 12% | $5.00 | $25.00 | 28 | |
| GPT-5.6 Luna Pro | OpenAI | 1.1M | 128K | 12% | $0.20 | $1.20 | 79 | |
| GPT-5.6 Luna Pro (batch) | OpenAI | 1.1M | 128K | 12% | $0.10 | $0.60 | 88 | |
| GPT-5.6 Luna | OpenAI | 1.1M | 128K | 12% | $0.20 | $1.20 | 79 | |
| GPT-5.6 Luna (batch) | OpenAI | 1.1M | 128K | 12% | $0.10 | $0.60 | 88 | |
| GPT-5.6 Terra Pro | OpenAI | 1.1M | 128K | 12% | $2.00 | $12.00 | 39 | |
| GPT-5.6 Terra Pro (batch) | OpenAI | 1.1M | 128K | 12% | $1.00 | $6.00 | 50 | |
| GPT-5.6 Terra | OpenAI | 1.1M | 128K | 12% | $2.00 | $12.00 | 39 | |
| GPT-5.6 Terra (batch) | OpenAI | 1.1M | 128K | 12% | $1.00 | $6.00 | 50 | |
| GPT-5.6 Sol Pro | OpenAI | 1.1M | 128K | 12% | $2.00 | $10.00 | 39 | |
| GPT-5.6 Sol Pro (batch) | OpenAI | 1.1M | 128K | 12% | $1.00 | $5.00 | 50 | |
| GPT-5.6 Sol | OpenAI | 1.1M | 128K | 12% | $2.00 | $10.00 | 39 | |
| GPT-5.6 Sol (batch) | OpenAI | 1.1M | 128K | 12% | $1.00 | $5.00 | 50 | |
| GPT-5.5 Pro | OpenAI | 1.1M | 128K | 12% | $30.00 | $180.00 | 17 | |
| GPT-5.5 Pro (batch) | OpenAI | 1.1M | 128K | 12% | $15.00 | $90.00 | 20 | |
| GPT-5.5 | OpenAI | 1.1M | 128K | 12% | $5.00 | $30.00 | 28 | |
| GPT-5.5 (batch) | OpenAI | 1.1M | 128K | 12% | $2.50 | $15.00 | 36 | |
| MiMo-V2.5-Pro | Xiaomi | 1.1M | 131K | 12% | $0.43 | $0.87 | 66 | |
| MiMo-V2.5 | Xiaomi | 1.1M | 131K | 12% | $0.14 | $0.28 | 84 | |
| GPT-5.4 Pro | OpenAI | 1.1M | 128K | 12% | $30.00 | $180.00 | 17 | |
| GPT-5.4 Pro (batch) | OpenAI | 1.1M | 128K | 12% | $15.00 | $90.00 | 20 | |
| GPT-5.4 | OpenAI | 1.1M | 128K | 12% | $2.50 | $15.00 | 36 | |
| GPT-5.4 (batch) | OpenAI | 1.1M | 128K | 12% | $1.25 | $7.50 | 46 | |
| LongCat 2.0 | Meituan | 1.0M | 262K | 25% | $0.30 | $1.20 | 73 | |
| MiMo-V2.6-Pro-UltraSpeed | Xiaomi | 1.0M | 131K | 13% | $4.35 | $8.70 | 29 | |
| MiMo-V2.6-Flash | Xiaomi | 1.0M | 131K | 13% | $0.14 | $0.28 | 84 | |
| MiMo-V2.6-Pro | Xiaomi | 1.0M | 131K | 13% | $0.43 | $0.87 | 66 | |
| GLM 5.3 FlashX | Zhipu AI | 1.0M | 131K | 13% | $0.37 | $1.25 | 69 | |
| DeepSeek Pro Latest | ~deepseek | 1.0M | 393K | 38% | $0.40 | $1.20 | 67 | |
| DeepSeek Flash Latest | ~deepseek | 1.0M | 944K | 90% | $0.12 | $0.48 | 86 | |
| DeepSeek V4.1 Flash | DeepSeek | 1.0M | 384K | 37% | $0.15 | $0.60 | 83 | |
| DeepSeek V4.1 Flash (batch) | DeepSeek | 1.0M | 131K | 13% | $0.11 | $0.34 | 87 | |
| Muse Spark 1.3 Contributor | meta | 1.0M | 944K | 90% | $0.10 | $0.20 | 88 | |
| Muse Spark 1.3 | meta | 1.0M | 944K | 90% | $1.25 | $4.25 | 46 | |
| Gemini 3.8 Flash | 1.0M | 66K | 6% | $0.75 | $3.75 | 55 | ||
| Gemini 3.8 Flash (batch) | 1.0M | 66K | 6% | $0.38 | $1.88 | 69 | ||
| Hy4 preview | Tencent | 1.0M | 64K | 6% | $0.83 | $2.50 | 53 | |
| GLM 5.3 Flash (batch) | Zhipu AI | 1.0M | 131K | 13% | $0.06 | $0.20 | 92 | |
| Muse Spark 1.2 Contributor | meta | 1.0M | 944K | 90% | $0.10 | $0.20 | 88 | |
| DeepSeek V4 Flash Vision Exp | DeepSeek | 1.0M | 944K | 90% | $0.22 | $0.66 | 78 | |
| GLM 5.3 (batch) | Zhipu AI | 1.0M | 131K | 13% | $0.72 | $2.40 | 56 | |
| Gemini 3.7 Flash | 1.0M | 66K | 6% | $0.75 | $3.75 | 55 | ||
| Gemini 3.7 Flash (batch) | 1.0M | 66K | 6% | $0.38 | $1.88 | 69 | ||
| Qwen3.8 2.4T A95B | Alibaba | 1.0M | 131K | 13% | $2.00 | $6.00 | 39 | |
| DeepSeek V4 Pro 0813 | DeepSeek | 1.0M | 384K | 37% | $0.66 | $1.98 | 58 | |
| Muse Spark 1.2 | meta | 1.0M | 944K | 90% | $1.25 | $4.25 | 46 | |
| Inkling Small | thinkingmachines | 1.0M | 262K | 25% | $0.45 | $1.20 | 65 | |
| Inkling Small (free) | thinkingmachines | 1.0M | 262K | 25% | Free | Free | 100 | |
| Laguna S 2.1 | poolside | 1.0M | 131K | 13% | $0.09 | $0.18 | 89 | |
| Gemini 3.6 Flash | 1.0M | 66K | 6% | $0.75 | $3.75 | 55 | ||
| Gemini 3.6 Flash (batch) | 1.0M | 66K | 6% | $0.38 | $1.88 | 69 | ||
| Gemini 3.5 Flash Lite | 1.0M | 66K | 6% | $0.30 | $2.50 | 73 | ||
| Gemini 3.5 Flash Lite (batch) | 1.0M | 66K | 6% | $0.15 | $1.25 | 83 | ||
| Inkling | thinkingmachines | 1.0M | 472K | 45% | $1.00 | $4.05 | 50 | |
| Inkling (free) | thinkingmachines | 1.0M | 262K | 25% | Free | Free | 100 | |
| Kimi K3 | Moonshot AI | 1.0M | 944K | 90% | $3.00 | $15.00 | 33 | |
| Kimi K3 (batch) | Moonshot AI | 1.0M | 16K | 2% | $2.28 | $11.40 | 37 | |
| Muse Spark 1.1 | meta | 1.0M | 944K | 90% | $1.25 | $4.25 | 46 | |
| Aion-3.0-Mini | aion-labs | 1.0M | 33K | 3% | $0.70 | $1.40 | 57 | |
| Aion-3.0 | aion-labs | 1.0M | 33K | 3% | $3.00 | $6.00 | 33 | |
| GLM 5.2 | Zhipu AI | 1.0M | 131K | 13% | $0.65 | $2.04 | 58 | |
| MiniMax M3 | MiniMax | 1.0M | 512K | 49% | $0.30 | $1.20 | 73 | |
| Gemini 3.5 Flash | 1.0M | 66K | 6% | $1.50 | $9.00 | 43 | ||
| Gemini 3.5 Flash (batch) | 1.0M | 66K | 6% | $0.75 | $4.50 | 55 | ||
| Gemini 3.1 Flash Lite | 1.0M | 66K | 6% | $0.25 | $1.50 | 76 | ||
| Gemini 3.1 Flash Lite (batch) | 1.0M | 66K | 6% | $0.13 | $0.75 | 85 | ||
| Gemini Pro Latest | 1.0M | 66K | 6% | $2.00 | $12.00 | 39 | ||
| Kimi Latest | ~moonshotai | 1.0M | 944K | 90% | $1.50 | $10.76 | 43 | |
| Gemini Flash Latest | 1.0M | 66K | 6% | $0.75 | $3.75 | 55 | ||
| DeepSeek V4 Pro 0423 | DeepSeek | 1.0M | 384K | 37% | $0.89 | $1.78 | 52 | |
| DeepSeek V4 Flash 0423 | DeepSeek | 1.0M | 384K | 37% | $0.05 | $0.10 | 94 | |
| Lyria 3 Pro Preview | 1.0M | 66K | 6% | Free | Free | 100 | ||
| Lyria 3 Clip Preview | 1.0M | 66K | 6% | Free | Free | 100 | ||
| Gemini 3.1 Flash Lite Preview | 1.0M | 66K | 6% | $0.25 | $1.50 | 76 | ||
| Gemini 3.1 Pro Preview Custom Tools | 1.0M | 66K | 6% | $2.00 | $12.00 | 39 | ||
| Aion-2.0 | aion-labs | 1.0M | 33K | 3% | $0.80 | $1.60 | 54 | |
| Gemini 3.1 Pro Preview | 1.0M | 66K | 6% | $2.00 | $12.00 | 39 | ||
| Gemini 3.1 Pro Preview (batch) | 1.0M | 66K | 6% | $1.00 | $6.00 | 50 | ||
| Gemini 3 Flash Preview | 1.0M | 66K | 6% | $0.50 | $3.00 | 63 | ||
| Gemini 3 Flash Preview (batch) | 1.0M | 66K | 6% | $0.25 | $1.50 | 76 | ||
| Gemini 2.5 Flash Lite | 1.0M | 66K | 6% | $0.10 | $0.40 | 88 | ||
| Gemini 2.5 Flash Lite (batch) | 1.0M | 66K | 6% | $0.05 | $0.20 | 93 | ||
| Gemini 2.5 Flash | 1.0M | 66K | 6% | $0.30 | $2.50 | 73 | ||
| Gemini 2.5 Flash (batch) | 1.0M | 66K | 6% | $0.15 | $1.25 | 83 | ||
| Gemini 2.5 Pro | 1.0M | 66K | 6% | $1.25 | $10.00 | 46 | ||
| Gemini 2.5 Pro (batch) | 1.0M | 66K | 6% | $0.63 | $5.00 | 59 | ||
| Gemini 2.5 Pro Preview 06-05 | 1.0M | 66K | 6% | $1.25 | $10.00 | 46 | ||
| Llama 4 Maverick | Meta | 1.0M | 16K | 2% | $0.19 | $0.65 | 80 | |
| GPT-4.1 | OpenAI | 1.0M | 33K | 3% | $2.00 | $8.00 | 39 | |
| GPT-4.1 (batch) | OpenAI | 1.0M | 33K | 3% | $1.00 | $4.00 | 50 | |
| GPT-4.1 Mini | OpenAI | 1.0M | 33K | 3% | $0.40 | $1.60 | 67 | |
| GPT-4.1 Mini (batch) | OpenAI | 1.0M | 33K | 3% | $0.20 | $0.80 | 79 | |
| GPT-4.1 Nano | OpenAI | 1.0M | 33K | 3% | $0.10 | $0.40 | 88 | |
| GPT-4.1 Nano (batch) | OpenAI | 1.0M | 33K | 3% | $0.05 | $0.20 | 93 | |
| Palmyra X5 | Writer | 1.0M | 8K | 1% | $0.60 | $6.00 | 60 | |
| MiniMax-01 | MiniMax | 1.0M | 900K | 90% | $0.20 | $1.10 | 79 | |
| Claude Opus 5.5 | Anthropic | 1M | 128K | 13% | $4.00 | $20.00 | 30 | |
| Claude Opus 5.5 (batch) | Anthropic | 1M | 128K | 13% | $2.00 | $10.00 | 39 | |
| Qwen3.8 Omni Flash | Alibaba | 1M | 131K | 13% | $0.15 | $0.47 | 83 | |
| Fugu Ultra v2 | sakana | 1M | 128K | 13% | $5.00 | $30.00 | 28 | |
| Fugu Max | sakana | 1M | 128K | 13% | $2.00 | $6.00 | 39 | |
| Qwen3.8 Max (0902) | Alibaba | 1M | 131K | 13% | $2.00 | $6.00 | 39 | |
| Claude Fable 5.1 | Anthropic | 1M | 128K | 13% | $10.00 | $50.00 | 22 | |
| Claude Fable 5.1 (batch) | Anthropic | 1M | 128K | 13% | $5.00 | $25.00 | 28 | |
| Qwen3.8 Flash | Alibaba | 1M | 131K | 13% | $0.15 | $0.47 | 83 | |
| Qwen3.8 27B | Alibaba | 1M | 131K | 13% | $0.42 | $3.00 | 66 | |
| Nemotron 3.5 Lightning (free) | NVIDIA | 1M | 66K | 7% | Free | Free | 100 | |
| Qwen3.7 Flash | Alibaba | 1M | 66K | 7% | $0.03 | $0.13 | 96 | |
| Claude Opus 5 | Anthropic | 1M | 128K | 13% | $5.00 | $25.00 | 28 | |
| Claude Opus 5 (batch) | Anthropic | 1M | 128K | 13% | $2.50 | $12.50 | 35 | |
| Claude Sonnet 5 | Anthropic | 1M | 128K | 13% | $2.00 | $10.00 | 39 | |
| Claude Sonnet 5 (batch) | Anthropic | 1M | 128K | 13% | $1.00 | $5.00 | 50 | |
| Fugu Ultra | sakana | 1M | 128K | 13% | $5.00 | $30.00 | 28 | |
| Claude Fable Latest | ~anthropic | 1M | 128K | 13% | $10.00 | $50.00 | 22 | |
| Claude Fable 5 | Anthropic | 1M | 128K | 13% | $10.00 | $50.00 | 22 | |
| Claude Fable 5 (batch) | Anthropic | 1M | 128K | 13% | $5.00 | $25.00 | 28 | |
| Nemotron 3 Ultra (free) | NVIDIA | 1M | 66K | 7% | Free | Free | 100 | |
| Qwen3.7 Plus | Alibaba | 1M | 131K | 13% | $0.32 | $1.28 | 71 | |
| Claude Opus 4.8 | Anthropic | 1M | 128K | 13% | $5.00 | $25.00 | 28 | |
| Claude Opus 4.8 (batch) | Anthropic | 1M | 128K | 13% | $2.50 | $12.50 | 35 | |
| Qwen3.7 Max | Alibaba | 1M | 131K | 13% | $1.48 | $4.42 | 43 | |
| Grok 4.3 | xAI | 1M | 900K | 90% | $1.25 | $2.50 | 46 | |
| Grok 4.3 (batch) | xAI | 1M | 900K | 90% | $1.00 | $2.00 | 50 | |
| Claude Sonnet Latest | ~anthropic | 1M | 128K | 13% | $2.00 | $10.00 | 39 | |
| Qwen3.5 Plus 2026-04-20 | Alibaba | 1M | 66K | 7% | $0.30 | $1.80 | 72 | |
| Qwen3.6 Flash | Alibaba | 1M | 66K | 7% | $0.19 | $1.13 | 80 | |
| Claude Opus Latest | ~anthropic | 1M | 128K | 13% | $4.00 | $20.00 | 30 | |
| Claude Opus 4.7 | Anthropic | 1M | 128K | 13% | $5.00 | $25.00 | 28 | |
| Claude Opus 4.7 (batch) | Anthropic | 1M | 128K | 13% | $2.50 | $12.50 | 35 | |
| Qwen3.6 Plus | Alibaba | 1M | 66K | 7% | $0.33 | $1.95 | 71 | |
| Qwen3.5-Flash | Alibaba | 1M | 66K | 7% | $0.07 | $0.26 | 91 | |
| Claude Sonnet 4.6 | Anthropic | 1M | 128K | 13% | $3.00 | $15.00 | 33 | |
| Claude Sonnet 4.6 (batch) | Anthropic | 1M | 128K | 13% | $1.50 | $7.50 | 43 | |
| Qwen3.5 Plus 2026-02-15 | Alibaba | 1M | 66K | 7% | $0.26 | $1.56 | 75 | |
| Claude Opus 4.6 | Anthropic | 1M | 128K | 13% | $5.00 | $25.00 | 28 | |
| Claude Opus 4.6 (batch) | Anthropic | 1M | 128K | 13% | $2.50 | $12.50 | 35 | |
| Nova 2 Lite | Amazon | 1M | 66K | 7% | $0.30 | $2.50 | 72 | |
| Nova Premier 1.0 | Amazon | 1M | 32K | 3% | $2.50 | $12.50 | 35 | |
| Claude Sonnet 4.5 | Anthropic | 1M | 64K | 6% | $3.00 | $15.00 | 33 | |
| Claude Sonnet 4.5 (batch) | Anthropic | 1M | 64K | 6% | $1.50 | $7.50 | 43 | |
| Qwen3 Coder Plus | Alibaba | 1M | 66K | 7% | $0.65 | $3.25 | 58 | |
| Qwen3 Coder Flash | Alibaba | 1M | 66K | 7% | $0.20 | $0.97 | 79 | |
| Qwen Plus 0728 | Alibaba | 1M | 33K | 3% | $0.26 | $0.78 | 75 | |
| MiniMax M1 | MiniMax | 1M | 40K | 4% | $0.40 | $2.20 | 67 | |
| Qwen-Plus | Alibaba | 1M | 33K | 3% | $0.26 | $0.78 | 75 | |
| Solar Pro 4 | Upstage | 524K | 131K | 25% | $0.09 | $0.36 | 84 | |
| Dots3-Note Preview (free) | dots-studio | 512K | 461K | 90% | Free | Free | 95 | |
| Grok 4.7 | xAI | 500K | 450K | 90% | $1.60 | $4.80 | 40 | |
| Grok 4.6 | xAI | 500K | 450K | 90% | $2.00 | $6.00 | 37 | |
| Grok 4.5 | xAI | 500K | 450K | 90% | $2.00 | $6.00 | 37 | |
| Grok Latest | ~x-ai | 500K | 450K | 90% | $1.60 | $4.80 | 40 | |
| GPT Chat Latest | OpenAI | 400K | 128K | 32% | $5.00 | $30.00 | 26 | |
| GPT Mini Latest | ~openai | 400K | 128K | 32% | $0.75 | $4.50 | 51 | |
| GPT-5.4 Nano | OpenAI | 400K | 128K | 32% | $0.20 | $1.25 | 74 | |
| GPT-5.4 Nano (batch) | OpenAI | 400K | 128K | 32% | $0.10 | $0.63 | 82 | |
| GPT-5.4 Mini | OpenAI | 400K | 128K | 32% | $0.75 | $4.50 | 51 | |
| GPT-5.4 Mini (batch) | OpenAI | 400K | 128K | 32% | $0.38 | $2.25 | 64 | |
| GPT-5.3-Codex | OpenAI | 400K | 128K | 32% | $1.75 | $14.00 | 38 | |
| GPT-5.2-Codex | OpenAI | 400K | 128K | 32% | $1.75 | $14.00 | 38 | |
| GPT-5.2 Pro | OpenAI | 400K | 128K | 32% | $21.00 | $168.00 | 17 | |
| GPT-5.2 Pro (batch) | OpenAI | 400K | 128K | 32% | $10.50 | $84.00 | 21 | |
| GPT-5.2 | OpenAI | 400K | 128K | 32% | $1.75 | $14.00 | 38 | |
| GPT-5.2 (batch) | OpenAI | 400K | 128K | 32% | $0.88 | $7.00 | 49 | |
| GPT-5.1-Codex-Max | OpenAI | 400K | 128K | 32% | $1.25 | $10.00 | 43 | |
| GPT-5.1 | OpenAI | 400K | 128K | 32% | $1.25 | $10.00 | 43 | |
| GPT-5.1 (batch) | OpenAI | 400K | 128K | 32% | $0.63 | $5.00 | 55 | |
| GPT-5.1-Codex | OpenAI | 400K | 128K | 32% | $1.25 | $10.00 | 43 | |
| GPT-5.1-Codex-Mini | OpenAI | 400K | 128K | 32% | $0.25 | $2.00 | 70 | |
| GPT-5 Pro | OpenAI | 400K | 128K | 32% | $15.00 | $120.00 | 19 | |
| GPT-5 Pro (batch) | OpenAI | 400K | 128K | 32% | $7.50 | $60.00 | 23 | |
| GPT-5 | OpenAI | 400K | 128K | 32% | $1.25 | $10.00 | 43 | |
| GPT-5 (batch) | OpenAI | 400K | 128K | 32% | $0.63 | $5.00 | 55 | |
| GPT-5 Mini | OpenAI | 400K | 128K | 32% | $0.25 | $2.00 | 70 | |
| GPT-5 Mini (batch) | OpenAI | 400K | 128K | 32% | $0.13 | $1.00 | 80 | |
| GPT-5 Nano | OpenAI | 400K | 128K | 32% | $0.05 | $0.40 | 87 | |
| GPT-5 Nano (batch) | OpenAI | 400K | 128K | 32% | $0.02 | $0.20 | 90 | |
| Nova Lite 1.0 | Amazon | 300K | 5K | 2% | $0.06 | $0.24 | 84 | |
| Nova Pro 1.0 | Amazon | 300K | 5K | 2% | $0.80 | $3.20 | 49 | |
| Ternary Bonsai 2 27B | prism-ml | 262K | 33K | 13% | $0.07 | $0.50 | 81 | |
| Pareto | unbiased | 262K | 131K | 50% | $2.50 | $7.50 | 32 | |
| Ling 3.0 Flash VL (free) | inclusionai | 262K | 33K | 13% | Free | Free | 90 | |
| Ling 3.0 Flash Sante (free) | inclusionai | 262K | 33K | 13% | Free | Free | 90 | |
| Ling 3.0 Flash Fin | inclusionai | 262K | 236K | 90% | $0.06 | $0.18 | 83 | |
| Ling 3.0 Flash Fin (free) | inclusionai | 262K | 33K | 13% | Free | Free | 90 | |
| Qwen3.8 27B (free) | Alibaba | 262K | 236K | 90% | Free | Free | 90 | |
| Seed 2.1 Turbo | ByteDance | 262K | 236K | 90% | $0.50 | $2.50 | 57 | |
| Seed-2.0-Code | ByteDance | 262K | 131K | 50% | $0.50 | $3.00 | 57 | |
| Nemotron 3.5 Lightning | NVIDIA | 262K | 236K | 90% | $0.07 | $0.20 | 82 | |
| Sakana Namazu | sakana | 262K | 66K | 25% | $0.95 | $4.00 | 46 | |
| Ling 3.0 Flash | inclusionai | 262K | 33K | 13% | $0.02 | $0.06 | 87 | |
| Laguna S 2.1 (free) | poolside | 262K | 33K | 13% | Free | Free | 90 | |
| KAT-Coder-Pro V2.5 | Kuaishou | 262K | 236K | 90% | $0.74 | $2.96 | 50 | |
| Hy3 | Tencent | 262K | 128K | 49% | $0.08 | $0.33 | 81 | |
| Laguna XS 2.1 | poolside | 262K | 33K | 13% | $0.06 | $0.12 | 83 | |
| Laguna XS 2.1 (free) | poolside | 262K | 33K | 13% | Free | Free | 90 | |
| Kimi K2.7 Code | Moonshot AI | 262K | 236K | 90% | $0.71 | $3.30 | 51 | |
| Nemotron 3 Ultra | NVIDIA | 262K | 183K | 70% | $0.60 | $2.40 | 54 | |
| Step 3.7 Flash | StepFun | 262K | 230K | 88% | $0.20 | $1.15 | 71 | |
| Mistral Medium 3.5 | Mistral AI | 262K | 210K | 80% | $1.50 | $7.50 | 39 | |
| Mistral Medium 3.5 (batch) | Mistral AI | 262K | 210K | 80% | $0.75 | $3.75 | 50 | |
| Qwen3.6 35B A3B | Alibaba | 262K | 236K | 90% | $0.15 | $1.00 | 75 | |
| Qwen3.6 Max Preview | Alibaba | 262K | 66K | 25% | $1.03 | $6.16 | 45 | |
| Qwen3.6 27B | Alibaba | 262K | 262K | 100% | $0.32 | $2.70 | 64 | |
| Hy3 preview | Tencent | 262K | 236K | 90% | $0.18 | $0.60 | 73 | |
| Kimi K2.6 | Moonshot AI | 262K | 236K | 90% | $0.95 | $4.00 | 46 | |
| Gemma 4 26B A4B | 262K | 236K | 90% | $0.09 | $0.30 | 80 | ||
| Gemma 4 26B A4B (free) | 262K | 33K | 13% | Free | Free | 90 | ||
| Gemma 4 31B | 262K | 16K | 6% | $0.09 | $0.34 | 80 | ||
| Gemma 4 31B (free) | 262K | 33K | 13% | Free | Free | 90 | ||
| Trinity Large Thinking | arcee-ai | 262K | 80K | 31% | $0.25 | $0.80 | 68 | |
| Mistral Small 4 | Mistral AI | 262K | 210K | 80% | $0.15 | $0.60 | 75 | |
| Mistral Small 4 (batch) | Mistral AI | 262K | 210K | 80% | $0.07 | $0.30 | 81 | |
| Nemotron 3 Super | NVIDIA | 262K | 236K | 90% | $0.08 | $0.45 | 81 | |
| Nemotron 3 Super (free) | NVIDIA | 262K | 236K | 90% | Free | Free | 90 | |
| Seed-2.0-Lite | ByteDance | 262K | 131K | 50% | $0.25 | $2.00 | 68 | |
| Qwen3.5-9B | Alibaba | 262K | 33K | 13% | $0.10 | $0.15 | 79 | |
| Seed-2.0-Mini | ByteDance | 262K | 131K | 50% | $0.10 | $0.40 | 79 | |
| Qwen3.5-35B-A3B | Alibaba | 262K | 16K | 6% | $0.31 | $1.25 | 65 | |
| Qwen3.5-27B | Alibaba | 262K | 66K | 25% | $0.20 | $1.56 | 72 | |
| Qwen3.5-122B-A10B | Alibaba | 262K | 66K | 25% | $0.26 | $2.08 | 67 | |
| Qwen3.5 397B A17B | Alibaba | 262K | 236K | 90% | $0.55 | $3.50 | 55 | |
| Qwen3 Max Thinking | Alibaba | 262K | 66K | 25% | $0.78 | $3.90 | 49 | |
| Qwen3 Coder Next | Alibaba | 262K | 236K | 90% | $0.12 | $0.80 | 77 | |
| Step 3.5 Flash | StepFun | 262K | 66K | 25% | $0.10 | $0.30 | 79 | |
| Kimi K2.5 | Moonshot AI | 262K | 236K | 90% | $0.45 | $2.25 | 59 | |
| Seed 1.6 Flash | ByteDance | 262K | 33K | 13% | $0.07 | $0.30 | 81 | |
| Seed 1.6 | ByteDance | 262K | 33K | 13% | $0.25 | $2.00 | 68 | |
| Nemotron 3 Nano 30B A3B | NVIDIA | 262K | 236K | 90% | $0.05 | $0.20 | 84 | |
| Devstral 2 2512 | Mistral AI | 262K | 210K | 80% | $0.40 | $2.00 | 61 | |
| Ministral 3 14B 2512 | Mistral AI | 262K | 210K | 80% | $0.20 | $0.20 | 71 | |
| Ministral 3 8B 2512 | Mistral AI | 262K | 210K | 80% | $0.15 | $0.15 | 75 | |
| Ministral 3 8B 2512 (batch) | Mistral AI | 262K | 210K | 80% | $0.07 | $0.07 | 81 | |
| Mistral Large 3 2512 (batch) | Mistral AI | 262K | 210K | 80% | $0.25 | $0.75 | 68 | |
| Kimi K2 Thinking | Moonshot AI | 262K | 98K | 38% | $0.60 | $2.50 | 54 | |
| Qwen3 VL 8B Instruct | Alibaba | 262K | 33K | 13% | $0.12 | $0.45 | 78 | |
| Qwen3 VL 30B A3B Thinking | Alibaba | 262K | 33K | 13% | $0.20 | $2.40 | 71 | |
| Qwen3 VL 30B A3B Instruct | Alibaba | 262K | 33K | 13% | $0.13 | $0.52 | 77 | |
| Qwen3 VL 235B A22B Instruct | Alibaba | 262K | 33K | 13% | $0.21 | $1.90 | 71 | |
| Qwen3 Max | Alibaba | 262K | 66K | 25% | $0.78 | $3.90 | 49 | |
| Qwen3 Next 80B A3B Thinking | Alibaba | 262K | 236K | 90% | $0.15 | $1.20 | 75 | |
| Qwen3 Next 80B A3B Instruct | Alibaba | 262K | 16K | 6% | $0.09 | $1.10 | 80 | |
| Kimi K2 0905 | Moonshot AI | 262K | 98K | 38% | $0.60 | $2.50 | 54 | |
| Qwen3 Coder 30B A3B Instruct | Alibaba | 262K | 236K | 90% | $0.07 | $0.28 | 82 | |
| Qwen3 30B A3B Instruct 2507 | Alibaba | 262K | 32K | 12% | $0.05 | $0.19 | 84 | |
| Qwen3 Coder 480B A35B | Alibaba | 262K | 66K | 25% | $0.30 | $1.00 | 65 | |
| Qwen3 235B A22B Instruct 2507 | Alibaba | 262K | 236K | 90% | $0.09 | $0.35 | 80 | |
| Falcon-H1-Arabic 34B Instruct | TII | 262K | 8K | 3% | Free | Free | 90 | |
| Falcon-H1-Arabic 7B Instruct | TII | 262K | 8K | 3% | Free | Free | 90 | |
| Mercury 2.5 | Inception | 260K | 66K | 25% | $0.04 | $0.15 | 85 | |
| North Mini Code (free) | Cohere | 256K | 64K | 25% | Free | Free | 90 | |
| Grok Build 0.1 | xAI | 256K | 230K | 90% | $1.00 | $2.00 | 45 | |
| Nemotron 3 Nano Omni (free) | NVIDIA | 256K | 66K | 26% | Free | Free | 90 | |
| Codestral 2508 | Mistral AI | 256K | 205K | 80% | $0.30 | $0.90 | 65 | |
| Codestral 2508 (batch) | Mistral AI | 256K | 205K | 80% | $0.15 | $0.45 | 75 | |
| Mistral Small 3.2 24B | Mistral AI | 256K | 16K | 6% | $0.09 | $0.25 | 80 | |
| Command A | Cohere | 256K | 8K | 3% | $2.50 | $10.00 | 32 | |
| GLM 5.1 | Zhipu AI | 205K | 128K | 63% | $0.97 | $3.04 | 45 | |
| MiniMax M2.7 | MiniMax | 205K | 131K | 64% | $0.30 | $1.20 | 64 | |
| MiniMax M2.5 | MiniMax | 205K | 128K | 63% | $0.27 | $1.08 | 66 | |
| GLM 5 | Zhipu AI | 205K | 128K | 63% | $0.60 | $1.92 | 53 | |
| MiniMax M2.1 | MiniMax | 205K | 131K | 64% | $0.30 | $1.20 | 64 | |
| GLM 4.7 | Zhipu AI | 205K | 131K | 64% | $0.40 | $1.75 | 59 | |
| MiniMax M2 | MiniMax | 205K | 131K | 64% | $0.26 | $1.02 | 66 | |
| GLM 4.6 | Zhipu AI | 205K | 16K | 8% | $0.43 | $1.75 | 58 | |
| GLM 5V Turbo | Zhipu AI | 203K | 131K | 65% | $1.20 | $4.00 | 41 | |
| GLM 5 Turbo | Zhipu AI | 203K | 131K | 65% | $1.20 | $4.00 | 41 | |
| Claude Haiku Latest | ~anthropic | 200K | 64K | 32% | $1.00 | $5.00 | 44 | |
| GLM 4.7 Flash | Zhipu AI | 200K | 118K | 59% | $0.06 | $0.40 | 81 | |
| Claude Opus 4.5 | Anthropic | 200K | 64K | 32% | $5.00 | $25.00 | 25 | |
| Claude Opus 4.5 (batch) | Anthropic | 200K | 64K | 32% | $2.50 | $12.50 | 31 | |
| Sonar Pro Search | Perplexity | 200K | 8K | 4% | $3.00 | $15.00 | 29 | |
| Claude Haiku 4.5 | Anthropic | 200K | 64K | 32% | $1.00 | $5.00 | 44 | |
| Claude Haiku 4.5 (batch) | Anthropic | 200K | 64K | 32% | $0.50 | $2.50 | 56 | |
| Claude Opus 4.1 | Anthropic | 200K | 32K | 16% | $15.00 | $75.00 | 18 | |
| Claude Opus 4.1 (batch) | Anthropic | 200K | 32K | 16% | $7.50 | $37.50 | 22 | |
| o3 Pro | OpenAI | 200K | 100K | 50% | $20.00 | $80.00 | 16 | |
| Claude Sonnet 4 | Anthropic | 200K | 64K | 32% | $3.00 | $15.00 | 29 | |
| o4 Mini High | OpenAI | 200K | 100K | 50% | $1.10 | $4.40 | 43 | |
| o3 | OpenAI | 200K | 100K | 50% | $2.00 | $8.00 | 34 | |
| o3 (batch) | OpenAI | 200K | 100K | 50% | $1.00 | $4.00 | 44 | |
| o4 Mini | OpenAI | 200K | 100K | 50% | $1.10 | $4.40 | 43 | |
| o4 Mini (batch) | OpenAI | 200K | 100K | 50% | $0.55 | $2.20 | 54 | |
| o1-pro | OpenAI | 200K | 100K | 50% | $150.00 | $600.00 | 11 | |
| Sonar Pro | Perplexity | 200K | 8K | 4% | $3.00 | $15.00 | 29 | |
| o3 Mini High | OpenAI | 200K | 100K | 50% | $1.10 | $4.40 | 43 | |
| o3 Mini | OpenAI | 200K | 100K | 50% | $1.10 | $4.40 | 43 | |
| o3 Mini (batch) | OpenAI | 200K | 100K | 50% | $0.55 | $2.20 | 54 | |
| o1 | OpenAI | 200K | 100K | 50% | $15.00 | $60.00 | 18 | |
| Claude 3 Haiku | Anthropic | 200K | 4K | 2% | $0.25 | $1.25 | 67 | |
| Composer 2 | Cursor | 200K | 66K | 33% | $0.50 | $2.50 | 56 | |
| Composer 2 Fast | Cursor | 200K | 66K | 33% | $1.50 | $7.50 | 38 | |
| DeepSeek V3.2 | DeepSeek | 164K | 66K | 40% | $0.27 | $0.40 | 64 | |
| DeepSeek V3.2 Exp | DeepSeek | 164K | 66K | 40% | $0.27 | $0.41 | 64 | |
| DeepSeek V3.1 Terminus | DeepSeek | 164K | 33K | 20% | $0.27 | $1.00 | 64 | |
| DeepSeek V3.1 | DeepSeek | 164K | 33K | 20% | $0.25 | $0.95 | 66 | |
| R1 0528 | DeepSeek | 164K | 33K | 20% | $0.50 | $2.15 | 55 | |
| Llama Guard 4 12B | Meta | 164K | 16K | 10% | $0.18 | $0.18 | 70 | |
| DeepSeek V3 0324 | DeepSeek | 164K | 147K | 90% | $0.25 | $1.00 | 66 | |
| DeepSeek V3 | DeepSeek | 164K | 16K | 10% | $0.32 | $0.89 | 62 | |
| Ling 3.0 Flash VL | inclusionai | 131K | 33K | 25% | $0.06 | $0.18 | 78 | |
| Granite 4.2 8B | IBM | 131K | 118K | 90% | $0.06 | $0.25 | 78 | |
| Muse Glimmer 30B | meta | 131K | 16K | 13% | $0.30 | $1.20 | 62 | |
| Nemotron 3.5 Content Safety | NVIDIA | 131K | 118K | 90% | $0.20 | $0.20 | 67 | |
| Solar Pro 3 | Upstage | 131K | 118K | 90% | $0.15 | $0.60 | 71 | |
| GLM 4.6V | Zhipu AI | 131K | 33K | 25% | $0.30 | $0.90 | 62 | |
| Ministral 3 3B 2512 | Mistral AI | 131K | 105K | 80% | $0.10 | $0.10 | 75 | |
| gpt-oss-safeguard-20b | OpenAI | 131K | 66K | 50% | $0.07 | $0.30 | 77 | |
| Qwen3 VL 32B Instruct | Alibaba | 131K | 33K | 25% | $0.10 | $0.42 | 74 | |
| Qwen3 VL 8B Thinking | Alibaba | 131K | 33K | 25% | $0.18 | $2.10 | 69 | |
| Qwen3 VL 235B A22B Thinking | Alibaba | 131K | 33K | 25% | $0.40 | $4.00 | 57 | |
| Mistral Medium 3.1 | Mistral AI | 131K | 105K | 80% | $0.40 | $2.00 | 57 | |
| Mistral Medium 3.1 (batch) | Mistral AI | 131K | 105K | 80% | $0.20 | $1.00 | 67 | |
| gpt-oss-120b | OpenAI | 131K | 66K | 50% | $0.15 | $0.60 | 71 | |
| gpt-oss-20b | OpenAI | 131K | 33K | 25% | $0.02 | $0.09 | 83 | |
| gpt-oss-20b (batch) | OpenAI | 131K | 118K | 90% | $0.02 | $0.11 | 82 | |
| GLM 4.5 | Zhipu AI | 131K | 98K | 75% | $0.60 | $2.20 | 51 | |
| GLM 4.5 Air | Zhipu AI | 131K | 98K | 75% | $0.13 | $0.85 | 72 | |
| Qwen3 235B A22B Thinking 2507 | Alibaba | 131K | 118K | 90% | $0.23 | $2.30 | 65 | |
| Kimi K2 0711 | Moonshot AI | 131K | 98K | 75% | $0.57 | $2.30 | 51 | |
| Hunyuan A13B Instruct | Tencent | 131K | 118K | 90% | $0.14 | $0.57 | 71 | |
| Mistral Medium 3 | Mistral AI | 131K | 105K | 80% | $0.40 | $2.00 | 57 | |
| Qwen3 30B A3B | Alibaba | 131K | 16K | 13% | $0.12 | $0.50 | 73 | |
| Qwen3 8B | Alibaba | 131K | 8K | 6% | $0.12 | $0.45 | 73 | |
| Qwen3 14B | Alibaba | 131K | 16K | 13% | $0.12 | $0.24 | 73 | |
| Qwen3 32B | Alibaba | 131K | 16K | 13% | $0.08 | $0.28 | 77 | |
| Qwen3 235B A22B | Alibaba | 131K | 8K | 6% | $0.45 | $1.82 | 55 | |
| Gemma 3 4B | 131K | 16K | 13% | $0.05 | $0.10 | 79 | ||
| Gemma 3 12B | 131K | 16K | 13% | $0.05 | $0.15 | 79 | ||
| Gemma 3 27B | 131K | 118K | 90% | $0.08 | $0.45 | 77 | ||
| Llama 3.3 70B Instruct | Meta | 131K | 16K | 13% | $0.10 | $0.32 | 75 | |
| Mistral Large 2407 | Mistral AI | 131K | 105K | 80% | $2.00 | $6.00 | 33 | |
| Llama 3.2 3B Instruct | Meta | 131K | 118K | 90% | $0.05 | $0.33 | 79 | |
| Llama 3.1 70B Instruct | Meta | 131K | 16K | 13% | $0.40 | $0.40 | 57 | |
| Llama 3.1 8B Instruct | Meta | 131K | 118K | 90% | $0.05 | $0.08 | 79 | |
| Mistral Nemo | Mistral AI | 131K | 16K | 13% | $0.02 | $0.03 | 83 | |
| Falcon-H1-Arabic 3B Instruct | TII | 131K | 8K | 6% | Free | Free | 85 | |
| Granite 4.0 Micro | IBM | 131K | 118K | 90% | $0.02 | $0.11 | 83 | |
| Schematron V2 Turbo | inference-net | 128K | 8K | 6% | $0.03 | $0.15 | 81 | |
| Schematron V2 Small | inference-net | 128K | 4K | 3% | $0.05 | $0.23 | 79 | |
| Nemotron 3.5 Content Safety (free) | NVIDIA | 128K | 8K | 6% | Free | Free | 85 | |
| Mercury 2 | Inception | 128K | 50K | 39% | $0.25 | $0.75 | 64 | |
| GPT Audio | OpenAI | 128K | 16K | 13% | $2.50 | $10.00 | 30 | |
| GPT Audio Mini | OpenAI | 128K | 16K | 13% | $0.60 | $2.40 | 51 | |
| GPT-5.2 Chat | OpenAI | 128K | 32K | 25% | $1.75 | $14.00 | 34 | |
| UI-TARS 7B | ByteDance | 128K | 2K | 2% | $0.10 | $0.20 | 75 | |
| Mistral Small 3.1 24B | Mistral AI | 128K | 102K | 80% | $0.35 | $0.55 | 59 | |
| Sonar Reasoning Pro | Perplexity | 128K | 115K | 90% | $2.00 | $8.00 | 33 | |
| Sonar Deep Research | Perplexity | 128K | 115K | 90% | $2.00 | $8.00 | 33 | |
| Qwen2.5 VL 72B Instruct | Alibaba | 128K | 115K | 90% | $0.80 | $1.00 | 46 | |
| Command R7B (12-2024) | Cohere | 128K | 4K | 3% | $0.04 | $0.15 | 81 | |
| Nova Micro 1.0 | Amazon | 128K | 5K | 4% | $0.04 | $0.14 | 81 | |
| GPT-4o (2024-11-20) | OpenAI | 128K | 16K | 13% | $2.50 | $10.00 | 30 | |
| Command R (08-2024) | Cohere | 128K | 4K | 3% | $0.15 | $0.60 | 71 | |
| Command R+ (08-2024) | Cohere | 128K | 4K | 3% | $2.50 | $10.00 | 30 | |
| GPT-4o (2024-08-06) | OpenAI | 128K | 16K | 13% | $2.50 | $10.00 | 30 | |
| GPT-4o-mini | OpenAI | 128K | 16K | 13% | $0.15 | $0.60 | 71 | |
| GPT-4o-mini (2024-07-18) | OpenAI | 128K | 16K | 13% | $0.15 | $0.60 | 71 | |
| GPT-4o-mini (batch) | OpenAI | 128K | 16K | 13% | $0.07 | $0.30 | 77 | |
| GPT-4o | OpenAI | 128K | 16K | 13% | $2.50 | $10.00 | 30 | |
| GPT-4o (2024-05-13) | OpenAI | 128K | 4K | 3% | $5.00 | $15.00 | 24 | |
| GPT-4o (batch) | OpenAI | 128K | 16K | 13% | $1.25 | $5.00 | 39 | |
| GPT-4 Turbo | OpenAI | 128K | 4K | 3% | $10.00 | $30.00 | 19 | |
| GPT-4 Turbo (batch) | OpenAI | 128K | 4K | 3% | $5.00 | $15.00 | 24 | |
| Mistral Large | Mistral AI | 128K | 102K | 80% | $2.00 | $6.00 | 33 | |
| Sonar | Perplexity | 127K | 114K | 90% | $1.00 | $1.00 | 42 | |
| ERNIE 4.5 VL 424B A47B | Baidu | 123K | 16K | 13% | $0.42 | $1.25 | 56 | |
| Qwen3 30B A3B Thinking 2507 | Alibaba | 82K | 33K | 40% | $0.20 | $2.40 | 65 | |
| LFM2.5-2.6B (free) | Liquid AI | 66K | 8K | 13% | Free | Free | 80 | |
| MiniMax M2-her | MiniMax | 66K | 2K | 3% | $0.30 | $1.20 | 58 | |
| GLM 4.5V | Zhipu AI | 66K | 16K | 25% | $0.60 | $1.80 | 48 | |
| Reka Flash 3 | rekaai | 66K | 59K | 90% | $0.10 | $0.20 | 70 | |
| Mixtral 8x22B Instruct | Mistral AI | 66K | 52K | 80% | $2.00 | $6.00 | 31 | |
| WizardLM-2 8x22B | Microsoft | 66K | 8K | 12% | $0.62 | $0.62 | 47 | |
| R1 | DeepSeek | 64K | 16K | 25% | $0.70 | $2.50 | 45 | |
| Llama 3.2 1B Instruct | Meta | 60K | 54K | 90% | $0.03 | $0.20 | 76 | |
| GLM 5.2 (free) | Zhipu AI | 33K | 29K | 90% | Free | Free | 75 | |
| Perceptron Mk1 | perceptron | 33K | 8K | 25% | $0.15 | $1.50 | 62 | |
| Voxtral Small 24B 2507 | Mistral AI | 33K | 26K | 80% | $0.10 | $0.30 | 66 | |
| Saba | Mistral AI | 33K | 26K | 80% | $0.20 | $0.60 | 59 | |
| Mistral Small 3 | Mistral AI | 33K | 16K | 50% | $0.05 | $0.08 | 70 | |
| Qwen2.5 Coder 32B Instruct | Alibaba | 33K | 29K | 90% | $0.66 | $1.00 | 43 | |
| Qwen2.5 7B Instruct | Alibaba | 33K | 29K | 90% | $0.10 | $0.20 | 66 | |
| Qwen2.5 72B Instruct | Alibaba | 33K | 16K | 50% | $0.36 | $0.40 | 52 | |
| Falcon Arabic 7B Instruct | TII | 33K | 8K | 25% | Free | Free | 75 | |
| Falcon3 10B Instruct | TII | 33K | 8K | 25% | Free | Free | 75 | |
| Falcon3 7B Instruct | TII | 33K | 8K | 25% | Free | Free | 75 | |
| Falcon Mamba 7B Instruct | TII | 33K | 8K | 25% | Free | Free | 75 | |
| GPT-3.5 Turbo 16k | OpenAI | 16K | 4K | 25% | $3.00 | $4.00 | 23 | |
| GPT-3.5 Turbo | OpenAI | 16K | 4K | 25% | $0.50 | $1.50 | 44 | |
| GPT-3.5 Turbo (batch) | OpenAI | 16K | 4K | 25% | $0.25 | $0.75 | 53 | |
| Reka Edge | rekaai | 16K | 15K | 90% | $0.10 | $0.10 | 62 | |
| Phi 4 | Microsoft | 16K | 15K | 90% | $0.07 | $0.14 | 64 | |
| Hy-MT2-1.8B | Tencent | 8K | 4K | 50% | $0.04 | $0.18 | 61 | |
| Hy-MT2-30B-A3B | Tencent | 8K | 4K | 50% | $0.07 | $0.29 | 59 | |
| Hy-MT2-7B | Tencent | 8K | 4K | 50% | $0.07 | $0.29 | 59 | |
| R1 Distill Llama 70B | DeepSeek | 8K | 7K | 90% | $0.80 | $0.80 | 35 | |
| Gemma 2 27B | 8K | 2K | 25% | $0.65 | $0.65 | 38 | ||
| GPT-4 | OpenAI | 8K | 4K | 50% | $30.00 | $60.00 | 11 | |
| ALLaM 7B Instruct (preview) | HUMAIN | 4K | 4K | 100% | Free | Free | 60 | |
| ALLaM 1 13B Instruct | HUMAIN | 4K | 4K | 100% | $1.80 | $1.80 | 24 | |
| ALLaM 2 7B Instruct | HUMAIN | 4K | 4K | 100% | Free | Free | 60 | |
| ALLaM 34B | HUMAIN | 4K | 4K | 100% | Free | Free | 60 | |
| GPT-3.5 Turbo (older v0613) | OpenAI | 4K | 4K | 90% | $1.00 | $2.00 | 30 | |
| GPT-3.5 Turbo Instruct | OpenAI | 4K | 4K | 90% | $1.50 | $2.00 | 26 | |
| SWE-1.5 | Windsurf | — | — | — | Free | Free | 0 | |
| autofixer-01 | Vercel | — | — | — | Free | Free | 0 | |
| Mellum | JetBrains | — | — | — | Free | Free | 0 |
Capabilities:VisionFunctionsStreamingJSON ModeReasoningWeb SearchImage Output
Image Generation Models
| Model | Provider | Input $/1M | Output $/1M | Capabilities |
|---|---|---|---|---|
| GPT-5 Image | OpenAI | $10.00 | $10.00 | |
| GPT-5.4 Image 2 | OpenAI | $8.00 | $15.00 | |
| GPT-5 Image Mini | OpenAI | $2.50 | $2.00 | |
| Nano Banana Pro (Gemini 3 Pro Image) | $2.00 | $12.00 | ||
| Nano Banana Pro (Gemini 3 Pro Image Preview) | $2.00 | $12.00 | ||
| Nano Banana 2 (Gemini 3.1 Flash Image) | $0.50 | $3.00 | ||
| Nano Banana 2 (Gemini 3.1 Flash Image Preview) | $0.50 | $3.00 | ||
| Nano Banana (Gemini 2.5 Flash Image) | $0.30 | $2.50 | ||
| Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) | $0.25 | $1.50 | ||
| Midjourney v6.1 | Midjourney | Free | Free | |
| DALL-E 3 | OpenAI | Free | $40000.00 | |
| Stable Diffusion 3.5 | Stability AI | Free | $35000.00 | |
| FLUX.1 Pro | Black Forest Labs | Free | $50000.00 | |
| Ideogram 2.0 | Ideogram | Free | $80000.00 | |
| Recraft V3 | Recraft | Free | $40000.00 | |
| Imagen 3 | Free | $40000.00 | ||
| Adobe Firefly 3 | Adobe | Free | Free | |
| Leonardo Phoenix | Leonardo AI | Free | Free |
Frequently Asked Questions
AI speed is measured by time-to-first-token (TTFT) and tokens-per-second (TPS). TTFT measures how quickly the model starts responding. TPS measures how fast it generates output. Both matter for different use cases.
Speed varies by provider. Groq-hosted Llama achieves the fastest inference. Among major providers, Gemini Flash and GPT-4o Mini are consistently fast. Reasoning models like o3 and R1 are intentionally slower for better accuracy.
Smaller, faster models may sacrifice some quality. However, provider optimizations (quantization, speculative decoding) can speed up models without quality loss. The same model runs at different speeds on different providers.