LLM API pricing, model by model
Each model page compares every provider serving it (first-party APIs, resellers and marketplaces), sorted by price. Open-weight models also get the self-hosting math.
Refreshed 2026-10-20 · 209 models with 2+ providers, plus 103 recent single-provider listings| Model | Cheapest in $/1M | Cheapest out $/1M | Providers | Listed | Cheapest input at |
|---|---|---|---|---|---|
| Glimpse | $0.600 | $3.00 | 1 | 2026-10-17 | OpenRouter |
| Beam 1.0 501B A23B | $0.300 | $1.00 | 2 | 2026-10-16 | OpenRouter |
| Mercury 3 | $0.100 | $0.350 | 1 | 2026-10-16 | OpenRouter |
| Muse Spark Open | $1.25 | $4.25 | 3 | 2026-10-15 | Fireworks AI |
| Nemotron 3.5 Super VL | $0.150 | $0.500 | 2 | 2026-10-15 | Together AI |
| Moondream 3 Preview | $0.300 | $2.50 | 1 | 2026-10-15 | OpenRouter |
| Moondream 3.1 | $0.300 | $2.50 | 1 | 2026-10-15 | OpenRouter |
| Pareto 26.10 | $0.800 | $3.20 | 1 | 2026-10-15 | OpenRouter |
| Gemini 4 Argon | $2.00 | $10.00 | 4 | 2026-10-13 | Google Gemini API |
| Extract | $0.040 | free | 2 | 2026-10-13 | OpenRouter |
| Summarize | $0.040 | free | 2 | 2026-10-13 | OpenRouter |
| Pareto Latest | $0.800 | $3.20 | 1 | 2026-10-13 | OpenRouter |
| Pareto 26.9 | $2.50 | $7.50 | 1 | 2026-10-13 | OpenRouter |
| LFM2.5-24B-A2B | $0.050 | $0.700 | 1 | 2026-10-13 | OpenRouter |
| Gemini 4 Argon (batch) | $1.00 | $5.00 | 1 | 2026-10-13 | OpenRouter |
| Muse Wonder | $4.00 | $20.00 | 1 | 2026-10-12 | OpenRouter |
| Step 5 Preview | $1.00 | $2.70 | 1 | 2026-10-08 | OpenRouter |
| Claude Haiku 5.5 | $0.100 | $0.500 | 6 | 2026-10-07 | Github Copilot |
| Claude Haiku 5.5 (batch) | $0.050 | $0.250 | 1 | 2026-10-07 | OpenRouter |
| Mistral Large 4 | $0.680 | $2.09 | 2 | 2026-10-06 | Mistral AI |
| Nano Banana 2.1 | $1.50 | $7.50 | 1 | 2026-10-06 | OpenRouter |
| Ling 3.1 Flash | $0.075 | $0.225 | 1 | 2026-10-02 | OpenRouter |
| GPT-6.1 Sol | $2.00 | $10.00 | 4 | 2026-09-29 | Azure AI Foundry |
| GPT-6.1 Sol Pro | $2.00 | $10.00 | 1 | 2026-09-29 | OpenRouter |
| GPT-6.1 Sol Pro (batch) | $1.00 | $5.00 | 1 | 2026-09-29 | OpenRouter |
| GPT-6.1 Sol (batch) | $1.00 | $5.00 | 1 | 2026-09-29 | OpenRouter |
| Claude Sonnet 5.5 | $2.00 | $10.00 | 6 | 2026-09-28 | Anthropic |
| Claude Sonnet 5.5 (batch) | $1.00 | $5.00 | 1 | 2026-09-28 | OpenRouter |
| Perceptron Mk1.5 | $0.150 | $1.50 | 1 | 2026-09-25 | OpenRouter |
| Ember-1 | $3.00 | $15.00 | 2 | 2026-09-24 | Fireworks AI |
| GLM 5.3 Prime | $2.80 | $8.80 | 1 | 2026-09-23 | OpenRouter |
| Qwen3.8 Max Prime | $4.00 | $12.00 | 1 | 2026-09-23 | OpenRouter |
| Aion 3.5 Mini | $0.700 | $1.40 | 1 | 2026-09-23 | OpenRouter |
| Aion 3.5 | $3.00 | $6.00 | 1 | 2026-09-23 | OpenRouter |
| Solar Mini 4 | $0.050 | $0.200 | 1 | 2026-09-23 | OpenRouter |
| Claude Opus 5.5 | $4.00 | $20.00 | 7 | 2026-09-22 | AWS Bedrock |
| GPT-6 Luna | $0.100 | $0.500 | 4 | 2026-09-22 | Azure AI Foundry |
| GPT-6 Sol | $2.00 | $10.00 | 4 | 2026-09-22 | Azure AI Foundry |
| Command A+ | $0.300 | $1.50 | 1 | 2026-09-22 | OpenRouter |
| GPT-6 Luna Pro | $0.100 | $0.500 | 1 | 2026-09-22 | OpenRouter |
| GPT-6 Luna Pro (batch) | $0.050 | $0.250 | 1 | 2026-09-22 | OpenRouter |
| GPT-6 Luna (batch) | $0.050 | $0.250 | 1 | 2026-09-22 | OpenRouter |
| GPT-6 Sol Pro | $2.00 | $10.00 | 1 | 2026-09-22 | OpenRouter |
| GPT-6 Sol Pro (batch) | $1.00 | $5.00 | 1 | 2026-09-22 | OpenRouter |
| GPT-6 Sol (batch) | $1.00 | $5.00 | 1 | 2026-09-22 | OpenRouter |
| Claude Opus 5.5 (batch) | $2.00 | $10.00 | 1 | 2026-09-22 | OpenRouter |
| Grok 4.7 | $2.00 | $6.00 | 6 | 2026-09-21 | xAI |
| Qwen3.8 Omni Flash | $0.150 | $0.470 | 3 | 2026-09-21 | Alibaba Model Studio |
| MiMo-V2.6-Pro | $0.435 | $0.870 | 2 | 2026-09-21 | Xiaomi Mimo |
| MiMo-V2.6-Flash | $0.140 | $0.280 | 2 | 2026-09-21 | Xiaomi Mimo |
| MiMo-V2.6-Pro-UltraSpeed | $4.35 | $8.70 | 1 | 2026-09-21 | OpenRouter |
| GLM 5.3 FlashX | $0.370 | $1.25 | 2 | 2026-09-18 | Tencent |
| Ternary Bonsai 2 27B | $0.075 | $0.500 | 1 | 2026-09-18 | OpenRouter |
| DeepSeek Flash Latest | $0.070 | $0.500 | 3 | 2026-09-14 | OpenRouter |
| DeepSeek Pro Latest | $0.131 | $8.00 | 1 | 2026-09-14 | OpenRouter |
| Schematron V2 Turbo | $0.030 | $0.150 | 1 | 2026-09-12 | OpenRouter |
| Schematron V2 Small | $0.050 | $0.230 | 1 | 2026-09-12 | OpenRouter |
| GPT Astra Latest | $10.00 | $50.00 | 1 | 2026-09-11 | OpenRouter |
| GPT Sol Latest | $2.00 | $10.00 | 1 | 2026-09-11 | OpenRouter |
| GPT Terra Latest | $2.00 | $12.00 | 1 | 2026-09-11 | OpenRouter |
| GPT Luna Latest | $0.100 | $0.500 | 1 | 2026-09-11 | OpenRouter |
| Fugu Ultra v2 | $5.00 | $30.00 | 1 | 2026-09-11 | OpenRouter |
| Fugu Max | $2.00 | $6.00 | 1 | 2026-09-11 | OpenRouter |
| DeepSeek V4.1 Flash | $0.010 | $0.120 | 15 | 2026-09-10 | Coralbricks |
| Ling 3.0 Flash VL | $0.060 | $0.180 | 1 | 2026-09-10 | OpenRouter |
| DeepSeek V4.1 Flash (batch) | $0.050 | $0.150 | 1 | 2026-09-10 | OpenRouter |
| Mercury 2.5 | $0.040 | $0.150 | 2 | 2026-09-08 | OpenRouter |
| Nex-N2.5-Mini | $0.025 | $0.100 | 1 | 2026-09-08 | OpenRouter |
| Nex-N2.5-Pro | $0.075 | $0.250 | 1 | 2026-09-08 | OpenRouter |
| GPT-6 Astra | $10.00 | $50.00 | 4 | 2026-09-04 | Azure AI Foundry |
| GPT-6 Astra (batch) | $5.00 | $25.00 | 1 | 2026-09-04 | OpenRouter |
| GPT-6 Astra Pro | $10.00 | $50.00 | 1 | 2026-09-04 | OpenRouter |
| GPT-6 Astra Pro (batch) | $5.00 | $25.00 | 1 | 2026-09-04 | OpenRouter |
| Qwen3.8 Max (0902) | $1.65 | $4.95 | 9 | 2026-09-03 | Scx AI |
| Gemini 3.8 Flash | $0.750 | $3.75 | 4 | 2026-09-02 | Google Vertex AI |
| Muse Spark 1.3 | $1.25 | $4.25 | 2 | 2026-09-02 | Meta |
| Muse Spark 1.3 Contributor | $0.100 | $0.200 | 2 | 2026-09-02 | Meta |
| Gemini 3.8 Flash (batch) | $0.375 | $1.88 | 1 | 2026-09-02 | OpenRouter |
| Claude Fable 5.1 | $10.00 | $50.00 | 7 | 2026-09-01 | AWS Bedrock |
| Claude Fable 5.1 (batch) | $5.00 | $25.00 | 1 | 2026-09-01 | OpenRouter |
| Granite 4.2 8B | $0.060 | $0.150 | 2 | 2026-08-31 | OpenRouter |
| Hy4 preview | $0.751 | $2.25 | 2 | 2026-08-28 | OpenRouter |
| GLM Flash Latest | $0.048 | $0.160 | 1 | 2026-08-27 | OpenRouter |
| GLM 5.3 Flash | $0.048 | $0.160 | 14 | 2026-08-26 | OpenRouter |
| Qwen3.8 Flash | $0.113 | $0.380 | 6 | 2026-08-26 | Aihubmix |
| GLM 5.3 Flash (batch) | $0.050 | $0.180 | 1 | 2026-08-26 | OpenRouter |
| DeepSeek V4 Flash Vision Exp | $0.216 | $0.647 | 4 | 2026-08-21 | OpenRouter |
| Muse Spark 1.2 Contributor | $0.100 | $0.200 | 2 | 2026-08-21 | Meta |
| Hy-MT2-1.8B | $0.044 | $0.177 | 1 | 2026-08-20 | OpenRouter |
| Hy-MT2-30B-A3B | $0.074 | $0.295 | 1 | 2026-08-20 | OpenRouter |
| GLM Latest | $0.079 | $1.40 | 2 | 2026-08-19 | OpenRouter |
| Hy-MT2-7B | $0.074 | $0.295 | 1 | 2026-08-19 | OpenRouter |
| GLM 5.3 | $0.079 | $1.40 | 17 | 2026-08-18 | OpenRouter |
| GLM 5.3 (batch) | $0.450 | $2.00 | 1 | 2026-08-18 | OpenRouter |
| Qwen3.8 27B | $0.040 | $1.35 | 5 | 2026-08-14 | OpenRouter |
| Gemini 3.7 Flash | $0.750 | $3.75 | 6 | 2026-08-13 | Google Vertex AI |
| Gemini 3.7 Flash (batch) | $0.375 | $1.88 | 1 | 2026-08-13 | OpenRouter |
| Grok 4.6 | $2.00 | $6.00 | 8 | 2026-08-12 | Azure AI Foundry |
| Qwen3.8 2.4T A95B | $2.00 | $6.00 | 4 | 2026-08-12 | Together AI |
| Seed-2.0-Code | $0.500 | $3.00 | 2 | 2026-08-12 | DeepInfra |
| Seed 2.1 Turbo | $0.500 | $2.50 | 1 | 2026-08-12 | OpenRouter |
| Nemotron 3.5 Lightning | $0.060 | $0.200 | 3 | 2026-08-11 | Nebius |
| Sakana Namazu | $0.950 | $4.00 | 1 | 2026-08-11 | OpenRouter |
| Solar Pro 4 | $0.150 | $0.600 | 1 | 2026-08-10 | OpenRouter |
| Muse Glimmer 30B | $0.300 | $1.20 | 4 | 2026-08-09 | DeepInfra |
| Muse Spark 1.2 | $1.25 | $4.25 | 3 | 2026-08-05 | Meta |
| Inkling Small | $0.450 | $1.20 | 3 | 2026-07-30 | DeepInfra |
| Qwen3.7 Flash | $0.030 | $0.130 | 1 | 2026-07-27 | OpenRouter |
| Claude Opus 5 | $5.00 | $25.00 | 9 | 2026-07-24 | AWS Bedrock |
| Claude Opus 5 (batch) | $2.50 | $12.50 | 1 | 2026-07-24 | OpenRouter |
| Ling 3.0 Flash | $0.021 | $0.063 | 3 | 2026-07-23 | OpenRouter |
| Gemini 3.5 Flash Lite | $0.300 | $2.50 | 5 | 2026-07-21 | Google Vertex AI |
| Gemini 3.6 Flash | $0.750 | $3.75 | 4 | 2026-07-21 | Google Vertex AI |
| Laguna S 2.1 | $0.090 | $0.180 | 1 | 2026-07-21 | OpenRouter |
| Gemini 3.6 Flash (batch) | $0.375 | $1.88 | 1 | 2026-07-21 | OpenRouter |
| Gemini 3.5 Flash Lite (batch) | $0.150 | $1.25 | 1 | 2026-07-21 | OpenRouter |
| LongCat 2.0 | $0.300 | $1.20 | 2 | 2026-07-20 | OpenRouter |
| Inkling | $0.950 | $4.05 | 6 | 2026-07-17 | DeepInfra |
| Kimi K3 | $0.239 | $11.94 | 15 | 2026-07-16 | OpenRouter |
| Muse Spark 1.1 | $1.25 | $4.25 | 2 | 2026-07-16 | Meta |
| Kimi K3 (batch) | $2.28 | $11.40 | 1 | 2026-07-16 | OpenRouter |
| GPT-5.6 Terra | $2.00 | $12.00 | 6 | 2026-07-09 | Azure AI Foundry |
| GPT-5.6 Luna | $0.200 | $1.20 | 6 | 2026-07-09 | Azure AI Foundry |
| GPT-5.6 Sol | $4.00 | $20.00 | 5 | 2026-07-09 | Azure AI Foundry |
| GPT-5.6 Luna Pro | $0.200 | $1.20 | 1 | 2026-07-09 | OpenRouter |
| GPT-5.6 Luna Pro (batch) | $0.100 | $0.600 | 1 | 2026-07-09 | OpenRouter |
| GPT-5.6 Luna (batch) | $0.100 | $0.600 | 1 | 2026-07-09 | OpenRouter |
| GPT-5.6 Terra Pro | $2.00 | $12.00 | 1 | 2026-07-09 | OpenRouter |
| GPT-5.6 Terra Pro (batch) | $1.00 | $6.00 | 1 | 2026-07-09 | OpenRouter |
| GPT-5.6 Terra (batch) | $1.00 | $6.00 | 1 | 2026-07-09 | OpenRouter |
| GPT-5.6 Sol Pro | $4.00 | $20.00 | 1 | 2026-07-09 | OpenRouter |
| GPT-5.6 Sol Pro (batch) | $2.00 | $10.00 | 1 | 2026-07-09 | OpenRouter |
| GPT-5.6 Sol (batch) | $2.00 | $10.00 | 1 | 2026-07-09 | OpenRouter |
| Grok 4.5 | $2.00 | $6.00 | 3 | 2026-07-08 | xAI |
| Grok Latest | $2.00 | $6.00 | 1 | 2026-07-08 | OpenRouter |
| Aion-3.0-Mini | $0.700 | $1.40 | 1 | 2026-07-07 | OpenRouter |
| Aion-3.0 | $3.00 | $6.00 | 1 | 2026-07-07 | OpenRouter |
| Hy3 | $0.083 | $0.330 | 4 | 2026-07-06 | OpenRouter |
| Laguna XS 2.1 | $0.060 | $0.120 | 1 | 2026-07-02 | OpenRouter |
| Claude Sonnet 5 | $2.00 | $10.00 | 9 | 2026-06-30 | AWS Bedrock |
| Claude Sonnet 5 (batch) | $1.00 | $5.00 | 1 | 2026-06-30 | OpenRouter |
| Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) | $0.250 | $1.50 | 1 | 2026-06-30 | OpenRouter |
| Fugu Ultra | $5.00 | $30.00 | 1 | 2026-06-24 | OpenRouter |
| GLM-5.2open weights · MIT | $0.610 | $1.98 | 20 | 2026-06-16 | Scx AI |
| Kimi K2.7 Codeopen weights · Modified MIT | $0.671 | $3.35 | 16 | 2026-06-12 | OpenRouter |
| Claude Fable 5 | $10.00 | $50.00 | 9 | 2026-06-09 | AWS Bedrock |
| Claude Fable Latest | $10.00 | $50.00 | 1 | 2026-06-09 | OpenRouter |
| Claude Fable 5 (batch) | $5.00 | $25.00 | 1 | 2026-06-09 | OpenRouter |
| Nemotron 3 Ultraopen weights · OpenMDW-1.1 | $0.500 | $2.15 | 6 | 2026-06-04 | W&B Inference |
| Nemotron 3.5 Content Safety | $0.200 | $0.200 | 1 | 2026-06-04 | OpenRouter |
| Qwen3.7 Plus | $0.282 | $1.13 | 4 | 2026-06-03 | Aihubmix |
| Qwen3.7 Plus (batch) | $0.230 | $0.920 | 1 | 2026-06-03 | OpenRouter |
| MiniMax M3open weights · MiniMax Community | $0.230 | $0.960 | 11 | 2026-05-31 | W&B Inference |
| Step 3.7 Flash | $0.200 | $1.15 | 4 | 2026-05-28 | Novita AI |
| Claude Opus 4.8 | $5.00 | $25.00 | 8 | 2026-05-27 | AWS Bedrock |
| Claude Opus 4.8 (batch) | $2.50 | $12.50 | 1 | 2026-05-27 | OpenRouter |
| Qwen3.7 Max | $1.25 | $3.75 | 7 | 2026-05-21 | Novita AI |
| Grok Build 0.1 | $1.00 | $2.00 | 3 | 2026-05-20 | xAI |
| Gemini 3.5 Flash | $1.50 | $9.00 | 5 | 2026-05-19 | Google Vertex AI |
| Gemini 3.5 Flash (batch) | $0.750 | $4.50 | 1 | 2026-05-19 | OpenRouter |
| Perceptron Mk1 | $0.150 | $1.50 | 1 | 2026-05-12 | OpenRouter |
| Gemini 3.1 Flash Lite | $0.250 | $1.50 | 5 | 2026-05-07 | Google Vertex AI |
| Gemini 3.1 Flash Lite (batch) | $0.125 | $0.750 | 1 | 2026-05-07 | OpenRouter |
| GPT Chat Latest | $5.00 | $30.00 | 3 | 2026-05-05 | Azure AI Foundry |
| Grok 4.3 | $1.25 | $2.50 | 5 | 2026-04-30 | Azure AI Foundry |
| Mistral Medium 3.5open weights · Modified MIT (revenue cap) | $1.50 | $7.50 | 3 | 2026-04-30 | Mistral AI |
| Grok 4.3 (batch) | $1.00 | $2.00 | 1 | 2026-04-30 | OpenRouter |
| Mistral Medium 3.5 (batch) | $0.750 | $3.75 | 1 | 2026-04-30 | OpenRouter |
| Qwen3.6 35B A3Bopen weights · Apache-2.0 | $0.050 | $0.400 | 9 | 2026-04-27 | Sail |
| Qwen3.6 27Bopen weights · Apache-2.0 | $0.150 | $0.500 | 7 | 2026-04-27 | Libertai |
| Gemini Flash Latest | $0.750 | $3.75 | 2 | 2026-04-27 | Google Gemini API |
| Gemini Pro Latest | $2.00 | $10.00 | 2 | 2026-04-27 | Google Gemini API |
| Claude Haiku Latest | $0.100 | $0.500 | 1 | 2026-04-27 | OpenRouter |
| GPT Mini Latest | $0.750 | $4.50 | 1 | 2026-04-27 | OpenRouter |
| Kimi Latest | $0.238 | $16.00 | 1 | 2026-04-27 | OpenRouter |
| Claude Sonnet Latest | $2.00 | $10.00 | 1 | 2026-04-27 | OpenRouter |
| Qwen3.5 Plus 2026-04-20 | $0.300 | $1.80 | 1 | 2026-04-27 | OpenRouter |
| Qwen3.6 Flash | $0.188 | $1.13 | 1 | 2026-04-27 | OpenRouter |
| DeepSeek V4 Flashopen weights · MIT | $0.090 | $0.180 | 23 | 2026-04-24 | Sail |
| DeepSeek V4 Proopen weights · MIT | $0.395 | $0.791 | 18 | 2026-04-24 | OpenRouter |
| GPT-5.5 | $5.00 | $30.00 | 5 | 2026-04-24 | Azure AI Foundry |
| GPT-5.5 Pro | $30.00 | $180 | 2 | 2026-04-24 | Aihubmix |
| GPT-5.5 Pro (batch) | $15.00 | $90.00 | 1 | 2026-04-24 | OpenRouter |
| GPT-5.5 (batch) | $2.50 | $15.00 | 1 | 2026-04-24 | OpenRouter |
| Kimi K2.6open weights · Modified MIT | $0.650 | $3.40 | 14 | 2026-04-20 | W&B Inference |
| Claude Opus 4.7 | $5.00 | $25.00 | 7 | 2026-04-16 | AWS Bedrock |
| GLM-5.1open weights · MIT | $0.966 | $3.04 | 11 | 2026-04-07 | OpenRouter |
| Gemma 4 26B A4B | $0.070 | $0.300 | 8 | 2026-04-03 | DeepInfra |
| Gemma 4 31B | $0.100 | $0.340 | 11 | 2026-04-02 | W&B Inference |
| MiniMax M2.7open weights · Modified MIT | $0.250 | $0.550 | 7 | 2026-03-18 | DeepInfra |
| GPT-5.4 Mini | $0.750 | $4.50 | 5 | 2026-03-17 | Azure AI Foundry |
| GPT-5.4 Nano | $0.200 | $1.25 | 5 | 2026-03-17 | Azure AI Foundry |
| Mistral Small 4 | $0.100 | $0.300 | 7 | 2026-03-16 | Mistral AI |
| Nemotron 3 Superopen weights · NVIDIA Open Model | $0.080 | $0.400 | 3 | 2026-03-11 | OpenRouter |
| Qwen3.5-9B | $0.100 | $0.150 | 4 | 2026-03-10 | DeepInfra |
| GPT-5.4 | $2.50 | $15.00 | 6 | 2026-03-05 | Azure AI Foundry |
| Qwen3.5-122B-A10B | $0.113 | $0.901 | 5 | 2026-02-25 | Aihubmix |
| Gemini 3.1 Pro Preview Custom Tools | $2.00 | $12.00 | 4 | 2026-02-25 | Google Vertex AI |
| Qwen3.5 27Bopen weights · Apache-2.0 | $0.195 | $1.56 | 4 | 2026-02-25 | Openinfer |
| Qwen3.5 35B A3Bopen weights · Apache-2.0 | $0.140 | $1.00 | 4 | 2026-02-25 | DeepInfra |
| Gemini 3.1 Pro Preview | $2.00 | $12.00 | 6 | 2026-02-19 | Google Vertex AI |
| Claude Sonnet 4.6 | $3.00 | $15.00 | 9 | 2026-02-17 | AWS Bedrock |
| Qwen3.5 397B A17Bopen weights · Apache-2.0 | $0.164 | $0.986 | 8 | 2026-02-16 | Aihubmix |
| MiniMax M2.5open weights · Modified MIT | $0.270 | $0.950 | 8 | 2026-02-12 | OpenRouter |
| GLM-5open weights · MIT | $0.600 | $2.08 | 9 | 2026-02-11 | DeepInfra |
| Claude Opus 4.6 | $5.00 | $25.00 | 7 | 2026-02-04 | AWS Bedrock |
| Kimi K2.5open weights · Modified MIT | $0.450 | $2.25 | 9 | 2026-01-27 | DeepInfra |
| GLM-4.7 Flashopen weights · MIT | $0.060 | $0.400 | 5 | 2026-01-19 | DeepInfra |
| MiniMax M2.1open weights · Modified MIT | $0.300 | $1.20 | 6 | 2025-12-23 | AWS Bedrock |
| GLM-4.7open weights · MIT | $0.400 | $1.75 | 10 | 2025-12-22 | GMI Cloud |
| Gemini 3 Flash Preview | $0.500 | $3.00 | 6 | 2025-12-17 | Google Vertex AI |
| Nemotron 3 Nanoopen weights · NVIDIA Open Model | $0.050 | $0.200 | 4 | 2025-12-14 | Novita AI |
| GPT-5.2 | $1.75 | $14.00 | 5 | 2025-12-10 | Azure AI Foundry |
| Ministral 3 3B 2512 | $0.040 | $0.040 | 4 | 2025-12-02 | Azure AI Foundry |
| DeepSeek V3.2open weights · MIT | $0.260 | $0.380 | 11 | 2025-12-01 | DeepInfra |
| Claude Opus 4.5 | $5.00 | $25.00 | 8 | 2025-11-24 | AWS Bedrock |
| GPT-5.1 | $1.25 | $10.00 | 5 | 2025-11-13 | Azure AI Foundry |
| Kimi K2 Thinkingopen weights · Modified MIT | $0.600 | $1.20 | 9 | 2025-11-06 | AWS Bedrock |
| GPT-OSS-Safeguard-20b | $0.070 | $0.200 | 4 | 2025-10-29 | AWS Bedrock |
| MiniMax M2open weights · MIT | $0.255 | $1.02 | 6 | 2025-10-23 | OpenRouter |
| Claude Haiku 4.5 | $1.00 | $5.00 | 12 | 2025-10-15 | AWS Bedrock |
| Qwen3 VL 8B Instruct | $0.080 | $0.200 | 5 | 2025-10-14 | Novita AI |
| Qwen3 VL 30B A3B Instruct | $0.150 | $0.600 | 4 | 2025-10-06 | Fireworks AI |
| GLM-4.6open weights · MIT | $0.450 | $1.80 | 8 | 2025-09-30 | Vercel AI Gateway |
| Claude Sonnet 4.5 | $3.00 | $15.00 | 10 | 2025-09-29 | AWS Bedrock |
| Qwen3 VL 235B A22B Instruct | $0.200 | $0.880 | 9 | 2025-09-23 | DeepInfra |
| DeepSeek V3.1 Terminus | $0.270 | $1.00 | 4 | 2025-09-22 | DeepInfra |
| Qwen3 Next 80B A3B Instruct | $0.090 | $0.900 | 10 | 2025-09-11 | DeepInfra |
| Qwen3 Next 80B A3B Thinking | $0.140 | $0.900 | 10 | 2025-09-11 | DeepInfra |
| GLM 4.5V | $0.600 | $1.20 | 4 | 2025-08-11 | Z.ai |
| GPT-5 | $1.25 | $10.00 | 8 | 2025-08-07 | Azure AI Foundry |
| GPT-5 Mini | $0.250 | $1.20 | 8 | 2025-08-07 | Azure AI Foundry |
| GPT-5 Nano | $0.050 | $0.400 | 7 | 2025-08-07 | Azure AI Foundry |
| GPT-OSS 120Bopen weights · Apache-2.0 | $0.030 | $0.170 | 25 | 2025-08-05 | W&B Inference |
| GPT-OSS 20Bopen weights · Apache-2.0 | $0.015 | $0.070 | 17 | 2025-08-05 | Darkbloom |
| Claude Opus 4.1 | $15.00 | $75.00 | 4 | 2025-08-05 | AWS Bedrock |
| Codestral 2508 | $0.200 | $0.600 | 5 | 2025-08-01 | Google Vertex AI |
| Qwen3 Coder 30B A3B Instruct | $0.070 | $0.270 | 5 | 2025-07-31 | Novita AI |
| GLM-4.5 Airopen weights · MIT | $0.125 | $0.450 | 7 | 2025-07-25 | Pinstripes |
| GLM-4.5open weights · MIT | $0.400 | $1.60 | 6 | 2025-07-25 | DeepInfra |
| Qwen3 235B A22B Thinking 2507 | $0.220 | $0.880 | 4 | 2025-07-25 | Fireworks AI |
| Qwen3 Coderopen weights · Apache-2.0 | $0.300 | $1.00 | 2 | 2025-07-23 | OpenRouter |
| Gemini 2.5 Flash Lite | $0.075 | $0.300 | 4 | 2025-07-22 | Oracle OCI |
| Qwen3 235B A22Bopen weights · Apache-2.0 | $0.090 | $0.540 | 10 | 2025-07-21 | OpenRouter |
| Kimi K2open weights · Modified MIT | $0.500 | $2.00 | 8 | 2025-07-11 | DeepInfra |
| Mistral Small 3.2 24B | $0.075 | $0.200 | 4 | 2025-06-20 | DeepInfra |
| Gemini 2.5 Flash | $0.150 | $0.600 | 8 | 2025-06-17 | Oracle OCI |
| Gemini 2.5 Pro | $1.25 | $10.00 | 7 | 2025-06-17 | Databricks |
| DeepSeek R1open weights · MIT | $0.200 | $0.400 | 17 | 2025-05-28 | Lambda |
| Qwen3 30B A3Bopen weights · Apache-2.0 | $0.051 | $0.200 | 8 | 2025-04-28 | Cloudflare |
| Qwen3 32Bopen weights · Apache-2.0 | $0.050 | $0.100 | 7 | 2025-04-28 | Lambda |
| Qwen3 14B | $0.050 | $0.200 | 5 | 2025-04-28 | W&B Inference |
| O3 | $2.00 | $8.00 | 5 | 2025-04-16 | Azure AI Foundry |
| o4 Mini | $1.00 | $4.00 | 5 | 2025-04-16 | Replicate |
| GPT-4.1 | $2.00 | $8.00 | 6 | 2025-04-14 | Azure AI Foundry |
| GPT-4.1 Mini | $0.400 | $1.60 | 5 | 2025-04-14 | Azure AI Foundry |
| GPT-4.1 Nano | $0.100 | $0.400 | 5 | 2025-04-14 | Azure AI Foundry |
| Gemma 3 12Bopen weights · Gemma | $0.050 | $0.100 | 5 | 2025-03-13 | DeepInfra |
| Gemma 3 27Bopen weights · Gemma | $0.080 | $0.160 | 6 | 2025-03-12 | DeepInfra |
| Qwen2.5 VL 72B Instruct | $0.250 | $0.750 | 6 | 2025-02-01 | Nebius |
| Qwen-Plus | $0.260 | $0.780 | 4 | 2025-02-01 | OpenRouter |
| o3 Mini | $1.10 | $4.40 | 5 | 2025-01-31 | Azure AI Foundry |
| Mistral Small 3 | $0.050 | $0.080 | 4 | 2025-01-30 | DeepInfra |
| Phi-4open weights · MIT | $0.070 | $0.140 | 3 | 2025-01-10 | DeepInfra |
| O1 | $15.00 | $60.00 | 5 | 2024-12-17 | Azure AI Foundry |
| Llama 3.3 70Bopen weights · Llama 3.3 Community | $0.100 | $0.200 | 18 | 2024-12-06 | OpenRouter |
| Llama 3.2 3Bopen weights · Llama 3.2 Community | $0.020 | $0.020 | 9 | 2024-09-25 | DeepInfra |
| Llama 3.2 1B Instruct | $0.020 | $0.020 | 6 | 2024-09-25 | Novita AI |
| Llama 3.1 8Bopen weights · Llama 3.1 Community | $0.020 | $0.030 | 13 | 2024-07-23 | Nebius |
| Llama 3.1 70B Instruct | $0.120 | $0.300 | 10 | 2024-07-23 | Hyperbolic |
| Mistral Nemo | $0.019 | $0.030 | 9 | 2024-07-19 | DeepInfra |
| GPT-4o-Mini | $0.150 | $0.600 | 6 | 2024-07-18 | Azure AI Foundry |
| GPT-4o | $2.50 | $10.00 | 6 | 2024-05-13 | Azure AI Foundry |
| GPT-4 Turbo | $10.00 | $30.00 | 4 | 2024-04-09 | OpenAI |
| Mistral Large | $0.500 | $1.50 | 7 | 2024-02-26 | Mistral AI |
| MythoMax 13B | $0.080 | $0.090 | 4 | 2023-07-02 | OpenRouter |
| GPT-3.5 Turbo | $0.500 | $1.50 | 4 | 2023-05-28 | Vercel AI Gateway |
| DeepSeek V3open weights · MIT | $0.190 | $0.200 | 16 | - | Inferenceapis |
| DeepSeek-V3.1 | $0.250 | $0.950 | 11 | - | DeepInfra |
| Llama 4 Scoutopen weights · Llama 4 Community | $0.050 | $0.100 | 9 | - | Lambda |
| DeepSeek R1 Distill Llama 70Bopen weights · MIT | $0.200 | $0.375 | 9 | - | DeepInfra |
| Llama 4 Maverickopen weights · Llama 4 Community | $0.050 | $0.100 | 8 | - | Lambda |
| Claude-Sonnet-4 | $3.00 | $15.00 | 7 | - | AWS Bedrock |
| QwQ-32B | $0.150 | $0.200 | 7 | - | DeepInfra |
| Claude-3-5-Sonnet | $3.00 | $15.00 | 6 | - | AWS Bedrock |
| Claude-3.7-Sonnet | $3.00 | $15.00 | 6 | - | AWS Bedrock |
| Claude-4-Opus | $5.00 | $25.00 | 6 | - | Snowflake |
| Llama-3-70b | $0.120 | $0.300 | 6 | - | Hyperbolic |
| Llama-3-8b | $0.030 | $0.040 | 6 | - | DeepInfra |
| Qwen2p5-Coder-32b | $0.060 | $0.200 | 6 | - | Nscale |
| Qwen3-Coder-480b-A35b-Instruct | $0.220 | $1.55 | 6 | - | Google Vertex AI |
| Claude-3.5-Haiku | $0.800 | $4.00 | 5 | - | AWS Bedrock |
| Mixtral-8x7B-Instruct-V0.1 | $0.150 | $0.150 | 5 | - | Anyscale |
| Grok-4-20-Reasoning | $1.25 | $2.50 | 5 | - | Azure AI Foundry |
| Grok-4-20-Non-Reasoning | $1.25 | $2.50 | 5 | - | Azure AI Foundry |
| Llama-Guard-3-8B | $0.020 | $0.030 | 5 | - | Nebius |
| DeepSeek R1 Distill Qwen 32Bopen weights · MIT | $0.150 | $0.150 | 5 | - | Nscale |
| Qwen3-VL-235b-A22b-Thinking | $0.220 | $0.880 | 5 | - | Fireworks AI |
| Qwen3-VL-32b-Instruct | $0.160 | $0.640 | 5 | - | Alibaba Model Studio |
| Qwen2p5-72b | $0.120 | $0.300 | 5 | - | Hyperbolic |
| Llama 3.1 405Bopen weights · Llama 3.1 Community | $0.120 | $0.300 | 5 | - | Hyperbolic |
| Claude-3-Opus | $15.00 | $75.00 | 4 | - | AWS Bedrock |
| Grok-4 | $3.00 | $15.00 | 4 | - | Azure AI Foundry |
| Llama3.1-70b | $0.120 | $0.300 | 4 | - | Lambda |
| Llama3.1-8b | $0.025 | $0.040 | 4 | - | Lambda |
| Llama-3.2-11b-Vision-Instruct | $0.049 | $0.049 | 4 | - | Cloudflare |
| Llama3.3-70b | $0.120 | $0.300 | 4 | - | Lambda |
| Ministral-3-14b-2512 | $0.200 | $0.200 | 4 | - | AWS Bedrock |
| Qwen2.5-Coder-7B | $0.010 | $0.030 | 4 | - | Nscale |
| DeepSeek-R1-Distill-Qwen-14B | $0.070 | $0.070 | 4 | - | Nscale |
| Mixtral 8x7Bopen weights · Apache-2.0 | $0.070 | $0.280 | 3 | - | Perplexity |
| IBM Granite 4.1 8Bopen weights · Apache-2.0 | $0.050 | $0.100 | 1 | - | W&B Inference |