LLM Pricing by use case
Pick a B2B scenario to see realistic cost estimates. Each preset fills in typical token counts — split into system prompt (fixed per call) vs. user + context (variable) — and daily call volume.
Customer Support
Ticket classification, auto-replies, agent assist
| Model | Provider | Type | Price Tier | Context | Input $/1M | Output $/1M | Blended | Per Call | API Calls/$1 ↓ |
|---|---|---|---|---|---|---|---|---|---|
LFM2-8B-A1B | Open | budget | 32K | $0.010 | $0.020 | $0.017 | $0.00002 | 50,000 | |
LFM2-2.6B | Open | budget | 32K | $0.010 | $0.020 | $0.017 | $0.00002 | 50,000 | |
Llama 3.2 3B Instruct | Open | budget | 131K | $0.020 | $0.020 | $0.020 | $0.00004 | 28,571 | |
Gemma 3n 4B | Open | budget | 32K | $0.020 | $0.040 | $0.033 | $0.00004 | 25,000 | |
Mistral Nemo | Open | budget | 131K | $0.020 | $0.040 | $0.033 | $0.00004 | 25,000 | |
Llama 3.1 8B Instruct | Open | budget | 16K | $0.020 | $0.050 | $0.040 | $0.00004 | 23,529 | |
Gemma 3 4B | Open | budget | 96K | $0.017 | $0.068 | $0.051 | $0.00004 | 23,483 | |
Llama Guard 3 8B | Open | budget | 131K | $0.020 | $0.060 | $0.047 | $0.00005 | 22,222 | |
DeepHermes 3 Mistral 24B Preview | Open | budget | 32K | $0.020 | $0.100 | $0.073 | $0.00005 | 18,182 | |
Llama 3 8B Instruct | Open | budget | 8K | $0.030 | $0.040 | $0.037 | $0.00006 | 18,182 | |
Qwen2.5 Coder 7B Instruct | Open | budget | 32K | $0.030 | $0.090 | $0.070 | $0.00007 | 14,815 | |
Gemma 2 9B | Open | budget | 8K | $0.030 | $0.090 | $0.070 | $0.00007 | 14,815 | |
Gemma 3 12B | Open | budget | 131K | $0.030 | $0.100 | $0.077 | $0.00007 | 14,286 | |
Ministral 3B | Open | budget | 131K | $0.040 | $0.040 | $0.040 | $0.00007 | 14,286 | |
Mistral Small 3.1 24B | Open | budget | 131K | $0.030 | $0.110 | $0.083 | $0.00007 | 13,793 | |
R1 Distill Llama 70B | Open | budget | 131K | $0.030 | $0.110 | $0.083 | $0.00007 | 13,793 | |
Qwen2.5 Coder 32B Instruct | Open | budget | 32K | $0.030 | $0.110 | $0.083 | $0.00007 | 13,793 | |
Llama 3 8B Lunaris | Open | budget | 8K | $0.040 | $0.050 | $0.047 | $0.00007 | 13,793 | |
gpt-oss-20b | Prop | budget | 131K | $0.030 | $0.140 | $0.103 | $0.00008 | 12,500 | |
Qwen2.5 7B Instruct | Open | budget | 32K | $0.040 | $0.100 | $0.080 | $0.00009 | 11,765 | |
Llama 3.2 11B Vision Instruct | Open | budget | 131K | $0.049 | $0.049 | $0.049 | $0.00009 | 11,662 | |
Nova Micro 1.0 | Prop | budget | 128K | $0.035 | $0.140 | $0.105 | $0.00009 | 11,429 | |
Llama 3.2 1B Instruct | Open | budget | 60K | $0.027 | $0.200 | $0.142 | $0.00009 | 11,050 | |
Command R7B (12-2024) | Prop | budget | 128K | $0.037 | $0.150 | $0.112 | $0.00009 | 10,667 | |
Mistral Small 3 | Open | budget | 32K | $0.050 | $0.080 | $0.070 | $0.00009 | 10,526 | |
Gemma 3 27B | Open | budget | 128K | $0.040 | $0.150 | $0.113 | $0.00010 | 10,256 | |
Nemotron Nano 9B V2 | Open | budget | 131K | $0.040 | $0.160 | $0.120 | $0.00010 | 10,000 | |
Trinity Mini | Open | budget | 131K | $0.045 | $0.150 | $0.115 | $0.00011 | 9,524 | |
gpt-oss-120b | Prop | budget | 131K | $0.039 | $0.190 | $0.140 | $0.00011 | 9,434 | |
gpt-oss-120b (exacto) | Prop | budget | 131K | $0.039 | $0.190 | $0.140 | $0.00011 | 9,434 | |
Nemotron 3 Nano 30B A3B | Open | budget | 262K | $0.050 | $0.200 | $0.150 | $0.00013 | 8,000 | |
Olmo 2 32B Instruct | Open | budget | 128K | $0.050 | $0.200 | $0.150 | $0.00013 | 8,000 | |
Qwen-Turbo | Open | budget | 1000K | $0.050 | $0.200 | $0.150 | $0.00013 | 8,000 | |
Phi 4 | Open | budget | 16K | $0.060 | $0.140 | $0.113 | $0.00013 | 8,000 | |
Devstral 2 2512 | Open | budget | 262K | $0.050 | $0.220 | $0.163 | $0.00013 | 7,692 | |
Qwen3 14B | Open | budget | 40K | $0.050 | $0.220 | $0.163 | $0.00013 | 7,692 | |
Qwen2.5 VL 32B Instruct | Open | budget | 16K | $0.050 | $0.220 | $0.163 | $0.00013 | 7,692 | |
Qwen3 235B A22B Instruct 2507 | Open | budget | 262K | $0.071 | $0.100 | $0.090 | $0.00013 | 7,605 | |
Mistral Small 3.2 24B | Open | budget | 131K | $0.060 | $0.180 | $0.140 | $0.00014 | 7,407 | |
Qwen3 30B A3B | Open | budget | 40K | $0.060 | $0.220 | $0.167 | $0.00015 | 6,897 | |
Nova Lite 1.0 | Prop | budget | 300K | $0.060 | $0.240 | $0.180 | $0.00015 | 6,667 | |
Qwen3 30B A3B Thinking 2507 | Open | budget | 32K | $0.051 | $0.340 | $0.244 | $0.00016 | 6,192 | |
Qwen3 Coder 30B A3B Instruct | Open | budget | 160K | $0.070 | $0.270 | $0.203 | $0.00017 | 5,797 | |
Ministral 3 3B 2512 | Open | budget | 131K | $0.100 | $0.100 | $0.100 | $0.00017 | 5,714 | |
ERNIE 4.5 21B A3B Thinking | Open | budget | 131K | $0.070 | $0.280 | $0.210 | $0.00018 | 5,714 | |
ERNIE 4.5 21B A3B | Open | budget | 120K | $0.070 | $0.280 | $0.210 | $0.00018 | 5,714 | |
GPT-5 Nano | Prop | budget | 400K | $0.050 | $0.400 | $0.283 | $0.00017 | 5,714 | |
GLM 4 32B | Open | budget | 128K | $0.100 | $0.100 | $0.100 | $0.00017 | 5,714 | |
Qwen3 8B | Open | budget | 32K | $0.050 | $0.400 | $0.283 | $0.00017 | 5,714 | |
Ministral 8B | Open | budget | 131K | $0.100 | $0.100 | $0.100 | $0.00017 | 5,714 | |
Pixtral 12B | Open | budget | 32K | $0.100 | $0.100 | $0.100 | $0.00017 | 5,714 | |
Qwen3 Coder Next | Open | budget | 262K | $0.070 | $0.300 | $0.223 | $0.00018 | 5,556 | |
Qwen3 32B | Open | budget | 40K | $0.080 | $0.240 | $0.187 | $0.00018 | 5,556 | |
Seed 1.6 Flash | Open | budget | 262K | $0.075 | $0.300 | $0.225 | $0.00019 | 5,333 | |
gpt-oss-safeguard-20b | Prop | budget | 131K | $0.075 | $0.300 | $0.225 | $0.00019 | 5,333 | |
Gemini 2.0 Flash Lite | Open | budget | 1M | $0.075 | $0.300 | $0.225 | $0.00019 | 5,333 | |
GLM 4.7 Flash | Open | budget | 202K | $0.060 | $0.400 | $0.287 | $0.00019 | 5,263 | |
Llama 4 Scout | Open | budget | 327K | $0.080 | $0.300 | $0.227 | $0.00019 | 5,128 | |
Olmo 3 7B Instruct | Open | budget | 65K | $0.100 | $0.200 | $0.167 | $0.00020 | 5,000 | |
UI-TARS 7B | Open | budget | 128K | $0.100 | $0.200 | $0.167 | $0.00020 | 5,000 | |
Qwen3 30B A3B Instruct 2507 | Open | budget | 262K | $0.080 | $0.330 | $0.247 | $0.00020 | 4,938 | |
MiMo-V2-Flash | Open | budget | 262K | $0.090 | $0.290 | $0.223 | $0.00021 | 4,819 | |
Mistral 7B Instruct v0.1 | Open | budget | 2K | $0.110 | $0.190 | $0.163 | $0.00021 | 4,706 | |
Mistral Small Creative | Open | budget | 32K | $0.100 | $0.300 | $0.233 | $0.00022 | 4,444 | |
Voxtral Small 24B 2507 | Open | budget | 32K | $0.100 | $0.300 | $0.233 | $0.00022 | 4,444 | |
Devstral Small 1.1 | Open | budget | 131K | $0.100 | $0.300 | $0.233 | $0.00022 | 4,444 | |
Olmo 3 7B Think | Open | budget | 65K | $0.120 | $0.200 | $0.173 | $0.00023 | 4,348 | |
Llama 3.3 70B Instruct | Open | budget | 131K | $0.100 | $0.320 | $0.247 | $0.00023 | 4,348 | |
Qwen3 VL 8B Instruct | Open | budget | 131K | $0.080 | $0.500 | $0.360 | $0.00024 | 4,082 | |
Hermes 2 Pro - Llama-3 8B | Open | budget | 8K | $0.140 | $0.140 | $0.140 | $0.00025 | 4,082 | |
Tongyi DeepResearch 30B A3B | Open | budget | 131K | $0.090 | $0.450 | $0.330 | $0.00025 | 4,040 | |
Llama 3.3 Nemotron Super 49B V1.5 | Open | budget | 131K | $0.100 | $0.400 | $0.300 | $0.00025 | 4,000 | |
Gemini 2.5 Flash Lite Preview 09-2025 | Open | budget | 1M | $0.100 | $0.400 | $0.300 | $0.00025 | 4,000 | |
Gemini 2.5 Flash Lite | Open | budget | 1M | $0.100 | $0.400 | $0.300 | $0.00025 | 4,000 | |
GPT-4.1 Nano | Prop | budget | 1047K | $0.100 | $0.400 | $0.300 | $0.00025 | 4,000 | |
Gemini 2.0 Flash | Open | budget | 1M | $0.100 | $0.400 | $0.300 | $0.00025 | 4,000 | |
Hermes 4 70B | Open | budget | 131K | $0.110 | $0.380 | $0.290 | $0.00026 | 3,846 | |
Ministral 3 8B 2512 | Open | budget | 262K | $0.150 | $0.150 | $0.150 | $0.00026 | 3,810 | |
Qwen2.5 72B Instruct | Open | budget | 32K | $0.120 | $0.390 | $0.300 | $0.00028 | 3,604 | |
Lumimaid v0.2 8B | Open | budget | 32K | $0.090 | $0.600 | $0.430 | $0.00028 | 3,509 | |
Qwen3 235B A22B Thinking 2507 | Open | budget | 262K | $0.110 | $0.600 | $0.437 | $0.00031 | 3,175 | |
Spotlight | Open | budget | 131K | $0.180 | $0.180 | $0.180 | $0.00032 | 3,175 | |
Llama Guard 4 12B | Open | budget | 163K | $0.180 | $0.180 | $0.180 | $0.00032 | 3,175 | |
QwQ 32B | Open | budget | 32K | $0.150 | $0.400 | $0.317 | $0.00032 | 3,077 | |
Molmo2 8B | Open | budget | 36K | $0.200 | $0.200 | $0.200 | $0.00035 | 2,857 | |
Olmo 3.1 32B Think | Open | budget | 65K | $0.150 | $0.500 | $0.383 | $0.00035 | 2,857 | |
Ministral 3 14B 2512 | Open | budget | 262K | $0.200 | $0.200 | $0.200 | $0.00035 | 2,857 | |
Olmo 3 32B Think | Open | budget | 65K | $0.150 | $0.500 | $0.383 | $0.00035 | 2,857 | |
ERNIE 4.5 VL 28B A3B | Open | budget | 30K | $0.140 | $0.560 | $0.420 | $0.00035 | 2,857 | |
Qwen2.5-VL 7B Instruct | Open | budget | 32K | $0.200 | $0.200 | $0.200 | $0.00035 | 2,857 | |
Mistral 7B Instruct v0.3 | Open | budget | 32K | $0.200 | $0.200 | $0.200 | $0.00035 | 2,857 | |
Mistral 7B Instruct | Open | budget | 32K | $0.200 | $0.200 | $0.200 | $0.00035 | 2,857 | |
LlamaGuard 2 8B | Open | budget | 8K | $0.200 | $0.200 | $0.200 | $0.00035 | 2,857 | |
Mistral 7B Instruct v0.2 | Open | budget | 32K | $0.200 | $0.200 | $0.200 | $0.00035 | 2,857 | |
Hunyuan A13B Instruct | Open | budget | 131K | $0.140 | $0.570 | $0.427 | $0.00035 | 2,837 | |
Rocinante 12B | Open | budget | 32K | $0.170 | $0.430 | $0.343 | $0.00036 | 2,759 | |
Qwen3 VL 30B A3B Instruct | Open | budget | 262K | $0.150 | $0.600 | $0.450 | $0.00038 | 2,667 | |
Llama 4 Maverick | Open | budget | 1M | $0.150 | $0.600 | $0.450 | $0.00038 | 2,667 | |
GPT-4o-mini Search Preview | Prop | budget | 128K | $0.150 | $0.600 | $0.450 | $0.00038 | 2,667 | |
Qwen2.5 VL 72B Instruct | Open | budget | 32K | $0.150 | $0.600 | $0.450 | $0.00038 | 2,667 | |
Command R (08-2024) | Prop | budget | 128K | $0.150 | $0.600 | $0.450 | $0.00038 | 2,667 | |
GPT-4o-mini (2024-07-18) | Prop | budget | 128K | $0.150 | $0.600 | $0.450 | $0.00038 | 2,667 | |
GPT-4o-mini | Prop | budget | 128K | $0.150 | $0.600 | $0.450 | $0.00038 | 2,667 | |
Jamba Mini 1.7 | Open | budget | 256K | $0.200 | $0.400 | $0.333 | $0.00040 | 2,500 | |
GLM 4.5 Air | Open | standard | 131K | $0.130 | $0.850 | $0.610 | $0.00041 | 2,454 | |
Qwen3 Next 80B A3B Instruct | Open | standard | 262K | $0.090 | $1.10 | $0.763 | $0.00041 | 2,439 | |
DeepSeek V3.1 | Open | standard | 32K | $0.150 | $0.750 | $0.550 | $0.00041 | 2,424 | |
Grok 4.1 Fast | Prop | budget | 1M | $0.200 | $0.500 | $0.400 | $0.00042 | 2,353 | |
Grok 4 Fast | Prop | budget | 1M | $0.200 | $0.500 | $0.400 | $0.00042 | 2,353 | |
Mistral Tiny | Open | budget | 32K | $0.250 | $0.250 | $0.250 | $0.00044 | 2,286 | |
Olmo 3.1 32B Instruct | Open | budget | 65K | $0.200 | $0.600 | $0.467 | $0.00045 | 2,222 | |
Nemotron Nano 12B 2 VL | Open | budget | 131K | $0.200 | $0.600 | $0.467 | $0.00045 | 2,222 | |
Qwen3 235B A22B | Open | budget | 40K | $0.200 | $0.600 | $0.467 | $0.00045 | 2,222 | |
Saba | Open | budget | 32K | $0.200 | $0.600 | $0.467 | $0.00045 | 2,222 | |
DeepSeek V3.2 | Open | budget | 163K | $0.250 | $0.380 | $0.337 | $0.00047 | 2,128 | |
Qwen VL Plus | Open | budget | 7K | $0.210 | $0.630 | $0.490 | $0.00047 | 2,116 | |
DeepSeek V3 0324 | Open | standard | 163K | $0.190 | $0.870 | $0.643 | $0.00050 | 1,990 | |
DeepSeek V3.2 Speciale | Open | budget | 163K | $0.270 | $0.410 | $0.363 | $0.00051 | 1,970 | |
DeepSeek V3.2 Exp | Open | budget | 163K | $0.270 | $0.410 | $0.363 | $0.00051 | 1,970 | |
R1 Distill Qwen 32B | Open | budget | 32K | $0.290 | $0.290 | $0.290 | $0.00051 | 1,970 | |
DeepSeek V3.1 Terminus (exacto) | Open | standard | 163K | $0.210 | $0.790 | $0.597 | $0.00051 | 1,951 | |
DeepSeek V3.1 Terminus | Open | standard | 163K | $0.210 | $0.790 | $0.597 | $0.00051 | 1,951 | |
Qwen3 VL 235B A22B Instruct | Open | standard | 262K | $0.200 | $0.880 | $0.653 | $0.00052 | 1,923 | |
Qwen3 Next 80B A3B Thinking | Open | standard | 128K | $0.150 | $1.20 | $0.850 | $0.00052 | 1,905 | |
Hermes 3 70B Instruct | Open | budget | 65K | $0.300 | $0.300 | $0.300 | $0.00052 | 1,905 | |
Qwen3 VL 30B A3B Thinking | Open | standard | 131K | $0.200 | $1.00 | $0.733 | $0.00055 | 1,818 | |
Cydonia 24B V4.1 | Open | budget | 131K | $0.300 | $0.500 | $0.433 | $0.00057 | 1,739 | |
Grok 3 Mini | Prop | budget | 131K | $0.300 | $0.500 | $0.433 | $0.00057 | 1,739 | |
Grok 3 Mini Beta | Prop | budget | 131K | $0.300 | $0.500 | $0.433 | $0.00057 | 1,739 | |
MiniMax-01 | Prop | standard | 1000K | $0.200 | $1.10 | $0.800 | $0.00057 | 1,739 | |
Qwen3 Coder 480B A35B | Open | standard | 262K | $0.220 | $1.00 | $0.740 | $0.00058 | 1,724 | |
R1T Chimera | Open | standard | 163K | $0.250 | $0.850 | $0.650 | $0.00059 | 1,702 | |
DeepSeek R1T2 Chimera | Open | standard | 163K | $0.250 | $0.850 | $0.650 | $0.00059 | 1,702 | |
Mercury | Open | standard | 128K | $0.250 | $1.00 | $0.750 | $0.00063 | 1,600 | |
Mercury Coder | Open | standard | 128K | $0.250 | $1.00 | $0.750 | $0.00063 | 1,600 | |
MiniMax M2 | Prop | standard | 196K | $0.255 | $1.00 | $0.752 | $0.00063 | 1,581 | |
MiniMax M2.1 | Prop | standard | 196K | $0.270 | $0.950 | $0.723 | $0.00064 | 1,556 | |
GLM 4.6V | Open | standard | 131K | $0.300 | $0.900 | $0.700 | $0.00067 | 1,481 | |
Grok Code Fast 1 | Prop | standard | 256K | $0.200 | $1.50 | $1.07 | $0.00068 | 1,481 | |
Codestral 2508 | Open | standard | 256K | $0.300 | $0.900 | $0.700 | $0.00067 | 1,481 | |
Claude 3 Haiku | Prop | standard | 200K | $0.250 | $1.25 | $0.917 | $0.00069 | 1,455 | |
ERNIE 4.5 300B A47B | Open | standard | 123K | $0.280 | $1.10 | $0.827 | $0.00070 | 1,439 | |
UnslopNemo 12B | Open | budget | 32K | $0.400 | $0.400 | $0.400 | $0.00070 | 1,429 | |
Llama 3.1 70B Instruct | Open | budget | 131K | $0.400 | $0.400 | $0.400 | $0.00070 | 1,429 | |
Kimi Dev 72B | Open | standard | 131K | $0.290 | $1.15 | $0.863 | $0.00072 | 1,384 | |
MiniMax M2-her | Prop | standard | 65K | $0.300 | $1.20 | $0.900 | $0.00075 | 1,333 | |
DeepSeek R1T Chimera | Open | standard | 163K | $0.300 | $1.20 | $0.900 | $0.00075 | 1,333 | |
DeepSeek V3 | Open | standard | 163K | $0.300 | $1.20 | $0.900 | $0.00075 | 1,333 | |
Qwen3 Coder 480B A35B (exacto) | Open | standard | 262K | $0.220 | $1.80 | $1.27 | $0.00078 | 1,282 | |
Qwen3 VL 8B Thinking | Open | standard | 256K | $0.180 | $2.10 | $1.46 | $0.00079 | 1,258 | |
Kimi K2.5 | Open | standard | 262K | $0.300 | $1.50 | $1.10 | $0.00082 | 1,212 | |
Qwen3 Coder Flash | Open | standard | 128K | $0.300 | $1.50 | $1.10 | $0.00082 | 1,212 | |
WizardLM-2 8x22B | Open | budget | 65K | $0.480 | $0.480 | $0.480 | $0.00084 | 1,190 | |
Seed 1.6 | Open | standard | 262K | $0.250 | $2.00 | $1.42 | $0.00088 | 1,143 | |
GPT-5.1-Codex-Mini | Prop | standard | 400K | $0.250 | $2.00 | $1.42 | $0.00088 | 1,143 | |
GPT-5 Mini | Prop | standard | 400K | $0.250 | $2.00 | $1.42 | $0.00088 | 1,143 | |
GLM 4.6 | Open | standard | 202K | $0.350 | $1.50 | $1.12 | $0.00090 | 1,111 | |
Qwen Plus 0728 | Open | standard | 1000K | $0.400 | $1.20 | $0.933 | $0.00090 | 1,111 | |
Qwen-Plus | Open | standard | 131K | $0.400 | $1.20 | $0.933 | $0.00090 | 1,111 | |
GLM 4.5 | Open | standard | 131K | $0.350 | $1.55 | $1.15 | $0.00091 | 1,096 | |
ERNIE 4.5 VL 424B A47B | Open | standard | 123K | $0.420 | $1.25 | $0.973 | $0.00094 | 1,061 | |
Mixtral 8x7B Instruct | Open | standard | 32K | $0.540 | $0.540 | $0.540 | $0.00094 | 1,058 | |
Coder Large | Open | standard | 32K | $0.500 | $0.800 | $0.700 | $0.00095 | 1,053 | |
Llama 3 70B Instruct | Open | standard | 8K | $0.510 | $0.740 | $0.663 | $0.00095 | 1,053 | |
GLM 4.7 | Open | standard | 202K | $0.400 | $1.50 | $1.13 | $0.00097 | 1,026 | |
GPT-4.1 Mini | Prop | standard | 1047K | $0.400 | $1.60 | $1.20 | $0.0010 | 1,000 | |
Skyfall 36B V2 | Open | standard | 32K | $0.550 | $0.800 | $0.717 | $0.0010 | 976 | |
Kimi K2 Thinking | Open | standard | 262K | $0.400 | $1.75 | $1.30 | $0.0010 | 964 | |
R1 0528 | Open | standard | 163K | $0.400 | $1.75 | $1.30 | $0.0010 | 964 | |
Kimi K2 0905 | Open | standard | 262K | $0.390 | $1.90 | $1.40 | $0.0011 | 943 | |
Nova 2 Lite | Prop | standard | 1000K | $0.300 | $2.50 | $1.77 | $0.0011 | 930 | |
Gemini 2.5 Flash Image (Nano Banana) | Open | standard | 32K | $0.300 | $2.50 | $1.77 | $0.0011 | 930 | |
Gemini 2.5 Flash Preview 09-2025 | Open | standard | 1M | $0.300 | $2.50 | $1.77 | $0.0011 | 930 | |
Gemini 2.5 Flash | Open | standard | 1M | $0.300 | $2.50 | $1.77 | $0.0011 | 930 | |
GLM 4.6 (exacto) | Open | standard | 204K | $0.440 | $1.76 | $1.32 | $0.0011 | 909 | |
Mistral Medium 3.1 | Open | standard | 131K | $0.400 | $2.00 | $1.47 | $0.0011 | 909 | |
Devstral Medium | Open | standard | 131K | $0.400 | $2.00 | $1.47 | $0.0011 | 909 | |
Mistral Medium 3 | Open | standard | 131K | $0.400 | $2.00 | $1.47 | $0.0011 | 909 | |
Mistral Large 3 2512 | Open | standard | 262K | $0.500 | $1.50 | $1.17 | $0.0011 | 889 | |
Qwen3 VL 32B Instruct | Open | standard | 262K | $0.500 | $1.50 | $1.17 | $0.0011 | 889 | |
GPT-3.5 Turbo | Prop | standard | 16K | $0.500 | $1.50 | $1.17 | $0.0011 | 889 | |
Gemma 2 27B | Open | standard | 8K | $0.650 | $0.650 | $0.650 | $0.0011 | 879 | |
MiniMax M1 | Prop | standard | 1000K | $0.400 | $2.20 | $1.60 | $0.0011 | 870 | |
Llama 3.3 Euryale 70B | Open | standard | 131K | $0.650 | $0.750 | $0.717 | $0.0012 | 860 | |
Llama 3.1 Euryale 70B v2.2 | Open | standard | 32K | $0.650 | $0.750 | $0.717 | $0.0012 | 860 | |
GLM 4.5V | Open | standard | 65K | $0.600 | $1.80 | $1.40 | $0.0013 | 741 | |
Kimi K2 0711 | Open | standard | 131K | $0.500 | $2.40 | $1.77 | $0.0014 | 741 | |
Llama 3.1 Nemotron Ultra 253B v1 | Open | standard | 131K | $0.600 | $1.80 | $1.40 | $0.0013 | 741 | |
Aion-1.0-Mini | Prop | standard | 131K | $0.700 | $1.40 | $1.17 | $0.0014 | 714 | |
Virtuoso Large | Open | standard | 131K | $0.750 | $1.20 | $1.05 | $0.0014 | 702 | |
GPT Audio Mini | Prop | standard | 128K | $0.600 | $2.40 | $1.80 | $0.0015 | 667 | |
Gemini 3 Flash Preview | Open | standard | 1M | $0.500 | $3.00 | $2.17 | $0.0015 | 667 | |
Morph V3 Fast | Prop | standard | 81K | $0.800 | $1.20 | $1.07 | $0.0015 | 667 | |
Kimi K2 0905 (exacto) | Open | standard | 262K | $0.600 | $2.50 | $1.87 | $0.0015 | 656 | |
Qwen3 VL 235B A22B Thinking | Open | standard | 262K | $0.450 | $3.50 | $2.48 | $0.0015 | 645 | |
Relace Apply 3 | Prop | standard | 256K | $0.850 | $1.25 | $1.12 | $0.0016 | 630 | |
Qwen Plus 0728 (thinking) | Open | standard | 1000K | $0.400 | $4.00 | $2.80 | $0.0016 | 625 | |
Aion-RP 1.0 (8B) | Prop | standard | 32K | $0.800 | $1.60 | $1.33 | $0.0016 | 625 | |
R1 | Open | standard | 64K | $0.700 | $2.50 | $1.90 | $0.0017 | 597 | |
Sonar | Prop | standard | 127K | $1.00 | $1.00 | $1.00 | $0.0018 | 571 | |
Hermes 3 405B Instruct | Open | standard | 131K | $1.00 | $1.00 | $1.00 | $0.0018 | 571 | |
Morph V3 Large | Prop | standard | 262K | $0.900 | $1.90 | $1.57 | $0.0018 | 548 | |
Noromaid 20B | Open | standard | 4K | $1.00 | $1.75 | $1.50 | $0.0019 | 516 | |
Qwen VL Max | Open | standard | 131K | $0.800 | $3.20 | $2.40 | $0.0020 | 500 | |
Nova Pro 1.0 | Prop | standard | 300K | $0.800 | $3.20 | $2.40 | $0.0020 | 500 | |
GPT-3.5 Turbo (older v0613) | Prop | standard | 4K | $1.00 | $2.00 | $1.67 | $0.0020 | 500 | |
Llama 3.1 Nemotron 70B Instruct | Open | standard | 131K | $1.20 | $1.20 | $1.20 | $0.0021 | 476 | |
Maestro Reasoning | Open | standard | 131K | $0.900 | $3.30 | $2.50 | $0.0022 | 460 | |
Claude 3.5 Haiku | Prop | standard | 200K | $0.800 | $4.00 | $2.93 | $0.0022 | 455 | |
Relace Search | Prop | standard | 256K | $1.00 | $3.00 | $2.33 | $0.0023 | 444 | |
Hermes 4 405B | Open | standard | 131K | $1.00 | $3.00 | $2.33 | $0.0023 | 444 | |
Llama 3 Euryale 70B v2.1 | Open | standard | 8K | $1.48 | $1.48 | $1.48 | $0.0026 | 386 | |
Claude Haiku 4.5 | Prop | standard | 200K | $1.00 | $5.00 | $3.67 | $0.0027 | 364 | |
Qwen3 Coder Plus | Open | standard | 128K | $1.00 | $5.00 | $3.67 | $0.0027 | 364 | |
o4 Mini High | Prop | standard | 200K | $1.10 | $4.40 | $3.30 | $0.0028 | 364 | |
o4 Mini | Prop | standard | 200K | $1.10 | $4.40 | $3.30 | $0.0028 | 364 | |
o3 Mini High | Prop | standard | 200K | $1.10 | $4.40 | $3.30 | $0.0028 | 364 | |
o3 Mini | Prop | standard | 200K | $1.10 | $4.40 | $3.30 | $0.0028 | 364 | |
GPT-3.5 Turbo Instruct | Prop | standard | 4K | $1.50 | $2.00 | $1.83 | $0.0027 | 364 | |
Qwen3 Max | Open | standard | 256K | $1.20 | $6.00 | $4.40 | $0.0033 | 303 | |
Qwen-Max | Open | standard | 32K | $1.60 | $6.40 | $4.80 | $0.0040 | 250 | |
GPT-5 Image Mini | Prop | standard | 400K | $2.50 | $2.00 | $2.17 | $0.0043 | 235 | |
GPT-5.1-Codex-Max | Prop | premium | 400K | $1.25 | $10.00 | $7.08 | $0.0044 | 229 | |
GPT-5.1 | Prop | premium | 400K | $1.25 | $10.00 | $7.08 | $0.0044 | 229 | |
GPT-5.1 Chat | Prop | premium | 128K | $1.25 | $10.00 | $7.08 | $0.0044 | 229 | |
GPT-5.1-Codex | Prop | premium | 400K | $1.25 | $10.00 | $7.08 | $0.0044 | 229 | |
GPT-5 Codex | Prop | premium | 400K | $1.25 | $10.00 | $7.08 | $0.0044 | 229 | |
GPT-5 Chat | Prop | premium | 128K | $1.25 | $10.00 | $7.08 | $0.0044 | 229 | |
GPT-5 | Prop | premium | 400K | $1.25 | $10.00 | $7.08 | $0.0044 | 229 | |
Gemini 2.5 Pro | Open | premium | 1M | $1.25 | $10.00 | $7.08 | $0.0044 | 229 | |
Gemini 2.5 Pro Preview 06-05 | Open | premium | 1M | $1.25 | $10.00 | $7.08 | $0.0044 | 229 | |
Gemini 2.5 Pro Preview 05-06 | Open | premium | 1M | $1.25 | $10.00 | $7.08 | $0.0044 | 229 | |
Mistral Large 2411 | Open | standard | 131K | $2.00 | $6.00 | $4.67 | $0.0045 | 222 | |
Mistral Large 2407 | Open | standard | 131K | $2.00 | $6.00 | $4.67 | $0.0045 | 222 | |
Pixtral Large 2411 | Open | standard | 131K | $2.00 | $6.00 | $4.67 | $0.0045 | 222 | |
Mixtral 8x22B Instruct | Open | standard | 65K | $2.00 | $6.00 | $4.67 | $0.0045 | 222 | |
Mistral Large | Open | standard | 128K | $2.00 | $6.00 | $4.67 | $0.0045 | 222 | |
o4 Mini Deep Research | Prop | premium | 200K | $2.00 | $8.00 | $6.00 | $0.0050 | 200 | |
Jamba Large 1.7 | Open | premium | 256K | $2.00 | $8.00 | $6.00 | $0.0050 | 200 | |
o3 | Prop | premium | 200K | $2.00 | $8.00 | $6.00 | $0.0050 | 200 | |
GPT-4.1 | Prop | premium | 1047K | $2.00 | $8.00 | $6.00 | $0.0050 | 200 | |
Sonar Reasoning Pro | Prop | premium | 128K | $2.00 | $8.00 | $6.00 | $0.0050 | 200 | |
Sonar Deep Research | Prop | premium | 128K | $2.00 | $8.00 | $6.00 | $0.0050 | 200 | |
Llama 3.1 70B Hanami x1 | Open | standard | 16K | $3.00 | $3.00 | $3.00 | $0.0052 | 190 | |
GPT-3.5 Turbo 16k | Prop | standard | 16K | $3.00 | $4.00 | $3.67 | $0.0055 | 182 | |
Nano Banana Pro (Gemini 3 Pro Image Preview) | Open | premium | 65K | $2.00 | $12.00 | $8.67 | $0.0060 | 167 | |
Gemini 3 Pro Preview | Open | premium | 1M | $2.00 | $12.00 | $8.67 | $0.0060 | 167 | |
GPT-5.2-Codex | Prop | premium | 400K | $1.75 | $14.00 | $9.92 | $0.0061 | 163 | |
GPT-5.2 Chat | Prop | premium | 128K | $1.75 | $14.00 | $9.92 | $0.0061 | 163 | |
GPT-5.2 | Prop | premium | 400K | $1.75 | $14.00 | $9.92 | $0.0061 | 163 | |
GPT Audio | Prop | premium | 128K | $2.50 | $10.00 | $7.50 | $0.0063 | 160 | |
GPT-4o Audio | Prop | premium | 128K | $2.50 | $10.00 | $7.50 | $0.0063 | 160 | |
Command A | Prop | premium | 256K | $2.50 | $10.00 | $7.50 | $0.0063 | 160 | |
GPT-4o Search Preview | Prop | premium | 128K | $2.50 | $10.00 | $7.50 | $0.0063 | 160 | |
GPT-4o (2024-11-20) | Prop | premium | 128K | $2.50 | $10.00 | $7.50 | $0.0063 | 160 | |
Inflection 3 Pi | Prop | premium | 8K | $2.50 | $10.00 | $7.50 | $0.0063 | 160 | |
Inflection 3 Productivity | Prop | premium | 8K | $2.50 | $10.00 | $7.50 | $0.0063 | 160 | |
Command R+ (08-2024) | Prop | premium | 128K | $2.50 | $10.00 | $7.50 | $0.0063 | 160 | |
GPT-4o (2024-08-06) | Prop | premium | 128K | $2.50 | $10.00 | $7.50 | $0.0063 | 160 | |
GPT-4o | Prop | premium | 128K | $2.50 | $10.00 | $7.50 | $0.0063 | 160 | |
Nova Premier 1.0 | Prop | premium | 1000K | $2.50 | $12.50 | $9.17 | $0.0069 | 145 | |
Llama 3.1 405B (base) | Open | standard | 32K | $4.00 | $4.00 | $4.00 | $0.0070 | 143 | |
Llama 3.1 405B Instruct | Open | standard | 131K | $4.00 | $4.00 | $4.00 | $0.0070 | 143 | |
Aion-1.0 | Prop | premium | 131K | $4.00 | $8.00 | $6.67 | $0.0080 | 125 | |
Sonar Pro Search | Prop | premium | 200K | $3.00 | $15.00 | $11.00 | $0.0083 | 121 | |
Claude Sonnet 4.5 | Prop | premium | 1000K | $3.00 | $15.00 | $11.00 | $0.0083 | 121 | |
Grok 4 | Prop | premium | 256K | $3.00 | $15.00 | $11.00 | $0.0083 | 121 | |
Grok 3 | Prop | premium | 131K | $3.00 | $15.00 | $11.00 | $0.0083 | 121 | |
Claude Sonnet 4 | Prop | premium | 1000K | $3.00 | $15.00 | $11.00 | $0.0083 | 121 | |
Grok 3 Beta | Prop | premium | 131K | $3.00 | $15.00 | $11.00 | $0.0083 | 121 | |
Sonar Pro | Prop | premium | 200K | $3.00 | $15.00 | $11.00 | $0.0083 | 121 | |
Claude 3.7 Sonnet (thinking) | Prop | premium | 200K | $3.00 | $15.00 | $11.00 | $0.0083 | 121 | |
Claude 3.7 Sonnet | Prop | premium | 200K | $3.00 | $15.00 | $11.00 | $0.0083 | 121 | |
ChatGPT-4o | Prop | premium | 128K | $5.00 | $15.00 | $11.67 | $0.011 | 89 | |
GPT-4o (2024-05-13) | Prop | premium | 128K | $5.00 | $15.00 | $11.67 | $0.011 | 89 | |
GPT-4o (extended) | Prop | premium | 128K | $6.00 | $18.00 | $14.00 | $0.013 | 74 | |
Claude Opus 4.6 | Prop | premium | 1000K | $5.00 | $25.00 | $18.33 | $0.014 | 73 | |
Claude Opus 4.5 | Prop | premium | 200K | $5.00 | $25.00 | $18.33 | $0.014 | 73 | |
Claude 3.5 Sonnet | Prop | premium | 200K | $6.00 | $30.00 | $22.00 | $0.017 | 61 | |
GPT-5 Image | Prop | premium | 400K | $10.00 | $10.00 | $10.00 | $0.017 | 57 | |
GPT-4 Turbo | Prop | premium | 128K | $10.00 | $30.00 | $23.33 | $0.022 | 44 | |
GPT-4 Turbo Preview | Prop | premium | 128K | $10.00 | $30.00 | $23.33 | $0.022 | 44 | |
GPT-4 Turbo (older v1106) | Prop | premium | 128K | $10.00 | $30.00 | $23.33 | $0.022 | 44 | |
o3 Deep Research | Prop | premium | 200K | $10.00 | $40.00 | $30.00 | $0.025 | 40 | |
o1 | Prop | premium | 200K | $15.00 | $60.00 | $45.00 | $0.037 | 27 | |
Claude Opus 4.1 | Prop | premium | 200K | $15.00 | $75.00 | $55.00 | $0.041 | 24 | |
Claude Opus 4 | Prop | premium | 200K | $15.00 | $75.00 | $55.00 | $0.041 | 24 | |
o3 Pro | Prop | premium | 200K | $20.00 | $80.00 | $60.00 | $0.050 | 20 | |
GPT-5 Pro | Prop | premium | 400K | $15.00 | $120 | $85.00 | $0.052 | 19 | |
GPT-4 (older v0314) | Prop | premium | 8K | $30.00 | $60.00 | $50.00 | $0.060 | 17 | |
GPT-4 | Prop | premium | 8K | $30.00 | $60.00 | $50.00 | $0.060 | 17 | |
GPT-5.2 Pro | Prop | premium | 400K | $21.00 | $168 | $119 | $0.074 | 14 | |
o1-pro | Prop | premium | 200K | $150 | $600 | $450 | $0.375 | 3 |
Methodology & Sources
Per Call = (input_tokens × input_price / 1M) + (output_tokens × output_price / 1M)
Monthly = per_call × calls_per_day × 30
Quality Tiers — based on Chatbot Arena ELO and composite benchmark scores. Frontier = ELO 1280+, Strong = 1220–1280, Good = 1150–1220, Budget = <1150 or unranked.
Self-host estimates assume cloud GPU rental at current market rates (H100 80GB ~$3.00/hr, A100 80GB ~$1.50/hr, L4 24GB ~$0.50/hr), 50% average GPU utilization, and vLLM-optimized serving.
Prices sourced from official provider pricing pages. Last verified February 2026.