DeepInfra
Price history
Blended ($/Mtok, 75% input / 25% output) price over time for every model this host serves. Click a legend entry to hide or show its line.
Hosted offerings
| Model | Variant | Input $/Mtok | Output $/Mtok | Confidence |
|---|---|---|---|---|
| Mistral: Mistral Nemo | fp8 | $0.019000 | $0.030000 | high |
| mistralai/Mistral-Nemo-Instruct-2407 | – | $0.019000 | $0.030000 | medium |
| Mistral-Nemo-Instruct-2407 | – | $0.019000 | $0.030000 | high |
| Meta: Llama 3.1 8B Instruct | fp8 | $0.020000 | $0.040000 | high |
| Meta: Llama 3.2 3B Instruct | – | $0.020000 | $0.020000 | medium |
| meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo | – | $0.020000 | $0.040000 | medium |
| Gemma 4 E4B IT | – | $0.020000 | $0.100000 | medium |
| Meta-Llama-3.1-8B-Instruct-Turbo | – | $0.020000 | $0.040000 | high |
| OpenAI: gpt-oss-20b | – | $0.030000 | $0.140000 | high |
| meta-llama/Meta-Llama-3-8B-Instruct | – | $0.030000 | $0.060000 | medium |
| meta-llama/Meta-Llama-3.1-8B-Instruct | – | $0.030000 | $0.050000 | medium |
| OpenAI: gpt-oss-20b | – | $0.030000 | $0.140000 | medium |
| OpenAI: gpt-oss-120b | – | $0.037000 | $0.170000 | high |
| OpenAI: gpt-oss-120b | – | $0.037000 | $0.170000 | medium |
| Sao10K: Llama 3 8B Lunaris | fp8 | $0.040000 | $0.050000 | high |
| Qwen2.5 7B Instruct | – | $0.040000 | $0.100000 | medium |
| Sao10K/L3-8B-Lunaris-v1-Turbo | – | $0.040000 | $0.050000 | medium |
| nvidia/NVIDIA-Nemotron-Nano-9B-v2 | – | $0.040000 | $0.160000 | medium |
| meta-llama/Llama-3.2-11B-Vision-Instruct | – | $0.049000 | $0.049000 | medium |
| NVIDIA: Nemotron 3 Nano 30B A3B | fp4 | $0.050000 | $0.200000 | high |
| Google: Gemma 3 4B | – | $0.050000 | $0.100000 | high |
| Google: Gemma 3 12B | – | $0.050000 | $0.150000 | high |
| Mistral: Mistral Small 3 | fp8 | $0.050000 | $0.080000 | high |
| Google: Gemma 3 12B | – | $0.050000 | $0.150000 | medium |
| Google: Gemma 3 4B | – | $0.050000 | $0.100000 | medium |
| Mistral: Mistral Small 3 | – | $0.050000 | $0.080000 | medium |
| NVIDIA: Nemotron 3 Nano 30B A3B | – | $0.050000 | $0.200000 | medium |
| gemma-3-12b-it | – | $0.050000 | $0.150000 | high |
| gemma-3-4b-it | – | $0.050000 | $0.100000 | high |
| Mistral-Small-24B-Instruct-2501 | – | $0.050000 | $0.080000 | high |
| meta-llama/Llama-Guard-3-8B | – | $0.055000 | $0.055000 | medium |
| inclusionAI: Ling 3.0 Flash VL | – | $0.060000 | $0.180000 | high |
| IBM: Granite 4.2 8B | – | $0.060000 | $0.250000 | high |
| inclusionAI: Ling 3.0 Flash Fin | fp4 | $0.060000 | $0.180000 | high |
| NVIDIA: Nemotron 3.5 Lightning (free) | – | $0.060000 | $0.160000 | high |
| DeepSeek: DeepSeek V4 Flash 0731 | fp8 | $0.060000 | $0.180000 | high |
| inclusionAI: Ling 3.0 Flash | – | $0.060000 | $0.180000 | high |
| GLM-4.7-Flash | – | $0.060000 | $0.400000 | medium |
| inclusionAI: Ling 3.0 Flash | – | $0.060000 | $0.180000 | medium |
| DeepSeek: DeepSeek V4 Flash 0731 | – | $0.060000 | $0.180000 | medium |
| deepseek-v4-flash-0731 | – | $0.060000 | $0.180000 | high |
| NVIDIA-Nemotron-3.5-Lightning | – | $0.060000 | $0.160000 | high |
| Google: Gemma 4 26B A4B (free) | fp8 | $0.070000 | $0.340000 | high |
| Microsoft: Phi 4 | – | $0.070000 | $0.140000 | high |
| Microsoft: Phi 4 | – | $0.070000 | $0.140000 | medium |
| Google: Gemma 4 26B A4B (free) | – | $0.070000 | $0.340000 | medium |
| gemma-4-26B-A4B-it | – | $0.070000 | $0.340000 | high |
| phi-4 | – | $0.070000 | $0.140000 | high |
| Z.ai: GLM 5.3 Flash | fp4 | $0.075000 | $0.250000 | high |
| Mistral: Mistral Small 3.2 24B | fp8 | $0.075000 | $0.200000 | high |
| mistralai/Mistral-Small-3.2-24B-Instruct-2506 | – | $0.075000 | $0.200000 | medium |
| Mistral-Small-3.2-24B-Instruct-2506 | – | $0.075000 | $0.200000 | high |
| Qwen: Qwen3 32B | fp8 | $0.080000 | $0.280000 | high |
| Google: Gemma 3 27B | fp8 | $0.080000 | $0.160000 | high |
| Qwen: Qwen3 32B | – | $0.080000 | $0.280000 | medium |
| Google: Gemma 3 27B | – | $0.080000 | $0.160000 | medium |
| nvidia/NVIDIA-Nemotron-3.5-Lightning | – | $0.080000 | $0.200000 | medium |
| deepseek-ai/DeepSeek-V4-Flash-0731 | – | $0.080000 | $0.180000 | medium |
| Qwen3 32B | – | $0.080000 | $0.280000 | medium |
| Qwen3-32B | – | $0.080000 | $0.280000 | high |
| gemma-3-27b-it | – | $0.080000 | $0.160000 | high |
| NVIDIA: Nemotron 3 Super (free) | – | $0.085000 | $0.400000 | high |
| nvidia/NVIDIA-Nemotron-3-Super-120B-A12B | – | $0.085000 | $0.400000 | medium |
| NVIDIA-Nemotron-3-Super-120B-A12B | – | $0.085000 | $0.400000 | high |
| DeepSeek: DeepSeek V4 Flash 0423 | fp8 | $0.090000 | $0.180000 | high |
| Google: Gemma 4 31B (free) | fp4 | $0.090000 | $0.340000 | high |
| Qwen: Qwen3 Next 80B A3B Instruct | fp8 | $0.090000 | $1.100000 | high |
| Qwen: Qwen3 235B A22B Instruct 2507 | fp8 | $0.090000 | $0.550000 | high |
| Qwen: Qwen3 235B A22B | – | $0.090000 | $0.550000 | medium |
| Qwen: Qwen3 Next 80B A3B Instruct | – | $0.090000 | $1.100000 | medium |
| google/gemma-4-31B-it-turbo | – | $0.090000 | $0.340000 | medium |
| deepseek-ai/DeepSeek-V4-Flash | – | $0.090000 | $0.180000 | medium |
| Qwen3-Next 80B-A3B Instruct | – | $0.090000 | $1.100000 | medium |
| DeepSeek: DeepSeek V4 Flash 0423 | – | $0.090000 | $0.180000 | medium |
| DeepSeek-V4-Flash | – | $0.090000 | $0.180000 | high |
| Qwen3-Next-80B-A3B-Instruct | – | $0.090000 | $1.100000 | high |
| Qwen3-235B-A22B-Instruct-2507 | – | $0.090000 | $0.550000 | high |
| gemma-4-31B-it-turbo | – | $0.090000 | $0.340000 | high |
| Qwen: Qwen3.6 35B A3B | fp8 | $0.100000 | $0.950000 | high |
| Qwen: Qwen3.5-9B | – | $0.100000 | $0.150000 | high |
| Meta: Llama 4 Scout | fp8 | $0.100000 | $0.300000 | high |
| Meta: Llama 3.3 70B Instruct | fp8 | $0.100000 | $0.320000 | high |
| Meta: Llama 3.3 70B Instruct | – | $0.100000 | $0.320000 | medium |
| Meta: Llama 4 Scout | – | $0.100000 | $0.300000 | medium |
| Llama 3.3 Nemotron Super 49B v1.5 | – | $0.100000 | $0.400000 | medium |
| Qwen: Qwen3.6 35B A3B | – | $0.100000 | $0.950000 | medium |
| ByteDance/Seed-2.0-mini | – | $0.100000 | $0.400000 | medium |
| Qwen: Qwen3.5-9B | – | $0.100000 | $0.150000 | medium |
| ByteDance Seed: Seed-2.0-Mini | – | $0.100000 | $0.400000 | medium |
| Qwen3.6-35B-A3B | – | $0.100000 | $0.950000 | high |
| qwen3-5-9b | – | $0.100000 | $0.150000 | high |
| Llama-4-Scout-17B-16E | – | $0.100000 | $0.300000 | high |
| Llama-3.3-70B-Instruct-Turbo | – | $0.100000 | $0.320000 | high |
| Qwen3.8 Flash | – | $0.113000 | $0.382000 | medium |
| Qwen: Qwen3 30B A3B | fp8 | $0.120000 | $0.500000 | high |
| Qwen: Qwen3 14B | fp8 | $0.120000 | $0.240000 | high |
| Qwen: Qwen3 14B | – | $0.120000 | $0.240000 | medium |
| Qwen: Qwen3 30B A3B | – | $0.120000 | $0.500000 | medium |
| Qwen3 30B A3B | – | $0.120000 | $0.500000 | medium |
| Qwen3-30B-A3B | – | $0.120000 | $0.500000 | high |
| Qwen3-14B | – | $0.120000 | $0.240000 | high |
| Tencent: Hy3 | fp4 | $0.130000 | $0.530000 | high |
| Google: Gemma 4 31B (free) | – | $0.130000 | $0.380000 | medium |
| Xiaomi: MiMo-V2.6-Flash | fp8 | $0.140000 | $0.280000 | high |
| DeepSeek: DeepSeek V4.1 Flash | fp8 | $0.140000 | $0.420000 | high |
| Qwen: Qwen3.5-35B-A3B | fp8 | $0.140000 | $1.000000 | high |
| Qwen: Qwen3 Next 80B A3B Thinking | – | $0.140000 | $1.400000 | medium |
| Qwen: Qwen3.5-35B-A3B | – | $0.140000 | $1.000000 | medium |
| Tencent: Hy3 | – | $0.140000 | $0.580000 | medium |
| Xiaomi: MiMo-V2.6-Flash | – | $0.140000 | $0.280000 | medium |
| Xiaomi: MiMo-V2.5 | – | $0.140000 | $0.280000 | medium |
| Qwen3.5-35B-A3B | – | $0.140000 | $1.000000 | high |
| Qwen: Qwen3.8 27B (free) | – | $0.150000 | $1.875000 | high |
| Google: Gemma 4 31B (free) | fp8 | $0.150000 | $0.400000 | high |
| Qwen: Qwen3 VL 30B A3B Instruct | fp8 | $0.150000 | $0.600000 | high |
| OpenAI: gpt-oss-120b | – | $0.150000 | $0.600000 | high |
| Qwen/QwQ-32B | – | $0.150000 | $0.400000 | medium |
| openai/gpt-oss-120b-Turbo | – | $0.150000 | $0.600000 | medium |
| Qwen: Qwen3 VL 30B A3B Instruct | – | $0.150000 | $0.600000 | medium |
| MiniMax-M2.5 | – | $0.150000 | $1.150000 | medium |
| GLM-5.3-Flash | – | $0.150000 | $0.500000 | medium |
| Qwen3-VL-30B-A3B-Instruct | – | $0.150000 | $0.600000 | high |
| gemma-4-31B-it | – | $0.150000 | $0.400000 | high |
| Meta: Llama Guard 4 12B | – | $0.180000 | $0.180000 | high |
| Qwen: Qwen3 235B A22B | – | $0.180000 | $0.540000 | medium |
| Meta: Llama Guard 4 12B | – | $0.180000 | $0.180000 | medium |
| Llama-Guard-4-12B | – | $0.180000 | $0.180000 | high |
| NVIDIA: Nemotron 3.5 Content Safety (free) | – | $0.200000 | $0.200000 | high |
| Qwen: Qwen3 VL 235B A22B Instruct | fp8 | $0.200000 | $0.880000 | high |
| Qwen/Qwen2.5-VL-32B-Instruct | – | $0.200000 | $0.600000 | medium |
| deepseek-ai/DeepSeek-R1-Distill-Llama-70B | – | $0.200000 | $0.600000 | medium |
| Meta: Llama 4 Maverick | – | $0.200000 | $0.800000 | medium |
| Qwen: Qwen3 VL 235B A22B Instruct | – | $0.200000 | $0.880000 | medium |
| nvidia/Nemotron-Content-Safety-3.5 | – | $0.200000 | $0.200000 | medium |
| Step 3.7 Flash | – | $0.200000 | $1.150000 | medium |
| openai/gpt-oss-120b-Ultra | – | $0.200000 | $0.950000 | medium |
| Qwen3 VL 235B A22B Instruct | – | $0.200000 | $0.880000 | medium |
| DeepSeek: DeepSeek V4.1 Flash | – | $0.200000 | $0.600000 | medium |
| StepFun: Step 3.7 Flash | – | $0.200000 | $1.150000 | medium |
| NVIDIA: Nemotron 3 Nano Omni (free) | – | $0.200000 | $0.800000 | medium |
| Qwen3-VL-235B-A22B-Instruct | – | $0.200000 | $0.880000 | high |
| Nemotron-Content-Safety-3.5 | – | $0.200000 | $0.200000 | high |
| DeepSeek: DeepSeek V4 Flash Vision Exp | fp8 | $0.215600 | $0.646800 | high |
| Meta: Llama 3.3 70B Instruct | – | $0.230000 | $0.400000 | medium |
| deepseek-ai/DeepSeek-V3-0324 | – | $0.240000 | $0.900000 | medium |
| DeepSeek V3 0324 | – | $0.240000 | $0.900000 | medium |
| DeepSeek: DeepSeek V3.1 | fp4 | $0.250000 | $0.950000 | high |
| DeepSeek: DeepSeek V3 | – | $0.250000 | $0.950000 | medium |
| MiniMax-M2.7 | – | $0.250000 | $1.000000 | medium |
| Google: Gemini 3.1 Flash Lite | – | $0.250000 | $1.500000 | medium |
| ByteDance/Seed-1.8 | – | $0.250000 | $2.000000 | medium |
| DeepSeek V3.1 | – | $0.250000 | $0.950000 | medium |
| DeepSeek-V3.1 | – | $0.250000 | $0.950000 | high |
| gemini-3.1-flash-lite | – | $0.250000 | $1.500000 | high |
| Qwen: Qwen3.5-27B | fp8 | $0.260000 | $2.600000 | high |
| DeepSeek: DeepSeek V3.2 | fp4 | $0.260000 | $0.380000 | high |
| Qwen: Qwen3.5-27B | – | $0.260000 | $2.600000 | medium |
| DeepSeek-V3.2 | – | $0.260000 | $0.380000 | medium |
| DeepSeek-V3.2 | – | $0.260000 | $0.380000 | high |
| Qwen3.5-27B | – | $0.260000 | $2.600000 | high |
| Qwen3.5 27B | – | $0.260000 | $2.600000 | medium |
| allenai/olmOCR-7B-0725-FP8 | – | $0.270000 | $1.500000 | medium |
| deepseek-ai/DeepSeek-R1-Distill-Qwen-32B | – | $0.270000 | $0.270000 | medium |
| deepseek-ai/DeepSeek-V3.1-Terminus | – | $0.270000 | $1.000000 | medium |
| google/gemma-4-31B-it-Ultra | – | $0.270000 | $0.760000 | medium |
| gemma-4-31B-it-Ultra | – | $0.270000 | $0.760000 | high |
| MiniMax: MiniMax M3 | fp8 | $0.280000 | $1.100000 | high |
| MiniMax-M3 | – | $0.280000 | $1.100000 | medium |
| Qwen: Qwen3.5-122B-A10B | – | $0.290000 | $2.400000 | medium |
| Qwen3.5 122B-A10B | – | $0.290000 | $2.400000 | medium |
| Meta: Muse Glimmer 30B | – | $0.300000 | $1.200000 | high |
| Qwen: Qwen3 Coder 480B A35B | fp4 | $0.300000 | $1.000000 | high |
| Qwen: Qwen3 235B A22B | – | $0.300000 | $2.900000 | medium |
| Qwen3 Coder 480B A35B Instruct | – | $0.300000 | $1.000000 | medium |
| Google: Gemini 2.5 Flash | – | $0.300000 | $2.500000 | medium |
| meta-models/Muse-Glimmer-30B | – | $0.300000 | $1.200000 | medium |
| Qwen3-Coder-480B-A35B-Instruct-Turbo | – | $0.300000 | $1.000000 | high |
| gemini-2.5-flash | – | $0.300000 | $2.500000 | high |
| Qwen: Qwen3.6 27B | fp8 | $0.320000 | $3.200000 | high |
| DeepSeek: DeepSeek V3 | fp4 | $0.320000 | $0.890000 | high |
| DeepSeek-V3 | – | $0.320000 | $0.890000 | medium |
| Qwen: Qwen3.6 27B | – | $0.320000 | $3.200000 | medium |
| DeepSeek-V3 | – | $0.320000 | $0.890000 | medium |
| DeepSeek-V3 | – | $0.320000 | $0.890000 | high |
| Qwen3.6-27B | – | $0.320000 | $3.200000 | high |
| Qwen3.6 27B | – | $0.320000 | $3.200000 | medium |
| Qwen2.5 72B Instruct | fp8 | $0.360000 | $0.400000 | high |
| Qwen2.5-72B-Instruct | – | $0.360000 | $0.400000 | medium |
| Qwen2.5-72B-Instruct | – | $0.360000 | $0.400000 | high |
| MiniMaxAI/MiniMax-M2.7-Turbo | – | $0.380000 | $1.700000 | medium |
| Z.ai: GLM 4.7 | fp4 | $0.400000 | $1.750000 | high |
| Meta: Llama 3.1 70B Instruct | fp8 | $0.400000 | $0.400000 | high |
| MythoMax 13B | – | $0.400000 | $0.400000 | high |
| MythoMax 13B | – | $0.400000 | $0.400000 | medium |
| Qwen3 Coder 480B A35B Instruct | – | $0.400000 | $1.600000 | medium |
| meta-llama/Meta-Llama-3.1-70B-Instruct | – | $0.400000 | $0.400000 | medium |
| meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo | – | $0.400000 | $0.400000 | medium |
| mistralai/Mixtral-8x7B-Instruct-v0.1 | – | $0.400000 | $0.400000 | medium |
| GLM-4.5 | – | $0.400000 | $1.600000 | medium |
| Qwen: Qwen3.8 27B (free) | – | $0.400000 | $3.000000 | medium |
| xiaomimimo/mimo-v2.5 | – | $0.400000 | $2.000000 | medium |
| GLM-4.7 | – | $0.400000 | $1.750000 | medium |
| Meta-Llama-3.1-70B-Instruct-Turbo | – | $0.400000 | $0.400000 | high |
| MythoMax-L2-13b | – | $0.400000 | $0.400000 | high |
| Xiaomi: MiMo-V2.6-Pro | fp8 | $0.430000 | $0.870000 | high |
| Xiaomi: MiMo-V2.6-Pro | – | $0.430000 | $0.870000 | medium |
| DeepSeek: DeepSeek V4 Flash Vision Exp | – | $0.440000 | $1.320000 | medium |
| Thinking Machines: Inkling Small (free) | fp8 | $0.450000 | $1.200000 | high |
| Qwen: Qwen3.5 397B A17B | fp8 | $0.450000 | $3.000000 | high |
| MoonshotAI: Kimi K2.5 | – | $0.450000 | $2.250000 | medium |
| Thinking Machines: Inkling Small (free) | – | $0.450000 | $1.200000 | medium |
| Qwen: Qwen3.5 397B A17B | – | $0.450000 | $3.000000 | medium |
| qwen3-5-397b-a17b | – | $0.450000 | $3.000000 | high |
| WizardLM-2 8x22B | – | $0.480000 | $0.480000 | medium |
| NVIDIA: Nemotron 3 Ultra (free) | fp4 | $0.500000 | $2.200000 | high |
| Z.ai: GLM 4.6 | fp4 | $0.500000 | $2.000000 | high |
| DeepSeek: R1 0528 | fp4 | $0.500000 | $2.150000 | high |
| DeepSeek-R1-0528 | – | $0.500000 | $2.150000 | medium |
| MoonshotAI: Kimi K2 0905 | – | $0.500000 | $2.000000 | medium |
| MoonshotAI: Kimi K2 0905 | – | $0.500000 | $2.000000 | medium |
| Z.ai: GLM 4.6 | – | $0.500000 | $2.000000 | medium |
| ByteDance/Seed-2.0-code | – | $0.500000 | $3.000000 | medium |
| Seed 2.0 Pro | – | $0.500000 | $3.000000 | medium |
| nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B | – | $0.500000 | $2.200000 | medium |
| ByteDance Seed: Seed-2.0-Code | – | $0.500000 | $3.000000 | medium |
| DeepSeek-R1-0528 | – | $0.500000 | $2.150000 | high |
| NVIDIA-Nemotron-3-Ultra-550B-A55B | – | $0.500000 | $2.200000 | high |
| Z.ai: GLM 5.3 | fp4 | $0.562500 | $2.500000 | high |
| Z.ai: GLM 5.2 | fp4 | $0.562500 | $1.800000 | high |
| Llama 3.1 Nemotron 70B Instruct | – | $0.600000 | $0.600000 | medium |
| GLM-5 | – | $0.600000 | $2.080000 | medium |
| Sao10K/L3.3-70B-Euryale-v2.3 | – | $0.650000 | $0.750000 | medium |
| MoonshotAI: Kimi K2.7 Code | – | $0.680000 | $3.400000 | medium |
| Kimi K2.7 Code | – | $0.680000 | $3.400000 | medium |
| Nous: Hermes 3 70B Instruct | fp8 | $0.700000 | $0.700000 | high |
| Nous: Hermes 3 70B Instruct | – | $0.700000 | $0.700000 | medium |
| DeepSeek: R1 | – | $0.700000 | $2.400000 | medium |
| MoonshotAI: Kimi K2.6 | fp4 | $0.750000 | $3.500000 | high |
| MoonshotAI: Kimi K2.6 | – | $0.750000 | $3.500000 | medium |
| Google: Gemini 3.7 Flash | – | $0.750000 | $3.750000 | medium |
| zai-org/GLM-5.2 | – | $0.750000 | $2.400000 | medium |
| GLM-5.2 | – | $0.750000 | $2.400000 | medium |
| Kimi-K2.6 | – | $0.750000 | $3.500000 | high |
| Tencent: Hy4 preview | fp8 | $0.834000 | $2.501000 | high |
| Tencent: Hy4 preview | – | $0.834000 | $2.501000 | medium |
| Sao10K: Llama 3.1 Euryale 70B v2.2 | fp8 | $0.850000 | $0.850000 | high |
| Sao10K/L3.1-70B-Euryale-v2.2 | – | $0.850000 | $0.850000 | medium |
| GLM-5.3 | – | $0.900000 | $4.000000 | medium |
| Thinking Machines: Inkling (free) | fp8 | $0.950000 | $4.050000 | high |
| Thinking Machines: Inkling (free) | – | $0.950000 | $4.050000 | medium |
| Nous: Hermes 3 405B Instruct | fp8 | $1.000000 | $1.000000 | high |
| Nous: Hermes 3 405B Instruct | – | $1.000000 | $1.000000 | medium |
| deepseek-ai/DeepSeek-R1-0528-Turbo | – | $1.000000 | $3.000000 | medium |
| deepseek-ai/DeepSeek-R1-Turbo | – | $1.000000 | $3.000000 | medium |
| xiaomimimo/mimo-v2.5-pro | – | $1.000000 | $3.000000 | medium |
| Anthropic: Claude Haiku 4.5 | – | $1.000000 | $5.000000 | medium |
| Xiaomi: MiMo-V2.5-Pro | – | $1.000000 | $3.000000 | medium |
| Claude Haiku 4.5 (AU) | – | $1.000000 | $5.000000 | high |
| GLM-5.1 | – | $1.050000 | $3.500000 | medium |
| Qwen: Qwen3 Max | – | $1.200000 | $6.000000 | medium |
| Qwen: Qwen3 Max Thinking | – | $1.200000 | $6.000000 | medium |
| Qwen3-Max-Thinking | – | $1.200000 | $6.000000 | high |
| Qwen3-Max | – | $1.200000 | $6.000000 | high |
| Google: Gemini 2.5 Pro | – | $1.250000 | $10.000000 | medium |
| gemini-2.5-pro | – | $1.250000 | $10.000000 | high |
| DeepSeek: DeepSeek V4 Pro 0813 | fp8 | $1.300000 | $2.600000 | high |
| DeepSeek: DeepSeek V4 Pro 0423 | fp8 | $1.300000 | $2.600000 | high |
| deepseek-ai/DeepSeek-V4-Pro-0813 | – | $1.300000 | $2.600000 | medium |
| deepseek-ai/DeepSeek-V4-Pro | – | $1.300000 | $2.600000 | medium |
| DeepSeek: DeepSeek V4 Pro 0813 | – | $1.300000 | $2.600000 | medium |
| DeepSeek: DeepSeek V4 Pro 0423 | – | $1.300000 | $2.600000 | medium |
| DeepSeek-V4-Pro | – | $1.300000 | $2.600000 | high |
| Google: Gemini 3.5 Flash | – | $1.500000 | $9.000000 | medium |
| gemini-3.5-flash | – | $1.500000 | $9.000000 | high |
| qwen/qwen3.8-max | – | $1.650000 | $4.951000 | medium |
| Qwen Max Latest (Qwen3.8 Max) | – | $1.650000 | $4.951000 | medium |
| qwen3-8-max | – | $1.650000 | $4.951000 | high |
| Qwen: Qwen3.8 2.4T A95B | fp4 | $2.000000 | $6.000000 | high |
| Qwen: Qwen3.8 2.4T A95B | – | $2.000000 | $6.000000 | medium |
| Anthropic: Claude Sonnet 5 | – | $2.000000 | $10.000000 | medium |
| google/gemini-3.1-pro | – | $2.000000 | $12.000000 | medium |
| gemini-3.1-pro | – | $2.000000 | $12.000000 | high |
| Qwen: Qwen3.7 Max | – | $2.500000 | $7.500000 | medium |
| Qwen3.7 Max | – | $2.500000 | $7.500000 | medium |
| Qwen3.7-Max | – | $2.500000 | $7.500000 | high |
| MoonshotAI: Kimi K3 | – | $2.850000 | $14.250000 | high |
| MoonshotAI: Kimi K3 | – | $2.850000 | $14.250000 | medium |
| Kimi K3 | – | $2.850000 | $14.250000 | medium |
| kimi-k3 | – | $2.850000 | $14.250000 | high |
| anthropic/claude-sonnet-4-6 | – | $3.000000 | $15.000000 | medium |
| claude-sonnet-5 | – | $3.000000 | $15.000000 | high |
| claude-sonnet-4-6 | – | $3.000000 | $15.000000 | high |
| anthropic/claude-3-7-sonnet-latest | – | $3.300000 | $16.500000 | medium |
| anthropic/claude-4-sonnet | – | $3.300000 | $16.500000 | medium |
| anthropic/claude-opus-4-8 | – | $5.000000 | $25.000000 | medium |
| Anthropic: Claude Opus 5 | – | $5.000000 | $25.000000 | medium |
| anthropic/claude-opus-4-7 | – | $5.000000 | $25.000000 | medium |
| claude-opus-5 | – | $5.000000 | $25.000000 | high |
| claude-opus-4-7 | – | $5.000000 | $25.000000 | high |
| claude-opus-4-8 | – | $5.000000 | $25.000000 | high |
| Anthropic: Claude Fable 5 | – | $10.000000 | $50.000000 | medium |
| claude-fable-5 | – | $10.000000 | $50.000000 | high |
| anthropic/claude-4-opus | – | $16.500000 | $82.500000 | medium |