DeepInfra
Hybrid190 models hostedZDR
Avg Price
$1.65/M
Range
$0.026-$34.00
Reasoning
131
With AA Score
124
Hosting
108 self-hosted
Tier Breakdown
Frontier
$25.50/M
2 models
$17.00 - $34.00
Standard
$3.73/M
10 models
$0.180 - $9.69
Budget
$1.47/M
43 models
$0.132 - $10.20
Micro
$1.20/M
135 models
$0.026 - $17.00
ZDR: ZDR default: input/output not stored to disk, memory-only during inference. Exceptions: Google/Anthropic models, image-gen outputs short-term, bulk APIs may store encrypted briefly.
Hosted Models (click column to sort)
| Model | Owner | Tier | Host | Quant | Input $/M | Output $/M | Blended $/M▲ | Cost / IQ | SIT Score |
|---|---|---|---|---|---|---|---|---|---|
| Mistral: Mistral Nemo | Mistral AI | Micro | - | fp8 | $0.019 | $0.030 | $0.026 | N/A | N/A |
| Mistral Nemo Instruct 2407 | Mistralai | Micro | Self | - | $0.019 | $0.030 | $0.026 | N/A | N/A |
| Meta: Llama 3.1 8B Instruct | Meta Llama | Micro | - | fp8 | $0.020 | $0.040 | $0.032 | $0.392 | N/A |
| Meta Llama 3.1 8B Instruct Turbo | Meta Llama | Micro | Self | - | $0.020 | $0.040 | $0.032 | N/A | N/A |
| L3 8B Lunaris v1 Turbo | Sao10K | Micro | Self | - | $0.040 | $0.050 | $0.046 | N/A | N/A |
| Sao10K: Llama 3 8B Lunaris | Sao10K | Micro | - | fp8 | $0.040 | $0.050 | $0.046 | $0.121 | N/A |
| gemma 4 E4B itREASONING | Micro | Self | - | $0.020 | $0.100 | $0.068 | N/A | N/A | |
| Mistral: Mistral Small 3 | Mistral AI | Micro | Self | - | $0.050 | $0.080 | $0.068 | $0.465 | N/A |
| Mistral: Mistral Small 3 | Mistral AI | Micro | - | fp8 | $0.050 | $0.080 | $0.068 | $0.465 | N/A |
| Google: Gemma 3 4B | Micro | - | bf16 | $0.050 | $0.100 | $0.080 | $0.662 | N/A | |
| Google: Gemma 3 4B | Micro | Self | - | $0.050 | $0.100 | $0.080 | $0.662 | N/A | |
| granite 4.2 3bREASONING | Ibm Granite | Micro | Self | - | $0.030 | $0.120 | $0.084 | N/A | N/A |
| OpenAI: gpt-oss-20bREASONING | OpenAI | Micro | - | bf16 | $0.030 | $0.140 | $0.096 | $0.464 | N/A |
| OpenAI: gpt-oss-20bREASONING | OpenAI | Micro | Self | - | $0.030 | $0.140 | $0.096 | $0.464 | N/A |
| Google: Gemma 3 12B | Micro | - | bf16 | $0.050 | $0.150 | $0.110 | $1.01 | N/A | |
| Google: Gemma 3 12B | Micro | Self | - | $0.050 | $0.150 | $0.110 | $1.01 | N/A | |
| Microsoft: Phi 4 | Microsoft | Micro | - | bf16 | $0.070 | $0.140 | $0.112 | $0.756 | N/A |
| Microsoft: Phi 4 | Microsoft | Micro | Self | - | $0.070 | $0.140 | $0.112 | $0.756 | N/A |
| OpenAI: gpt-oss-120bREASONING | OpenAI | Micro | Self | - | $0.037 | $0.170 | $0.117 | $1.45 | N/A |
| NVIDIA: Nemotron 3.5 LightningREASONING | NVIDIA | Micro | - | bf16 | $0.060 | $0.160 | $0.120 | $0.414 | N/A |
| NVIDIA Nemotron 3.5 Lightning | Nvidia | Micro | Self | - | $0.060 | $0.160 | $0.120 | N/A | N/A |
| Google: Gemma 3 27B | Micro | Self | - | $0.080 | $0.160 | $0.128 | $1.38 | N/A | |
| Google: Gemma 3 27B | Micro | - | fp8 | $0.080 | $0.160 | $0.128 | $1.38 | N/A | |
| Qwen: Qwen3.5-9BREASONING | Qwen | Micro | - | bf16 | $0.100 | $0.150 | $0.130 | $0.464 | N/A |
| Qwen: Qwen3.5-9BREASONING | Qwen | Micro | Self | - | $0.100 | $0.150 | $0.130 | $0.464 | N/A |
| DeepSeek V4 Flash 0731REASONING | Deepseek Ai | Micro | Self | - | $0.060 | $0.180 | $0.132 | N/A | N/A |
| DeepSeek: DeepSeek V4 Flash 0731REASONING | DeepSeek | Budget | - | fp8 | $0.060 | $0.180 | $0.132 | $0.302 | N/A |
| inclusionAI: Ling 3.0 FlashREASONING | Inclusionai | Budget | - | bf16 | $0.060 | $0.180 | $0.132 | $0.212 | N/A |
| inclusionAI: Ling 3.0 FlashREASONING | Inclusionai | Budget | Self | - | $0.060 | $0.180 | $0.132 | $0.212 | N/A |
| inclusionAI: Ling 3.0 Flash FinREASONING | Inclusionai | Budget | Self | - | $0.060 | $0.180 | $0.132 | $0.260 | N/A |
| inclusionAI: Ling 3.0 Flash FinREASONING | Inclusionai | Budget | - | fp4 | $0.060 | $0.180 | $0.132 | $0.260 | N/A |
| inclusionAI: Ling 3.0 Flash VLREASONING | Inclusionai | Budget | Self | - | $0.060 | $0.180 | $0.132 | $0.239 | N/A |
| inclusionAI: Ling 3.0 Flash VLREASONING | Inclusionai | Budget | - | fp16 | $0.060 | $0.180 | $0.132 | $0.239 | N/A |
| NVIDIA: Nemotron 3 Nano 30B A3BREASONING | NVIDIA | Micro | Self | - | $0.050 | $0.200 | $0.140 | $0.629 | N/A |
| NVIDIA: Nemotron 3 Nano 30B A3BREASONING | NVIDIA | Micro | - | fp4 | $0.050 | $0.200 | $0.140 | $0.629 | N/A |
| DeepSeek V4 FlashREASONING | Deepseek Ai | Micro | Self | - | $0.090 | $0.180 | $0.144 | N/A | N/A |
| DeepSeek: DeepSeek V4 Flash 0423REASONING | DeepSeek | Budget | - | fp8 | $0.090 | $0.180 | $0.144 | $0.257 | N/A |
| Mistral: Mistral Small 3.2 24B | Mistral AI | Micro | - | fp8 | $0.075 | $0.200 | $0.150 | $1.21 | N/A |
| Mistral Small 3.2 24B Instruct 2506 | Mistralai | Micro | Self | - | $0.075 | $0.200 | $0.150 | N/A | N/A |
| IBM: Granite 4.2 8BREASONING | IBM Granite | Micro | - | bf16 | $0.060 | $0.250 | $0.174 | $0.549 | N/A |
| IBM: Granite 4.2 8BREASONING | IBM Granite | Micro | Self | - | $0.060 | $0.250 | $0.174 | $0.549 | N/A |
| Meta: Llama Guard 4 12B | Meta Llama | Budget | - | bf16 | $0.180 | $0.180 | $0.180 | N/A | N/A |
| Meta: Llama Guard 4 12B | Meta Llama | Budget | Self | - | $0.180 | $0.180 | $0.180 | N/A | N/A |
| Z.ai: GLM 5.3 FlashREASONING | Z.ai | Standard | - | fp4 | $0.075 | $0.250 | $0.180 | $0.344 | N/A |
| Xiaomi: MiMo-V2.6-FlashREASONING | Xiaomi | Budget | - | fp8 | $0.119 | $0.238 | $0.190 | $0.237 | N/A |
| Qwen: Qwen3 14BREASONING | Qwen | Micro | Self | - | $0.120 | $0.240 | $0.192 | $0.942 | N/A |
| Qwen: Qwen3 14BREASONING | Qwen | Micro | - | fp8 | $0.120 | $0.240 | $0.192 | $0.942 | N/A |
| NVIDIA: Nemotron 3.5 Content SafetyREASONING | NVIDIA | Budget | - | bf16 | $0.200 | $0.200 | $0.200 | N/A | N/A |
| Qwen: Qwen3 32BREASONING | Qwen | Micro | Self | - | $0.080 | $0.280 | $0.200 | $1.39 | N/A |
| Qwen: Qwen3 32BREASONING | Qwen | Micro | - | fp8 | $0.080 | $0.280 | $0.200 | $1.39 | N/A |
| Xiaomi: MiMo-V2.5REASONING | Xiaomi | Budget | - | fp8 | $0.133 | $0.266 | $0.213 | $0.392 | N/A |
| Meta: Llama 4 Scout | Meta Llama | Micro | - | fp8 | $0.100 | $0.300 | $0.220 | $2.11 | N/A |
| Llama 4 Scout Instruct | Meta Llama | Micro | Self | - | $0.100 | $0.300 | $0.220 | N/A | N/A |
| XiaomiMiMo/MiMo-V2.5REASONING | Xiaomimimo | Micro | Self | - | $0.140 | $0.280 | $0.224 | N/A | N/A |
| MiMo V2.6 FlashREASONING | Xiaomimimo | Micro | Self | - | $0.140 | $0.280 | $0.224 | N/A | N/A |
| MiMo V2.6 Flash RLREASONING | Xiaomimimo | Micro | Self | - | $0.140 | $0.280 | $0.224 | N/A | N/A |
| Google: Gemma 4 26B A4B REASONING | Micro | Self | - | $0.070 | $0.340 | $0.232 | $0.547 | N/A | |
| Google: Gemma 4 26B A4B REASONING | Micro | - | fp8 | $0.070 | $0.340 | $0.232 | $0.547 | N/A | |
| Meta: Llama 3.3 70B Instruct | Meta Llama | Micro | - | fp8 | $0.100 | $0.320 | $0.232 | $3.71 | N/A |
| Llama 3.3 70B Instruct Turbo | Meta Llama | Micro | Self | - | $0.100 | $0.320 | $0.232 | N/A | N/A |
| Google: Gemma 4 31BREASONING | Micro | - | fp4 | $0.090 | $0.340 | $0.240 | $0.624 | N/A | |
| gemma 4 31B it turboREASONING | Micro | Self | - | $0.090 | $0.340 | $0.240 | N/A | N/A | |
| NVIDIA: Nemotron 3 SuperREASONING | NVIDIA | Micro | - | bf16 | $0.085 | $0.400 | $0.274 | $0.898 | N/A |
| Qwen: Qwen3.8 FlashREASONING | Qwen | Budget | Self | - | $0.113 | $0.382 | $0.274 | N/A | N/A |
| Seed 2.0 miniREASONING | Bytedance | Micro | Self | - | $0.100 | $0.400 | $0.280 | N/A | N/A |
| Google: Gemma 4 31BREASONING | Micro | Self | - | $0.130 | $0.380 | $0.280 | $0.624 | N/A | |
| Google: Gemma 4 31BREASONING | Micro | - | fp8 | $0.130 | $0.380 | $0.280 | $0.624 | N/A | |
| DeepSeek: DeepSeek V4.1 FlashREASONING | DeepSeek | Standard | - | fp8 | $0.140 | $0.420 | $0.308 | $0.798 | N/A |
| DeepSeek V3.2 | Deepseek Ai | Micro | Self | - | $0.260 | $0.380 | $0.332 | N/A | N/A |
| DeepSeek: DeepSeek V3.2REASONING | DeepSeek | Micro | - | fp4 | $0.260 | $0.380 | $0.332 | $1.39 | N/A |
| Qwen: Qwen3 30B A3BREASONING | Qwen | Micro | Self | - | $0.120 | $0.500 | $0.348 | $1.87 | N/A |
| Qwen: Qwen3 30B A3BREASONING | Qwen | Micro | - | fp8 | $0.120 | $0.500 | $0.348 | $1.87 | N/A |
| GLM 5.3 FlashREASONING | Zai Org | Micro | Self | - | $0.150 | $0.500 | $0.360 | N/A | N/A |
| Qwen: Qwen3 235B A22B Instruct 2507 | Qwen | Micro | - | fp8 | $0.090 | $0.550 | $0.366 | $1.81 | N/A |
| Qwen3 235B A22B Instruct 2507 | Qwen | Micro | Self | - | $0.090 | $0.550 | $0.366 | N/A | N/A |
| Tencent: Hy3REASONING | Tencent | Budget | Self | - | $0.130 | $0.530 | $0.370 | $0.639 | N/A |
| Tencent: Hy3REASONING | Tencent | Budget | - | fp4 | $0.130 | $0.530 | $0.370 | $0.639 | N/A |
| Qwen2.5 72B Instruct | Qwen | Micro | - | fp8 | $0.360 | $0.400 | $0.384 | $2.01 | N/A |
| Qwen2.5 72B Instruct | Qwen | Micro | Self | - | $0.360 | $0.400 | $0.384 | N/A | N/A |
| MythoMax 13B | Gryphe | Micro | Self | - | $0.400 | $0.400 | $0.400 | N/A | N/A |
| MythoMax 13B | Gryphe | Micro | - | fp16 | $0.400 | $0.400 | $0.400 | N/A | N/A |
| Meta: Llama 3.1 70B Instruct | Meta Llama | Micro | - | fp8 | $0.400 | $0.400 | $0.400 | $3.39 | N/A |
| Meta Llama 3.1 70B Instruct Turbo | Meta Llama | Micro | Self | - | $0.400 | $0.400 | $0.400 | N/A | N/A |
| OpenAI: gpt-oss-120bREASONING | OpenAI | Micro | - | bf16 | $0.150 | $0.600 | $0.420 | $1.45 | N/A |
| gpt oss 120b TurboREASONING | OpenAI | Micro | Self | - | $0.150 | $0.600 | $0.420 | N/A | N/A |
| Qwen: Qwen3 VL 30B A3B Instruct | Qwen | Micro | Self | - | $0.150 | $0.600 | $0.420 | $2.32 | N/A |
| Qwen: Qwen3 VL 30B A3B Instruct | Qwen | Micro | - | fp8 | $0.150 | $0.600 | $0.420 | $2.32 | N/A |
| DeepSeek V4.1 FlashREASONING | DeepSeek | Micro | Self | - | $0.200 | $0.600 | $0.440 | N/A | N/A |
| granite 4.2 30bREASONING | Ibm Granite | Micro | Self | - | $0.160 | $0.650 | $0.454 | N/A | N/A |
| DeepSeek: DeepSeek V4 Flash Vision ExpREASONING | DeepSeek | Budget | - | fp8 | $0.216 | $0.647 | $0.474 | $1.11 | N/A |
| Meta: Llama 4 Maverick | Meta Llama | Micro | - | fp8 | $0.200 | $0.800 | $0.560 | $2.47 | N/A |
| Llama 4 Maverick Instruct | Meta Llama | Micro | Self | - | $0.200 | $0.800 | $0.560 | N/A | N/A |
| gemma 4 31B it UltraREASONING | Micro | Self | - | $0.270 | $0.760 | $0.564 | N/A | N/A | |
| Qwen: Qwen3 VL 235B A22B Instruct | Qwen | Micro | Self | - | $0.200 | $0.880 | $0.608 | $2.93 | N/A |
| Qwen: Qwen3 VL 235B A22B Instruct | Qwen | Micro | - | fp8 | $0.200 | $0.880 | $0.608 | $2.93 | N/A |
| Qwen: Qwen3.6 35B A3BREASONING | Qwen | Micro | Self | - | $0.100 | $0.950 | $0.610 | $1.43 | N/A |
| Qwen: Qwen3.6 35B A3BREASONING | Qwen | Micro | - | fp8 | $0.100 | $0.950 | $0.610 | $1.43 | N/A |
| StepFun: Step 3.7 FlashREASONING | StepFun | Micro | - | unknown | $0.160 | $0.920 | $0.616 | $1.58 | N/A |
| DeepSeek V3 0324 | Deepseek Ai | Micro | Self | - | $0.240 | $0.900 | $0.636 | N/A | N/A |
| DeepSeek: DeepSeek V3 0324 | DeepSeek | Micro | - | fp4 | $0.240 | $0.900 | $0.636 | $2.88 | N/A |
| OpenAI: gpt-oss-120bREASONING | OpenAI | Micro | - | fp8 | $0.200 | $0.950 | $0.650 | $1.45 | N/A |
| gpt oss 120b UltraREASONING | OpenAI | Micro | Self | - | $0.200 | $0.950 | $0.650 | N/A | N/A |
| Qwen: Qwen3.5-35B-A3BREASONING | Qwen | Micro | Self | - | $0.140 | $1.00 | $0.656 | $1.78 | N/A |
| Qwen: Qwen3.5-35B-A3BREASONING | Qwen | Micro | - | fp8 | $0.140 | $1.00 | $0.656 | $1.78 | N/A |
| DeepSeek V3 | Deepseek Ai | Micro | Self | - | $0.320 | $0.890 | $0.662 | N/A | N/A |
| DeepSeek: DeepSeek V3 | DeepSeek | Budget | - | fp4 | $0.320 | $0.890 | $0.662 | N/A | N/A |
| DeepSeek V3.1REASONING | Deepseek Ai | Micro | Self | - | $0.250 | $0.950 | $0.670 | N/A | N/A |
| DeepSeek: DeepSeek V3.1REASONING | DeepSeek | Micro | - | fp4 | $0.250 | $0.950 | $0.670 | $3.44 | N/A |
| Xiaomi: MiMo-V2.6-ProREASONING | Xiaomi | Standard | - | fp8 | $0.430 | $0.870 | $0.694 | $0.601 | N/A |
| MiMo V2.6 ProREASONING | Xiaomimimo | Micro | Self | - | $0.430 | $0.870 | $0.694 | N/A | N/A |
| Qwen: Qwen3 Next 80B A3B Instruct | Qwen | Micro | Self | - | $0.090 | $1.10 | $0.696 | $2.90 | N/A |
| Qwen: Qwen3 Next 80B A3B Instruct | Qwen | Micro | - | fp8 | $0.090 | $1.10 | $0.696 | $2.90 | N/A |
| Nous: Hermes 3 70B Instruct | Nous Research | Micro | Self | - | $0.700 | $0.700 | $0.700 | $4.67 | N/A |
| Nous: Hermes 3 70B Instruct | Nous Research | Micro | - | fp8 | $0.700 | $0.700 | $0.700 | $4.67 | N/A |
| Qwen: Qwen3 Coder 480B A35B | Qwen | Micro | - | fp4 | $0.300 | $1.00 | $0.720 | $3.64 | N/A |
| Qwen3 Coder 480B A35B Instruct Turbo | Qwen | Micro | Self | - | $0.300 | $1.00 | $0.720 | N/A | N/A |
| Step 3.7 Flash | Stepfun Ai | Micro | Self | - | $0.200 | $1.15 | $0.770 | N/A | N/A |
| MiniMax: MiniMax M3REASONING | MiniMax | Budget | - | fp8 | $0.280 | $1.10 | $0.772 | $1.15 | N/A |
| MiniMax M3REASONING | Minimaxai | Micro | Self | - | $0.280 | $1.10 | $0.772 | N/A | N/A |
| Muse Glimmer 30B | Meta | Micro | Self | - | $0.300 | $1.20 | $0.840 | N/A | N/A |
| Meta: Muse Glimmer 30BREASONING | Meta | Micro | - | bf16 | $0.300 | $1.20 | $0.840 | $1.92 | N/A |
| L3.1 70B Euryale v2.2 | Sao10K | Micro | Self | - | $0.850 | $0.850 | $0.850 | N/A | N/A |
| Sao10K: Llama 3.1 Euryale 70B v2.2 | Sao10K | Micro | - | fp8 | $0.850 | $0.850 | $0.850 | $3.02 | N/A |
| Xiaomi: MiMo-V2.5-ProREASONING | Xiaomi | Budget | - | fp8 | $0.390 | $1.17 | $0.858 | $1.18 | N/A |
| Thinking Machines: Inkling SmallREASONING | Thinking Machines | Budget | Self | - | $0.450 | $1.20 | $0.900 | $1.30 | N/A |
| Thinking Machines: Inkling SmallREASONING | Thinking Machines | Budget | - | fp8 | $0.450 | $1.20 | $0.900 | $1.30 | N/A |
| DeepSeek V4 Flash Vision ExpREASONING | DeepSeek | Micro | Self | - | $0.440 | $1.32 | $0.968 | N/A | N/A |
| Google: Gemini 3.1 Flash LiteREASONING | Micro | Self | - | $0.250 | $1.50 | $1.00 | $2.57 | N/A | |
| Nous: Hermes 3 405B Instruct | Nous Research | Budget | Self | - | $1.00 | $1.00 | $1.00 | N/A | N/A |
| Nous: Hermes 3 405B Instruct | Nous Research | Budget | - | fp8 | $1.00 | $1.00 | $1.00 | N/A | N/A |
| MiniMax: MiniMax M2.7REASONING | MiniMax | Budget | - | fp8 | $0.380 | $1.70 | $1.17 | $1.48 | N/A |
| MiniMax M2.7 TurboREASONING | Minimaxai | Micro | Self | - | $0.380 | $1.70 | $1.17 | N/A | N/A |
| Qwen: Qwen3.8 27BREASONING | Qwen | Budget | - | bf16 | $0.150 | $1.88 | $1.19 | $1.96 | N/A |
| Z.ai: GLM 4.7REASONING | Z.ai | Micro | - | fp4 | $0.400 | $1.75 | $1.21 | $2.81 | N/A |
| GLM-4.7REASONING | Zai Org | Micro | Self | - | $0.400 | $1.75 | $1.21 | N/A | N/A |
| Seed 1.8REASONING | Bytedance | Micro | Self | - | $0.250 | $2.00 | $1.30 | N/A | N/A |
| Z.ai: GLM 5.2REASONING | Z.ai | Budget | - | fp4 | $0.563 | $1.80 | $1.30 | $3.69 | N/A |
| Z.ai: GLM 4.6REASONING | Z.ai | Micro | - | fp4 | $0.500 | $2.00 | $1.40 | $3.94 | N/A |
| GLM 4.6REASONING | Zai Org | Micro | Self | - | $0.500 | $2.00 | $1.40 | N/A | N/A |
| DeepSeek R1 0528REASONING | Deepseek Ai | Micro | Self | - | $0.500 | $2.15 | $1.49 | N/A | N/A |
| DeepSeek: R1 0528REASONING | DeepSeek | Micro | - | fp4 | $0.500 | $2.15 | $1.49 | $4.74 | N/A |
| NVIDIA: Nemotron 3 UltraREASONING | NVIDIA | Budget | - | fp4 | $0.500 | $2.20 | $1.52 | $2.93 | N/A |
| Qwen: Qwen3.5-122B-A10BREASONING | Qwen | Micro | Self | - | $0.290 | $2.40 | $1.56 | $4.00 | N/A |
| Qwen: Qwen3.5-122B-A10BREASONING | Qwen | Micro | - | fp4 | $0.290 | $2.40 | $1.56 | $4.00 | N/A |
| Qwen: Qwen3.8 27BREASONING | Qwen | Budget | Self | - | $0.200 | $2.50 | $1.58 | $1.96 | N/A |
| Google: Gemini 2.5 FlashREASONING | Micro | Self | - | $0.300 | $2.50 | $1.62 | $6.58 | N/A | |
| Qwen: Qwen3.5-27BREASONING | Qwen | Budget | Self | - | $0.260 | $2.60 | $1.66 | $2.59 | N/A |
| Qwen: Qwen3.5-27BREASONING | Qwen | Budget | - | fp8 | $0.260 | $2.60 | $1.66 | $2.59 | N/A |
| Z.ai: GLM 5.3REASONING | Z.ai | Standard | - | fp4 | $0.563 | $2.50 | $1.73 | $2.50 | N/A |
| GLM 5.2REASONING | Zai Org | Micro | Self | - | $0.750 | $2.40 | $1.74 | N/A | N/A |
| Qwen: Qwen3.5 397B A17BREASONING | Qwen | Micro | Self | - | $0.450 | $3.00 | $1.98 | $5.08 | N/A |
| Qwen: Qwen3.5 397B A17BREASONING | Qwen | Micro | - | fp8 | $0.450 | $3.00 | $1.98 | $5.08 | N/A |
| Seed 2.0 codeREASONING | Bytedance | Micro | Self | - | $0.500 | $3.00 | $2.00 | N/A | N/A |
| Seed 2.0 proREASONING | Bytedance | Micro | Self | - | $0.500 | $3.00 | $2.00 | N/A | N/A |
| Qwen: Qwen3.6 27BREASONING | Qwen | Micro | Self | - | $0.320 | $3.20 | $2.05 | $3.81 | N/A |
| Qwen: Qwen3.6 27BREASONING | Qwen | Micro | - | fp8 | $0.320 | $3.20 | $2.05 | $3.81 | N/A |
| DeepSeek V4 Pro | Deepseek Ai | Micro | Self | - | $1.30 | $2.60 | $2.08 | N/A | N/A |
| DeepSeek V4 Pro 0813 | Deepseek Ai | Micro | Self | - | $1.30 | $2.60 | $2.08 | N/A | N/A |
| DeepSeek: DeepSeek V4 Pro 0423REASONING | DeepSeek | Budget | - | fp8 | $1.30 | $2.60 | $2.08 | $2.76 | N/A |
| DeepSeek: DeepSeek V4 Pro 0813REASONING | DeepSeek | Budget | - | fp8 | $1.30 | $2.60 | $2.08 | $3.23 | N/A |
| XiaomiMiMo/MiMo-V2.5-ProREASONING | Xiaomimimo | Micro | Self | - | $1.00 | $3.00 | $2.20 | N/A | N/A |
| MoonshotAI: Kimi K2.7 CodeREASONING | Moonshot AI | Budget | Self | - | $0.680 | $3.40 | $2.31 | $4.31 | N/A |
| MoonshotAI: Kimi K2.7 CodeREASONING | Moonshot AI | Budget | - | fp4 | $0.680 | $3.40 | $2.31 | $4.31 | N/A |
| MoonshotAI: Kimi K2.6REASONING | Moonshot AI | Budget | Self | - | $0.750 | $3.50 | $2.40 | $3.56 | N/A |
| MoonshotAI: Kimi K2.6REASONING | Moonshot AI | Budget | - | fp4 | $0.750 | $3.50 | $2.40 | $3.56 | N/A |
| Z.ai: GLM 5.1REASONING | Z.ai | Budget | - | fp4 | $1.05 | $3.50 | $2.52 | $4.90 | N/A |
| GLM-5.1REASONING | Zai Org | Micro | Self | - | $1.05 | $3.50 | $2.52 | N/A | N/A |
| Google: Gemini 3.7 FlashREASONING | Standard | Self | - | $0.750 | $3.75 | $2.55 | $1.31 | N/A | |
| GLM 5.3REASONING | Zai Org | Micro | Self | - | $0.900 | $4.00 | $2.76 | N/A | N/A |
| Thinking Machines: InklingREASONING | Thinking Machines | Budget | Self | - | $0.950 | $4.05 | $2.81 | $4.51 | N/A |
| Thinking Machines: InklingREASONING | Thinking Machines | Budget | - | fp8 | $0.950 | $4.05 | $2.81 | $4.51 | N/A |
| claude haiku 4 5REASONING | Anthropic | Micro | Self | - | $1.00 | $5.00 | $3.40 | N/A | N/A |
| Qwen: Qwen3.8 MaxREASONING | Qwen | Standard | Self | - | $1.65 | $4.95 | $3.63 | $3.54 | N/A |
| Qwen: Qwen3 MaxREASONING | Qwen | Micro | Self | - | $1.20 | $6.00 | $4.08 | $10.45 | N/A |
| Qwen: Qwen3 Max ThinkingREASONING | Qwen | Micro | Self | - | $1.20 | $6.00 | $4.08 | $6.33 | N/A |
| Qwen: Qwen3.8 2.4T A95BREASONING | Qwen | Standard | Self | - | $2.00 | $6.00 | $4.40 | $4.41 | N/A |
| Qwen: Qwen3.8 2.4T A95BREASONING | Qwen | Standard | - | fp4 | $2.00 | $6.00 | $4.40 | $4.41 | N/A |
| Qwen: Qwen3.7 MaxREASONING | Qwen | Budget | Self | - | $2.50 | $7.50 | $5.50 | $4.44 | N/A |
| Google: Gemini 3.5 FlashREASONING | Budget | Self | - | $1.50 | $9.00 | $6.00 | $7.54 | N/A | |
| Google: Gemini 2.5 ProREASONING | Micro | Self | - | $1.25 | $10.00 | $6.50 | $16.17 | N/A | |
| gemini 3.1 proREASONING | Micro | Self | - | $2.00 | $12.00 | $8.00 | N/A | N/A | |
| MoonshotAI: Kimi K3REASONING | Moonshot AI | Standard | - | bf16 | $2.85 | $14.25 | $9.69 | $9.36 | N/A |
| MoonshotAI: Kimi K3REASONING | Moonshot AI | Standard | Self | - | $2.85 | $14.25 | $9.69 | $9.36 | N/A |
| claude sonnet 4 6REASONING | Anthropic | Micro | Self | - | $3.00 | $15.00 | $10.20 | N/A | N/A |
| Anthropic: Claude Sonnet 5REASONING | Anthropic | Budget | Self | - | $3.00 | $15.00 | $10.20 | $7.84 | N/A |
| Claude Opus 5.5 | Anthropic | Micro | Self | - | $4.00 | $20.00 | $13.60 | N/A | N/A |
| claude opus 4 7REASONING | Anthropic | Micro | Self | - | $5.00 | $25.00 | $17.00 | N/A | N/A |
| claude opus 4 8REASONING | Anthropic | Micro | Self | - | $5.00 | $25.00 | $17.00 | N/A | N/A |
| Anthropic: Claude Opus 5REASONING | Anthropic | Frontier | Self | - | $5.00 | $25.00 | $17.00 | $14.73 | N/A |
| Anthropic: Claude Fable 5REASONING | Anthropic | Frontier | Self | - | $10.00 | $50.00 | $34.00 | $27.41 | N/A |