| qwen/qwen3.6-max-preview @ alibaba/fp8 |
$45.53 |
— |
$0.60 |
$0.015 |
— |
$46.15 |
| qwen/qwen3.6-max-preview @ alibaba |
$28.64 |
$0.070 |
$1.36 |
$0.0039 |
— |
$30.08 |
| z-ai/glm-5.2 @ siliconflow/fp8 |
$23.08 |
$4.03 |
— |
$0.0043 |
— |
$27.11 |
| deepseek/deepseek-v4-flash-0731 @ wafer/fast |
$4.08 |
$0.44 |
— |
$0.00071 |
— |
$4.52 |
| z-ai/glm-5.2 @ novita/fp8 |
$2.93 |
$0.66 |
— |
$0.0016 |
— |
$3.59 |
| deepseek/deepseek-v4-pro @ gmicloud/fp8 |
$2.39 |
$0.40 |
— |
$0.0014 |
— |
$2.80 |
| xiaomi/mimo-v2.5-pro @ xiaomi/fp8 |
$2.23 |
$0.24 |
— |
$0.00046 |
— |
$2.47 |
| google/gemini-3.1-pro-preview @ google-ai-studio |
$2.30 |
— |
— |
$0.0029 |
— |
$2.30 |
| google/gemini-3.1-pro-preview @ google-vertex/global |
$2.24 |
— |
— |
$0.0026 |
— |
$2.24 |
| minimax/minimax-m2.5 @ minimax/fp8 |
$0.33 |
$1.83 |
— |
$0.0017 |
— |
$2.15 |
| z-ai/glm-5.2 @ wafer/fp4 |
$0.39 |
$1.56 |
$0.15 |
$0.0010 |
— |
$2.11 |
| google/gemini-3.1-pro-preview @ google-ai-studio/priority |
$2.07 |
— |
— |
$0.0024 |
— |
$2.07 |
| z-ai/glm-5.2 @ atlas-cloud/fp8 |
$1.80 |
$0.25 |
— |
$0.0023 |
— |
$2.06 |
| qwen/qwen3-vl-32b-instruct @ alibaba |
$1.76 |
$0.29 |
$0.0040 |
$0.00026 |
— |
$2.06 |
| google/gemini-3.1-pro-preview @ google-vertex/global/priority |
$2.02 |
— |
— |
$0.0022 |
— |
$2.02 |
| google/gemini-3.1-pro-preview @ google-ai-studio/flex |
$1.91 |
$0.084 |
— |
$0.0012 |
— |
$1.99 |
| z-ai/glm-5.2 @ parasail/fp4 |
$1.82 |
$0.17 |
— |
$0.0020 |
— |
$1.99 |
| anthropic/claude-sonnet-4.5 @ anthropic |
$1.60 |
$0.28 |
— |
$0.0040 |
— |
$1.89 |
| x-ai/grok-4.6 @ xai/zdr/priority |
— |
— |
$1.85 |
— |
— |
$1.85 |
| x-ai/grok-4.6 @ xai/priority |
— |
— |
$1.81 |
— |
— |
$1.81 |
| z-ai/glm-5.2 @ phala |
$1.32 |
$0.49 |
— |
$0.0018 |
— |
$1.81 |
| x-ai/grok-build-0.1 @ xai/priority |
— |
— |
$1.78 |
— |
— |
$1.78 |
| x-ai/grok-build-0.1 @ xai/zdr/priority |
— |
— |
$1.77 |
— |
— |
$1.77 |
| minimax/minimax-m3 @ together |
$1.44 |
$0.33 |
— |
$0.0054 |
— |
$1.77 |
| anthropic/claude-sonnet-4.6 @ claude-on-aws |
$1.59 |
$0.10 |
— |
$0.00058 |
— |
$1.70 |
| z-ai/glm-5.2 @ z-ai/fp8 |
$1.45 |
$0.19 |
— |
$0.0024 |
— |
$1.65 |
| x-ai/grok-4.3 @ xai/priority |
— |
— |
$1.65 |
— |
— |
$1.65 |
| x-ai/grok-4.3 @ xai/zdr/priority |
— |
— |
$1.65 |
— |
— |
$1.65 |
| z-ai/glm-5.2 @ fireworks/fast |
$1.35 |
$0.28 |
— |
$0.0034 |
— |
$1.64 |
| z-ai/glm-5.2 @ together |
$1.36 |
$0.19 |
— |
$0.0023 |
— |
$1.55 |
| z-ai/glm-5.2 @ cloudflare |
$1.35 |
$0.19 |
— |
$0.0019 |
— |
$1.54 |
| deepseek/deepseek-v4-pro @ streamlake |
$1.41 |
$0.080 |
— |
— |
— |
$1.49 |
| deepseek/deepseek-v4-pro @ novita/fp8 |
$1.24 |
$0.22 |
— |
$0.00099 |
— |
$1.46 |
| z-ai/glm-5.2 @ friendli |
$1.28 |
$0.15 |
— |
$0.0023 |
— |
$1.43 |
| moonshotai/kimi-k2.6 @ streamlake |
— |
— |
$1.40 |
— |
— |
$1.40 |
| x-ai/grok-4.5 @ xai/zdr/priority |
— |
— |
$1.37 |
— |
— |
$1.37 |
| x-ai/grok-4.5 @ xai/priority |
— |
— |
$1.36 |
— |
— |
$1.36 |
| z-ai/glm-5.2 @ decart/fp4 |
$1.20 |
$0.14 |
— |
$0.0014 |
— |
$1.34 |
| moonshotai/kimi-k2.5 @ streamlake |
— |
— |
$1.32 |
— |
— |
$1.32 |
| moonshotai/kimi-k2.5 @ streamlake/fp8 |
— |
— |
$1.28 |
— |
— |
$1.28 |
| moonshotai/kimi-k2.6 @ streamlake/fp8 |
— |
— |
$1.18 |
— |
— |
$1.18 |
| z-ai/glm-5.2 @ gmicloud/fp8 |
$0.98 |
$0.13 |
$0.058 |
$0.00088 |
— |
$1.17 |
| deepseek/deepseek-v4-pro @ streamlake/fp8 |
$1.07 |
$0.084 |
— |
$0.00072 |
— |
$1.15 |
| xiaomi/mimo-v2.5 @ gmicloud/fp8 |
$0.97 |
$0.14 |
— |
$0.0010 |
— |
$1.11 |
| anthropic/claude-sonnet-4.6 @ amazon-bedrock/global |
$0.88 |
$0.23 |
— |
$0.0040 |
— |
$1.11 |
| xiaomi/mimo-v2.5 @ xiaomi/fp8 |
$0.71 |
$0.34 |
— |
$0.0049 |
— |
$1.05 |
| z-ai/glm-5.2 @ coreweave/fp4 |
$0.90 |
$0.15 |
— |
$0.00056 |
— |
$1.05 |
| z-ai/glm-5.1 @ gmicloud/fp8 |
— |
— |
$0.99 |
$0.0021 |
— |
$0.99 |
| deepseek/deepseek-v4-pro @ deepseek |
$0.88 |
$0.078 |
— |
$0.00064 |
— |
$0.96 |
| x-ai/grok-4.6 @ xai |
— |
— |
$0.94 |
— |
— |
$0.94 |
| z-ai/glm-5.2 @ ionstream/fp4 |
$0.88 |
$0.059 |
— |
$0.00070 |
— |
$0.94 |
| x-ai/grok-4.6 @ xai/zdr |
— |
— |
$0.93 |
— |
— |
$0.93 |
| z-ai/glm-5.2 @ akashml/fp8 |
$0.79 |
$0.12 |
— |
$0.0016 |
— |
$0.91 |
| anthropic/claude-sonnet-4.5 @ claude-on-aws |
$0.79 |
$0.10 |
— |
$0.00058 |
— |
$0.89 |
| x-ai/grok-build-0.1 @ xai |
— |
— |
$0.88 |
$0.0016 |
— |
$0.89 |
| z-ai/glm-5.2 @ morph |
$0.74 |
$0.14 |
— |
$0.0014 |
— |
$0.88 |
| z-ai/glm-5.2 @ digitalocean |
$0.73 |
$0.15 |
— |
$0.0018 |
— |
$0.88 |
| x-ai/grok-build-0.1 @ xai/zdr |
— |
— |
$0.88 |
— |
— |
$0.88 |
| z-ai/glm-5.2 @ cloudflare/fast |
$0.68 |
$0.18 |
— |
$0.0011 |
— |
$0.86 |
| z-ai/glm-5.2 @ alibaba |
$0.48 |
$0.20 |
$0.17 |
$0.00090 |
— |
$0.84 |
| z-ai/glm-5.2 @ wafer/fast |
— |
— |
$0.84 |
— |
— |
$0.84 |
| x-ai/grok-4.3 @ xai |
— |
— |
$0.83 |
$0.0014 |
— |
$0.83 |
| x-ai/grok-4.3 @ xai/zdr |
— |
— |
$0.82 |
— |
— |
$0.82 |
| gryphe/mythomax-l2-13b @ mancer/fp8 |
$0.70 |
$0.10 |
$0.0093 |
$0.0018 |
— |
$0.81 |
| z-ai/glm-5.2 @ sail-research/fp8 |
$0.63 |
$0.13 |
— |
$0.00061 |
— |
$0.76 |
| qwen/qwen3-max-thinking @ alibaba |
$0.66 |
$0.063 |
$0.0073 |
$0.00094 |
— |
$0.73 |
| deepseek/deepseek-v4-flash @ alibaba |
$0.67 |
$0.018 |
— |
$0.00074 |
— |
$0.69 |
| z-ai/glm-5.2 @ baidu/fp8 |
$0.56 |
$0.13 |
— |
$0.0014 |
— |
$0.69 |
| anthropic/claude-haiku-4.5 @ anthropic |
$0.60 |
$0.085 |
— |
$0.0013 |
— |
$0.69 |
| ai21/jamba-large-1.7 @ ai21/fp8 |
$0.60 |
$0.082 |
— |
$0.0024 |
— |
$0.68 |
| x-ai/grok-4.5 @ xai/zdr |
— |
— |
$0.68 |
— |
— |
$0.68 |
| x-ai/grok-4.5 @ xai |
— |
— |
$0.68 |
— |
— |
$0.68 |
| deepseek/deepseek-v4-pro @ venice |
$0.54 |
$0.12 |
— |
$0.0013 |
— |
$0.66 |
| z-ai/glm-5.2 @ fireworks |
$0.45 |
$0.19 |
— |
$0.0024 |
— |
$0.64 |
| minimax/minimax-m2.7 @ minimax/fp8 |
$0.57 |
$0.058 |
— |
$0.0016 |
— |
$0.63 |
| xiaomi/mimo-v2.5 @ deepinfra/bf16 |
$0.51 |
$0.11 |
— |
$0.0014 |
— |
$0.63 |
| z-ai/glm-5.2 @ venice/fp8 |
$0.42 |
$0.19 |
— |
$0.0023 |
— |
$0.61 |
| z-ai/glm-5.2 @ wafer |
— |
— |
$0.60 |
— |
— |
$0.60 |
| deepseek/deepseek-v4-flash @ streamlake |
$0.52 |
$0.074 |
— |
$0.0000019 |
— |
$0.59 |
| cohere/command-r-plus-08-2024 @ cohere |
$0.50 |
$0.085 |
— |
$0.0013 |
— |
$0.59 |
| z-ai/glm-5.2 @ crusoe/fp8 |
$0.45 |
$0.13 |
— |
$0.00063 |
— |
$0.58 |
| deepseek/deepseek-v4-flash @ streamlake/fp8 |
$0.50 |
$0.073 |
— |
$0.00028 |
— |
$0.57 |
| minimax/minimax-m3 @ venice/fp8 |
$0.57 |
— |
— |
$0.0027 |
— |
$0.57 |
| deepseek/deepseek-v4-flash @ gmicloud/fp8 |
$0.52 |
$0.045 |
— |
$0.00066 |
— |
$0.57 |
| z-ai/glm-5.2 @ baseten/fast |
$0.56 |
— |
— |
$0.0017 |
— |
$0.56 |
| deepseek/deepseek-v4-pro @ parasail/fp8 |
$0.47 |
$0.087 |
— |
$0.0011 |
— |
$0.55 |
| z-ai/glm-5.2 @ chutes/fp4 |
$0.45 |
$0.081 |
— |
$0.00068 |
— |
$0.53 |
| x-ai/grok-4.20 @ xai/priority |
— |
— |
$0.53 |
— |
— |
$0.53 |
| x-ai/grok-4.20 @ xai/zdr/priority |
— |
— |
$0.53 |
— |
— |
$0.53 |
| minimax/minimax-m2.1 @ minimax/highspeed |
$0.40 |
$0.11 |
— |
$0.0020 |
— |
$0.52 |
| deepseek/deepseek-v4-flash @ phala |
$0.49 |
$0.027 |
— |
$0.00010 |
— |
$0.51 |
| z-ai/glm-5.2 @ ambient/fp8 |
$0.36 |
$0.15 |
— |
$0.0016 |
— |
$0.51 |
| z-ai/glm-5.2 @ inceptron/fp4 |
$0.36 |
$0.13 |
— |
$0.0015 |
— |
$0.49 |
| z-ai/glm-5.2 @ wandb/fp4 |
$0.45 |
$0.032 |
— |
$0.00094 |
— |
$0.48 |
| moonshotai/kimi-k2.7-code @ modelrun/fp4 |
$0.43 |
$0.037 |
— |
$0.00053 |
— |
$0.47 |
| z-ai/glm-5.3 @ z-ai/fp8 |
$0.45 |
$0.014 |
— |
$0.00032 |
— |
$0.47 |
| openai/gpt-oss-120b @ cerebras/fp16 |
$0.46 |
— |
— |
$0.0058 |
— |
$0.46 |
| z-ai/glm-5.2 @ fireworks/fast-us |
$0.42 |
$0.037 |
— |
$0.00027 |
— |
$0.46 |
| z-ai/glm-5.2 @ modelrun/fp4 |
$0.44 |
$0.0089 |
— |
$0.00012 |
— |
$0.45 |
| z-ai/glm-5.2 @ streamlake/fp8 |
$0.32 |
$0.13 |
— |
$0.0013 |
— |
$0.45 |
| openai/gpt-oss-120b @ baseten/fp4 |
$0.38 |
$0.066 |
— |
$0.0013 |
— |
$0.44 |
| qwen/qwen3.5-27b @ alibaba |
— |
— |
$0.44 |
$0.00070 |
— |
$0.44 |
| deepseek/deepseek-v4-flash @ atlas-cloud/fp4 |
$0.38 |
$0.048 |
— |
$0.00036 |
— |
$0.43 |
| z-ai/glm-5.3 @ modal |
$0.41 |
$0.0090 |
— |
$0.000090 |
— |
$0.42 |
| deepseek/deepseek-v4-pro @ baseten/fp4 |
$0.28 |
$0.13 |
— |
$0.0011 |
— |
$0.41 |
| bytedance-seed/seed-2.0-lite @ seed/fp8 |
$0.30 |
$0.10 |
— |
$0.0019 |
— |
$0.41 |
| z-ai/glm-5.2 @ alibaba/fp8 |
$0.31 |
$0.093 |
— |
$0.00070 |
— |
$0.40 |
| moonshotai/kimi-k2.6 @ moonshotai/int4 |
$0.28 |
$0.11 |
— |
$0.0011 |
— |
$0.39 |
| deepseek/deepseek-v4-pro @ ionstream/fp4 |
$0.32 |
$0.055 |
$0.010 |
$0.00048 |
— |
$0.39 |
| z-ai/glm-5.3 @ fireworks |
$0.37 |
$0.0086 |
— |
$0.000090 |
— |
$0.38 |
| z-ai/glm-5.2 @ baseten/fp8 |
$0.37 |
— |
— |
$0.0013 |
— |
$0.37 |
| z-ai/glm-5.2 @ deepinfra/fp4 |
$0.24 |
$0.12 |
— |
$0.0014 |
— |
$0.37 |
| z-ai/glm-5.2 @ phala/fp8 |
$0.33 |
$0.037 |
— |
$0.00024 |
— |
$0.37 |
| minimax/minimax-m2 @ minimax/fp8 |
$0.27 |
$0.093 |
— |
$0.0014 |
— |
$0.36 |
| deepseek/deepseek-v4-pro @ deepinfra/fp4 |
$0.30 |
$0.055 |
— |
$0.00070 |
— |
$0.35 |
| aion-labs/aion-2.0 @ aion-labs |
$0.32 |
$0.032 |
— |
$0.00085 |
— |
$0.35 |
| morph/morph-v3-large @ morph |
— |
— |
$0.35 |
$0.000091 |
— |
$0.35 |
| deepseek/deepseek-v4-pro @ together |
$0.23 |
$0.11 |
— |
$0.00096 |
— |
$0.34 |
| qwen/qwen3-max @ alibaba/fp8 |
$0.34 |
$0.00 |
$0.0033 |
$0.00020 |
— |
$0.34 |
| z-ai/glm-5.2 @ mistral/eu |
$0.31 |
$0.012 |
— |
$0.00015 |
— |
$0.33 |
| deepseek/deepseek-v4-flash-0731 @ phala |
$0.28 |
$0.041 |
— |
$0.00053 |
— |
$0.32 |
| deepseek/deepseek-v4-pro @ azure/us |
$0.27 |
$0.043 |
— |
$0.00024 |
— |
$0.31 |
| z-ai/glm-5.2 @ mistral |
$0.29 |
$0.026 |
— |
$0.00018 |
— |
$0.31 |
| z-ai/glm-5.2 @ decart/fp8 |
$0.29 |
$0.011 |
— |
$0.00022 |
— |
$0.30 |
| deepseek/deepseek-v4-pro @ digitalocean |
$0.20 |
$0.092 |
$0.015 |
$0.00089 |
— |
$0.30 |
| deepseek/deepseek-v4-pro @ alibaba/fp8 |
$0.25 |
$0.046 |
— |
$0.00049 |
— |
$0.30 |
| z-ai/glm-5.2 @ mistral/zdr |
$0.29 |
$0.011 |
— |
$0.00014 |
— |
$0.30 |
| tencent/hy3 @ atlas-cloud/fp8 |
$0.26 |
$0.036 |
— |
$0.00030 |
— |
$0.29 |
| deepseek/deepseek-v4-pro @ fireworks |
$0.24 |
$0.042 |
— |
$0.00069 |
— |
$0.29 |
| deepseek/deepseek-v4-pro @ wandb/fp8 |
$0.24 |
$0.032 |
$0.0096 |
$0.00068 |
— |
$0.29 |
| qwen/qwen3-235b-a22b-thinking-2507 @ novita/fp8 |
— |
— |
$0.27 |
$0.0013 |
— |
$0.27 |
| z-ai/glm-5.2 @ morph/fp4 |
$0.24 |
$0.035 |
— |
$0.00020 |
— |
$0.27 |
| deepseek/deepseek-v4-pro @ baidu/fp8 |
$0.23 |
$0.043 |
— |
$0.00077 |
— |
$0.27 |
| qwen/qwen3-max @ alibaba |
$0.22 |
$0.041 |
$0.0073 |
$0.00094 |
— |
$0.27 |
| qwen/qwen3.6-27b @ alibaba |
— |
— |
$0.27 |
$0.0013 |
— |
$0.27 |
| x-ai/grok-4.20 @ xai |
— |
— |
$0.27 |
$0.00047 |
— |
$0.27 |
| x-ai/grok-4.20 @ xai/zdr |
— |
— |
$0.27 |
— |
— |
$0.27 |
| z-ai/glm-5 @ digitalocean |
$0.23 |
$0.039 |
— |
$0.00073 |
— |
$0.26 |
| qwen/qwen3.5-397b-a17b @ alibaba |
— |
— |
$0.26 |
$0.0051 |
— |
$0.26 |
| bytedance-seed/seed-2.0-mini @ seed/fp8 |
$0.22 |
$0.039 |
— |
$0.00056 |
— |
$0.26 |
| relace/relace-search @ relace/bf16 |
$0.18 |
$0.084 |
— |
$0.0012 |
— |
$0.26 |
| z-ai/glm-5 @ deepinfra/fp4 |
$0.23 |
$0.032 |
— |
$0.00053 |
— |
$0.26 |
| z-ai/glm-5.2 @ relace/fp8 |
$0.25 |
$0.00 |
— |
$0.000051 |
— |
$0.25 |
| z-ai/glm-5.1 @ phala |
— |
— |
$0.25 |
$0.00064 |
— |
$0.25 |
| deepseek/deepseek-v4-pro @ coreweave/fp8 |
$0.22 |
$0.021 |
$0.0079 |
$0.00041 |
— |
$0.25 |
| moonshotai/kimi-k2.5 @ moonshotai/int4 |
$0.18 |
$0.068 |
— |
$0.00073 |
— |
$0.25 |
| minimax/minimax-m2.1 @ minimax/fp8 |
$0.25 |
— |
— |
$0.00089 |
— |
$0.25 |
| z-ai/glm-4.7 @ cerebras/fp16 |
$0.24 |
— |
— |
$0.0014 |
— |
$0.25 |
| z-ai/glm-5.2 @ reka/fp8 |
$0.23 |
$0.016 |
— |
$0.00012 |
— |
$0.25 |
| deepseek/deepseek-v4-flash-0731 @ coreweave/fp8 |
$0.23 |
$0.012 |
— |
$0.000066 |
— |
$0.24 |
| deepseek/deepseek-v4-flash-0731 @ gmicloud/fp8 |
$0.22 |
$0.022 |
— |
$0.00032 |
— |
$0.24 |
| deepseek/deepseek-v4-flash-0731 @ ambient/fp4 |
$0.23 |
$0.013 |
— |
$0.000049 |
— |
$0.24 |
| qwen/qwen3.5-122b-a10b @ alibaba |
— |
— |
$0.24 |
$0.00034 |
— |
$0.24 |
| moonshotai/kimi-k2.7-code @ ambient/int4 |
$0.21 |
$0.030 |
— |
$0.00088 |
— |
$0.24 |
| minimax/minimax-m2.7 @ fireworks |
$0.23 |
$0.0076 |
— |
$0.00084 |
— |
$0.24 |
| qwen/qwen3-max-thinking @ alibaba/fp8 |
$0.22 |
$0.015 |
$0.0033 |
$0.00020 |
— |
$0.24 |
| google/gemma-4-31b-it @ cerebras/fp16 |
$0.23 |
— |
— |
$0.0011 |
— |
$0.23 |
| moonshotai/kimi-k2.7-code @ ambient |
$0.19 |
$0.033 |
— |
$0.00019 |
— |
$0.23 |
| deepseek/deepseek-v4-flash-0731 @ atlas-cloud/fp8 |
$0.21 |
$0.010 |
— |
$0.000096 |
— |
$0.22 |
| z-ai/glm-5.1 @ baseten/fp4 |
$0.22 |
$0.0027 |
— |
$0.00078 |
— |
$0.22 |
| perceptron/perceptron-mk1 @ perceptron |
$0.22 |
— |
— |
$0.0021 |
— |
$0.22 |
| arcee-ai/trinity-large-thinking @ arcee-ai |
$0.20 |
$0.024 |
— |
$0.00036 |
— |
$0.22 |
| deepseek/deepseek-v4-flash @ deepseek |
$0.21 |
$0.012 |
— |
$0.00044 |
— |
$0.22 |
| deepseek/deepseek-v4-flash-0731 @ together |
$0.21 |
$0.0089 |
— |
$0.000095 |
— |
$0.22 |
| deepseek/deepseek-v4-flash @ siliconflow/fp8 |
$0.13 |
$0.082 |
— |
$0.00025 |
— |
$0.21 |
| aion-labs/aion-rp-llama-3.1-8b @ aion-labs |
$0.18 |
$0.033 |
— |
$0.00099 |
— |
$0.21 |
| z-ai/glm-5.1 @ wafer/fp4 |
$0.17 |
$0.035 |
— |
$0.00073 |
— |
$0.20 |
| nvidia/nemotron-3-ultra-550b-a55b @ baseten/fp4 |
$0.20 |
— |
— |
$0.00079 |
— |
$0.20 |
| deepseek/deepseek-v3.2 @ atlas-cloud/fp8 |
$0.18 |
$0.021 |
$0.00048 |
$0.00023 |
— |
$0.20 |
| qwen/qwen3.5-27b @ alibaba/fp8 |
— |
— |
$0.20 |
— |
— |
$0.20 |
| moonshotai/kimi-k2.6 @ sail-research/int4 |
$0.19 |
— |
— |
$0.00031 |
— |
$0.19 |
| deepseek/deepseek-v3.2 @ alibaba/fp8 |
$0.18 |
$0.015 |
— |
$0.00011 |
— |
$0.19 |
| z-ai/glm-5.1 @ streamlake/fp8 |
$0.18 |
$0.0053 |
$0.0074 |
$0.0018 |
— |
$0.19 |
| tencent/hy3 @ tencent/fp8 |
$0.17 |
$0.017 |
— |
$0.00012 |
— |
$0.19 |
| deepseek/deepseek-chat-v3.1 @ atlas-cloud/fp8 |
$0.17 |
$0.016 |
— |
$0.00028 |
— |
$0.19 |
| z-ai/glm-5.2 @ makora/fp8 |
$0.19 |
$0.0019 |
— |
$0.000053 |
— |
$0.19 |
| deepseek/deepseek-v4-pro-0813 @ fireworks |
$0.19 |
— |
— |
$0.00019 |
— |
$0.19 |
| xiaomi/mimo-v2.5 @ venice/fp8 |
$0.17 |
$0.018 |
— |
$0.00043 |
— |
$0.19 |
| deepseek/deepseek-v4-flash-0731 @ fireworks |
$0.18 |
— |
— |
$0.00039 |
— |
$0.18 |
| z-ai/glm-5.1 @ alibaba/fp8 |
— |
— |
$0.18 |
$0.00036 |
— |
$0.18 |
| deepseek/deepseek-v4-flash-0731 @ sail-research/fp4 |
$0.16 |
$0.022 |
$0.0014 |
$0.00014 |
— |
$0.18 |
| qwen/qwen3.5-397b-a17b @ deepinfra/fp8 |
$0.16 |
$0.010 |
— |
$0.00076 |
— |
$0.17 |
| deepseek/deepseek-v4-pro @ cloudflare |
$0.17 |
$0.0017 |
$0.0040 |
$0.00021 |
— |
$0.17 |
| thedrummer/skyfall-36b-v2 @ parasail/fp8 |
— |
— |
$0.17 |
$0.0022 |
— |
$0.17 |
| tencent/hy3 @ deepinfra/fp8 |
$0.15 |
$0.020 |
— |
$0.00016 |
— |
$0.17 |
| z-ai/glm-5v-turbo @ z-ai/fp8 |
$0.17 |
— |
— |
$0.0012 |
— |
$0.17 |
| deepseek/deepseek-v4-pro @ wafer/fp4 |
$0.17 |
$0.0017 |
— |
$0.000050 |
— |
$0.17 |
| qwen/qwen3.5-397b-a17b @ digitalocean |
$0.12 |
$0.038 |
— |
$0.00060 |
— |
$0.16 |
| nex-agi/nex-n2-pro @ nex-agi/fp8 |
$0.11 |
$0.048 |
— |
$0.0013 |
— |
$0.16 |
| nvidia/nemotron-3-ultra-550b-a55b @ venice/fp8 |
$0.16 |
— |
— |
$0.00096 |
— |
$0.16 |
| google/gemma-4-31b-it @ crusoe |
$0.14 |
$0.017 |
— |
$0.00011 |
— |
$0.16 |
| tencent/hy3 @ gmicloud/bf16 |
$0.14 |
$0.018 |
— |
$0.00017 |
— |
$0.16 |
| qwen/qwen3.5-35b-a3b @ alibaba |
— |
— |
$0.16 |
$0.00023 |
— |
$0.16 |
| openai/gpt-oss-120b @ sambanova |
$0.16 |
— |
— |
$0.0011 |
— |
$0.16 |
| minimax/minimax-m2.5 @ inceptron/fp8 |
$0.12 |
$0.031 |
— |
$0.00065 |
— |
$0.16 |
| minimax/minimax-m2.7 @ mara |
$0.15 |
— |
— |
$0.00096 |
— |
$0.16 |
| mistralai/mistral-large-2512 @ mistral |
$0.13 |
$0.020 |
— |
$0.00036 |
— |
$0.15 |
| z-ai/glm-5.2 @ makora/fp4 |
$0.15 |
$0.0074 |
— |
$0.000064 |
— |
$0.15 |
| tencent/hy3 @ novita |
$0.15 |
— |
— |
$0.00013 |
— |
$0.15 |
| moonshotai/kimi-k2.6 @ modelrun/fp4 |
$0.15 |
— |
— |
$0.00070 |
— |
$0.15 |
| moonshotai/kimi-k2.6 @ inceptron/int4 |
$0.14 |
— |
— |
$0.00094 |
— |
$0.14 |
| qwen/qwen3.8-2.4t-a95b @ alibaba |
— |
— |
$0.14 |
— |
— |
$0.14 |
| xiaomi/mimo-v2.5 @ digitalocean |
$0.13 |
$0.010 |
— |
$0.00035 |
— |
$0.14 |
| google/gemma-4-31b-it @ modelrun/fp4 |
$0.13 |
$0.014 |
— |
$0.00052 |
— |
$0.14 |
| minimax/minimax-m2.5 @ chutes/fp8 |
$0.12 |
$0.020 |
— |
$0.00046 |
— |
$0.14 |
| minimax/minimax-m2.5 @ mara |
$0.14 |
— |
— |
$0.00065 |
— |
$0.14 |
| aion-labs/aion-3.0-mini @ aion-labs |
$0.14 |
— |
— |
$0.00064 |
— |
$0.14 |
| google/gemma-4-31b-it @ sambanova |
$0.13 |
— |
— |
$0.0018 |
— |
$0.13 |
| qwen/qwen3.7-max @ alibaba/fp8 |
— |
— |
$0.13 |
$0.00024 |
— |
$0.13 |
| deepseek/deepseek-v4-flash @ novita/fp8 |
$0.085 |
$0.043 |
— |
$0.00032 |
— |
$0.13 |
| moonshotai/kimi-k2.6 @ decart/fp4 |
$0.12 |
— |
— |
$0.00090 |
— |
$0.12 |
| z-ai/glm-5 @ streamlake/fp8 |
$0.11 |
$0.0099 |
— |
$0.0016 |
— |
$0.12 |
| xiaomi/mimo-v2.5 @ parasail/fp8 |
$0.081 |
$0.036 |
— |
$0.00049 |
— |
$0.12 |
| qwen/qwen3.5-35b-a3b @ akashml/fp8 |
$0.10 |
$0.011 |
— |
$0.00023 |
— |
$0.11 |
| z-ai/glm-4.6v @ z-ai/fp8 |
$0.084 |
$0.029 |
— |
$0.00054 |
— |
$0.11 |
| openai/gpt-4o-2024-05-13 @ azure |
— |
— |
$0.11 |
$0.0015 |
— |
$0.11 |
| openai/gpt-4o-2024-05-13 @ openai |
— |
— |
$0.11 |
$0.0015 |
— |
$0.11 |
| google/gemma-4-31b-it @ morph/fp4 |
$0.095 |
$0.011 |
$0.0019 |
$0.000092 |
— |
$0.11 |
| meta-llama/llama-3.3-70b-instruct @ sambanova-turbo |
$0.090 |
— |
$0.017 |
$0.00060 |
— |
$0.11 |
| thedrummer/cydonia-24b-v4.1 @ parasail/bf16 |
— |
— |
$0.10 |
$0.0015 |
— |
$0.11 |
| stepfun/step-3.7-flash @ stepfun/fp8 |
$0.075 |
$0.026 |
— |
$0.00031 |
— |
$0.10 |
| deepseek/deepseek-v3.2 @ friendli |
$0.081 |
$0.014 |
$0.0050 |
$0.00040 |
— |
$0.10 |
| bytedance-seed/seed-1.6-flash @ seed/fp8 |
$0.098 |
— |
— |
$0.00029 |
— |
$0.098 |
| xiaomi/mimo-v2.5 @ io-net/fp8 |
$0.095 |
$0.0027 |
— |
$0.000077 |
— |
$0.097 |
| poolside/laguna-s-2.1 @ poolside/bf16 |
$0.092 |
$0.0047 |
— |
$0.00011 |
— |
$0.096 |
| qwen/qwen3-coder @ alibaba/opensource |
— |
— |
$0.092 |
$0.0018 |
— |
$0.094 |
| google/gemma-4-31b-it @ friendli |
$0.074 |
$0.017 |
— |
$0.00014 |
— |
$0.091 |
| xiaomi/mimo-v2.5 @ deepinfra/fp8 |
$0.083 |
$0.0033 |
— |
$0.000029 |
— |
$0.087 |
| anthracite-org/magnum-v4-72b @ mancer/fp8 |
— |
— |
$0.082 |
$0.0033 |
— |
$0.085 |
| qwen/qwen3.6-27b @ chutes/fp8 |
$0.084 |
— |
— |
$0.00055 |
— |
$0.085 |
| z-ai/glm-4.5v @ z-ai/fp8 |
$0.081 |
— |
— |
$0.00087 |
— |
$0.082 |
| z-ai/glm-4.5-air @ z-ai/fp8 |
$0.060 |
$0.022 |
— |
$0.00040 |
— |
$0.082 |
| poolside/laguna-s-2.1 @ poolside/fp4 |
$0.068 |
$0.012 |
— |
$0.00014 |
— |
$0.080 |
| openai/gpt-oss-120b @ digitalocean |
$0.079 |
— |
— |
$0.0013 |
— |
$0.080 |
| moonshotai/kimi-k2.5 @ chutes/int4 |
$0.077 |
— |
— |
$0.00036 |
— |
$0.078 |
| deepseek/deepseek-v4-flash @ ambient/fp4 |
$0.066 |
$0.0080 |
— |
$0.000039 |
— |
$0.074 |
| deepseek/deepseek-v4-flash-0731 @ baseten/fp8 |
$0.074 |
— |
— |
$0.00025 |
— |
$0.074 |
| qwen/qwen3.8-27b @ alibaba |
— |
— |
$0.072 |
— |
— |
$0.072 |
| morph/morph-v3-large @ morph/fp8 |
— |
— |
$0.072 |
— |
— |
$0.072 |
| tencent/hy3-preview @ gmicloud/bf16 |
$0.062 |
$0.0097 |
— |
$0.00014 |
— |
$0.072 |
| deepseek/deepseek-chat-v3.1 @ sambanova/fp8 |
$0.071 |
— |
— |
$0.00047 |
— |
$0.071 |
| openai/gpt-oss-120b @ mancer/fp8 |
$0.064 |
— |
$0.0071 |
$0.00030 |
— |
$0.071 |
| qwen/qwen-plus-2025-07-28:thinking @ alibaba |
— |
— |
$0.070 |
$0.00027 |
— |
$0.070 |
| meta-llama/llama-3.1-8b-instruct @ groq |
$0.062 |
$0.0045 |
— |
$0.00019 |
— |
$0.066 |
| tencent/hy3 @ phala |
$0.061 |
$0.0055 |
— |
$0.000036 |
— |
$0.066 |
| deepseek/deepseek-v4-pro-0813 @ deepseek |
$0.061 |
$0.0043 |
— |
$0.000095 |
— |
$0.065 |
| nvidia/nemotron-3-ultra-550b-a55b @ deepinfra/fp4 |
$0.063 |
— |
— |
$0.00085 |
— |
$0.063 |
| openai/gpt-4o-2024-08-06 @ openai |
— |
— |
$0.059 |
$0.0031 |
— |
$0.062 |
| openai/gpt-4o-2024-11-20 @ openai |
— |
— |
$0.059 |
$0.0031 |
— |
$0.062 |
| openai/gpt-4o @ openai |
— |
— |
$0.059 |
$0.0031 |
— |
$0.062 |
| openai/gpt-4o-2024-08-06 @ azure |
— |
— |
$0.058 |
$0.0029 |
— |
$0.061 |
| openai/gpt-4o @ azure |
— |
— |
$0.058 |
$0.0029 |
— |
$0.061 |
| qwen/qwen3.6-27b @ alibaba/fp8 |
— |
— |
$0.060 |
$0.000061 |
— |
$0.060 |
| openai/gpt-3.5-turbo-16k @ azure |
— |
— |
$0.055 |
$0.0029 |
— |
$0.058 |
| openai/gpt-3.5-turbo-16k @ openai |
— |
— |
$0.055 |
$0.0029 |
— |
$0.058 |
| deepseek/deepseek-v4-flash @ mancer/fp4 |
$0.050 |
$0.0077 |
— |
$0.000041 |
— |
$0.058 |
| deepseek/deepseek-v4-flash-0731 @ mancer/fp8 |
$0.045 |
$0.013 |
— |
$0.000056 |
— |
$0.058 |
| google/gemma-4-31b-it @ chutes/fp4 |
$0.041 |
$0.016 |
— |
$0.00020 |
— |
$0.057 |
| deepseek/deepseek-v4-flash-0731 @ deepseek |
$0.057 |
$0.00039 |
— |
$0.000049 |
— |
$0.057 |
| deepseek/deepseek-v4-flash @ alibaba/fp8 |
$0.049 |
$0.0072 |
— |
$0.000046 |
— |
$0.056 |
| qwen/qwen3.6-35b-a3b @ io-net/fp8 |
$0.055 |
— |
— |
$0.00022 |
— |
$0.056 |
| deepseek/deepseek-v3.2 @ gmicloud/fp8 |
$0.027 |
$0.027 |
— |
$0.00017 |
— |
$0.054 |
| qwen/qwen3.5-397b-a17b @ atlas-cloud/fp8 |
— |
— |
— |
$0.054 |
— |
$0.054 |
| google/gemma-4-26b-a4b-it @ nextbit/bf16 |
$0.042 |
$0.0075 |
$0.0041 |
$0.00022 |
— |
$0.054 |
| openai/gpt-4o-mini @ openai |
$0.036 |
$0.013 |
$0.0035 |
$0.00019 |
— |
$0.052 |
| openai/gpt-4o-mini-2024-07-18 @ openai |
$0.036 |
$0.013 |
$0.0035 |
$0.00019 |
— |
$0.052 |
| openai/gpt-4o-mini @ azure |
$0.036 |
$0.013 |
$0.0035 |
$0.00019 |
— |
$0.052 |
| qwen/qwen3.5-9b @ together |
$0.037 |
$0.015 |
— |
$0.00022 |
— |
$0.052 |
| qwen/qwen3.5-122b-a10b @ alibaba/fp8 |
— |
— |
$0.051 |
$0.000040 |
— |
$0.051 |
| qwen/qwen-plus-2025-07-28:thinking @ alibaba/fp8 |
— |
— |
$0.051 |
— |
— |
$0.051 |
| z-ai/glm-5.3-flash @ modal/fp8 |
$0.049 |
$0.0020 |
— |
$0.000015 |
— |
$0.051 |
| moonshotai/kimi-k2.7-code @ alibaba/fp8 |
— |
— |
$0.050 |
$0.00049 |
— |
$0.051 |
| z-ai/glm-5.3-flash @ wafer |
$0.049 |
$0.0015 |
— |
$0.000012 |
— |
$0.050 |
| deepseek/deepseek-chat-v3.1 @ mara |
$0.043 |
— |
$0.0069 |
$0.00034 |
— |
$0.050 |
| z-ai/glm-5.3-flash @ friendli |
$0.049 |
$0.00098 |
— |
$0.0000098 |
— |
$0.050 |
| deepseek/deepseek-v4-flash @ parasail/fp8 |
$0.039 |
$0.0098 |
— |
$0.000099 |
— |
$0.049 |
| openai/gpt-4o-mini @ azure/swedencentral |
$0.033 |
$0.012 |
$0.0038 |
$0.00020 |
— |
$0.049 |
| qwen/qwen3.5-397b-a17b @ alibaba/fp8 |
— |
— |
$0.049 |
$0.00017 |
— |
$0.049 |
| google/gemma-3n-e4b-it @ together |
$0.042 |
$0.0066 |
— |
$0.00011 |
— |
$0.049 |
| google/gemma-4-31b-it @ open-inference/bf16 |
$0.035 |
$0.011 |
$0.0013 |
$0.000092 |
— |
$0.048 |
| qwen/qwen3.6-plus @ alibaba |
— |
— |
$0.047 |
$0.00065 |
— |
$0.048 |
| deepseek/deepseek-v4-flash @ coreweave/fp8 |
$0.039 |
$0.0068 |
$0.0011 |
$0.000047 |
— |
$0.047 |
| qwen/qwen3.6-plus @ alibaba/fp8 |
— |
— |
$0.047 |
$0.000075 |
— |
$0.047 |
| sao10k/l3.3-euryale-70b @ nextbit/bf16 |
— |
— |
$0.046 |
$0.00079 |
— |
$0.047 |
| deepseek/deepseek-v4-flash @ morph |
$0.039 |
$0.0062 |
$0.0012 |
$0.000080 |
— |
$0.047 |
| deepseek/deepseek-v3.2-exp @ atlas-cloud/fp8 |
$0.035 |
$0.010 |
$0.00028 |
$0.00018 |
— |
$0.046 |
| deepseek/deepseek-chat @ streamlake |
$0.035 |
$0.010 |
— |
$0.00011 |
— |
$0.046 |
| deepseek/deepseek-v4-flash @ akashml/fp8 |
$0.040 |
$0.0045 |
$0.00096 |
$0.000068 |
— |
$0.045 |
| z-ai/glm-5.3-flash @ phala/fp8 |
$0.044 |
$0.00049 |
— |
$0.0000098 |
— |
$0.045 |
| z-ai/glm-5.3-flash @ fireworks |
$0.042 |
$0.00098 |
— |
$0.0000098 |
— |
$0.043 |
| z-ai/glm-5.3-flash @ makora |
$0.043 |
$0.00 |
— |
$0.0000069 |
— |
$0.043 |
| qwen/qwen3.5-plus-20260420 @ alibaba |
— |
— |
$0.042 |
$0.00070 |
— |
$0.043 |
| meta-llama/llama-4-scout @ groq |
$0.031 |
$0.011 |
— |
$0.00016 |
— |
$0.042 |
| deepseek/deepseek-v4-flash @ nextbit/fp8 |
$0.039 |
$0.0018 |
$0.00021 |
$0.000021 |
— |
$0.041 |
| qwen/qwen3.5-plus-20260420 @ alibaba/fp8 |
— |
— |
$0.041 |
$0.000070 |
— |
$0.041 |
| upstage/solar-pro4 @ upstage |
$0.034 |
$0.0061 |
— |
$0.000038 |
— |
$0.040 |
| rekaai/reka-flash-3 @ reka/fp8 |
$0.039 |
— |
$0.0012 |
$0.00022 |
— |
$0.040 |
| google/gemma-4-26b-a4b-it @ wafer/fp8 |
$0.037 |
— |
$0.0014 |
$0.00010 |
— |
$0.039 |
| deepseek/deepseek-v4-flash-0731 @ reka/fp4 |
$0.035 |
$0.0035 |
— |
$0.000040 |
— |
$0.039 |
| qwen/qwen3.5-35b-a3b @ alibaba/fp8 |
— |
— |
$0.039 |
$0.000025 |
— |
$0.039 |
| deepseek/deepseek-v3.2 @ sambanova |
— |
— |
$0.036 |
$0.0019 |
— |
$0.038 |
| deepseek/deepseek-v4-flash @ azure/us |
$0.032 |
$0.0052 |
— |
$0.000029 |
— |
$0.038 |
| qwen/qwen3.7-plus @ alibaba |
— |
— |
$0.037 |
$0.00054 |
— |
$0.037 |
| deepseek/deepseek-v4-flash @ io-net/fp8 |
$0.033 |
$0.0039 |
$0.00017 |
$0.000043 |
— |
$0.037 |
| z-ai/glm-5.3-flash @ baseten/fp8 |
$0.037 |
— |
— |
$0.000010 |
— |
$0.037 |
| qwen/qwen-2.5-7b-instruct @ phala |
$0.026 |
$0.0091 |
$0.0013 |
$0.00020 |
— |
$0.037 |
| qwen/qwen3-coder-next @ ionstream/fp8 |
$0.030 |
$0.0040 |
$0.0023 |
$0.00015 |
— |
$0.036 |
| qwen/qwen3.5-plus-02-15 @ alibaba/fp8 |
— |
— |
$0.036 |
$0.00011 |
— |
$0.036 |
| qwen/qwen3.5-plus-02-15 @ alibaba |
— |
— |
$0.035 |
$0.00034 |
— |
$0.036 |
| x-ai/grok-4.20-multi-agent @ xai |
— |
— |
— |
$0.036 |
— |
$0.036 |
| upstage/solar-pro4 @ upstage/zdr |
$0.034 |
$0.0014 |
— |
$0.000010 |
— |
$0.036 |
| deepseek/deepseek-v4-flash @ venice |
$0.023 |
$0.012 |
— |
$0.00012 |
— |
$0.035 |
| qwen/qwen3.6-35b-a3b @ darkbloom/fp4 |
$0.033 |
$0.0026 |
— |
$0.000020 |
— |
$0.035 |
| qwen/qwen3.7-plus @ alibaba/fp8 |
— |
— |
$0.035 |
$0.000059 |
— |
$0.035 |
| google/gemma-3-27b-it @ nebius/fp8 |
$0.027 |
$0.0077 |
— |
$0.00013 |
— |
$0.034 |
| meta-llama/llama-3.1-70b-instruct @ coreweave/bf16 |
— |
— |
$0.034 |
$0.00050 |
— |
$0.034 |
| tencent/hy3 @ baidu/fp8 |
$0.034 |
— |
— |
$0.000060 |
— |
$0.034 |
| openai/gpt-oss-120b @ akashml/bf16 |
$0.031 |
— |
$0.0024 |
$0.000070 |
— |
$0.033 |
| deepseek/deepseek-v4-flash-0731 @ venice |
$0.024 |
$0.0089 |
— |
$0.00026 |
— |
$0.033 |
| openai/gpt-oss-20b @ fireworks |
$0.032 |
— |
— |
$0.0011 |
— |
$0.033 |
| qwen/qwen3-30b-a3b-instruct-2507 @ nebius/fp8 |
$0.024 |
$0.0084 |
— |
$0.00012 |
— |
$0.033 |
| deepseek/deepseek-v4-flash-0731 @ baidu/fp8 |
$0.011 |
$0.021 |
— |
$0.00018 |
— |
$0.032 |
| qwen/qwen3.6-35b-a3b @ akashml/fp8 |
$0.032 |
— |
— |
$0.00026 |
— |
$0.032 |
| meta-llama/llama-3.3-70b-instruct @ coreweave/fp16 |
— |
— |
$0.030 |
$0.00044 |
— |
$0.030 |
| google/gemma-4-31b-it @ phala |
$0.030 |
— |
— |
$0.00024 |
— |
$0.030 |
| qwen/qwen3.6-35b-a3b @ darkbloom |
$0.027 |
$0.0024 |
— |
$0.0000049 |
— |
$0.029 |
| deepseek/deepseek-v4-flash @ fireworks |
$0.025 |
$0.0037 |
— |
$0.000064 |
— |
$0.029 |
| deepseek/deepseek-v4-flash @ deepinfra/fp4 |
$0.024 |
$0.0039 |
— |
$0.000053 |
— |
$0.028 |
| deepseek/deepseek-v4-flash @ cloudflare |
$0.020 |
$0.0057 |
$0.0027 |
$0.00010 |
— |
$0.028 |
| nex-agi/nex-n2-mini @ nex-agi |
$0.023 |
$0.0041 |
— |
$0.000025 |
— |
$0.027 |
| qwen/qwen2.5-vl-72b-instruct @ parasail/fp8 |
— |
— |
$0.025 |
$0.0013 |
— |
$0.027 |
| nex-agi/nex-n2-mini @ nex-agi/fp8 |
$0.023 |
$0.0033 |
— |
$0.000093 |
— |
$0.027 |
| qwen/qwen3-235b-a22b-2507 @ gmicloud/fp8 |
$0.023 |
$0.0018 |
$0.0017 |
$0.00010 |
— |
$0.026 |
| ibm-granite/granite-4.0-h-micro @ cloudflare |
$0.022 |
$0.0024 |
$0.0013 |
$0.000066 |
— |
$0.026 |
| deepseek/deepseek-v4-flash @ mancer/fp8 |
$0.023 |
$0.0030 |
— |
$0.000019 |
— |
$0.026 |
| qwen/qwen3-14b @ nextbit/int4 |
$0.026 |
— |
— |
$0.00026 |
— |
$0.026 |
| tencent/hy3-preview @ siliconflow |
$0.022 |
$0.0035 |
— |
$0.000069 |
— |
$0.026 |
| z-ai/glm-5.3-flash @ z-ai/fp8 |
$0.025 |
$0.00098 |
— |
$0.0000073 |
— |
$0.025 |
| deepseek/deepseek-v4-flash @ digitalocean |
$0.016 |
$0.0082 |
$0.0013 |
$0.000074 |
— |
$0.025 |
| z-ai/glm-5.3-flash @ deepinfra/fp8 |
$0.025 |
$0.00049 |
— |
$0.000011 |
— |
$0.025 |
| z-ai/glm-5.3-flash @ gmicloud/fp8 |
$0.024 |
$0.00073 |
— |
$0.0000073 |
— |
$0.025 |
| meta-llama/llama-3.1-70b-instruct @ wandb/bf16 |
— |
— |
$0.024 |
$0.00058 |
— |
$0.025 |
| z-ai/glm-5.3-flash @ relace/fp4 |
$0.024 |
$0.00024 |
— |
$0.0000036 |
— |
$0.025 |
| qwen/qwen3-coder-30b-a3b-instruct @ siliconflow/fp8 |
$0.018 |
$0.0064 |
— |
$0.000094 |
— |
$0.025 |
| deepseek/deepseek-v4-flash-0731 @ akashml/fp8 |
$0.020 |
$0.0051 |
— |
$0.000026 |
— |
$0.025 |
| qwen/qwen3-30b-a3b-instruct-2507 @ siliconflow/fp8 |
$0.022 |
$0.0022 |
— |
$0.00011 |
— |
$0.025 |
| qwen/qwen3-vl-30b-a3b-instruct @ darkbloom/fp4 |
$0.024 |
$0.00024 |
$0.000015 |
$0.0000036 |
— |
$0.024 |
| mistralai/ministral-8b-2512 @ nextbit/fp8 |
$0.023 |
— |
$0.0014 |
$0.00010 |
— |
$0.024 |
| deepseek/deepseek-v4-flash-0731 @ inceptron/fp4 |
$0.021 |
$0.0033 |
— |
$0.000020 |
— |
$0.024 |
| deepseek/deepseek-v4-flash @ wandb/fp8 |
$0.020 |
$0.0032 |
$0.00079 |
$0.000055 |
— |
$0.024 |
| deepseek/deepseek-v4-flash-0731 @ io-net/fp8 |
$0.021 |
$0.0025 |
— |
$0.000028 |
— |
$0.023 |
| qwen/qwen3.6-flash @ alibaba/fp8 |
— |
— |
$0.023 |
$0.000044 |
— |
$0.023 |
| meta-llama/llama-3.3-70b-instruct @ wandb/fp16 |
— |
— |
$0.022 |
$0.00052 |
— |
$0.022 |
| deepseek/deepseek-v4-flash-0731 @ morph/bf16 |
$0.019 |
$0.0023 |
— |
$0.000018 |
— |
$0.022 |
| google/gemma-4-26b-a4b-it @ darkbloom |
$0.019 |
$0.0019 |
$0.00024 |
$0.000010 |
— |
$0.021 |
| deepseek/deepseek-v4-flash-0731 @ morph |
$0.018 |
$0.0035 |
— |
$0.0000078 |
— |
$0.021 |
| deepseek/deepseek-v4-flash @ baidu/fp8 |
$0.014 |
$0.0071 |
— |
$0.000067 |
— |
$0.021 |
| deepseek/deepseek-v4-flash @ ionstream/fp4 |
$0.019 |
$0.0012 |
$0.00019 |
$0.000018 |
— |
$0.021 |
| openai/gpt-3.5-turbo-0613 @ azure |
— |
— |
$0.020 |
$0.0010 |
— |
$0.021 |
| deepseek/deepseek-v4-flash-0731 @ streamlake/fp8 |
$0.019 |
$0.0014 |
— |
$0.000026 |
— |
$0.021 |
| cohere/command-r-08-2024 @ cohere |
$0.015 |
$0.0053 |
— |
$0.000077 |
— |
$0.020 |
| z-ai/glm-5 @ novita/fp8 |
— |
— |
— |
$0.020 |
— |
$0.020 |
| deepseek/deepseek-v4-flash-0731 @ ionstream/fp4 |
$0.018 |
$0.0014 |
— |
$0.000010 |
— |
$0.020 |
| deepseek/deepseek-v4-flash-0731 @ nebius/fp8 |
$0.020 |
$0.00 |
— |
$0.0000029 |
— |
$0.020 |
| qwen/qwen3.5-397b-a17b @ novita |
— |
— |
— |
$0.019 |
— |
$0.019 |
| ibm-granite/granite-4.1-8b @ coreweave/bf16 |
$0.017 |
$0.0013 |
$0.00063 |
$0.000026 |
— |
$0.019 |
| z-ai/glm-5 @ z-ai/fp8 |
— |
— |
— |
$0.019 |
— |
$0.019 |
| qwen/qwen3-vl-235b-a22b-instruct @ alibaba |
— |
— |
$0.018 |
$0.00075 |
— |
$0.019 |
| z-ai/glm-4.7-flash @ venice/fp8 |
$0.014 |
$0.0044 |
— |
$0.00010 |
— |
$0.019 |
| openai/gpt-oss-120b @ mara |
— |
— |
$0.018 |
$0.00086 |
— |
$0.019 |
| deepseek/deepseek-v4-flash @ open-inference/fp8 |
$0.016 |
$0.0017 |
$0.00020 |
$0.0000094 |
— |
$0.018 |
| qwen/qwen3-30b-a3b-instruct-2507 @ streamlake |
$0.012 |
$0.0044 |
$0.0012 |
$0.000063 |
— |
$0.018 |
| qwen/qwen3.7-flash @ alibaba |
$0.012 |
— |
$0.0057 |
$0.000093 |
— |
$0.017 |
| meta-llama/llama-3.2-3b-instruct @ parasail/bf16 |
$0.014 |
— |
$0.0033 |
$0.000073 |
— |
$0.017 |
| meta-llama/llama-3.3-70b-instruct @ parasail/fp8 |
— |
— |
$0.016 |
$0.00032 |
— |
$0.017 |
| qwen/qwen3-coder-30b-a3b-instruct @ alibaba |
— |
— |
$0.015 |
$0.00079 |
— |
$0.016 |
| qwen/qwen3.5-flash-02-23 @ alibaba |
$0.016 |
— |
— |
$0.00018 |
— |
$0.016 |
| deepseek/deepseek-v4-flash-0731 @ gmicloud/fp4 |
$0.016 |
$0.00 |
— |
$0.000011 |
— |
$0.016 |
| minimax/minimax-m3 @ parasail/fp8 |
— |
— |
$0.014 |
$0.0014 |
— |
$0.016 |
| poolside/laguna-xs-2.1 @ poolside/fp8 |
$0.015 |
— |
— |
$0.000095 |
— |
$0.015 |
| deepseek/deepseek-v4-flash-0731 @ digitalocean |
$0.013 |
$0.0023 |
— |
$0.000017 |
— |
$0.015 |
| qwen/qwen3.5-flash-02-23 @ alibaba/fp8 |
$0.015 |
— |
— |
$0.0000078 |
— |
$0.015 |
| minimax/minimax-m3 @ morph |
— |
— |
$0.014 |
$0.00043 |
— |
$0.015 |
| deepseek/deepseek-v4-flash @ deepinfra/fp8 |
$0.013 |
$0.0019 |
— |
$0.000011 |
— |
$0.015 |
| deepseek/deepseek-v4-flash-0731 @ deepinfra/fp4 |
$0.013 |
$0.0016 |
— |
$0.0000098 |
— |
$0.014 |
| deepseek/deepseek-v4-flash @ sail-research/fp4 |
$0.012 |
$0.0015 |
$0.00039 |
$0.000010 |
— |
$0.014 |
| mistralai/mistral-small-3.2-24b-instruct @ venice/fp8 |
$0.011 |
$0.0033 |
— |
$0.000057 |
— |
$0.014 |
| mistralai/mistral-small-3.2-24b-instruct @ parasail/bf16 |
$0.010 |
$0.0025 |
$0.0012 |
$0.000059 |
— |
$0.014 |
| z-ai/glm-5.3-flash @ relace/fp8 |
$0.014 |
— |
— |
$0.0000024 |
— |
$0.014 |
| mancer/weaver @ mancer/fp8 |
— |
— |
$0.014 |
— |
— |
$0.014 |
| deepseek/deepseek-v4-flash-0731 @ open-inference/fp4 |
$0.012 |
$0.0018 |
— |
$0.0000083 |
— |
$0.014 |
| deepseek/deepseek-v4-flash-0731 @ makora |
$0.013 |
$0.00065 |
— |
$0.0000052 |
— |
$0.013 |
| deepseek/deepseek-chat-v3.1 @ google-vertex/us-west2 |
— |
— |
$0.013 |
$0.00064 |
— |
$0.013 |
| rekaai/reka-edge @ reka/bf16 |
$0.012 |
— |
$0.0014 |
$0.000072 |
— |
$0.013 |
| qwen/qwen3-vl-235b-a22b-instruct @ alibaba/fp8 |
— |
— |
$0.012 |
$0.00051 |
— |
$0.012 |
| deepseek/deepseek-v4-flash-0731 @ decart/fp4 |
$0.011 |
$0.0012 |
— |
$0.0000085 |
— |
$0.012 |
| qwen/qwen3-235b-a22b-2507 @ friendli |
$0.0066 |
$0.0026 |
$0.0028 |
$0.00020 |
— |
$0.012 |
| mistralai/mistral-nemo @ io-net/fp16 |
$0.011 |
$0.0016 |
$0.000031 |
$0.000012 |
— |
$0.012 |
| undi95/remm-slerp-l2-13b @ mancer/fp8 |
— |
— |
$0.010 |
$0.0019 |
— |
$0.012 |
| openai/gpt-3.5-turbo @ openai |
— |
— |
$0.011 |
$0.00057 |
— |
$0.011 |
| meta-llama/llama-3.3-70b-instruct @ akashml/fp8 |
— |
— |
$0.011 |
$0.00054 |
— |
$0.011 |
| mistralai/mistral-small-3.2-24b-instruct @ mistral |
$0.010 |
$0.00084 |
— |
$0.000050 |
— |
$0.011 |
| mistralai/voxtral-small-24b-2507 @ mistral |
$0.011 |
— |
— |
$0.000072 |
— |
$0.011 |
| qwen/qwen3-coder-flash @ alibaba |
— |
— |
$0.010 |
$0.00052 |
— |
$0.011 |
| qwen/qwen3-coder-30b-a3b-instruct @ alibaba/fp8 |
— |
— |
$0.0100 |
$0.00051 |
— |
$0.010 |
| meta-llama/llama-3.3-70b-instruct @ novita/bf16 |
— |
— |
$0.010 |
$0.00020 |
— |
$0.010 |
| undi95/remm-slerp-l2-13b @ nextbit/bf16 |
— |
— |
$0.0084 |
$0.0018 |
— |
$0.010 |
| qwen/qwen3-vl-8b-instruct @ alibaba |
— |
— |
$0.0097 |
$0.00033 |
— |
$0.010 |
| meta-llama/llama-4-maverick @ parasail/fp8 |
— |
— |
$0.0094 |
$0.00050 |
— |
$0.0099 |
| qwen/qwen3-next-80b-a3b-instruct @ alibaba |
— |
— |
$0.0093 |
$0.00037 |
— |
$0.0096 |
| meta-llama/llama-3.1-8b-instruct @ coreweave/bf16 |
— |
— |
$0.0093 |
$0.00014 |
— |
$0.0094 |
| qwen/qwen3-coder @ wandb/bf16 |
— |
— |
$0.0086 |
$0.00059 |
— |
$0.0092 |
| qwen/qwen-plus-2025-07-28 @ alibaba/fp8 |
— |
— |
$0.0086 |
$0.00049 |
— |
$0.0091 |
| google/gemini-2.5-flash-lite @ google-ai-studio |
$0.0090 |
— |
— |
$0.000062 |
— |
$0.0091 |
| deepseek/deepseek-v3.2 @ google-vertex |
— |
— |
$0.0086 |
$0.00042 |
— |
$0.0090 |
| sao10k/l3-lunaris-8b @ parasail/bf16 |
$0.0083 |
— |
$0.00047 |
$0.000017 |
— |
$0.0088 |
| qwen/qwen3.5-397b-a17b @ venice |
— |
— |
— |
$0.0087 |
— |
$0.0087 |
| qwen/qwen2.5-vl-72b-instruct @ nebius/fp8 |
— |
— |
$0.0081 |
$0.00039 |
— |
$0.0085 |
| qwen/qwen3-coder-30b-a3b-instruct @ digitalocean |
— |
— |
$0.0080 |
$0.00046 |
— |
$0.0084 |
| meta-llama/llama-3.1-8b-instruct @ novita/fp8 |
$0.0048 |
$0.0020 |
$0.0015 |
$0.000029 |
— |
$0.0084 |
| meta-llama/llama-3.2-1b-instruct @ cloudflare |
$0.0082 |
— |
— |
$0.000054 |
— |
$0.0082 |
| qwen/qwen-plus @ alibaba |
— |
— |
$0.0076 |
$0.00049 |
— |
$0.0081 |
| kwaipilot/kat-coder-pro-v2 @ streamlake |
— |
— |
$0.0077 |
$0.00040 |
— |
$0.0081 |
| mistralai/ministral-3b-2512 @ mistral |
$0.0078 |
— |
— |
$0.000051 |
— |
$0.0079 |
| tencent/hy-mt2-7b @ tencent/fp8 |
$0.0078 |
— |
— |
$0.0000052 |
— |
$0.0078 |
| amazon/nova-micro-v1 @ amazon-bedrock |
$0.0065 |
$0.0012 |
— |
$0.000017 |
— |
$0.0077 |
| qwen/qwen3-vl-235b-a22b-instruct @ parasail/fp8 |
— |
— |
$0.0072 |
$0.00038 |
— |
$0.0076 |
| google/gemini-2.5-flash-lite @ google-vertex |
$0.0075 |
— |
— |
$0.000051 |
— |
$0.0076 |
| google/gemini-2.5-flash-lite @ google-vertex/eu |
$0.0075 |
— |
— |
$0.000051 |
— |
$0.0076 |
| mistralai/ministral-3b-2512 @ mistral/zdr |
$0.0075 |
— |
— |
$0.0000040 |
— |
$0.0075 |
| inclusionai/ling-3.0-flash @ novita |
$0.0074 |
— |
— |
$0.000013 |
— |
$0.0074 |
| deepseek/deepseek-chat-v3.1 @ coreweave/fp8 |
— |
— |
$0.0069 |
$0.00024 |
— |
$0.0071 |
| qwen/qwen3-coder-flash @ alibaba/fp8 |
— |
— |
$0.0067 |
$0.00034 |
— |
$0.0071 |
| qwen/qwen3-coder-plus @ alibaba |
— |
— |
$0.0061 |
$0.00078 |
— |
$0.0068 |
| meta-llama/llama-4-maverick @ digitalocean |
— |
— |
$0.0064 |
$0.00036 |
— |
$0.0067 |
| meta-llama/llama-3.1-8b-instruct @ wandb/bf16 |
— |
— |
$0.0065 |
$0.00016 |
— |
$0.0067 |
| meta-llama/llama-3.3-70b-instruct @ sambanova/bf16 |
$0.00 |
— |
$0.0066 |
$0.00011 |
— |
$0.0067 |
| qwen/qwen3-vl-8b-instruct @ alibaba/fp8 |
— |
— |
$0.0065 |
$0.00021 |
— |
$0.0067 |
| qwen/qwen3-coder @ google-vertex/us-south1 |
— |
— |
$0.0063 |
$0.00030 |
— |
$0.0066 |
| qwen/qwen3-235b-a22b-2507 @ alibaba |
— |
— |
$0.0062 |
$0.00038 |
— |
$0.0066 |
| qwen/qwen3-next-80b-a3b-instruct @ alibaba/fp8 |
— |
— |
$0.0062 |
$0.00026 |
— |
$0.0064 |
| tencent/hunyuan-a13b-instruct @ siliconflow/fp8 |
$0.0063 |
— |
— |
$0.000078 |
— |
$0.0064 |
| qwen/qwen3-235b-a22b-2507 @ google-vertex/us-south1 |
— |
— |
$0.0056 |
$0.00063 |
— |
$0.0063 |
| inclusionai/ling-2.6-flash @ novita |
$0.0044 |
$0.0012 |
$0.00040 |
$0.000021 |
— |
$0.0061 |
| qwen/qwen3-vl-8b-instruct @ parasail/bf16 |
— |
— |
$0.0057 |
$0.00031 |
— |
$0.0061 |
| deepseek/deepseek-v3.2 @ digitalocean |
— |
— |
$0.0056 |
$0.00032 |
— |
$0.0059 |
| qwen/qwen3-235b-a22b-2507 @ streamlake |
— |
— |
$0.0054 |
$0.00028 |
— |
$0.0057 |
| openai/gpt-oss-120b @ parasail/fp4 |
— |
— |
$0.0042 |
$0.0014 |
— |
$0.0056 |
| google/gemma-4-26b-a4b-it @ google-vertex/global |
— |
— |
$0.0053 |
$0.00028 |
— |
$0.0055 |
| qwen/qwen-plus-2025-07-28 @ alibaba |
— |
— |
$0.0050 |
$0.00040 |
— |
$0.0054 |
| tencent/hy-mt2-1.8b @ tencent/fp8 |
$0.0053 |
— |
— |
$0.0000042 |
— |
$0.0053 |
| qwen/qwen3-next-80b-a3b-instruct @ google-vertex/global |
— |
— |
$0.0050 |
$0.00025 |
— |
$0.0053 |
| deepseek/deepseek-chat-v3.1 @ wandb/fp8 |
— |
— |
$0.0050 |
$0.00028 |
— |
$0.0053 |
| qwen/qwen-plus @ alibaba/fp8 |
— |
— |
$0.0048 |
$0.00027 |
— |
$0.0051 |
| google/gemma-4-31b-it @ parasail/fp8 |
— |
— |
$0.0048 |
$0.00025 |
— |
$0.0050 |
| cohere/command-a @ cohere |
$0.0050 |
— |
— |
$0.000043 |
— |
$0.0050 |
| qwen/qwen3-vl-30b-a3b-instruct @ alibaba |
— |
— |
$0.0046 |
$0.00027 |
— |
$0.0049 |
| qwen/qwen3-30b-a3b-instruct-2507 @ alibaba |
— |
— |
$0.0044 |
$0.00028 |
— |
$0.0047 |
| google/gemma-4-26b-a4b-it @ venice/bf16 |
— |
— |
$0.0045 |
$0.00023 |
— |
$0.0047 |
| google/gemma-4-26b-a4b-it @ novita/bf16 |
— |
— |
$0.0044 |
$0.00023 |
— |
$0.0046 |
| google/gemma-4-26b-a4b-it @ parasail/bf16 |
— |
— |
$0.0043 |
$0.00023 |
— |
$0.0046 |
| google/gemma-4-31b-it @ novita/bf16 |
— |
— |
$0.0043 |
$0.00024 |
— |
$0.0046 |
| google/gemini-2.5-flash-lite @ google-ai-studio/flex |
$0.0045 |
— |
— |
$0.000022 |
— |
$0.0045 |
| bytedance/ui-tars-1.5-7b @ parasail/bf16 |
— |
— |
$0.0043 |
$0.00023 |
— |
$0.0045 |
| amazon/nova-micro-v1 @ amazon-bedrock/eu-west-1 |
$0.0032 |
$0.0011 |
— |
$0.000017 |
— |
$0.0043 |
| qwen/qwen3-235b-a22b-2507 @ alibaba/fp8 |
— |
— |
$0.0040 |
$0.00025 |
— |
$0.0042 |
| qwen/qwen3-235b-a22b-2507 @ parasail/fp8 |
— |
— |
$0.0040 |
$0.00021 |
— |
$0.0042 |
| thedrummer/unslopnemo-12b @ nextbit/fp8 |
— |
— |
$0.0039 |
$0.00032 |
— |
$0.0042 |
| google/gemma-4-31b-it @ venice/bf16 |
— |
— |
$0.0039 |
$0.00020 |
— |
$0.0041 |
| qwen/qwen3-next-80b-a3b-instruct @ parasail/fp8 |
— |
— |
$0.0039 |
$0.00021 |
— |
$0.0041 |
| xiaomi/mimo-v2.5-pro @ deepinfra/fp8 |
— |
— |
— |
$0.0041 |
— |
$0.0041 |
| meta-llama/llama-3.1-8b-instruct @ deepinfra/fp8 |
$0.0040 |
— |
— |
$0.000025 |
— |
$0.0040 |
| anthropic/claude-sonnet-4.5 @ amazon-bedrock |
— |
— |
— |
$0.0040 |
— |
$0.0040 |
| anthropic/claude-sonnet-4.5 @ google-vertex/global |
— |
— |
— |
$0.0040 |
— |
$0.0040 |
| anthropic/claude-sonnet-4.6 @ google-vertex/global |
— |
— |
— |
$0.0040 |
— |
$0.0040 |
| anthropic/claude-sonnet-4 @ amazon-bedrock |
— |
— |
— |
$0.0040 |
— |
$0.0040 |
| anthropic/claude-sonnet-4 @ amazon-bedrock/eu-west-1 |
— |
— |
— |
$0.0040 |
— |
$0.0040 |
| anthropic/claude-sonnet-4 @ google-vertex |
— |
— |
— |
$0.0040 |
— |
$0.0040 |
| anthropic/claude-sonnet-4 @ google-vertex/europe |
— |
— |
— |
$0.0040 |
— |
$0.0040 |
| anthropic/claude-sonnet-4 @ google-vertex/global |
— |
— |
— |
$0.0040 |
— |
$0.0040 |
| meta-llama/llama-guard-4-12b @ together |
— |
— |
— |
$0.0040 |
— |
$0.0040 |
| google/gemini-3-pro-image @ google-ai-studio/global |
— |
— |
— |
$0.0040 |
— |
$0.0040 |
| inclusionai/ling-2.6-1t @ novita |
— |
— |
$0.0037 |
$0.00020 |
— |
$0.0039 |
| anthropic/claude-sonnet-4.6 @ anthropic |
— |
— |
— |
$0.0039 |
— |
$0.0039 |
| google/gemini-3-pro-image-preview @ google-ai-studio/global |
— |
— |
— |
$0.0039 |
— |
$0.0039 |
| google/gemini-3.1-pro-preview-customtools @ google-ai-studio |
— |
— |
— |
$0.0039 |
— |
$0.0039 |
| mistralai/mixtral-8x22b-instruct @ mistral |
— |
— |
— |
$0.0039 |
— |
$0.0039 |
| qwen/qwen3-coder-next @ parasail/bf16 |
— |
— |
$0.0037 |
$0.00019 |
— |
$0.0039 |
| z-ai/glm-5.1 @ novita/fp8 |
— |
— |
— |
$0.0038 |
— |
$0.0038 |
| moonshotai/kimi-k2.6 @ novita |
— |
— |
— |
$0.0037 |
— |
$0.0037 |
| qwen/qwen3-next-80b-a3b-instruct @ novita/bf16 |
— |
— |
$0.0034 |
$0.00029 |
— |
$0.0037 |
| z-ai/glm-4.7 @ z-ai/fp4 |
— |
— |
— |
$0.0036 |
— |
$0.0036 |
| google/gemma-4-26b-a4b-it @ cloudflare |
— |
— |
$0.0033 |
$0.00018 |
— |
$0.0035 |
| deepcogito2fcogito-v2.1-671b23together |
— |
— |
— |
$0.0034 |
— |
$0.0034 |
| anthropic2fclaude-sonnet-4.523anthropic2f2 |
— |
— |
— |
$0.0034 |
— |
$0.0034 |
| anthropic2fclaude-sonnet-4.523anthropic2fclaude-on-aws |
— |
— |
— |
$0.0034 |
— |
$0.0034 |
| anthropic2fclaude-sonnet-4.623anthropic2f2 |
— |
— |
— |
$0.0034 |
— |
$0.0034 |
| mistralai/mistral-nemo @ deepinfra/fp8 |
$0.0027 |
$0.00062 |
— |
$0.000016 |
— |
$0.0034 |
| minimax/minimax-m2.5 @ minimax/highspeed |
— |
— |
— |
$0.0033 |
— |
$0.0033 |
| minimax/minimax-m2.7 @ minimax/highspeed |
— |
— |
— |
$0.0033 |
— |
$0.0033 |
| mistralai/mistral-medium-3-5 @ mistral |
— |
— |
— |
$0.0032 |
— |
$0.0032 |
| google/gemini-2.5-flash-image @ google-vertex/global |
— |
— |
— |
$0.0032 |
— |
$0.0032 |
| nvidia/nemotron-3-nano-30b-a3b @ crusoe/fp8 |
$0.0031 |
— |
— |
$0.000049 |
— |
$0.0032 |
| qwen/qwen3-vl-30b-a3b-instruct @ alibaba/fp8 |
— |
— |
$0.0030 |
$0.00017 |
— |
$0.0032 |
| z-ai/glm-4.6 @ venice/fp4 |
— |
— |
— |
$0.0031 |
— |
$0.0031 |
| qwen/qwen3-30b-a3b-instruct-2507 @ alibaba/fp8 |
— |
— |
$0.0028 |
$0.00016 |
— |
$0.0030 |
| nex-agi/nex-n2-pro @ siliconflow |
— |
— |
— |
$0.0029 |
— |
$0.0029 |
| qwen/qwen3.5-35b-a3b @ atlas-cloud/fp8 |
— |
— |
— |
$0.0029 |
— |
$0.0029 |
| qwen/qwen3-coder-plus @ alibaba/fp8 |
— |
— |
$0.0027 |
$0.00016 |
— |
$0.0029 |
| nousresearch/hermes-4-405b @ nebius/fp8 |
— |
— |
— |
$0.0029 |
— |
$0.0029 |
| openai/gpt-oss-120b @ groq |
— |
— |
— |
$0.0029 |
— |
$0.0029 |
| anthropic2fclaude-sonnet-4.623azure2fus-east-2 |
— |
— |
— |
$0.0028 |
— |
$0.0028 |
| qwen/qwen3-coder @ coreweave/bf16 |
— |
— |
$0.0026 |
$0.00022 |
— |
$0.0028 |
| qwen/qwen3-vl-32b-instruct @ alibaba/fp8 |
— |
— |
$0.0026 |
$0.00016 |
— |
$0.0028 |
| openai/gpt-oss-120b @ together |
— |
— |
— |
$0.0028 |
— |
$0.0028 |
| meta-llama/llama-3.3-70b-instruct @ google-vertex/us-central1 |
— |
— |
— |
$0.0027 |
— |
$0.0027 |
| openai/gpt-oss-120b @ nebius/fp4 |
— |
— |
— |
$0.0027 |
— |
$0.0027 |
| moonshotai/kimi-k2.5 @ atlas-cloud/int4 |
— |
— |
— |
$0.0027 |
— |
$0.0027 |
| openai/gpt-oss-120b @ phala |
— |
— |
— |
$0.0027 |
— |
$0.0027 |
| anthropic/claude-sonnet-4.5 @ amazon-bedrock/eu-west-1 |
— |
— |
— |
$0.0026 |
— |
$0.0026 |
| anthropic/claude-sonnet-4.5 @ google-vertex/us-east5 |
— |
— |
— |
$0.0026 |
— |
$0.0026 |
| anthropic/claude-sonnet-4.6 @ amazon-bedrock/eu-west-1 |
— |
— |
— |
$0.0026 |
— |
$0.0026 |
| anthropic/claude-sonnet-4.6 @ google-vertex/europe |
— |
— |
— |
$0.0026 |
— |
$0.0026 |
| google/gemini-2.5-pro @ google-ai-studio |
— |
— |
— |
$0.0026 |
— |
$0.0026 |
| google/gemma-3-27b-it @ parasail/fp8 |
— |
— |
$0.0025 |
$0.00013 |
— |
$0.0026 |
| z-ai/glm-5-turbo @ z-ai |
— |
— |
— |
$0.0026 |
— |
$0.0026 |
| meta-llama/llama-3.3-70b-instruct @ google-vertex |
— |
— |
— |
$0.0025 |
— |
$0.0025 |
| deepseek/deepseek-v4-pro-0813 @ digitalocean |
— |
— |
$0.0025 |
— |
— |
$0.0025 |
| google/gemini-2.5-pro-preview @ google-ai-studio |
— |
— |
— |
$0.0025 |
— |
$0.0025 |
| microsoft/wizardlm-2-8x22b @ novita/bf16 |
— |
— |
— |
$0.0024 |
— |
$0.0024 |
| z-ai/glm-4.6 @ atlas-cloud/fp8 |
— |
— |
— |
$0.0023 |
— |
$0.0023 |
| openai/gpt-oss-120b @ deepinfra/turbo |
— |
— |
— |
$0.0023 |
— |
$0.0023 |
| meta-llama/llama-3.3-70b-instruct @ groq |
— |
— |
— |
$0.0023 |
— |
$0.0023 |
| mistralai/mistral-nemo @ dekallm/fp8 |
$0.0022 |
— |
— |
$0.0000063 |
— |
$0.0023 |
| moonshotai2fkimi-k2-090523groq |
— |
— |
— |
$0.0022 |
— |
$0.0022 |
| thinkingmachines/inkling @ together |
— |
— |
— |
$0.0022 |
— |
$0.0022 |
| thinkingmachines/inkling @ baseten/fp8 |
— |
— |
— |
$0.0022 |
— |
$0.0022 |
| google/gemini-2.5-pro-preview-05-06 @ google-ai-studio |
— |
— |
— |
$0.0022 |
— |
$0.0022 |
| z-ai/glm-4.7 @ novita/fp8 |
— |
— |
— |
$0.0022 |
— |
$0.0022 |
| qwen/qwen-2.5-coder-32b-instruct @ cloudflare |
— |
— |
— |
$0.0021 |
— |
$0.0021 |
| thedrummer/rocinante-12b @ parasail/bf16 |
— |
— |
$0.0017 |
$0.00043 |
— |
$0.0021 |
| moonshotai/kimi-k2.7-code @ moonshotai/highspeed |
— |
— |
— |
$0.0021 |
— |
$0.0021 |
| thedrummer/unslopnemo-12b @ parasail/bf16 |
— |
— |
$0.0020 |
$0.00011 |
— |
$0.0021 |
| google/gemini-3-pro-image @ google-vertex/global |
— |
— |
— |
$0.0020 |
— |
$0.0020 |
| z-ai/glm-4.7 @ atlas-cloud/fp8 |
— |
— |
— |
$0.0020 |
— |
$0.0020 |
| amazon/nova-2-lite-v1 @ amazon-bedrock |
— |
— |
— |
$0.0020 |
— |
$0.0020 |
| amazon/nova-2-lite-v1 @ amazon-bedrock/eu-west-1 |
— |
— |
— |
$0.0019 |
— |
$0.0019 |
| anthropic/claude-opus-4.5 @ amazon-bedrock/eu-west-1 |
— |
— |
— |
$0.0019 |
— |
$0.0019 |
| anthropic/claude-opus-4.6 @ google-vertex/europe |
— |
— |
— |
$0.0019 |
— |
$0.0019 |
| google/gemini-2.5-pro-preview-05-06 @ google-ai-studio/flex |
— |
— |
— |
$0.0019 |
— |
$0.0019 |
| google/gemini-2.5-pro-preview @ google-ai-studio/flex |
— |
— |
— |
$0.0019 |
— |
$0.0019 |
| google/gemini-2.5-pro @ google-ai-studio/flex |
— |
— |
— |
$0.0019 |
— |
$0.0019 |
| google/gemini-3-pro-image-preview @ google-ai-studio/global/flex |
— |
— |
— |
$0.0019 |
— |
$0.0019 |
| qwen/qwen3-235b-a22b-thinking-2507 @ venice/fp8 |
— |
— |
— |
$0.0019 |
— |
$0.0019 |
| deepseek/deepseek-r1-0528 @ streamlake |
— |
— |
— |
$0.0019 |
— |
$0.0019 |
| moonshotai/kimi-k2.6 @ atlas-cloud/int4 |
— |
— |
— |
$0.0018 |
— |
$0.0018 |
| google/gemma-4-31b-it @ coreweave/bf16 |
— |
— |
$0.0018 |
$0.000072 |
— |
$0.0018 |
| moonshotai/kimi-k2-thinking @ novita/bf16 |
— |
— |
— |
$0.0018 |
— |
$0.0018 |
| sao10k/l3.1-euryale-70b @ novita/fp8 |
— |
— |
— |
$0.0018 |
— |
$0.0018 |
| qwen/qwen3-vl-30b-a3b-thinking @ alibaba |
— |
— |
— |
$0.0018 |
— |
$0.0018 |
| anthropic/claude-opus-4.5 @ amazon-bedrock |
— |
— |
— |
$0.0018 |
— |
$0.0018 |
| anthropic/claude-opus-4.5 @ anthropic |
— |
— |
— |
$0.0018 |
— |
$0.0018 |
| anthropic/claude-opus-4.5 @ google-vertex/global |
— |
— |
— |
$0.0018 |
— |
$0.0018 |
| anthropic/claude-opus-4.6 @ anthropic |
— |
— |
— |
$0.0018 |
— |
$0.0018 |
| anthropic/claude-opus-4.6 @ google-vertex/global |
— |
— |
— |
$0.0018 |
— |
$0.0018 |
| z-ai/glm-5.1 @ atlas-cloud/fp8 |
— |
— |
— |
$0.0018 |
— |
$0.0018 |
| z-ai/glm-4.6 @ deepinfra/fp4 |
— |
— |
— |
$0.0017 |
— |
$0.0017 |
| minimax/minimax-m2.7 @ deepinfra/turbo |
— |
— |
— |
$0.0017 |
— |
$0.0017 |
| anthropic2fclaude-sonnet-4.523azure2fus-east-2 |
— |
— |
— |
$0.0017 |
— |
$0.0017 |
| minimax/minimax-m3 @ gmicloud/fp8 |
— |
— |
— |
$0.0017 |
— |
$0.0017 |
| moonshotai/kimi-k2.5 @ venice |
— |
— |
— |
$0.0017 |
— |
$0.0017 |
| openai/gpt-oss-120b @ google-vertex/global |
— |
— |
— |
$0.0017 |
— |
$0.0017 |
| google/gemma-4-31b-it @ wandb/bf16 |
— |
— |
$0.0016 |
$0.00011 |
— |
$0.0017 |
| minimax/minimax-m2.1 @ novita/fp8 |
— |
— |
— |
$0.0017 |
— |
$0.0017 |
| minimax/minimax-m2.5 @ novita/fp8 |
— |
— |
— |
$0.0017 |
— |
$0.0017 |
| minimax/minimax-m2 @ novita/fp8 |
— |
— |
— |
$0.0016 |
— |
$0.0016 |
| minimax/minimax-m2-her @ minimax |
— |
— |
— |
$0.0016 |
— |
$0.0016 |
| moonshotai2fkimi-k2.7-code23atlas-cloud2fint4 |
— |
— |
— |
$0.0016 |
— |
$0.0016 |
| minimax/minimax-m2.5 @ atlas-cloud/fp8 |
— |
— |
— |
$0.0016 |
— |
$0.0016 |
| thinkingmachines/inkling @ deepinfra/fp8 |
— |
— |
— |
$0.0016 |
— |
$0.0016 |
| gryphe/mythomax-l2-13b @ deepinfra/fp16 |
— |
— |
— |
$0.0015 |
— |
$0.0015 |
| minimax/minimax-m2.7 @ groq |
— |
— |
— |
$0.0015 |
— |
$0.0015 |
| z-ai/glm-5.1 @ venice/fp8 |
— |
— |
— |
$0.0015 |
— |
$0.0015 |
| qwen/qwen3-vl-235b-a22b-thinking @ alibaba |
— |
— |
— |
$0.0014 |
— |
$0.0014 |
| mistralai/mistral-large-2407 @ mistral |
— |
— |
— |
$0.0014 |
— |
$0.0014 |
| mistralai/mistral-large @ mistral |
— |
— |
— |
$0.0014 |
— |
$0.0014 |
| openai/gpt-3.5-turbo-instruct @ openai |
— |
— |
— |
$0.0014 |
— |
$0.0014 |
| moonshotai/kimi-k2-thinking @ google-vertex |
— |
— |
— |
$0.0014 |
— |
$0.0014 |
| openai/gpt-oss-20b @ groq |
— |
— |
— |
$0.0014 |
— |
$0.0014 |
| openai/gpt-oss-safeguard-20b @ groq |
— |
— |
— |
$0.0014 |
— |
$0.0014 |
| qwen/qwen3-30b-a3b-instruct-2507 @ coreweave/bf16 |
— |
— |
$0.0014 |
$0.000058 |
— |
$0.0014 |
| mistralai/ministral-14b-2512 @ nextbit/fp8 |
— |
— |
$0.0013 |
$0.000091 |
— |
$0.0014 |
| anthropic/claude-haiku-4.5 @ amazon-bedrock/eu-west-1 |
— |
— |
— |
$0.0014 |
— |
$0.0014 |
| anthropic/claude-haiku-4.5 @ google-vertex/europe |
— |
— |
— |
$0.0014 |
— |
$0.0014 |
| z-ai/glm-4.6 @ novita/bf16 |
— |
— |
— |
$0.0014 |
— |
$0.0014 |
| qwen/qwen3.5-397b-a17b @ streamlake |
— |
— |
— |
$0.0014 |
— |
$0.0014 |
| moonshotai2fkimi-k2.623together |
— |
— |
— |
$0.0014 |
— |
$0.0014 |
| moonshotai/kimi-k2.7-code @ novita/int4 |
— |
— |
— |
$0.0014 |
— |
$0.0014 |
| minimax/minimax-m2.7 @ novita/fp8 |
— |
— |
— |
$0.0014 |
— |
$0.0014 |
| z-ai/glm-4.6 @ z-ai/fp4 |
— |
— |
— |
$0.0013 |
— |
$0.0013 |
| anthropic/claude-haiku-4.5 @ amazon-bedrock/global |
— |
— |
— |
$0.0013 |
— |
$0.0013 |
| minimax/minimax-m2.5 @ friendli |
— |
— |
— |
$0.0013 |
— |
$0.0013 |
| aion-labs/aion-3.0 @ aion-labs |
— |
— |
— |
$0.0013 |
— |
$0.0013 |
| anthropic/claude-haiku-4.5 @ google-vertex/global |
— |
— |
— |
$0.0013 |
— |
$0.0013 |
| nvidia/nemotron-3-ultra-550b-a55b @ together |
$0.00 |
— |
— |
$0.0013 |
— |
$0.0013 |
| moonshotai/kimi-k2.6 @ siliconflow/fp8 |
— |
— |
— |
$0.0013 |
— |
$0.0013 |
| meta-llama/llama-3.3-70b-instruct @ cloudflare/fp8 |
— |
— |
— |
$0.0013 |
— |
$0.0013 |
| z-ai/glm-5.1 @ friendli |
— |
— |
— |
$0.0013 |
— |
$0.0013 |
| minimax/minimax-m3 @ minimax/fp8 |
— |
— |
— |
$0.0013 |
— |
$0.0013 |
| gryphe/mythomax-l2-13b @ nextbit/int4 |
— |
— |
$0.0010 |
$0.00023 |
— |
$0.0013 |
| openai/gpt-oss-20b @ parasail/fp4 |
— |
— |
$0.0012 |
$0.000041 |
— |
$0.0013 |
| openai/gpt-oss-20b @ siliconflow/fp8 |
— |
— |
— |
$0.0013 |
— |
$0.0013 |
| moonshotai/kimi-k2.6 @ cloudflare |
— |
— |
— |
$0.0013 |
— |
$0.0013 |
| moonshotai/kimi-k2.7-code @ cloudflare |
— |
— |
— |
$0.0013 |
— |
$0.0013 |
| z-ai/glm-5.1 @ parasail/fp8 |
— |
— |
— |
$0.0013 |
— |
$0.0013 |
| moonshotai/kimi-k2.6 @ phala |
— |
— |
— |
$0.0013 |
— |
$0.0013 |
| gryphe/mythomax-l2-13b @ parasail/fp16 |
— |
— |
$0.0011 |
$0.00011 |
— |
$0.0013 |
| anthropic/claude-sonnet-4.5 @ azure/global |
— |
— |
— |
$0.0012 |
— |
$0.0012 |
| anthropic/claude-sonnet-4.6 @ azure/global |
— |
— |
— |
$0.0012 |
— |
$0.0012 |
| moonshotai/kimi-k2.7-code @ together |
— |
— |
— |
$0.0012 |
— |
$0.0012 |
| nousresearch/hermes-3-llama-3.1-405b @ deepinfra/fp8 |
— |
— |
— |
$0.0012 |
— |
$0.0012 |
| minimax/minimax-m2.7 @ gmicloud/fp8 |
— |
— |
— |
$0.0012 |
— |
$0.0012 |
| z-ai/glm-5 @ amazon-bedrock |
— |
— |
— |
$0.0012 |
— |
$0.0012 |
| qwen/qwen3-vl-235b-a22b-thinking @ novita/bf16 |
— |
— |
— |
$0.0012 |
— |
$0.0012 |
| minimax/minimax-m2.5 @ streamlake |
— |
— |
— |
$0.0012 |
— |
$0.0012 |
| moonshotai/kimi-k2.5 @ novita |
— |
— |
— |
$0.0012 |
— |
$0.0012 |
| qwen/qwen3-vl-30b-a3b-instruct @ novita/bf16 |
— |
— |
$0.00093 |
$0.00026 |
— |
$0.0012 |
| z-ai/glm-5.1 @ baidu/fp8 |
— |
— |
— |
$0.0011 |
— |
$0.0011 |
| deepseek/deepseek-r1-distill-llama-70b @ novita/bf16 |
— |
— |
— |
$0.0011 |
— |
$0.0011 |
| qwen/qwen3.5-27b @ novita/bf16 |
— |
— |
— |
$0.0011 |
— |
$0.0011 |
| z-ai/glm-5.2 @ io-net/fp8 |
$0.00 |
— |
— |
$0.0011 |
— |
$0.0011 |
| openai/gpt-oss-120b @ siliconflow/fp8 |
— |
— |
— |
$0.0011 |
— |
$0.0011 |
| minimax/minimax-m2.7 @ deepinfra/fp8 |
— |
— |
— |
$0.0011 |
— |
$0.0011 |
| z-ai/glm-5.1 @ siliconflow/fp8 |
— |
— |
— |
$0.0011 |
— |
$0.0011 |
| z-ai/glm-5.1 @ z-ai/fp8 |
— |
— |
— |
$0.0011 |
— |
$0.0011 |
| moonshotai/kimi-k2.7-code @ moonshotai/int4 |
— |
— |
— |
$0.0011 |
— |
$0.0011 |
| openai/gpt-oss-20b @ google-vertex/us-central1 |
— |
— |
— |
$0.0011 |
— |
$0.0011 |
| qwen/qwen3-30b-a3b-instruct-2507 @ wandb/bf16 |
— |
— |
$0.00099 |
$0.000067 |
— |
$0.0011 |
| sao10k/l3.1-euryale-70b @ deepinfra/fp8 |
— |
— |
— |
$0.0011 |
— |
$0.0011 |
| moonshotai/kimi-k2.6 @ digitalocean |
— |
— |
— |
$0.0010 |
— |
$0.0010 |
| meta-llama2fllama-3.3-70b-instruct23together2ffp8 |
— |
— |
— |
$0.0010 |
— |
$0.0010 |
| minimax/minimax-m2.5 @ digitalocean |
— |
— |
— |
$0.0010 |
— |
$0.0010 |
| moonshotai/kimi-k2.6 @ parasail/int4 |
— |
— |
— |
$0.0010 |
— |
$0.0010 |
| moonshotai/kimi-k2.6 @ venice/int4 |
— |
— |
— |
$0.0010 |
— |
$0.0010 |
| minimax/minimax-m2.7 @ atlas-cloud/fp8 |
— |
— |
— |
$0.0010 |
— |
$0.0010 |
| moonshotai/kimi-k2.7-code @ inceptron/int4 |
— |
— |
— |
$0.0010 |
— |
$0.0010 |
| moonshotai/kimi-k2.6 @ deepinfra/fp4 |
— |
— |
— |
$0.0010 |
— |
$0.0010 |
| moonshotai/kimi-k2.7-code @ venice/int4 |
— |
— |
— |
$0.0010 |
— |
$0.0010 |
| z-ai/glm-5.1 @ nebius/fp8 |
— |
— |
— |
$0.00100 |
— |
$0.00100 |
| moonshotai/kimi-k2.6 @ baidu/fp4 |
— |
— |
— |
$0.00099 |
— |
$0.00099 |
| deepseek/deepseek-chat-v3-0324 @ gmicloud/fp8 |
— |
— |
$0.00086 |
$0.00013 |
— |
$0.00099 |
| google/gemma-4-26b-a4b-it @ dekallm/bf16 |
— |
— |
$0.00091 |
$0.000060 |
— |
$0.00097 |
| z-ai/glm-5.1 @ digitalocean |
— |
— |
— |
$0.00097 |
— |
$0.00097 |
| deepseek/deepseek-v4-flash-0731 @ siliconflow/fp8 |
— |
— |
— |
$0.00097 |
— |
$0.00097 |
| anthropic/claude-sonnet-4.6 @ google-vertex/us-east5 |
— |
— |
— |
$0.00097 |
— |
$0.00097 |
| moonshotai/kimi-k2.7-code @ deepinfra/fp4 |
— |
— |
— |
$0.00096 |
— |
$0.00096 |
| qwen/qwen3.5-27b @ atlas-cloud/fp8 |
— |
— |
— |
$0.00096 |
— |
$0.00096 |
| qwen/qwen3.5-397b-a17b @ phala |
— |
— |
— |
$0.00095 |
— |
$0.00095 |
| minimax2fminimax-m2.523parasail2ffp8 |
— |
— |
— |
$0.00095 |
— |
$0.00095 |
| inclusionai2fring-2.6-1t23novita |
— |
— |
— |
$0.00095 |
— |
$0.00095 |
| moonshotai/kimi-k2.6 @ chutes/int4 |
— |
— |
— |
$0.00095 |
— |
$0.00095 |
| moonshotai/kimi-k2.7-code @ parasail/int4 |
— |
— |
— |
$0.00095 |
— |
$0.00095 |
| qwen2fqwen3-235b-a22b-thinking-250723deepinfra2ffp8 |
— |
— |
— |
$0.00095 |
— |
$0.00095 |
| deepseek/deepseek-r1 @ novita/fp8 |
— |
— |
— |
$0.00093 |
— |
$0.00093 |
| openai/gpt-oss-120b @ novita/fp4 |
— |
— |
— |
$0.00093 |
— |
$0.00093 |
| moonshotai/kimi-k2-0905 @ novita/fp8 |
— |
— |
— |
$0.00093 |
— |
$0.00093 |
| z-ai/glm-5.1 @ chutes/fp8 |
— |
— |
— |
$0.00092 |
— |
$0.00092 |
| z-ai/glm-5 @ gmicloud/fp8 |
— |
— |
— |
$0.00092 |
— |
$0.00092 |
| qwen/qwen3.5-397b-a17b @ parasail/fp8 |
— |
— |
— |
$0.00092 |
— |
$0.00092 |
| qwen/qwen3-32b @ groq |
— |
— |
— |
$0.00091 |
— |
$0.00091 |
| anthropic2fclaude-opus-4.623anthropic2f2 |
— |
— |
— |
$0.00091 |
— |
$0.00091 |
| google/gemma-4-26b-a4b-it @ ionstream/bf16 |
$0.00 |
— |
$0.00085 |
$0.000056 |
— |
$0.00091 |
| z-ai/glm-5 @ venice/fp8 |
— |
— |
— |
$0.00090 |
— |
$0.00090 |
| qwen/qwen3.8-2.4t-a95b @ digitalocean |
— |
— |
$0.00090 |
— |
— |
$0.00090 |
| z-ai/glm-5.1 @ deepinfra/fp4 |
— |
— |
— |
$0.00089 |
— |
$0.00089 |
| qwen/qwen3-30b-a3b-thinking-2507 @ alibaba |
— |
— |
— |
$0.00089 |
— |
$0.00089 |
| moonshotai/kimi-k2 @ novita/fp8 |
— |
— |
— |
$0.00088 |
— |
$0.00088 |
| qwen/qwen3-vl-8b-thinking @ alibaba |
— |
— |
— |
$0.00088 |
— |
$0.00088 |
| z-ai/glm-4.5v @ novita/fp8 |
— |
— |
— |
$0.00087 |
— |
$0.00087 |
| qwen/qwen3.5-122b-a10b @ novita/bf16 |
— |
— |
— |
$0.00086 |
— |
$0.00086 |
| mistralai/mistral-small-24b-instruct-2501 @ deepinfra/fp8 |
— |
— |
— |
$0.00085 |
— |
$0.00085 |
| anthropic2fclaude-opus-4.523anthropic2f2 |
— |
— |
— |
$0.00084 |
— |
$0.00084 |
| google/gemini-3.1-flash-lite-preview @ google-ai-studio/priority |
— |
— |
— |
$0.00084 |
— |
$0.00084 |
| minimax/minimax-m2 @ google-vertex |
— |
— |
— |
$0.00083 |
— |
$0.00083 |
| minimax2fminimax-m2.723together2ffp4 |
— |
— |
— |
$0.00083 |
— |
$0.00083 |
| google/gemini-3.1-flash-lite @ google-ai-studio/priority |
— |
— |
— |
$0.00082 |
— |
$0.00082 |
| anthropic/claude-sonnet-4.6 @ amazon-bedrock/us |
— |
— |
— |
$0.00082 |
— |
$0.00082 |
| google/gemini-3.1-flash-lite @ google-vertex/global/priority |
— |
— |
— |
$0.00081 |
— |
$0.00081 |
| moonshotai/kimi-k2.7-code @ siliconflow/fp8 |
— |
— |
— |
$0.00081 |
— |
$0.00081 |
| meta/muse-glimmer-30b @ together |
— |
— |
— |
$0.00080 |
— |
$0.00080 |
| z-ai/glm-5 @ siliconflow/fp8 |
— |
— |
— |
$0.00079 |
— |
$0.00079 |
| deepseek/deepseek-r1-0528 @ siliconflow/fp8 |
— |
— |
— |
$0.00077 |
— |
$0.00077 |
| meta/muse-glimmer-30b @ fireworks |
— |
— |
— |
$0.00077 |
— |
$0.00077 |
| nousresearch/hermes-3-llama-3.1-70b @ deepinfra/fp8 |
— |
— |
— |
$0.00075 |
— |
$0.00075 |
| z-ai2fglm-5.123fireworks |
— |
— |
— |
$0.00074 |
— |
$0.00074 |
| openai/gpt-oss-20b @ novita/fp4 |
— |
— |
— |
$0.00074 |
— |
$0.00074 |
| qwen/qwen3-next-80b-a3b-thinking @ alibaba |
— |
— |
— |
$0.00073 |
— |
$0.00073 |
| deepseek/deepseek-v4-flash-0731 @ novita/fp8 |
— |
— |
— |
$0.00072 |
— |
$0.00072 |
| minimax/minimax-m2.5 @ siliconflow/fp8 |
— |
— |
— |
$0.00072 |
— |
$0.00072 |
| minimax2fminimax-m2.523wandb2ffp8 |
— |
— |
— |
$0.00072 |
— |
$0.00072 |
| openai/gpt-4.1-mini @ azure/swedencentral |
— |
— |
— |
$0.00072 |
— |
$0.00072 |
| moonshotai2fkimi-k2.623wandb2ffp4 |
— |
— |
— |
$0.00070 |
— |
$0.00070 |
| qwen/qwen3.5-397b-a17b @ chutes/fp8 |
$0.00 |
— |
— |
$0.00069 |
— |
$0.00069 |
| moonshotai/kimi-k2.5 @ siliconflow/int4 |
— |
— |
— |
$0.00068 |
— |
$0.00068 |
| moonshotai/kimi-k2.5 @ digitalocean |
— |
— |
— |
$0.00068 |
— |
$0.00068 |
| z-ai2fglm-523parasail2ffp8 |
— |
— |
— |
$0.00068 |
— |
$0.00068 |
| moonshotai/kimi-k2.5 @ phala |
— |
— |
— |
$0.00068 |
— |
$0.00068 |
| xiaomi/mimo-v2.5-pro @ atlas-cloud/fp8 |
— |
— |
— |
$0.00068 |
— |
$0.00068 |
| qwen/qwen3.6-27b @ venice/fp8 |
— |
— |
— |
$0.00068 |
— |
$0.00068 |
| google/gemini-2.5-pro-preview @ google-ai-studio/priority |
— |
— |
— |
$0.00068 |
— |
$0.00068 |
| openai/gpt-4.1-mini @ openai |
— |
— |
— |
$0.00067 |
— |
$0.00067 |
| qwen/qwen3.6-27b @ siliconflow/fp8 |
— |
— |
— |
$0.00067 |
— |
$0.00067 |
| qwen/qwen3-30b-a3b @ alibaba |
— |
— |
— |
$0.00067 |
— |
$0.00067 |
| z-ai/glm-5 @ atlas-cloud/fp8 |
— |
— |
— |
$0.00066 |
— |
$0.00066 |
| minimax2fminimax-m2.723morph |
— |
— |
— |
$0.00066 |
— |
$0.00066 |
| z-ai/glm-5 @ baidu/fp8 |
— |
— |
— |
$0.00066 |
— |
$0.00066 |
| openai/gpt-4.1-mini @ azure |
— |
— |
— |
$0.00066 |
— |
$0.00066 |
| qwen/qwen3.6-35b-a3b @ atlas-cloud/fp8 |
— |
— |
— |
$0.00066 |
— |
$0.00066 |
| qwen/qwen3.6-27b @ deepinfra/fp8 |
— |
— |
— |
$0.00065 |
— |
$0.00065 |
| openai/gpt-oss-20b @ phala |
— |
— |
— |
$0.00065 |
— |
$0.00065 |
| meta/muse-glimmer-30b @ deepinfra/bf16 |
— |
— |
— |
$0.00064 |
— |
$0.00064 |
| minimax2fminimax-m2.523phala |
— |
— |
— |
$0.00064 |
— |
$0.00064 |
| moonshotai/kimi-k2.5 @ deepinfra/fp4 |
— |
— |
— |
$0.00064 |
— |
$0.00064 |
| moonshotai/kimi-k2.5 @ amazon-bedrock/us-east-2 |
— |
— |
— |
$0.00063 |
— |
$0.00063 |
| qwen/qwen3.6-27b @ phala |
— |
— |
— |
$0.00063 |
— |
$0.00063 |
| z-ai/glm-5.1 @ crusoe/fp8 |
— |
— |
— |
$0.00063 |
— |
$0.00063 |
| deepseek/deepseek-v4-flash-0731 @ cloudflare |
— |
— |
— |
$0.00062 |
— |
$0.00062 |
| mistralai/ministral-3b-2512 @ nextbit/fp8 |
$0.00 |
— |
$0.00058 |
$0.000039 |
— |
$0.00061 |
| qwen/qwen3-235b-a22b-thinking-2507 @ alibaba |
— |
— |
— |
$0.00061 |
— |
$0.00061 |
| openai/gpt-oss-120b @ deepinfra/bf16 |
— |
— |
— |
$0.00061 |
— |
$0.00061 |
| qwen/qwen3.5-122b-a10b @ atlas-cloud/fp8 |
— |
— |
— |
$0.00061 |
— |
$0.00061 |
| z-ai/glm-4.7 @ venice/fp4 |
— |
— |
— |
$0.00060 |
— |
$0.00060 |
| bytedance-seed/seed-1.6 @ seed/fp8 |
— |
— |
— |
$0.00060 |
— |
$0.00060 |
| z-ai/glm-4.5 @ z-ai/fp8 |
— |
— |
— |
$0.00060 |
— |
$0.00060 |
| openai/gpt-4 @ azure |
— |
— |
— |
$0.00060 |
— |
$0.00060 |
| openai/gpt-4 @ openai |
— |
— |
— |
$0.00060 |
— |
$0.00060 |
| z-ai/glm-4.7 @ google-vertex |
— |
— |
— |
$0.00060 |
— |
$0.00060 |
| mistralai/mistral-nemo @ novita/fp8 |
— |
— |
$0.00052 |
$0.000072 |
— |
$0.00060 |
| anthropic2fclaude-opus-4.623amazon-bedrock2fus-east-1 |
— |
— |
— |
$0.00059 |
— |
$0.00059 |
| qwen/qwen3.5-27b @ phala |
— |
— |
— |
$0.00058 |
— |
$0.00058 |
| deepseek/deepseek-v4-flash-0731 @ atlas-cloud/fp4 |
— |
— |
— |
$0.00058 |
— |
$0.00058 |
| bytedance-seed/seed-2-1-turbo @ seed/fp8 |
— |
— |
— |
$0.00058 |
— |
$0.00058 |
| anthropic2fclaude-haiku-4.523azure2fus-east-2 |
— |
— |
— |
$0.00057 |
— |
$0.00057 |
| qwen2fqwen3.6-27b23wandb2ffp8 |
— |
— |
— |
$0.00057 |
— |
$0.00057 |
| qwen/qwen3.5-27b @ deepinfra/fp8 |
— |
— |
— |
$0.00056 |
— |
$0.00056 |
| moonshotai/kimi-k2.7-code @ fireworks |
— |
— |
— |
$0.00055 |
— |
$0.00055 |
| qwen/qwen3-8b @ alibaba |
— |
— |
— |
$0.00055 |
— |
$0.00055 |
| z-ai/glm-4.6v @ novita/bf16 |
— |
— |
— |
$0.00054 |
— |
$0.00054 |
| meta-llama/llama-4-maverick @ google-vertex/us-east5 |
— |
— |
— |
$0.00054 |
— |
$0.00054 |
| qwen/qwen3.7-max @ alibaba |
— |
— |
— |
$0.00054 |
— |
$0.00054 |
| deepseek/deepseek-v3.2-exp @ siliconflow/fp8 |
— |
— |
— |
$0.00053 |
— |
$0.00053 |
| minimax/minimax-m2.5 @ venice |
— |
— |
— |
$0.00052 |
— |
$0.00052 |
| deepseek/deepseek-r1-0528 @ deepinfra/fp4 |
— |
— |
— |
$0.00052 |
— |
$0.00052 |
| openai/gpt-oss-120b @ mancer/fp4 |
$0.00 |
— |
— |
$0.00052 |
— |
$0.00052 |
| qwen/qwen3-coder @ novita/fp8 |
— |
— |
— |
$0.00051 |
— |
$0.00051 |
| xiaomi/mimo-v2.5-pro @ novita |
— |
— |
— |
$0.00051 |
— |
$0.00051 |
| minimax/minimax-m1 @ novita/bf16 |
— |
— |
— |
$0.00050 |
— |
$0.00050 |
| kwaipilot/kat-coder-pro-v2 @ atlas-cloud/fp8 |
— |
— |
— |
$0.00050 |
— |
$0.00050 |
| openai/gpt-oss-120b @ amazon-bedrock |
— |
— |
— |
$0.00050 |
— |
$0.00050 |
| openai/gpt-oss-120b @ amazon-bedrock/eu-west-1 |
— |
— |
— |
$0.00050 |
— |
$0.00050 |
| qwen2fqwen3.6-27b23io-net2ffp8 |
— |
— |
— |
$0.00050 |
— |
$0.00050 |
| z-ai2fglm-523chutes2ffp8 |
— |
— |
— |
$0.00050 |
— |
$0.00050 |
| qwen/qwen3.6-27b @ coreweave/fp8 |
— |
— |
— |
$0.00049 |
— |
$0.00049 |
| qwen/qwen3.5-27b @ siliconflow/fp8 |
— |
— |
— |
$0.00049 |
— |
$0.00049 |
| qwen/qwen3.5-122b-a10b @ siliconflow/fp8 |
— |
— |
— |
$0.00049 |
— |
$0.00049 |
| poolside/laguna-m.1 @ poolside/fp4 |
$0.00 |
— |
— |
$0.00049 |
— |
$0.00049 |
| openai/gpt-oss-20b @ deepinfra/bf16 |
— |
— |
— |
$0.00049 |
— |
$0.00049 |
| google/gemini-2.5-pro-preview-05-06 @ google-ai-studio/priority |
— |
— |
— |
$0.00048 |
— |
$0.00048 |
| google/gemini-2.5-pro @ google-ai-studio/priority |
— |
— |
— |
$0.00048 |
— |
$0.00048 |
| meta-llama/llama-3.1-70b-instruct @ deepinfra/turbo |
— |
— |
— |
$0.00048 |
— |
$0.00048 |
| moonshotai/kimi-k2.7-code @ coreweave/int4 |
— |
— |
— |
$0.00048 |
— |
$0.00048 |
| google/gemini-3.1-flash-lite-preview @ google-ai-studio |
— |
— |
— |
$0.00048 |
— |
$0.00048 |
| google/gemini-3.1-flash-lite @ google-ai-studio |
— |
— |
— |
$0.00048 |
— |
$0.00048 |
| qwen/qwen3.5-9b @ parasail/bf16 |
— |
— |
$0.00038 |
$0.000096 |
— |
$0.00047 |
| qwen/qwen3.5-35b-a3b @ venice |
— |
— |
— |
$0.00047 |
— |
$0.00047 |
| ibm-granite/granite-4.1-8b @ wandb/bf16 |
$0.00 |
— |
$0.00044 |
$0.000031 |
— |
$0.00047 |
| z-ai2fglm-5-turbo23atlas-cloud2ffp8 |
— |
— |
— |
$0.00047 |
— |
$0.00047 |
| deepseek/deepseek-v3.2 @ phala |
— |
— |
— |
$0.00047 |
— |
$0.00047 |
| moonshotai/kimi-k2.6 @ crusoe/bf16 |
— |
— |
— |
$0.00046 |
— |
$0.00046 |
| qwen/qwen3.5-35b-a3b @ siliconflow/fp8 |
— |
— |
— |
$0.00046 |
— |
$0.00046 |
| bytedance-seed/seed-2.0-code @ seed/fp8 |
— |
— |
— |
$0.00045 |
— |
$0.00045 |
| moonshotai/kimi-k2.6 @ coreweave/fp4 |
— |
— |
— |
$0.00045 |
— |
$0.00045 |
| qwen/qwen3-coder @ venice/fp8 |
— |
— |
— |
$0.00045 |
— |
$0.00045 |
| qwen/qwen3-235b-a22b @ alibaba |
— |
— |
— |
$0.00045 |
— |
$0.00045 |
| openai2fgpt-oss-120b23wandb2ffp4 |
— |
— |
— |
$0.00045 |
— |
$0.00045 |
| qwen/qwen3-vl-30b-a3b-thinking @ siliconflow/fp8 |
— |
— |
— |
$0.00044 |
— |
$0.00044 |
| qwen2fqwen3.6-27b23morph |
— |
— |
— |
$0.00044 |
— |
$0.00044 |
| google/gemini-3.1-flash-lite @ google-vertex/global |
— |
— |
— |
$0.00044 |
— |
$0.00044 |
| qwen/qwen3-vl-235b-a22b-instruct @ novita/bf16 |
— |
— |
— |
$0.00043 |
— |
$0.00043 |
| meta/muse-glimmer-30b @ parasail/bf16 |
— |
— |
— |
$0.00043 |
— |
$0.00043 |
| z-ai/glm-4.7 @ deepinfra/fp4 |
— |
— |
— |
$0.00043 |
— |
$0.00043 |
| z-ai2fglm-4.723phala |
— |
— |
— |
$0.00042 |
— |
$0.00042 |
| anthropic/claude-haiku-4.5 @ azure/global |
— |
— |
— |
$0.00042 |
— |
$0.00042 |
| google/gemini-2.5-flash @ google-ai-studio/priority |
— |
— |
— |
$0.00041 |
— |
$0.00041 |
| qwen/qwen3.6-flash @ alibaba |
— |
— |
— |
$0.00041 |
— |
$0.00041 |
| amazon/nova-pro-v1 @ amazon-bedrock |
— |
— |
— |
$0.00041 |
— |
$0.00041 |
| amazon/nova-pro-v1 @ amazon-bedrock/eu-west-1 |
— |
— |
— |
$0.00041 |
— |
$0.00041 |
| openai2fgpt-oss-120b23dekallm2fbf16 |
— |
— |
— |
$0.00040 |
— |
$0.00040 |
| meta-llama/llama-4-maverick @ novita/fp8 |
— |
— |
— |
$0.00039 |
— |
$0.00039 |
| mistralai/mistral-saba @ mistral |
— |
— |
— |
$0.00039 |
— |
$0.00039 |
| qwen/qwen3.6-35b-a3b @ siliconflow/fp8 |
— |
— |
— |
$0.00039 |
— |
$0.00039 |
| anthropic/claude-opus-4.1 @ amazon-bedrock |
— |
— |
— |
$0.00039 |
— |
$0.00039 |
| anthropic/claude-opus-4.1 @ google-vertex/global |
— |
— |
— |
$0.00039 |
— |
$0.00039 |
| anthropic/claude-opus-4 @ google-vertex |
— |
— |
— |
$0.00039 |
— |
$0.00039 |
| nvidia/nemotron-3-super-120b-a12b @ digitalocean |
— |
— |
— |
$0.00039 |
— |
$0.00039 |
| qwen/qwen3-30b-a3b @ deepinfra/fp8 |
— |
— |
— |
$0.00039 |
— |
$0.00039 |
| stepfun/step-3.7-flash @ deepinfra |
— |
— |
— |
$0.00039 |
— |
$0.00039 |
| anthropic/claude-haiku-4.5 @ google-vertex/us-east5 |
— |
— |
— |
$0.00039 |
— |
$0.00039 |
| z-ai2fglm-5.123together |
— |
— |
— |
$0.00038 |
— |
$0.00038 |
| z-ai/glm-5.2 @ parasail/fp8 |
$0.00 |
— |
— |
$0.00038 |
— |
$0.00038 |
| mistralai/mistral-small-2603 @ venice/fp8 |
— |
— |
— |
$0.00038 |
— |
$0.00038 |
| nousresearch/hermes-4-70b @ nebius/fp8 |
— |
— |
— |
$0.00038 |
— |
$0.00038 |
| thinkingmachines/inkling-small @ together |
— |
— |
— |
$0.00038 |
— |
$0.00038 |
| qwen/qwen3-vl-235b-a22b-instruct @ venice/fp8 |
— |
— |
— |
$0.00037 |
— |
$0.00037 |
| deepseek/deepseek-v4-flash-0731 @ parasail/fp8 |
— |
— |
— |
$0.00037 |
— |
$0.00037 |
| google/gemini-2.5-flash @ google-vertex/global/priority |
— |
— |
— |
$0.00037 |
— |
$0.00037 |
| minimax/minimax-m1 @ minimax |
— |
— |
— |
$0.00037 |
— |
$0.00037 |
| mistralai/mistral-medium-3.1 @ mistral |
— |
— |
— |
$0.00037 |
— |
$0.00037 |
| mistralai/mistral-medium-3 @ mistral |
— |
— |
— |
$0.00037 |
— |
$0.00037 |
| deepseek/deepseek-v4-pro @ siliconflow/fp8 |
— |
— |
— |
$0.00037 |
— |
$0.00037 |
| minimax2fminimax-m2.723sambanova2fminimax-m2.7-dedicated |
— |
— |
— |
$0.00037 |
— |
$0.00037 |
| nvidia2fllama-3.3-nemotron-super-49b-v1.523deepinfra2ffp8 |
— |
— |
— |
$0.00037 |
— |
$0.00037 |
| qwen/qwen3-coder @ deepinfra/turbo |
— |
— |
— |
$0.00037 |
— |
$0.00037 |
| nvidia2fnemotron-3-ultra-550b-a55b23nebius2ffp4 |
— |
— |
— |
$0.00036 |
— |
$0.00036 |
| qwen/qwen3-vl-30b-a3b-instruct @ siliconflow/fp8 |
— |
— |
— |
$0.00036 |
— |
$0.00036 |
| qwen/qwen3-30b-a3b-instruct-2507 @ atlas-cloud/fp8 |
$0.00 |
— |
$0.00034 |
$0.000019 |
— |
$0.00036 |
| meituan/longcat-2.0 @ atlas-cloud/fp8 |
— |
— |
— |
$0.00036 |
— |
$0.00036 |
| thinkingmachines/inkling-small @ deepinfra/fp8 |
— |
— |
— |
$0.00035 |
— |
$0.00035 |
| google/gemini-2.5-pro @ google-vertex/global/priority |
— |
— |
— |
$0.00035 |
— |
$0.00035 |
| openai2fgpt-oss-20b23wandb2ffp4 |
— |
— |
— |
$0.00035 |
— |
$0.00035 |
| meta/muse-glimmer-30b @ phala |
— |
— |
— |
$0.00035 |
— |
$0.00035 |
| moonshotai2fkimi-k2.7-code23wandb2fint4 |
— |
— |
— |
$0.00035 |
— |
$0.00035 |
| qwen/qwen-2.5-72b-instruct @ deepinfra/fp8 |
— |
— |
— |
$0.00035 |
— |
$0.00035 |
| stepfun/step-3.7-flash @ novita/fp8 |
— |
— |
— |
$0.00035 |
— |
$0.00035 |
| qwen/qwen3-235b-a22b-2507 @ atlas-cloud/fp8 |
— |
— |
— |
$0.00034 |
— |
$0.00034 |
| qwen/qwen3-coder-next @ novita/fp8 |
— |
— |
— |
$0.00034 |
— |
$0.00034 |
| deepseek/deepseek-v4-pro @ atlas-cloud/fp4 |
— |
— |
— |
$0.00034 |
— |
$0.00034 |
| anthropic/claude-3-haiku @ amazon-bedrock |
— |
— |
— |
$0.00033 |
— |
$0.00033 |
| writer/palmyra-x5 @ amazon-bedrock |
— |
— |
— |
$0.00033 |
— |
$0.00033 |
| poolside2flaguna-xs.223poolside2ffp8 |
— |
— |
— |
$0.00033 |
— |
$0.00033 |
| deepseek/deepseek-v3.2 @ streamlake/fp8 |
— |
— |
$0.000059 |
$0.00027 |
— |
$0.00033 |
| qwen/qwen3-coder-next @ alibaba |
— |
— |
— |
$0.00033 |
— |
$0.00033 |
| deepseek/deepseek-chat-v3.1 @ siliconflow/fp8 |
— |
— |
— |
$0.00033 |
— |
$0.00033 |
| deepseek/deepseek-v3.1-terminus @ siliconflow/fp8 |
— |
— |
— |
$0.00033 |
— |
$0.00033 |
| moonshotai/kimi-k2.7-code @ gmicloud/fp8 |
— |
— |
— |
$0.00032 |
— |
$0.00032 |
| qwen/qwen3-14b @ alibaba |
— |
— |
— |
$0.00032 |
— |
$0.00032 |
| qwen2fqwen3-30b-a3b23nextbit2ffp8 |
— |
— |
— |
$0.00032 |
— |
$0.00032 |
| google/gemini-2.5-flash @ google-ai-studio |
— |
— |
— |
$0.00032 |
— |
$0.00032 |
| google/gemini-2.5-flash-image @ google-ai-studio/priority |
— |
— |
— |
$0.00032 |
— |
$0.00032 |
| deepseek/deepseek-v3.2 @ baidu/fp8 |
$0.00 |
— |
— |
$0.00031 |
— |
$0.00031 |
| openai2fgpt-oss-20b23dekallm2fbf16 |
— |
— |
— |
$0.00031 |
— |
$0.00031 |
| qwen/qwen3.5-122b-a10b @ deepinfra/fp4 |
— |
— |
— |
$0.00031 |
— |
$0.00031 |
| qwen2fqwen3.5-35b-a3b23nextbit2ffp8 |
— |
— |
— |
$0.00031 |
— |
$0.00031 |
| qwen/qwen3-32b @ siliconflow/fp8 |
— |
— |
— |
$0.00031 |
— |
$0.00031 |
| mistralai/mistral-small-2603 @ mistral |
— |
— |
— |
$0.00031 |
— |
$0.00031 |
| deepseek/deepseek-chat @ novita/fp8 |
— |
— |
— |
$0.00030 |
— |
$0.00030 |
| deepseek2fdeepseek-r1-052823atlas-cloud2ffp8 |
— |
— |
— |
$0.00029 |
— |
$0.00029 |
| minimax2fminimax-m2.523deepinfra2ffp8 |
— |
— |
— |
$0.00029 |
— |
$0.00029 |
| nvidia2fnemotron-3-super-120b-a12b23nebius2ffp4 |
— |
— |
— |
$0.00029 |
— |
$0.00029 |
| qwen/qwen3-235b-a22b-2507 @ wandb/bf16 |
— |
— |
$0.00028 |
$0.000014 |
— |
$0.00029 |
| qwen/qwen3-next-80b-a3b-thinking @ google-vertex/global |
— |
— |
— |
$0.00029 |
— |
$0.00029 |
| qwen/qwen3-14b @ deepinfra/fp8 |
— |
— |
— |
$0.00029 |
— |
$0.00029 |
| google/gemini-2.5-flash @ google-vertex |
— |
— |
— |
$0.00029 |
— |
$0.00029 |
| google/gemini-2.5-flash @ google-vertex/eu |
— |
— |
— |
$0.00029 |
— |
$0.00029 |
| google/gemini-2.5-flash @ google-vertex/global |
— |
— |
— |
$0.00029 |
— |
$0.00029 |
| minimax/minimax-01 @ minimax |
— |
— |
— |
$0.00029 |
— |
$0.00029 |
| deepseek/deepseek-v3.2 @ novita/fp8 |
— |
— |
— |
$0.00028 |
— |
$0.00028 |
| meta-llama/llama-4-maverick @ deepinfra/base |
— |
— |
— |
$0.00028 |
— |
$0.00028 |
| deepseek2fdeepseek-v4-flash-073123deepseek2ffp8 |
— |
— |
— |
$0.00028 |
— |
$0.00028 |
| z-ai/glm-4.5-air @ novita/bf16 |
— |
— |
— |
$0.00028 |
— |
$0.00028 |
| qwen/qwen3-32b @ nebius/base |
— |
— |
— |
$0.00028 |
— |
$0.00028 |
| deepseek/deepseek-v3.1-terminus @ atlas-cloud/fp8 |
— |
— |
— |
$0.00028 |
— |
$0.00028 |
| mistralai/mistral-medium-3-5 @ mistral/eu |
— |
— |
— |
$0.00028 |
— |
$0.00028 |
| qwen/qwen3-vl-235b-a22b-instruct @ deepinfra/fp8 |
— |
— |
— |
$0.00028 |
— |
$0.00028 |
| deepseek2fdeepseek-v4-pro23atlas-cloud2ffp8 |
$0.00 |
— |
— |
$0.00027 |
— |
$0.00027 |
| anthropic/claude-haiku-4.5 @ amazon-bedrock/us |
— |
— |
— |
$0.00027 |
— |
$0.00027 |
| minimax2fminimax-m2.523coreweave2ffp8 |
— |
— |
— |
$0.00027 |
— |
$0.00027 |
| thedrummer/rocinante-12b @ infermatic/bf16 |
$0.00 |
— |
— |
$0.00027 |
— |
$0.00027 |
| openai/gpt-4.1-nano @ azure/swedencentral |
— |
— |
— |
$0.00027 |
— |
$0.00027 |
| qwen/qwen3.5-35b-a3b @ parasail/fp8 |
— |
— |
— |
$0.00027 |
— |
$0.00027 |
| qwen2fqwen3-8b23alibaba2ffp8 |
— |
— |
— |
$0.00027 |
— |
$0.00027 |
| qwen/qwen3.8-27b @ coreweave/fp8 |
— |
— |
— |
$0.00027 |
— |
$0.00027 |
| qwen/qwen3.6-35b-a3b @ parasail/fp8 |
— |
— |
— |
$0.00026 |
— |
$0.00026 |
| meta-llama/llama-4-scout @ novita/bf16 |
— |
— |
— |
$0.00026 |
— |
$0.00026 |
| meta-llama/llama-3.3-70b-instruct @ together |
— |
— |
— |
$0.00026 |
— |
$0.00026 |
| qwen/qwen3.5-35b-a3b @ deepinfra/fp8 |
— |
— |
— |
$0.00026 |
— |
$0.00026 |
| google/gemini-3.1-flash-lite-image @ google-ai-studio |
— |
— |
— |
$0.00026 |
— |
$0.00026 |
| qwen/qwen3-coder-next @ streamlake |
— |
— |
— |
$0.00026 |
— |
$0.00026 |
| mistralai2fdevstral-251223mistral |
— |
— |
— |
$0.00026 |
— |
$0.00026 |
| minimax2fminimax-m2.523nebius2ffp4 |
— |
— |
— |
$0.00026 |
— |
$0.00026 |
| qwen/qwen3-8b @ atlas-cloud/fp8 |
— |
— |
— |
$0.00026 |
— |
$0.00026 |
| mistralai/mistral-medium-3-5 @ mistral/zdr |
— |
— |
— |
$0.00025 |
— |
$0.00025 |
| morph/morph-v3-fast @ morph |
— |
— |
— |
$0.00025 |
— |
$0.00025 |
| qwen/qwen-2.5-7b-instruct @ together/fp8 |
— |
— |
— |
$0.00025 |
— |
$0.00025 |
| google/gemini-3.1-flash-lite @ google-vertex/us |
— |
— |
— |
$0.00025 |
— |
$0.00025 |
| z-ai/glm-5.2 @ dekallm |
$0.00 |
— |
— |
$0.00024 |
— |
$0.00024 |
| z-ai2fglm-5.123coreweave2ffp8 |
— |
— |
— |
$0.00024 |
— |
$0.00024 |
| deepseek/deepseek-chat-v3.1 @ novita/fp8 |
— |
— |
— |
$0.00024 |
— |
$0.00024 |
| deepseek/deepseek-v3.1-terminus @ novita/fp8 |
— |
— |
— |
$0.00024 |
— |
$0.00024 |
| moonshotai2fkimi-k2.523modelrun2ffp4 |
— |
— |
— |
$0.00024 |
— |
$0.00024 |
| openai/gpt-4.1-nano @ azure |
— |
— |
— |
$0.00024 |
— |
$0.00024 |
| openai/gpt-4.1-nano @ openai |
— |
— |
— |
$0.00024 |
— |
$0.00024 |
| qwen/qwen3-32b @ deepinfra/fp8 |
— |
— |
— |
$0.00024 |
— |
$0.00024 |
| qwen2fqwen3.5-397b-a17b23morph |
— |
— |
— |
$0.00023 |
— |
$0.00023 |
| openai/gpt-oss-120b @ coreweave/fp4 |
— |
— |
— |
$0.00023 |
— |
$0.00023 |
| deepseek/deepseek-chat-v3-0324 @ novita/fp8 |
— |
— |
— |
$0.00023 |
— |
$0.00023 |
| deepseek/deepseek-chat @ deepinfra/fp4 |
— |
— |
— |
$0.00023 |
— |
$0.00023 |
| meta-llama/llama-3.2-3b-instruct @ cloudflare |
— |
— |
— |
$0.00022 |
— |
$0.00022 |
| google/gemma-4-31b-it @ siliconflow/fp8 |
— |
— |
— |
$0.00022 |
— |
$0.00022 |
| z-ai/glm-4.5-air @ siliconflow/fp8 |
— |
— |
— |
$0.00022 |
— |
$0.00022 |
| google/gemini-3.1-flash-lite @ google-ai-studio/flex |
— |
— |
— |
$0.00022 |
— |
$0.00022 |
| openai/gpt-4-turbo @ openai |
— |
— |
— |
$0.00022 |
— |
$0.00022 |
| switchpoint2frouter23switchpoint |
— |
— |
— |
$0.00022 |
— |
$0.00022 |
| meta-llama/llama-3.1-8b-instruct @ cloudflare/fp8 |
— |
— |
— |
$0.00022 |
— |
$0.00022 |
| qwen/qwen3-30b-a3b-instruct-2507 @ dekallm |
$0.00 |
— |
$0.00020 |
$0.000018 |
— |
$0.00022 |
| mistralai/codestral-2508 @ mistral |
— |
— |
— |
$0.00022 |
— |
$0.00022 |
| openai2fgpt-oss-20b23together |
— |
— |
— |
$0.00022 |
— |
$0.00022 |
| openai/gpt-oss-20b @ amazon-bedrock |
— |
— |
— |
$0.00021 |
— |
$0.00021 |
| openai/gpt-oss-20b @ amazon-bedrock/eu-west-1 |
— |
— |
— |
$0.00021 |
— |
$0.00021 |
| qwen/qwen3-235b-a22b-2507 @ venice/fp8 |
— |
— |
— |
$0.00021 |
— |
$0.00021 |
| google/gemini-2.5-flash-image @ google-ai-studio |
— |
— |
— |
$0.00021 |
— |
$0.00021 |
| deepseek/deepseek-v4-pro-0813 @ baseten/fp4 |
— |
— |
— |
$0.00021 |
— |
$0.00021 |
| deepseek/deepseek-chat-v3.1 @ deepinfra/fp4 |
— |
— |
— |
$0.00021 |
— |
$0.00021 |
| google/gemma-4-26b-a4b-it @ siliconflow/fp8 |
— |
— |
— |
$0.00021 |
— |
$0.00021 |
| deepseek/deepseek-v3.2 @ venice |
— |
— |
— |
$0.00021 |
— |
$0.00021 |
| qwen2fqwen3.5-35b-a3b23wandb2ffp8 |
— |
— |
— |
$0.00021 |
— |
$0.00021 |
| openai/gpt-oss-20b @ coreweave/fp4 |
— |
— |
— |
$0.00021 |
— |
$0.00021 |
| google/gemma-4-31b-it @ deepinfra/fp8 |
— |
— |
— |
$0.00020 |
— |
$0.00020 |
| deepseek2fdeepseek-v4-pro23alibaba |
— |
— |
— |
$0.00020 |
— |
$0.00020 |
| z-ai2fglm-5.123inceptron2ffp8 |
— |
— |
— |
$0.00020 |
— |
$0.00020 |
| moonshotai2fkimi-k2-090523atlas-cloud2ffp8 |
— |
— |
— |
$0.00020 |
— |
$0.00020 |
| meta-llama/llama-3.3-70b-instruct @ nebius/fp8 |
— |
— |
— |
$0.00020 |
— |
$0.00020 |
| mistralai/mistral-small-3.1-24b-instruct @ cloudflare |
— |
— |
— |
$0.00020 |
— |
$0.00020 |
| deepseek/deepseek-v3.1-terminus @ deepinfra/fp4 |
— |
— |
— |
$0.00020 |
— |
$0.00020 |
| amazon/nova-premier-v1 @ amazon-bedrock |
— |
— |
— |
$0.00020 |
— |
$0.00020 |
| deepseek/deepseek-chat-v3-0324 @ siliconflow/fp8 |
— |
— |
— |
$0.00020 |
— |
$0.00020 |
| microsoft/phi-4-mini-instruct @ wandb/bf16 |
$0.00 |
— |
$0.00019 |
$0.0000094 |
— |
$0.00020 |
| qwen/qwen3-vl-30b-a3b-instruct @ deepinfra/fp8 |
— |
— |
— |
$0.00020 |
— |
$0.00020 |
| qwen/qwen3-next-80b-a3b-instruct @ deepinfra/fp8 |
— |
— |
— |
$0.00020 |
— |
$0.00020 |
| anthropic2fclaude-opus-4.123anthropic |
— |
— |
— |
$0.00019 |
— |
$0.00019 |
| google/gemma-4-31b-it @ coreweave/fp4 |
— |
— |
$0.00018 |
$0.000014 |
— |
$0.00019 |
| thinkingmachines/inkling-small @ baseten/fp8 |
— |
— |
— |
$0.00019 |
— |
$0.00019 |
| deepseek/deepseek-chat-v3-0324 @ crusoe/bf16 |
— |
— |
— |
$0.00019 |
— |
$0.00019 |
| qwen/qwen3.5-35b-a3b @ coreweave/fp8 |
— |
— |
— |
$0.00019 |
— |
$0.00019 |
| qwen/qwen3.6-35b-a3b @ coreweave/fp8 |
— |
— |
— |
$0.00019 |
— |
$0.00019 |
| nvidia/nemotron-3-super-120b-a12b @ deepinfra/bf16 |
— |
— |
— |
$0.00019 |
— |
$0.00019 |
| google/gemma-4-31b-it @ deepinfra/turbo |
— |
— |
— |
$0.00019 |
— |
$0.00019 |
| qwen/qwen3-235b-a22b-2507 @ nebius/fp8 |
— |
— |
— |
$0.00019 |
— |
$0.00019 |
| moonshotai2fkimi-k2.7-code23novita |
— |
— |
— |
$0.00019 |
— |
$0.00019 |
| minimax2fminimax-m223atlas-cloud2ffp8 |
— |
— |
— |
$0.00018 |
— |
$0.00018 |
| z-ai2fglm-523friendli |
— |
— |
— |
$0.00018 |
— |
$0.00018 |
| deepseek/deepseek-chat-v3-0324 @ deepinfra/fp4 |
— |
— |
— |
$0.00018 |
— |
$0.00018 |
| meta-llama/llama-3.2-11b-vision-instruct @ deepinfra/fp8 |
— |
— |
— |
$0.00018 |
— |
$0.00018 |
| deepseek/deepseek-v4-pro @ nextbit/fp8 |
$0.00 |
— |
— |
$0.00018 |
— |
$0.00018 |
| deepseek/deepseek-v3.2-exp @ novita/fp8 |
— |
— |
— |
$0.00018 |
— |
$0.00018 |
| z-ai/glm-5.2 @ wandb/fp8 |
$0.00 |
— |
— |
$0.00018 |
— |
$0.00018 |
| meta-llama/llama-3.3-70b-instruct @ crusoe/bf16 |
— |
— |
— |
$0.00018 |
— |
$0.00018 |
| moonshotai2fkimi-k2.623nebius2fint4 |
— |
— |
— |
$0.00018 |
— |
$0.00018 |
| deepseek/deepseek-v3.2 @ siliconflow/fp8 |
— |
— |
— |
$0.00018 |
— |
$0.00018 |
| deepseek/deepseek-v4-flash-0731 @ relace/fp4 |
$0.0000039 |
— |
$0.00014 |
$0.000027 |
— |
$0.00017 |
| qwen2fqwen3-coder23atlas-cloud2ffp8 |
— |
— |
— |
$0.00017 |
— |
$0.00017 |
| baidu/ernie-4.5-vl-424b-a47b @ novita/fp16 |
— |
— |
— |
$0.00017 |
— |
$0.00017 |
| qwen2fqwen3.6-35b-a3b23wandb2ffp8 |
— |
— |
— |
$0.00017 |
— |
$0.00017 |
| deepseek2fdeepseek-v3.223alibaba |
— |
— |
— |
$0.00017 |
— |
$0.00017 |
| z-ai/glm-4.7 @ mancer/fp4 |
— |
— |
— |
$0.00017 |
— |
$0.00017 |
| qwen/qwen3.8-27b @ io-net/fp8 |
— |
— |
— |
$0.00017 |
— |
$0.00017 |
| deepseek/deepseek-v3.2 @ deepinfra/fp4 |
— |
— |
— |
$0.00016 |
— |
$0.00016 |
| arcee-ai/trinity-large-thinking @ parasail/fp4 |
— |
— |
— |
$0.00016 |
— |
$0.00016 |
| google/gemini-2.5-pro-preview @ google-vertex/us |
— |
— |
— |
$0.00016 |
— |
$0.00016 |
| deepseek/deepseek-v4-pro-0813 @ parasail/fp8 |
— |
— |
— |
$0.00016 |
— |
$0.00016 |
| deepseek/deepseek-v3.2 @ streamlake |
— |
— |
$0.00015 |
$0.0000030 |
— |
$0.00016 |
| moonshotai/kimi-k2.6 @ gmicloud/fp8 |
— |
— |
— |
$0.00016 |
— |
$0.00016 |
| minimax/minimax-m2.7 @ sambanova |
— |
— |
— |
$0.00015 |
— |
$0.00015 |
| qwen/qwen3.8-27b @ venice/fp8 |
— |
— |
— |
$0.00015 |
— |
$0.00015 |
| google/gemini-2.5-pro @ google-vertex/us |
— |
— |
— |
$0.00015 |
— |
$0.00015 |
| qwen/qwen3.8-27b @ akashml/bf16 |
— |
— |
— |
$0.00015 |
— |
$0.00015 |
| meta-llama/llama-3.3-70b-instruct @ deepinfra/turbo |
— |
— |
— |
$0.00015 |
— |
$0.00015 |
| qwen/qwen3.6-35b-a3b @ phala |
— |
— |
— |
$0.00015 |
— |
$0.00015 |
| meta-llama/llama-4-scout @ deepinfra/fp8 |
— |
— |
— |
$0.00014 |
— |
$0.00014 |
| qwen2fqwen3.5-397b-a17b23together |
— |
— |
— |
$0.00014 |
— |
$0.00014 |
| z-ai/glm-5.3 @ parasail/fp8 |
— |
— |
— |
$0.00014 |
— |
$0.00014 |
| z-ai/glm-5.3 @ together |
— |
— |
— |
$0.00014 |
— |
$0.00014 |
| qwen/qwen3-235b-a22b-2507 @ novita/fp8 |
— |
— |
— |
$0.00014 |
— |
$0.00014 |
| qwen/qwen3.8-27b @ chutes/fp8 |
— |
— |
— |
$0.00014 |
— |
$0.00014 |
| qwen/qwen3.8-27b @ parasail/fp8 |
— |
— |
— |
$0.00014 |
— |
$0.00014 |
| stepfun/step-3.5-flash @ siliconflow/fp8 |
— |
— |
— |
$0.00014 |
— |
$0.00014 |
| google/gemma-3-27b-it @ novita/bf16 |
— |
— |
— |
$0.00014 |
— |
$0.00014 |
| qwen/qwen3.8-27b @ reka/fp8 |
— |
— |
— |
$0.00014 |
— |
$0.00014 |
| nvidia2fnemotron-3-ultra-550b-a55b23deepinfra2fbf16 |
— |
— |
— |
$0.00014 |
— |
$0.00014 |
| z-ai2fglm-523phala |
— |
— |
— |
$0.00014 |
— |
$0.00014 |
| tencent/hy4-preview @ tencent/fp8 |
— |
— |
— |
$0.00014 |
— |
$0.00014 |
| deepseek/deepseek-v4-pro-0813 @ together |
— |
— |
— |
$0.00014 |
— |
$0.00014 |
| google/gemma-4-31b-it @ deepinfra/ultra |
— |
— |
— |
$0.00014 |
— |
$0.00014 |
| deepseek2fdeepseek-v4-flash-073123cloudflare2ffp8 |
— |
— |
— |
$0.00013 |
— |
$0.00013 |
| google/gemini-2.5-pro-preview-05-06 @ google-vertex/global/priority |
— |
— |
— |
$0.00013 |
— |
$0.00013 |
| google/gemini-2.5-pro-preview @ google-vertex/global/priority |
— |
— |
— |
$0.00013 |
— |
$0.00013 |
| google/gemma-4-26b-a4b-it @ deepinfra/fp8 |
— |
— |
— |
$0.00013 |
— |
$0.00013 |
| qwen/qwen3.5-9b @ siliconflow/fp8 |
— |
— |
— |
$0.00013 |
— |
$0.00013 |
| qwen/qwen3.5-9b @ venice/fp8 |
— |
— |
— |
$0.00013 |
— |
$0.00013 |
| mistralai/mistral-nemo @ parasail/fp8 |
— |
— |
$0.00013 |
— |
— |
$0.00013 |
| qwen/qwen3-235b-a22b-2507 @ deepinfra/fp8 |
— |
— |
— |
$0.00012 |
— |
$0.00012 |
| kwaipilot/kat-coder-pro-v2.5 @ atlas-cloud/fp8 |
— |
— |
— |
$0.00012 |
— |
$0.00012 |
| qwen/qwen3-next-80b-a3b-thinking @ nebius/fp8 |
— |
— |
— |
$0.00012 |
— |
$0.00012 |
| qwen2fqwen3-vl-30b-a3b-instruct23phala |
$0.00 |
— |
— |
$0.00012 |
— |
$0.00012 |
| google/gemini-2.5-flash @ google-ai-studio/flex |
— |
— |
— |
$0.00011 |
— |
$0.00011 |
| deepseek/deepseek-v4-flash @ wafer/fp4 |
$0.00 |
— |
$0.00011 |
$0.0000025 |
— |
$0.00011 |
| minimax2fminimax-m2.523akashml2ffp8 |
— |
— |
— |
$0.00011 |
— |
$0.00011 |
| qwen/qwen3.6-35b-a3b @ venice/fp8 |
— |
— |
— |
$0.00011 |
— |
$0.00011 |
| nvidia/nemotron-3-nano-30b-a3b @ deepinfra/fp4 |
— |
— |
— |
$0.00011 |
— |
$0.00011 |
| nvidia2fnemotron-3-super-120b-a12b23dekallm2ffp8 |
— |
— |
— |
$0.00010 |
— |
$0.00010 |
| google/gemini-3.1-flash-lite @ google-vertex/global/flex |
— |
— |
— |
$0.00010 |
— |
$0.00010 |
| mistralai/ministral-14b-2512 @ mistral |
— |
— |
— |
$0.00010 |
— |
$0.00010 |
| deepseek/deepseek-v3.1-terminus @ streamlake |
— |
— |
— |
$0.00010 |
— |
$0.00010 |
| qwen/qwen3.8-27b @ cloudflare |
— |
— |
— |
$0.000099 |
— |
$0.000099 |
| nvidia/nemotron-3-nano-30b-a3b @ novita/fp4 |
— |
— |
— |
$0.000099 |
— |
$0.000099 |
| z-ai/glm-5.3 @ baseten/fp4 |
— |
— |
— |
$0.000096 |
— |
$0.000096 |
| deepseek/deepseek-v4-pro-0813 @ sail-research/fp4 |
— |
— |
— |
$0.000095 |
— |
$0.000095 |
| qwen/qwen3.5-9b @ deepinfra/bf16 |
— |
— |
— |
$0.000094 |
— |
$0.000094 |
| qwen/qwen3-coder-30b-a3b-instruct @ novita/fp8 |
— |
— |
— |
$0.000093 |
— |
$0.000093 |
| mistralai/mistral-large-2407 @ mistral/eu |
— |
— |
— |
$0.000092 |
— |
$0.000092 |
| mistralai/mistral-large @ mistral/eu |
— |
— |
— |
$0.000092 |
— |
$0.000092 |
| z-ai/glm-5.3 @ atlas-cloud/fp8 |
— |
— |
— |
$0.000091 |
— |
$0.000091 |
| z-ai/glm-5.3 @ cloudflare |
— |
— |
— |
$0.000090 |
— |
$0.000090 |
| z-ai/glm-5.3 @ digitalocean |
— |
— |
— |
$0.000090 |
— |
$0.000090 |
| z-ai/glm-5.3 @ friendli |
— |
— |
— |
$0.000090 |
— |
$0.000090 |
| z-ai/glm-5.3 @ gmicloud/fp8 |
— |
— |
— |
$0.000090 |
— |
$0.000090 |
| z-ai/glm-5.3 @ novita/fp8 |
— |
— |
— |
$0.000090 |
— |
$0.000090 |
| qwen/qwen3-235b-a22b-2507 @ crusoe/bf16 |
— |
— |
— |
$0.000089 |
— |
$0.000089 |
| moonshotai2fkimi-k2.623ambient2fint4 |
— |
— |
— |
$0.000087 |
— |
$0.000087 |
| z-ai/glm-5.3 @ morph/fp4 |
— |
— |
— |
$0.000087 |
— |
$0.000087 |
| z-ai/glm-5.3 @ akashml/fp8 |
— |
— |
— |
$0.000085 |
— |
$0.000085 |
| nvidia/nemotron-3-nano-30b-a3b @ nebius/fp8 |
$0.0000013 |
— |
— |
$0.000082 |
— |
$0.000083 |
| google/gemma-3-27b-it @ deepinfra/fp8 |
— |
— |
— |
$0.000083 |
— |
$0.000083 |
| z-ai/glm-4.7-flash @ novita/bf16 |
— |
— |
— |
$0.000081 |
— |
$0.000081 |
| z-ai/glm-5.3 @ siliconflow/fp8 |
— |
— |
— |
$0.000081 |
— |
$0.000081 |
| google/gemini-2.5-flash-image @ google-ai-studio/flex |
— |
— |
— |
$0.000081 |
— |
$0.000081 |
| z-ai/glm-5.3 @ io-net/fp8 |
— |
— |
— |
$0.000081 |
— |
$0.000081 |
| google/gemini-2.5-flash-lite @ google-ai-studio/priority |
— |
— |
— |
$0.000080 |
— |
$0.000080 |
| google/gemini-3.1-flash-lite-preview @ google-ai-studio/flex |
— |
— |
— |
$0.000078 |
— |
$0.000078 |
| z-ai/glm-4.7-flash @ deepinfra/bf16 |
— |
— |
— |
$0.000078 |
— |
$0.000078 |
| mistralai/ministral-8b-2512 @ mistral |
— |
— |
— |
$0.000077 |
— |
$0.000077 |
| aion-labs/aion-1.0-mini @ aion-labs/bf16 |
$0.00 |
— |
— |
$0.000077 |
— |
$0.000077 |
| qwen2fqwen3-235b-a22b-250723together |
— |
— |
— |
$0.000077 |
— |
$0.000077 |
| qwen/qwen3.6-35b-a3b @ deepinfra/fp8 |
— |
— |
— |
$0.000074 |
— |
$0.000074 |
| deepseek/deepseek-v4-pro-0813 @ deepinfra/fp8 |
— |
— |
— |
$0.000073 |
— |
$0.000073 |
| google/gemini-2.5-pro-preview-05-06 @ google-vertex/global |
— |
— |
— |
$0.000073 |
— |
$0.000073 |
| microsoft/phi-4 @ deepinfra/bf16 |
— |
— |
— |
$0.000072 |
— |
$0.000072 |
| deepseek2fdeepseek-v4-flash-073123streamlake |
— |
— |
— |
$0.000072 |
— |
$0.000072 |
| z-ai/glm-4.7-flash @ cloudflare |
— |
— |
— |
$0.000071 |
— |
$0.000071 |
| qwen2fqwen3-vl-235b-a22b-instruct23atlas-cloud2ffp8 |
— |
— |
— |
$0.000067 |
— |
$0.000067 |
| google/gemma-3-12b-it @ deepinfra/bf16 |
— |
— |
— |
$0.000067 |
— |
$0.000067 |
| google/gemma-2-27b-it @ nextbit/int4 |
— |
— |
— |
$0.000064 |
— |
$0.000064 |
| sao10k/l3-lunaris-8b @ novita/bf16 |
— |
— |
— |
$0.000062 |
— |
$0.000062 |
| nvidia2fnemotron-3-ultra-550b-a55b23crusoe2ffp4 |
— |
— |
— |
$0.000061 |
— |
$0.000061 |
| google/gemma-3-4b-it @ deepinfra/bf16 |
— |
— |
— |
$0.000059 |
— |
$0.000059 |
| z-ai/glm-5.3 @ deepinfra/fp8 |
— |
— |
— |
$0.000059 |
— |
$0.000059 |
| deepseek/deepseek-v4-flash-0731 @ nextbit/fp8 |
— |
— |
— |
$0.000057 |
— |
$0.000057 |
| mistralai/mistral-large @ mistral/zdr |
— |
— |
— |
$0.000056 |
— |
$0.000056 |
| google/gemini-3.1-flash-lite @ google-vertex/eu |
— |
— |
— |
$0.000054 |
— |
$0.000054 |
| meta-llama/llama-3-8b-instruct @ together/int4 |
— |
— |
— |
$0.000054 |
— |
$0.000054 |
| qwen/qwen3.8-27b @ akashml/fp8 |
— |
— |
— |
$0.000053 |
— |
$0.000053 |
| mistralai/mistral-nemo @ mistral |
— |
— |
— |
$0.000051 |
— |
$0.000051 |
| sao10k/l3-lunaris-8b @ deepinfra/turbo |
— |
— |
— |
$0.000050 |
— |
$0.000050 |
| moonshotai/kimi-k2.7-code @ nebius/fp4 |
— |
— |
— |
$0.000050 |
— |
$0.000050 |
| qwen2fqwen3.6-27b23morph2ffp4 |
— |
— |
— |
$0.000049 |
— |
$0.000049 |
| mistralai/mistral-small-3.2-24b-instruct @ deepinfra/fp8 |
— |
— |
— |
$0.000048 |
— |
$0.000048 |
| qwen2fqwen3-coder-next23atlas-cloud2ffp8 |
— |
— |
— |
$0.000048 |
— |
$0.000048 |
| qwen2fqwen3-next-80b-a3b-instruct23atlas-cloud2ffp8 |
— |
— |
— |
$0.000046 |
— |
$0.000046 |
| nvidia/nemotron-3.5-lightning @ coreweave/bf16 |
— |
— |
— |
$0.000041 |
— |
$0.000041 |
| moonshotai/kimi-k2.6 @ baseten/fp4 |
— |
— |
— |
$0.000040 |
— |
$0.000040 |
| qwen2fqwen3-32b23atlas-cloud2ffp8 |
— |
— |
— |
$0.000040 |
— |
$0.000040 |
| z-ai/glm-5.3 @ deepinfra/fp4 |
— |
— |
— |
$0.000039 |
— |
$0.000039 |
| deepseek/deepseek-v4-flash-0731 @ alibaba |
— |
— |
— |
$0.000039 |
— |
$0.000039 |
| qwen2fqwen3.6-35b-a3b23dekallm |
— |
— |
— |
$0.000039 |
— |
$0.000039 |
| inclusionai/ling-3.0-flash @ deepinfra/bf16 |
— |
— |
— |
$0.000038 |
— |
$0.000038 |
| z-ai/glm-5.2 @ io-net/fp4 |
$0.00 |
— |
— |
$0.000038 |
— |
$0.000038 |
| deepseek/deepseek-chat-v3-0324 @ modelrun/fp4 |
$0.00 |
— |
$0.000034 |
— |
— |
$0.000034 |
| mistralai/mistral-medium-3.1 @ mistral/eu |
— |
— |
— |
$0.000032 |
— |
$0.000032 |
| mistralai/mistral-medium-3 @ mistral/eu |
— |
— |
— |
$0.000032 |
— |
$0.000032 |
| qwen/qwen3.8-flash @ alibaba |
— |
— |
— |
$0.000032 |
— |
$0.000032 |
| mistralai/devstral-2512 @ mistral/eu |
— |
— |
— |
$0.000031 |
— |
$0.000031 |
| qwen2fqwen3-vl-30b-a3b-instruct23atlas-cloud2ffp8 |
— |
— |
— |
$0.000031 |
— |
$0.000031 |
| amazon/nova-lite-v1 @ amazon-bedrock |
— |
— |
— |
$0.000031 |
— |
$0.000031 |
| amazon/nova-lite-v1 @ amazon-bedrock/eu-west-1 |
— |
— |
— |
$0.000031 |
— |
$0.000031 |
| mistralai/mistral-large-2512 @ mistral/eu |
— |
— |
— |
$0.000031 |
— |
$0.000031 |
| nvidia/nemotron-3.5-lightning @ deepinfra/bf16 |
— |
— |
— |
$0.000030 |
— |
$0.000030 |
| mistralai/mistral-medium-3.1 @ mistral/zdr |
— |
— |
— |
$0.000029 |
— |
$0.000029 |
| mistralai/mistral-medium-3 @ mistral/zdr |
— |
— |
— |
$0.000029 |
— |
$0.000029 |
| google/gemma-3-27b-it @ phala |
— |
— |
— |
$0.000028 |
— |
$0.000028 |
| deepseek/deepseek-chat-v3-0324 @ atlas-cloud/fp8 |
— |
— |
— |
$0.000028 |
— |
$0.000028 |
| qwen2fqwen-2.5-7b-instruct23together |
— |
— |
— |
$0.000027 |
— |
$0.000027 |
| openai/gpt-oss-120b @ open-inference/int8 |
$0.00 |
— |
— |
$0.000027 |
— |
$0.000027 |
| mistralai/mistral-small-2603 @ mistral/eu |
— |
— |
— |
$0.000026 |
— |
$0.000026 |
| qwen2fqwen3-235b-a22b-thinking-250723wandb2fbf16 |
— |
— |
— |
$0.000025 |
— |
$0.000025 |
| moonshotai/kimi-k2.6 @ fireworks |
— |
— |
— |
$0.000025 |
— |
$0.000025 |
| mistralai/mistral-saba @ mistral/eu |
— |
— |
— |
$0.000025 |
— |
$0.000025 |
| mistralai/mistral-large-2512 @ mistral/zdr |
— |
— |
— |
$0.000024 |
— |
$0.000024 |
| qwen/qwen3-vl-8b-instruct @ novita/fp8 |
— |
— |
— |
$0.000022 |
— |
$0.000022 |
| arcee-ai/trinity-mini @ clarifai/bf16 |
$0.00 |
— |
— |
$0.000021 |
— |
$0.000021 |
| openai/gpt-oss-20b @ darkbloom/fp8 |
— |
— |
— |
$0.000020 |
— |
$0.000020 |
| qwen/qwen3-vl-8b-instruct @ atlas-cloud/fp8 |
$0.00 |
— |
— |
$0.000020 |
— |
$0.000020 |
| mistralai/codestral-2508 @ mistral/eu |
— |
— |
— |
$0.000018 |
— |
$0.000018 |
| nvidia2fnemotron-3.5-lightning23venice2ffp4 |
— |
— |
— |
$0.000018 |
— |
$0.000018 |
| stepfun/step-3.5-flash @ deepinfra/fp8 |
— |
— |
— |
$0.000017 |
— |
$0.000017 |
| google2fgemini-2.5-flash-lite-preview-09-202523google-vertex2fglobal |
— |
— |
— |
$0.000015 |
— |
$0.000015 |
| z-ai/glm-5.3-flash @ cloudflare |
— |
— |
— |
$0.000015 |
— |
$0.000015 |
| z-ai/glm-5.3-flash @ io-net/fp8 |
— |
— |
— |
$0.000015 |
— |
$0.000015 |
| z-ai/glm-5.3-flash @ parasail/fp8 |
— |
— |
— |
$0.000015 |
— |
$0.000015 |
| z-ai/glm-5.3-flash @ reka/fp8 |
— |
— |
— |
$0.000015 |
— |
$0.000015 |
| z-ai/glm-5.3-flash @ together |
— |
— |
— |
$0.000015 |
— |
$0.000015 |
| mistralai/mistral-small-3.2-24b-instruct @ mistral/eu |
— |
— |
— |
$0.000015 |
— |
$0.000015 |
| google2fgemini-3.1-flash-lite-preview23google-vertex2fglobal |
— |
— |
— |
$0.000013 |
— |
$0.000013 |
| mistralai/mistral-small-2603 @ mistral/us |
— |
— |
— |
$0.000013 |
— |
$0.000013 |
| z-ai/glm-5.3-flash @ venice |
— |
— |
— |
$0.000013 |
— |
$0.000013 |
| z-ai2fglm-5.123ambient2ffp8 |
— |
— |
— |
$0.000013 |
— |
$0.000013 |
| liquid/lfm-2-24b-a2b @ together |
$0.00 |
— |
— |
$0.000013 |
— |
$0.000013 |
| qwen/qwen3.5-35b-a3b @ darkbloom/fp4 |
— |
— |
— |
$0.000012 |
— |
$0.000012 |
| z-ai/glm-5.3-flash @ digitalocean |
— |
— |
— |
$0.000012 |
— |
$0.000012 |
| z-ai/glm-5.3-flash @ morph/fp8 |
$0.00 |
— |
— |
$0.000012 |
— |
$0.000012 |
| z-ai2fglm-523streamlake |
— |
— |
— |
$0.000012 |
— |
$0.000012 |
| meta-llama/llama-3.1-8b-instruct @ deepinfra/bf16 |
— |
— |
— |
$0.000011 |
— |
$0.000011 |
| qwen2fqwen3.6-27b23dekallm |
— |
— |
— |
$0.000011 |
— |
$0.000011 |
| inclusionai/ling-3.0-flash @ novita/fast |
— |
— |
— |
$0.000010 |
— |
$0.000010 |
| deepseek/deepseek-v4-flash-0731 @ deepinfra/fp8 |
— |
— |
— |
$0.000010 |
— |
$0.000010 |
| z-ai2fglm-4.723streamlake |
— |
— |
— |
$0.0000093 |
— |
$0.0000093 |
| z-ai/glm-4.7 @ streamlake/fp8 |
— |
— |
— |
$0.0000093 |
— |
$0.0000093 |
| thedrummer/rocinante-12b @ nextbit/bf16 |
— |
— |
$0.0000089 |
— |
— |
$0.0000089 |
| mistralai/ministral-14b-2512 @ mistral/eu |
— |
— |
— |
$0.0000088 |
— |
$0.0000088 |
| mistralai/ministral-14b-2512 @ mistral/zdr |
— |
— |
— |
$0.0000080 |
— |
$0.0000080 |
| google/gemini-3.1-flash-image-preview @ google-ai-studio |
— |
— |
— |
$0.0000080 |
— |
$0.0000080 |
| z-ai/glm-5.3-flash @ novita/fp8 |
— |
— |
— |
$0.0000073 |
— |
$0.0000073 |
| stepfun/step-3.7-flash @ ambient/fp8 |
$0.00 |
— |
— |
$0.0000072 |
— |
$0.0000072 |
| mistralai/ministral-8b-2512 @ mistral/eu |
— |
— |
— |
$0.0000066 |
— |
$0.0000066 |
| mistralai/ministral-8b-2512 @ mistral/zdr |
— |
— |
— |
$0.0000060 |
— |
$0.0000060 |
| mistralai/mistral-nemo @ mistral/eu |
— |
— |
— |
$0.0000058 |
— |
$0.0000058 |
| microsoft/phi-4 @ nextbit/int4 |
$0.00 |
— |
$0.0000053 |
— |
— |
$0.0000053 |
| z-ai/glm-5.3-flash @ siliconflow/fp8 |
— |
— |
— |
$0.0000049 |
— |
$0.0000049 |
| mistralai/ministral-3b-2512 @ mistral/eu |
— |
— |
— |
$0.0000044 |
— |
$0.0000044 |
| google/gemini-3.1-flash-image @ google-ai-studio |
— |
— |
— |
$0.0000040 |
— |
$0.0000040 |
| upstage/solar-pro4 @ upstage/bf16 |
$0.00 |
— |
— |
$0.0000034 |
— |
$0.0000034 |
| mistralai/voxtral-small-24b-2507 @ mistral/eu |
— |
— |
— |
$0.0000031 |
— |
$0.0000031 |
| mistralai/voxtral-small-24b-2507 @ mistral/zdr |
— |
— |
— |
$0.0000028 |
— |
$0.0000028 |
| mistralai/ministral-8b @ mistral/us |
— |
— |
— |
$0.0000022 |
— |
$0.0000022 |
| z-ai/glm-4.7-flash @ phala |
$0.00 |
— |
— |
$0.0000021 |
— |
$0.0000021 |
| deepseek/deepseek-v4-flash-0731 @ open-inference/fp8 |
$0.00 |
— |
— |
$0.0000018 |
— |
$0.0000018 |
| deepseek/deepseek-v4-flash @ dekallm |
$0.00 |
— |
— |
$0.0000012 |
— |
$0.0000012 |
| google2fgemini-3-pro-image-preview23google-vertex2fglobal2fflex |
— |
— |
— |
$0.00 |
— |
$0.00 |
| google/gemma-4-31b-it @ ambient |
— |
— |
$0.00 |
— |
— |
$0.00 |
| minimax/minimax-m3 @ atlas-cloud/fp8 |
— |
— |
— |
$0.00 |
— |
$0.00 |
| openai/gpt-5-image-mini @ openai |
— |
— |
— |
$0.00 |
— |
$0.00 |
| openai/gpt-5-image @ openai |
— |
— |
— |
$0.00 |
— |
$0.00 |
| perplexity/sonar-deep-research @ perplexity |
— |
— |
— |
$0.00 |
— |
$0.00 |
| perplexity/sonar-reasoning-pro @ perplexity |
— |
— |
— |
$0.00 |
— |
$0.00 |
| qwen/qwen3.5-397b-a17b @ gmicloud/fp8 |
— |
— |
— |
$0.00 |
— |
$0.00 |