Inference host prices: hf-router
Open-weight models served by inference hosts, with each host's price per 1M tokens (input, output). One row per model, host and quantization.
Sources for this list
- Last verified 2026-10-24T13:00:53+00:00 · https://router.huggingface.co/v1/models (community cross-check,
hf-inference-providers)
No first-party source is read for this model yet; this value is a community cross-check and can lag the provider.
| SKU | Name | Input / 1M | Output / 1M | Cached input | Context window | Last verified | Source |
|---|---|---|---|---|---|---|---|
| aisingapore/gemma-sea-lion-v4-27b-it/publicai/unknown | aisingapore/gemma-sea-lion-v4-27b-it via publicai | USD 0.20 | USD 0.40 | – | 131,072 | 2026-10-24 13:00 UTC | source cross-check |
| aisingapore/nemotron-sea-lion-v4.8-120b-a12b/publicai/unknown | aisingapore/nemotron-sea-lion-v4.8-120b-a12b via publicai | USD 0.50 | USD 2.00 | – | 262,144 | 2026-10-24 13:00 UTC | source cross-check |
| aisingapore/qwen-sea-lion-v4-32b-it/publicai/unknown | aisingapore/qwen-sea-lion-v4-32b-it via publicai | USD 0.25 | USD 0.50 | – | 32,000 | 2026-10-24 13:00 UTC | source cross-check |
| aisingapore/qwen-sea-lion-v4.5-27b-it/publicai/unknown | aisingapore/qwen-sea-lion-v4.5-27b-it via publicai | USD 0.20 | USD 0.40 | – | 262,144 | 2026-10-24 13:00 UTC | source cross-check |
| alpindale/wizardlm-2-8x22b/novita/unknown | alpindale/wizardlm-2-8x22b via Novita | USD 0.62 | USD 0.62 | – | 65,535 | 2026-10-24 13:00 UTC | source cross-check |
| deepseek/deepseek-chat-v3.1/deepinfra/unknown | deepseek/deepseek-chat-v3.1 via DeepInfra | USD 0.25 | USD 0.95 | – | 163,840 | 2026-10-24 13:00 UTC | source cross-check |
| deepseek/deepseek-r1-0528/deepinfra/unknown | deepseek/deepseek-r1-0528 via DeepInfra | USD 0.50 | USD 2.15 | – | 163,840 | 2026-10-24 13:00 UTC | source cross-check |
| deepseek/deepseek-r1-0528/novita/unknown | deepseek/deepseek-r1-0528 via Novita | USD 0.70 | USD 2.50 | – | 163,840 | 2026-10-24 13:00 UTC | source cross-check |
| deepseek/deepseek-r1-distill-llama-8b/nscale/unknown | deepseek/deepseek-r1-distill-llama-8b via nscale | USD 0.05 | USD 0.05 | – | 131,072 | 2026-10-24 13:00 UTC | source cross-check |
| deepseek/deepseek-r1-distill-qwen-14b/nscale/unknown | deepseek/deepseek-r1-distill-qwen-14b via nscale | USD 0.20 | USD 0.20 | – | 131,072 | 2026-10-24 13:00 UTC | source cross-check |
| deepseek/deepseek-r1-distill-qwen-7b/nscale/unknown | deepseek/deepseek-r1-distill-qwen-7b via nscale | USD 0.15 | USD 0.15 | – | 131,072 | 2026-10-24 13:00 UTC | source cross-check |
| deepseek/deepseek-r1/novita/unknown | deepseek/deepseek-r1 via Novita | USD 0.70 | USD 2.50 | – | 64,000 | 2026-10-24 13:00 UTC | source cross-check |
| deepseek/deepseek-v3-0324/deepinfra/unknown | deepseek/deepseek-v3-0324 via DeepInfra | USD 0.24 | USD 0.90 | – | 163,840 | 2026-10-24 13:00 UTC | source cross-check |
| deepseek/deepseek-v3.1-terminus/deepinfra/unknown | deepseek/deepseek-v3.1-terminus via DeepInfra | USD 0.27 | USD 0.95 | – | 163,840 | 2026-10-24 13:00 UTC | source cross-check |
| deepseek/deepseek-v3.2/deepinfra/unknown | deepseek/deepseek-v3.2 via DeepInfra | USD 0.26 | USD 0.38 | – | 16,384 | 2026-10-24 13:00 UTC | source cross-check |
| deepseek/deepseek-v3/deepinfra/unknown | deepseek/deepseek-v3 via DeepInfra | USD 0.32 | USD 0.89 | – | 163,840 | 2026-10-24 13:00 UTC | source cross-check |
| deepseek/deepseek-v4-flash-0731/baseten/unknown | deepseek/deepseek-v4-flash-0731 via BaseTen | USD 0.13 | USD 0.26 | – | 1,048,576 | 2026-10-24 13:00 UTC | source cross-check |
| deepseek/deepseek-v4-flash-0731/deepinfra/unknown | deepseek/deepseek-v4-flash-0731 via DeepInfra | USD 0.06 | USD 0.18 | – | 1,048,576 | 2026-10-24 13:00 UTC | source cross-check |
| deepseek/deepseek-v4-flash-0731/novita/unknown | deepseek/deepseek-v4-flash-0731 via Novita | USD 0.44 | USD 1.32 | – | 1,048,576 | 2026-10-24 13:00 UTC | source cross-check |
| deepseek/deepseek-v4-flash-vision-exp/deepinfra/unknown | deepseek/deepseek-v4-flash-vision-exp via DeepInfra | USD 0.44 | USD 1.32 | – | 1,048,576 | 2026-10-24 13:00 UTC | source cross-check |
| deepseek/deepseek-v4-flash/deepinfra/unknown | deepseek/deepseek-v4-flash via DeepInfra | USD 0.09 | USD 0.18 | – | 1,048,576 | 2026-10-24 13:00 UTC | source cross-check |
| deepseek/deepseek-v4-pro-0813/baseten/unknown | deepseek/deepseek-v4-pro-0813 via BaseTen | USD 1.32 | USD 3.96 | – | 1,048,576 | 2026-10-24 13:00 UTC | source cross-check |
| deepseek/deepseek-v4-pro-0813/deepinfra/unknown | deepseek/deepseek-v4-pro-0813 via DeepInfra | USD 1.30 | USD 2.60 | – | 1,048,576 | 2026-10-24 13:00 UTC | source cross-check |
| deepseek/deepseek-v4-pro-0813/novita/unknown | deepseek/deepseek-v4-pro-0813 via Novita | USD 1.32 | USD 3.96 | – | 1,048,576 | 2026-10-24 13:00 UTC | source cross-check |
| deepseek/deepseek-v4-pro/deepinfra/unknown | deepseek/deepseek-v4-pro via DeepInfra | USD 1.30 | USD 2.60 | – | 1,048,576 | 2026-10-24 13:00 UTC | source cross-check |
| deepseek/deepseek-v4-pro/novita/unknown | deepseek/deepseek-v4-pro via Novita | USD 1.60 | USD 3.20 | – | 1,048,576 | 2026-10-24 13:00 UTC | source cross-check |
| deepseek/deepseek-v4.1-flash-1017/baseten/unknown | deepseek/deepseek-v4.1-flash-1017 via BaseTen | USD 0.30 | USD 1.20 | – | 1,048,576 | 2026-10-24 13:00 UTC | source cross-check |
| deepseek/deepseek-v4.1-flash-1017/novita/unknown | deepseek/deepseek-v4.1-flash-1017 via Novita | USD 0.30 | USD 1.20 | – | 1,048,576 | 2026-10-24 13:00 UTC | source cross-check |
| deepseek/deepseek-v4.1-flash/baseten/unknown | deepseek/deepseek-v4.1-flash via BaseTen | USD 0.30 | USD 1.20 | – | 1,048,576 | 2026-10-24 13:00 UTC | source cross-check |
| deepseek/deepseek-v4.1-flash/deepinfra/unknown | deepseek/deepseek-v4.1-flash via DeepInfra | USD 0.20 | USD 0.60 | – | 1,048,576 | 2026-10-24 13:00 UTC | source cross-check |
| deepseek/deepseek-v4.1-flash/novita/unknown | deepseek/deepseek-v4.1-flash via Novita | USD 0.30 | USD 1.20 | – | 1,048,576 | 2026-10-24 13:00 UTC | source cross-check |
| google/gemma-3-12b-it/deepinfra/unknown | google/gemma-3-12b-it via DeepInfra | USD 0.05 | USD 0.15 | – | 131,072 | 2026-10-24 13:00 UTC | source cross-check |
| google/gemma-3-27b-it/deepinfra/unknown | google/gemma-3-27b-it via DeepInfra | USD 0.08 | USD 0.16 | – | 131,072 | 2026-10-24 13:00 UTC | source cross-check |
| google/gemma-3-4b-it/deepinfra/unknown | google/gemma-3-4b-it via DeepInfra | USD 0.05 | USD 0.10 | – | 131,072 | 2026-10-24 13:00 UTC | source cross-check |
| google/gemma-4-26b-a4b-it/deepinfra/unknown | google/gemma-4-26b-a4b-it via DeepInfra | USD 0.07 | USD 0.34 | – | 262,144 | 2026-10-24 13:00 UTC | source cross-check |
| google/gemma-4-26b-a4b-it/novita/unknown | google/gemma-4-26b-a4b-it via Novita | USD 0.13 | USD 0.40 | – | 262,144 | 2026-10-24 13:00 UTC | source cross-check |
| google/gemma-4-26b-a4b-it/scaleway/unknown | google/gemma-4-26b-a4b-it via scaleway | USD 0.285 | USD 0.57 | – | 2026-10-24 13:00 UTC | source cross-check | |
| google/gemma-4-31b-it/deepinfra/unknown | google/gemma-4-31b-it via DeepInfra | USD 0.20 | USD 0.40 | – | 262,144 | 2026-10-24 13:00 UTC | source cross-check |
| google/gemma-4-31b-it/novita/unknown | google/gemma-4-31b-it via Novita | USD 0.14 | USD 0.40 | – | 262,144 | 2026-10-24 13:00 UTC | source cross-check |
| ibm-granite/granite-4.2-30b/deepinfra/unknown | ibm-granite/granite-4.2-30b via DeepInfra | USD 0.16 | USD 0.65 | – | 131,072 | 2026-10-24 13:00 UTC | source cross-check |
| ibm-granite/granite-4.2-3b/deepinfra/unknown | ibm-granite/granite-4.2-3b via DeepInfra | USD 0.03 | USD 0.12 | – | 131,072 | 2026-10-24 13:00 UTC | source cross-check |
| ibm-granite/granite-4.2-8b/deepinfra/unknown | ibm-granite/granite-4.2-8b via DeepInfra | USD 0.06 | USD 0.25 | – | 131,072 | 2026-10-24 13:00 UTC | source cross-check |
| inclusionai/ling-3.0-flash-fin/deepinfra/unknown | inclusionai/ling-3.0-flash-fin via DeepInfra | USD 0.06 | USD 0.18 | – | 262,144 | 2026-10-24 13:00 UTC | source cross-check |
| inclusionai/ling-3.0-flash-fin/novita/unknown | inclusionai/ling-3.0-flash-fin via Novita | USD 0.075 | USD 0.22 | – | 262,144 | 2026-10-24 13:00 UTC | source cross-check |
| inclusionai/ling-3.0-flash-vl/novita/unknown | inclusionai/ling-3.0-flash-vl via Novita | USD 0.075 | USD 0.22 | – | 262,144 | 2026-10-24 13:00 UTC | source cross-check |
| inclusionai/ling-3.0-flash/novita/unknown | inclusionai/ling-3.0-flash via Novita | USD 0.06 | USD 0.18 | – | 262,144 | 2026-10-24 13:00 UTC | source cross-check |
| inclusionai/ling-3.1-flash/novita/unknown | inclusionai/ling-3.1-flash via Novita | USD 0.30 | USD 0.90 | – | 262,144 | 2026-10-24 13:00 UTC | source cross-check |
| meta-llama/llama-3.1-8b-instruct/deepinfra/unknown | meta-llama/llama-3.1-8b-instruct via DeepInfra | USD 0.02 | USD 0.05 | – | 131,072 | 2026-10-24 13:00 UTC | source cross-check |
| meta-llama/llama-3.1-8b-instruct/novita/unknown | meta-llama/llama-3.1-8b-instruct via Novita | USD 0.02 | USD 0.05 | – | 16,384 | 2026-10-24 13:00 UTC | source cross-check |
| meta-llama/llama-3.1-8b-instruct/nscale/unknown | meta-llama/llama-3.1-8b-instruct via nscale | USD 0.06 | USD 0.06 | – | 131,072 | 2026-10-24 13:00 UTC | source cross-check |
| meta-llama/llama-3.3-70b-instruct/novita/unknown | meta-llama/llama-3.3-70b-instruct via Novita | USD 0.135 | USD 0.40 | – | 12,288 | 2026-10-24 13:00 UTC | source cross-check |
| meta-llama/llama-3.3-70b-instruct/ovhcloud/unknown | meta-llama/llama-3.3-70b-instruct via ovhcloud | USD 0.74 | USD 0.74 | – | 131,072 | 2026-10-24 13:00 UTC | source cross-check |
| meta-llama/llama-3.3-70b-instruct/scaleway/unknown | meta-llama/llama-3.3-70b-instruct via scaleway | USD 1.026 | USD 1.026 | – | 2026-10-24 13:00 UTC | source cross-check | |
| meta-llama/llama-4-maverick-17b-128e-instruct-fp8/novita/unknown | meta-llama/llama-4-maverick-17b-128e-instruct-fp8 via Novita | USD 0.27 | USD 0.85 | – | 1,048,576 | 2026-10-24 13:00 UTC | source cross-check |
| meta-llama/llama-4-scout-17b-16e-instruct/deepinfra/unknown | meta-llama/llama-4-scout-17b-16e-instruct via DeepInfra | USD 0.10 | USD 0.30 | – | 327,680 | 2026-10-24 13:00 UTC | source cross-check |
| meta-llama/llama-4-scout-17b-16e-instruct/novita/unknown | meta-llama/llama-4-scout-17b-16e-instruct via Novita | USD 0.18 | USD 0.59 | – | 131,072 | 2026-10-24 13:00 UTC | source cross-check |
| meta-llama/llama-4-scout-17b-16e-instruct/nscale/unknown | meta-llama/llama-4-scout-17b-16e-instruct via nscale | USD 0.09 | USD 0.29 | – | 890,000 | 2026-10-24 13:00 UTC | source cross-check |
| meta-llama/llama-guard-4-12b/deepinfra/unknown | meta-llama/llama-guard-4-12b via DeepInfra | USD 0.18 | USD 0.18 | – | 163,840 | 2026-10-24 13:00 UTC | source cross-check |
| meta-models/muse-glimmer-30b/deepinfra/unknown | meta-models/muse-glimmer-30b via DeepInfra | USD 0.30 | USD 1.20 | – | 131,072 | 2026-10-24 13:00 UTC | source cross-check |
| meta-models/muse-spark-open-816b-a42b/baseten/unknown | meta-models/muse-spark-open-816b-a42b via BaseTen | USD 1.25 | USD 4.25 | – | 1,048,576 | 2026-10-24 13:00 UTC | source cross-check |
| microsoft/phi-4/deepinfra/unknown | microsoft/phi-4 via DeepInfra | USD 0.07 | USD 0.14 | – | 16,384 | 2026-10-24 13:00 UTC | source cross-check |
| minimax/minimax-m1-80k/novita/unknown | minimax/minimax-m1-80k via Novita | USD 0.55 | USD 2.20 | – | 1,000,000 | 2026-10-24 13:00 UTC | source cross-check |
| minimax/minimax-m2.5/novita/unknown | minimax/minimax-m2.5 via Novita | USD 0.30 | USD 1.20 | – | 204,800 | 2026-10-24 13:00 UTC | source cross-check |
| minimax/minimax-m2.7/novita/unknown | minimax/minimax-m2.7 via Novita | USD 0.30 | USD 1.20 | – | 204,800 | 2026-10-24 13:00 UTC | source cross-check |
| minimax/minimax-m3/novita/unknown | minimax/minimax-m3 via Novita | USD 0.30 | USD 1.20 | – | 1,000,000 | 2026-10-24 13:00 UTC | source cross-check |
| moonshotai/kimi-k2-instruct-0905/novita/unknown | moonshotai/kimi-k2-instruct-0905 via Novita | USD 0.60 | USD 2.50 | – | 262,144 | 2026-10-24 13:00 UTC | source cross-check |
| moonshotai/kimi-k2-instruct/novita/unknown | moonshotai/kimi-k2-instruct via Novita | USD 0.57 | USD 2.30 | – | 131,072 | 2026-10-24 13:00 UTC | source cross-check |
| moonshotai/kimi-k2.5/deepinfra/unknown | moonshotai/kimi-k2.5 via DeepInfra | USD 0.45 | USD 2.25 | – | 262,144 | 2026-10-24 13:00 UTC | source cross-check |
| moonshotai/kimi-k2.5/novita/unknown | moonshotai/kimi-k2.5 via Novita | USD 0.60 | USD 3.00 | – | 262,144 | 2026-10-24 13:00 UTC | source cross-check |
| moonshotai/kimi-k2.6/deepinfra/unknown | moonshotai/kimi-k2.6 via DeepInfra | USD 0.75 | USD 3.50 | – | 262,144 | 2026-10-24 13:00 UTC | source cross-check |
| moonshotai/kimi-k2.6/novita/unknown | moonshotai/kimi-k2.6 via Novita | USD 0.80 | USD 3.40 | – | 262,144 | 2026-10-24 13:00 UTC | source cross-check |
| moonshotai/kimi-k2.7-code/deepinfra/unknown | moonshotai/kimi-k2.7-code via DeepInfra | USD 0.68 | USD 3.40 | – | 262,144 | 2026-10-24 13:00 UTC | source cross-check |
| moonshotai/kimi-k2.7-code/novita/unknown | moonshotai/kimi-k2.7-code via Novita | USD 0.95 | USD 4.00 | – | 262,144 | 2026-10-24 13:00 UTC | source cross-check |
| moonshotai/kimi-k3/baseten/unknown | moonshotai/kimi-k3 via BaseTen | USD 3.00 | USD 15.00 | – | 1,048,576 | 2026-10-24 13:00 UTC | source cross-check |
| moonshotai/kimi-k3/deepinfra/unknown | moonshotai/kimi-k3 via DeepInfra | USD 2.85 | USD 14.25 | – | 1,048,576 | 2026-10-24 13:00 UTC | source cross-check |
| nousresearch/hermes-3-llama-3.1-70b/deepinfra/unknown | nousresearch/hermes-3-llama-3.1-70b via DeepInfra | USD 0.70 | USD 0.70 | – | 131,072 | 2026-10-24 13:00 UTC | source cross-check |
| nvidia/nvidia-nemotron-3-ultra-550b-a55b-bf16/deepinfra/unknown | nvidia/nvidia-nemotron-3-ultra-550b-a55b-bf16 via DeepInfra | USD 1.00 | USD 5.00 | – | 262,144 | 2026-10-24 13:00 UTC | source cross-check |
| nvidia/nvidia-nemotron-3.5-super-vl-120b-a12b-nvfp4/baseten/unknown | nvidia/nvidia-nemotron-3.5-super-vl-120b-a12b-nvfp4 via BaseTen | USD 0.20 | USD 0.50 | – | 1,048,576 | 2026-10-24 13:00 UTC | source cross-check |
| openai/gpt-oss-120b/baseten/unknown | openai/gpt-oss-120b via BaseTen | USD 0.10 | USD 0.50 | – | 128,072 | 2026-10-24 13:00 UTC | source cross-check |
| openai/gpt-oss-120b/cerebras/unknown | openai/gpt-oss-120b via Cerebras | USD 0.35 | USD 0.75 | – | 131,072 | 2026-10-24 13:00 UTC | source cross-check |
| openai/gpt-oss-120b/deepinfra/unknown | openai/gpt-oss-120b via DeepInfra | USD 0.037 | USD 0.17 | – | 131,072 | 2026-10-24 13:00 UTC | source cross-check |
| openai/gpt-oss-120b/groq/unknown | openai/gpt-oss-120b via Groq | USD 0.15 | USD 0.75 | – | 131,072 | 2026-10-24 13:00 UTC | source cross-check |
| openai/gpt-oss-120b/novita/unknown | openai/gpt-oss-120b via Novita | USD 0.05 | USD 0.25 | – | 131,072 | 2026-10-24 13:00 UTC | source cross-check |
| openai/gpt-oss-120b/nscale/unknown | openai/gpt-oss-120b via nscale | USD 0.10 | USD 0.40 | – | 131,072 | 2026-10-24 13:00 UTC | source cross-check |
| openai/gpt-oss-120b/ovhcloud/unknown | openai/gpt-oss-120b via ovhcloud | USD 0.09 | USD 0.47 | – | 131,072 | 2026-10-24 13:00 UTC | source cross-check |
| openai/gpt-oss-120b/scaleway/unknown | openai/gpt-oss-120b via scaleway | USD 0.171 | USD 0.684 | – | 2026-10-24 13:00 UTC | source cross-check | |
| openai/gpt-oss-20b/deepinfra/unknown | openai/gpt-oss-20b via DeepInfra | USD 0.03 | USD 0.14 | – | 131,072 | 2026-10-24 13:00 UTC | source cross-check |
| openai/gpt-oss-20b/groq/unknown | openai/gpt-oss-20b via Groq | USD 0.10 | USD 0.50 | – | 131,072 | 2026-10-24 13:00 UTC | source cross-check |
| openai/gpt-oss-20b/nscale/unknown | openai/gpt-oss-20b via nscale | USD 0.05 | USD 0.20 | – | 131,072 | 2026-10-24 13:00 UTC | source cross-check |
| openai/gpt-oss-20b/ovhcloud/unknown | openai/gpt-oss-20b via ovhcloud | USD 0.05 | USD 0.18 | – | 131,072 | 2026-10-24 13:00 UTC | source cross-check |
| qwen/qwen2.5-72b-instruct/deepinfra/unknown | qwen/qwen2.5-72b-instruct via DeepInfra | USD 0.36 | USD 0.40 | – | 32,768 | 2026-10-24 13:00 UTC | source cross-check |
| qwen/qwen2.5-coder-32b-instruct/nscale/unknown | qwen/qwen2.5-coder-32b-instruct via nscale | USD 0.06 | USD 0.20 | – | 131,072 | 2026-10-24 13:00 UTC | source cross-check |
| qwen/qwen2.5-coder-3b-instruct/nscale/unknown | qwen/qwen2.5-coder-3b-instruct via nscale | USD 0.01 | USD 0.03 | – | 32,768 | 2026-10-24 13:00 UTC | source cross-check |
| qwen/qwen2.5-coder-7b-instruct/nscale/unknown | qwen/qwen2.5-coder-7b-instruct via nscale | USD 0.01 | USD 0.03 | – | 131,072 | 2026-10-24 13:00 UTC | source cross-check |
| qwen/qwen2.5-vl-72b-instruct/ovhcloud/unknown | qwen/qwen2.5-vl-72b-instruct via ovhcloud | USD 1.01 | USD 1.01 | – | 32,768 | 2026-10-24 13:00 UTC | source cross-check |
| qwen/qwen3-14b/deepinfra/unknown | qwen/qwen3-14b via DeepInfra | USD 0.12 | USD 0.24 | – | 40,960 | 2026-10-24 13:00 UTC | source cross-check |
| qwen/qwen3-14b/nscale/unknown | qwen/qwen3-14b via nscale | USD 0.07 | USD 0.20 | – | 40,960 | 2026-10-24 13:00 UTC | source cross-check |
| qwen/qwen3-235b-a22b-instruct-2507/deepinfra/unknown | qwen/qwen3-235b-a22b-instruct-2507 via DeepInfra | USD 0.09 | USD 0.55 | – | 262,144 | 2026-10-24 13:00 UTC | source cross-check |
| qwen/qwen3-235b-a22b-instruct-2507/nscale/unknown | qwen/qwen3-235b-a22b-instruct-2507 via nscale | USD 0.20 | USD 0.60 | – | 32,768 | 2026-10-24 13:00 UTC | source cross-check |
| qwen/qwen3-235b-a22b-instruct-2507/scaleway/unknown | qwen/qwen3-235b-a22b-instruct-2507 via scaleway | USD 0.855 | USD 2.565 | – | 2026-10-24 13:00 UTC | source cross-check | |
| qwen/qwen3-235b-a22b-thinking-2507/deepinfra/unknown | qwen/qwen3-235b-a22b-thinking-2507 via DeepInfra | USD 0.23 | USD 2.30 | – | 262,144 | 2026-10-24 13:00 UTC | source cross-check |
| qwen/qwen3-235b-a22b/nscale/unknown | qwen/qwen3-235b-a22b via nscale | USD 0.20 | USD 0.60 | – | 32,000 | 2026-10-24 13:00 UTC | source cross-check |
| qwen/qwen3-30b-a3b/deepinfra/unknown | qwen/qwen3-30b-a3b via DeepInfra | USD 0.12 | USD 0.50 | – | 40,960 | 2026-10-24 13:00 UTC | source cross-check |
| qwen/qwen3-32b/deepinfra/unknown | qwen/qwen3-32b via DeepInfra | USD 0.08 | USD 0.28 | – | 40,960 | 2026-10-24 13:00 UTC | source cross-check |
| qwen/qwen3-32b/nscale/unknown | qwen/qwen3-32b via nscale | USD 0.08 | USD 0.25 | – | 40,960 | 2026-10-24 13:00 UTC | source cross-check |
| qwen/qwen3-4b-instruct-2507/nscale/unknown | qwen/qwen3-4b-instruct-2507 via nscale | USD 0.01 | USD 0.03 | – | 262,144 | 2026-10-24 13:00 UTC | source cross-check |
| qwen/qwen3-4b-thinking-2507/nscale/unknown | qwen/qwen3-4b-thinking-2507 via nscale | USD 0.01 | USD 0.03 | – | 262,144 | 2026-10-24 13:00 UTC | source cross-check |
| qwen/qwen3-8b/nscale/unknown | qwen/qwen3-8b via nscale | USD 0.07 | USD 0.18 | – | 40,960 | 2026-10-24 13:00 UTC | source cross-check |
| qwen/qwen3-next-80b-a3b-instruct/deepinfra/unknown | qwen/qwen3-next-80b-a3b-instruct via DeepInfra | USD 0.09 | USD 1.10 | – | 262,144 | 2026-10-24 13:00 UTC | source cross-check |
| qwen/qwen3-vl-235b-a22b-instruct/deepinfra/unknown | qwen/qwen3-vl-235b-a22b-instruct via DeepInfra | USD 0.20 | USD 0.88 | – | 262,144 | 2026-10-24 13:00 UTC | source cross-check |
| qwen/qwen3-vl-30b-a3b-instruct/deepinfra/unknown | qwen/qwen3-vl-30b-a3b-instruct via DeepInfra | USD 0.15 | USD 0.60 | – | 262,144 | 2026-10-24 13:00 UTC | source cross-check |
| qwen/qwen3-vl-30b-a3b-instruct/novita/unknown | qwen/qwen3-vl-30b-a3b-instruct via Novita | USD 0.20 | USD 0.70 | – | 131,072 | 2026-10-24 13:00 UTC | source cross-check |
| qwen/qwen3.5-122b-a10b/deepinfra/unknown | qwen/qwen3.5-122b-a10b via DeepInfra | USD 0.29 | USD 2.40 | – | 262,144 | 2026-10-24 13:00 UTC | source cross-check |
| qwen/qwen3.5-122b-a10b/novita/unknown | qwen/qwen3.5-122b-a10b via Novita | USD 0.40 | USD 3.20 | – | 262,144 | 2026-10-24 13:00 UTC | source cross-check |
| qwen/qwen3.5-27b/deepinfra/unknown | qwen/qwen3.5-27b via DeepInfra | USD 0.26 | USD 2.60 | – | 262,144 | 2026-10-24 13:00 UTC | source cross-check |
| qwen/qwen3.5-27b/novita/unknown | qwen/qwen3.5-27b via Novita | USD 0.30 | USD 2.40 | – | 262,144 | 2026-10-24 13:00 UTC | source cross-check |
| qwen/qwen3.5-35b-a3b/deepinfra/unknown | qwen/qwen3.5-35b-a3b via DeepInfra | USD 0.14 | USD 1.00 | – | 262,144 | 2026-10-24 13:00 UTC | source cross-check |
| qwen/qwen3.5-35b-a3b/novita/unknown | qwen/qwen3.5-35b-a3b via Novita | USD 0.25 | USD 2.00 | – | 262,144 | 2026-10-24 13:00 UTC | source cross-check |
| qwen/qwen3.5-397b-a17b/deepinfra/unknown | qwen/qwen3.5-397b-a17b via DeepInfra | USD 0.45 | USD 3.00 | – | 262,144 | 2026-10-24 13:00 UTC | source cross-check |
| qwen/qwen3.5-397b-a17b/novita/unknown | qwen/qwen3.5-397b-a17b via Novita | USD 0.60 | USD 3.60 | – | 262,144 | 2026-10-24 13:00 UTC | source cross-check |
| qwen/qwen3.5-397b-a17b/ovhcloud/unknown | qwen/qwen3.5-397b-a17b via ovhcloud | USD 0.71 | USD 4.25 | – | 262,144 | 2026-10-24 13:00 UTC | source cross-check |
| qwen/qwen3.5-397b-a17b/scaleway/unknown | qwen/qwen3.5-397b-a17b via scaleway | USD 0.684 | USD 4.104 | – | 2026-10-24 13:00 UTC | source cross-check | |
| qwen/qwen3.5-9b/deepinfra/unknown | qwen/qwen3.5-9b via DeepInfra | USD 0.10 | USD 0.15 | – | 262,144 | 2026-10-24 13:00 UTC | source cross-check |
| qwen/qwen3.5-9b/ovhcloud/unknown | qwen/qwen3.5-9b via ovhcloud | USD 0.12 | USD 0.18 | – | 262,144 | 2026-10-24 13:00 UTC | source cross-check |
| qwen/qwen3.6-27b/deepinfra/unknown | qwen/qwen3.6-27b via DeepInfra | USD 0.32 | USD 3.20 | – | 262,144 | 2026-10-24 13:00 UTC | source cross-check |
| qwen/qwen3.6-27b/ovhcloud/unknown | qwen/qwen3.6-27b via ovhcloud | USD 0.47 | USD 3.19 | – | 262,144 | 2026-10-24 13:00 UTC | source cross-check |
| qwen/qwen3.6-35b-a3b/deepinfra/unknown | qwen/qwen3.6-35b-a3b via DeepInfra | USD 0.10 | USD 0.95 | – | 262,144 | 2026-10-24 13:00 UTC | source cross-check |
| qwen/qwen3.6-35b-a3b/scaleway/unknown | qwen/qwen3.6-35b-a3b via scaleway | USD 0.285 | USD 1.71 | – | 2026-10-24 13:00 UTC | source cross-check | |
| qwen/qwen3.8-2.4t-a95b/deepinfra/unknown | qwen/qwen3.8-2.4t-a95b via DeepInfra | USD 2.00 | USD 6.00 | – | 262,144 | 2026-10-24 13:00 UTC | source cross-check |
| qwen/qwen3.8-2.4t-a95b/novita/unknown | qwen/qwen3.8-2.4t-a95b via Novita | USD 2.00 | USD 6.00 | – | 1,000,000 | 2026-10-24 13:00 UTC | source cross-check |
| qwen/qwen3.8-27b/cerebras/unknown | qwen/qwen3.8-27b via Cerebras | USD 0.99 | USD 1.49 | – | 65,536 | 2026-10-24 13:00 UTC | source cross-check |
| qwen/qwen3.8-27b/deepinfra/unknown | qwen/qwen3.8-27b via DeepInfra | USD 0.20 | USD 2.50 | – | 262,144 | 2026-10-24 13:00 UTC | source cross-check |
| qwen/qwen3.8-27b/novita/unknown | qwen/qwen3.8-27b via Novita | USD 0.42 | USD 3.00 | – | 1,000,000 | 2026-10-24 13:00 UTC | source cross-check |
| qwen/qwen3.8-27b/ovhcloud/unknown | qwen/qwen3.8-27b via ovhcloud | USD 0.47 | USD 3.19 | – | 262,144 | 2026-10-24 13:00 UTC | source cross-check |
| reflection/beam-1.0-501b-a23b/baseten/unknown | reflection/beam-1.0-501b-a23b via BaseTen | USD 0.40 | USD 1.20 | – | 1,048,576 | 2026-10-24 13:00 UTC | source cross-check |
| sao10k/l3-8b-stheno-v3.2/novita/unknown | sao10k/l3-8b-stheno-v3.2 via Novita | USD 0.05 | USD 0.05 | – | 8,192 | 2026-10-24 13:00 UTC | source cross-check |
| speakleash/bielik-11b-v3.0-instruct/publicai/unknown | speakleash/bielik-11b-v3.0-instruct via publicai | USD 0.40 | USD 0.40 | – | 2026-10-24 13:00 UTC | source cross-check | |
| stepfun/step-3.7-flash/deepinfra/unknown | stepfun/step-3.7-flash via DeepInfra | USD 0.20 | USD 1.15 | – | 262,144 | 2026-10-24 13:00 UTC | source cross-check |
| swiss-ai/apertus-70b-instruct-2509/publicai/unknown | swiss-ai/apertus-70b-instruct-2509 via publicai | USD 0.82 | USD 2.92 | – | 2026-10-24 13:00 UTC | source cross-check | |
| swiss-ai/apertus-8b-instruct-2509/publicai/unknown | swiss-ai/apertus-8b-instruct-2509 via publicai | USD 0.10 | USD 0.20 | – | 2026-10-24 13:00 UTC | source cross-check | |
| swiss-ai/apertus-v1.5-70b/publicai/unknown | swiss-ai/apertus-v1.5-70b via publicai | USD 0.82 | USD 2.92 | – | 2026-10-24 13:00 UTC | source cross-check | |
| tencent/hy3/deepinfra/unknown | tencent/hy3 via DeepInfra | USD 0.13 | USD 0.53 | – | 262,144 | 2026-10-24 13:00 UTC | source cross-check |
| tencent/hy4-preview/deepinfra/unknown | tencent/hy4-preview via DeepInfra | USD 0.834 | USD 2.501 | – | 1,048,576 | 2026-10-24 13:00 UTC | source cross-check |
| tencent/hy4-preview/novita/unknown | tencent/hy4-preview via Novita | USD 0.834 | USD 2.501 | – | 1,000,000 | 2026-10-24 13:00 UTC | source cross-check |
| thinkingmachines/inkling-small/deepinfra/unknown | thinkingmachines/inkling-small via DeepInfra | USD 0.45 | USD 1.20 | – | 524,288 | 2026-10-24 13:00 UTC | source cross-check |
| thinkingmachines/inkling/deepinfra/unknown | thinkingmachines/inkling via DeepInfra | USD 0.95 | USD 4.05 | – | 524,288 | 2026-10-24 13:00 UTC | source cross-check |
| xiaomi/mimo-v2.5-pro/deepinfra/unknown | xiaomi/mimo-v2.5-pro via DeepInfra | USD 1.00 | USD 3.00 | – | 1,048,576 | 2026-10-24 13:00 UTC | source cross-check |
| xiaomi/mimo-v2.5/deepinfra/unknown | xiaomi/mimo-v2.5 via DeepInfra | USD 0.14 | USD 0.28 | – | 262,144 | 2026-10-24 13:00 UTC | source cross-check |
| xiaomi/mimo-v2.6-flash-rl/novita/unknown | xiaomi/mimo-v2.6-flash-rl via Novita | USD 0.14 | USD 0.28 | – | 1,048,576 | 2026-10-24 13:00 UTC | source cross-check |
| xiaomi/mimo-v2.6-pro-rl/novita/unknown | xiaomi/mimo-v2.6-pro-rl via Novita | USD 0.435 | USD 0.87 | – | 1,048,576 | 2026-10-24 13:00 UTC | source cross-check |
| z-ai/autoglm-phone-9b-multilingual/novita/unknown | z-ai/autoglm-phone-9b-multilingual via Novita | USD 0.035 | USD 0.138 | – | 65,536 | 2026-10-24 13:00 UTC | source cross-check |
| z-ai/glm-4.5-air/novita/unknown | z-ai/glm-4.5-air via Novita | USD 0.13 | USD 0.85 | – | 131,072 | 2026-10-24 13:00 UTC | source cross-check |
| z-ai/glm-4.5v/novita/unknown | z-ai/glm-4.5v via Novita | USD 0.60 | USD 1.80 | – | 65,536 | 2026-10-24 13:00 UTC | source cross-check |
| z-ai/glm-4.6/deepinfra/unknown | z-ai/glm-4.6 via DeepInfra | USD 0.50 | USD 2.00 | – | 202,752 | 2026-10-24 13:00 UTC | source cross-check |
| z-ai/glm-4.6/novita/unknown | z-ai/glm-4.6 via Novita | USD 0.55 | USD 2.20 | – | 204,800 | 2026-10-24 13:00 UTC | source cross-check |
| z-ai/glm-4.6v-flash/novita/unknown | z-ai/glm-4.6v-flash via Novita | USD 0.30 | USD 0.90 | – | 131,072 | 2026-10-24 13:00 UTC | source cross-check |
| z-ai/glm-4.7-flash/deepinfra/unknown | z-ai/glm-4.7-flash via DeepInfra | USD 0.06 | USD 0.40 | – | 202,752 | 2026-10-24 13:00 UTC | source cross-check |
| z-ai/glm-4.7-flash/novita/unknown | z-ai/glm-4.7-flash via Novita | USD 0.07 | USD 0.40 | – | 200,000 | 2026-10-24 13:00 UTC | source cross-check |
| z-ai/glm-4.7/deepinfra/unknown | z-ai/glm-4.7 via DeepInfra | USD 0.40 | USD 1.75 | – | 202,752 | 2026-10-24 13:00 UTC | source cross-check |
| z-ai/glm-4.7/novita/unknown | z-ai/glm-4.7 via Novita | USD 0.60 | USD 2.20 | – | 204,800 | 2026-10-24 13:00 UTC | source cross-check |
| z-ai/glm-5.1/deepinfra/unknown | z-ai/glm-5.1 via DeepInfra | USD 1.05 | USD 3.50 | – | 202,752 | 2026-10-24 13:00 UTC | source cross-check |
| z-ai/glm-5.2/baseten/unknown | z-ai/glm-5.2 via BaseTen | USD 1.40 | USD 4.40 | – | 1,048,576 | 2026-10-24 13:00 UTC | source cross-check |
| z-ai/glm-5.2/deepinfra/unknown | z-ai/glm-5.2 via DeepInfra | USD 0.75 | USD 2.40 | – | 1,048,576 | 2026-10-24 13:00 UTC | source cross-check |
| z-ai/glm-5.2/novita/unknown | z-ai/glm-5.2 via Novita | USD 1.40 | USD 4.40 | – | 1,048,576 | 2026-10-24 13:00 UTC | source cross-check |
| z-ai/glm-5.2/scaleway/unknown | z-ai/glm-5.2 via scaleway | USD 2.052 | USD 6.27 | – | 2026-10-24 13:00 UTC | source cross-check | |
| z-ai/glm-5.3-flash/baseten/unknown | z-ai/glm-5.3-flash via BaseTen | USD 0.15 | USD 0.50 | – | 1,048,576 | 2026-10-24 13:00 UTC | source cross-check |
| z-ai/glm-5.3-flash/deepinfra/unknown | z-ai/glm-5.3-flash via DeepInfra | USD 0.15 | USD 0.50 | – | 1,048,576 | 2026-10-24 13:00 UTC | source cross-check |
| z-ai/glm-5.3-flash/novita/unknown | z-ai/glm-5.3-flash via Novita | USD 0.15 | USD 0.50 | – | 1,048,576 | 2026-10-24 13:00 UTC | source cross-check |
| z-ai/glm-5.3/baseten/unknown | z-ai/glm-5.3 via BaseTen | USD 1.40 | USD 4.40 | – | 1,048,576 | 2026-10-24 13:00 UTC | source cross-check |
| z-ai/glm-5.3/deepinfra/unknown | z-ai/glm-5.3 via DeepInfra | USD 0.90 | USD 4.00 | – | 1,048,576 | 2026-10-24 13:00 UTC | source cross-check |
| z-ai/glm-5.3/novita/unknown | z-ai/glm-5.3 via Novita | USD 1.40 | USD 4.40 | – | 1,048,576 | 2026-10-24 13:00 UTC | source cross-check |
| z-ai/glm-5/deepinfra/unknown | z-ai/glm-5 via DeepInfra | USD 0.60 | USD 2.08 | – | 202,752 | 2026-10-24 13:00 UTC | source cross-check |
| z-ai/glm-5/novita/unknown | z-ai/glm-5 via Novita | USD 1.00 | USD 3.20 | – | 202,800 | 2026-10-24 13:00 UTC | source cross-check |