Fornecedor
DeepInfra
147 Modelos · 237 Preços · Mais barato em 74 · Disponibilidade 100% · atualizado 2026-11-03 07:16 UTC
Sinais de confiança · SLA · transparência de versão · estabilidade de preços · degradação por quantização · resposta a incidentes · privacidade — medido pela sonda TKX (em ativação).
Sobre
DeepInfra is an AI inference provider that offers machine learning capabilities, serving 101 models through platforms like Hugging Face, official repositories, and OpenRouter. It specializes in deploying and managing machine learning models efficiently.
Resumo gerado por IA a partir de informações públicas — é seu? Reivindicar e editar
Modelos servidos
| Modelo | $ in /1M | $ out /1M | Mais barato | Router / Fonte | Evidência |
|---|---|---|---|---|---|
| Llama-3.2-3B-Instruct | $0.020 | $0.020 | ✓ | Pricebook (LiteLLM) ↗ | Tabela oficial |
| Mistral-Nemo-Instruct-2407 | $0.019 | $0.030 | ✓ | Pricebook (LiteLLM) ↗ | Tabela oficial |
| Meta-Llama-3.1-8B-Instruct-Turbo | $0.020 | $0.040 | ✓ | Pricebook (LiteLLM) ↗ | Tabela oficial |
| Llama-3.1-8B-Instruct | $0.020 | $0.050 | ✓ | HuggingFace Router ↗ | Medido por API |
| Meta-Llama-3.1-8B-Instruct | $0.030 | $0.050 | — | Pricebook (LiteLLM) ↗ | Tabela oficial |
| Meta-Llama-3-8B-Instruct | $0.030 | $0.060 | ✓ | Pricebook (LiteLLM) ↗ | Tabela oficial |
| gemma-4-E4B-it | $0.020 | $0.100 | ✓ | Pricebook (LiteLLM) ↗ | Tabela oficial |
| L3-8B-Lunaris-v1-Turbo | $0.040 | $0.050 | ✓ | Pricebook (LiteLLM) ↗ | Tabela oficial |
| Llama-3.2-11B-Vision-Instruct | $0.049 | $0.049 | ✓ | Pricebook (LiteLLM) ↗ | Tabela oficial |
| granite-4.2-3b | $0.030 | $0.120 | ✓ | HuggingFace Router ↗ | Medido por API |
| Qwen2.5-7B-Instruct | $0.040 | $0.100 | ✓ | Pricebook (LiteLLM) ↗ | Tabela oficial |
| Llama-Guard-3-8B | $0.055 | $0.055 | — | Pricebook (LiteLLM) ↗ | Tabela oficial |
| gpt-oss-20b | $0.030 | $0.140 | — | Pricebook (LiteLLM) ↗ | Tabela oficial |
| Mistral-Small-24B-Instruct-2501 | $0.050 | $0.080 | ✓ | Pricebook (LiteLLM) ↗ | Tabela oficial |
| gemma-3-4b-it | $0.050 | $0.100 | ✓ | Pricebook (LiteLLM) ↗ | Tabela oficial |
| NVIDIA-Nemotron-Nano-9B-v2 | $0.040 | $0.160 | ✓ | Pricebook (LiteLLM) ↗ | Tabela oficial |
| gpt-oss-120b (batch) | $0.037 | $0.170 | — | OpenRouter ↗ | Medido por API |
| gemma-3-12b-it | $0.050 | $0.150 | — | Pricebook (LiteLLM) ↗ | Tabela oficial |
| phi-4 | $0.070 | $0.140 | — | Pricebook (LiteLLM) ↗ | Tabela oficial |
| Nemotron-3-Nano-30B-A3B | $0.050 | $0.200 | — | Pricebook (LiteLLM) ↗ | Tabela oficial |
| Ling-3.0-flash | $0.060 | $0.180 | — | Pricebook (LiteLLM) ↗ | Tabela oficial |
| DeepSeek-V4-Flash-0731 | $0.060 | $0.180 | — | HuggingFace Router ↗ | Medido por API |
| Ling-3.0-flash-Fin | $0.060 | $0.180 | ✓ | HuggingFace Router ↗ | Medido por API |
| Ling-3.0-flash-VL | $0.060 | $0.180 | ✓ | HuggingFace Router ↗ | Medido por API |
| gemma-3-27b-it | $0.080 | $0.160 | ✓ | Pricebook (LiteLLM) ↗ | Tabela oficial |
| Mistral-Small-3.2-24B-Instruct-2506 | $0.075 | $0.200 | ✓ | Pricebook (LiteLLM) ↗ | Tabela oficial |
| granite-4.2-8b | $0.060 | $0.250 | — | HuggingFace Router ↗ | Medido por API |
| NVIDIA-Nemotron-3.5-Lightning | $0.080 | $0.200 | ✓ | Pricebook (LiteLLM) ↗ | Tabela oficial |
| DeepSeek-V4-Flash | $0.090 | $0.180 | — | Pricebook (LiteLLM) ↗ | Tabela oficial |
| Qwen3.5-9B | $0.100 | $0.150 | — | Pricebook (LiteLLM) ↗ | Tabela oficial |
| Qwen3-32B | $0.080 | $0.280 | — | Pricebook (LiteLLM) ↗ | Tabela oficial |
| gemma-4-26B-A4B-it | $0.070 | $0.340 | — | Pricebook (LiteLLM) ↗ | Tabela oficial |
| GLM-4.7-Flash | $0.060 | $0.400 | — | Pricebook (LiteLLM) ↗ | Tabela oficial |
| Qwen3-14B | $0.120 | $0.240 | — | Pricebook (LiteLLM) ↗ | Tabela oficial |
| Llama-4-Scout-17B-16E-Instruct | $0.100 | $0.300 | — | Pricebook (LiteLLM) ↗ | Tabela oficial |
| Step-3.5-Flash | $0.100 | $0.300 | ✓ | HuggingFace Router ↗ | Medido por API |
| gemma-4-31B-it-turbo | $0.090 | $0.340 | ✓ | Pricebook (LiteLLM) ↗ | Tabela oficial |
| Llama 3.3 70B Instruct | $0.100 | $0.320 | ✓ | OpenRouter ↗ | Medido por API |
| Llama-3.3-70B-Instruct-Turbo | $0.100 | $0.320 | — | Pricebook (LiteLLM) ↗ | Tabela oficial |
| NVIDIA-Nemotron-3-Super-120B-A12B | $0.085 | $0.400 | — | Pricebook (LiteLLM) ↗ | Tabela oficial |
| DeepSeek V4.1 Flash (batch) | $0.112 | $0.336 | — | OpenRouter ↗ | Medido por API |
| Llama-3.3-Nemotron-Super-49B-v1.5 | $0.100 | $0.400 | ✓ | Pricebook (LiteLLM) ↗ | Tabela oficial |
| MiMo-V2.5 | $0.140 | $0.280 | ✓ | HuggingFace Router ↗ | Medido por API |
| Seed-2.0-mini | $0.100 | $0.400 | ✓ | Pricebook (LiteLLM) ↗ | Tabela oficial |
| Llama-Guard-4-12B | $0.180 | $0.180 | ✓ | Pricebook (LiteLLM) ↗ | Tabela oficial |
| gemma-4-31B-it | $0.130 | $0.380 | — | Pricebook (LiteLLM) ↗ | Tabela oficial |
| Nemotron-Content-Safety-3.5 | $0.200 | $0.200 | ✓ | Pricebook (LiteLLM) ↗ | Tabela oficial |
| Qwen3-235B-A22B-Instruct-2507 | $0.090 | $0.550 | — | Pricebook (LiteLLM) ↗ | Tabela oficial |
| DeepSeek-V4.1-Flash-1017 | $0.140 | $0.420 | — | Pricebook (LiteLLM) ↗ | Tabela oficial |
| QwQ-32B | $0.150 | $0.400 | — | Pricebook (LiteLLM) ↗ | Tabela oficial |
| Qwen3-30B-A3B | $0.120 | $0.500 | — | Pricebook (LiteLLM) ↗ | Tabela oficial |
| Hy3 | $0.130 | $0.530 | ✓ | HuggingFace Router ↗ | Medido por API |
| GLM-5.3-Flash | $0.150 | $0.500 | — | HuggingFace Router ↗ | Medido por API |
| gpt-oss-120b-Turbo | $0.150 | $0.600 | ✓ | Pricebook (LiteLLM) ↗ | Tabela oficial |
| Qwen3-VL-30B-A3B-Instruct | $0.150 | $0.600 | ✓ | Pricebook (LiteLLM) ↗ | Tabela oficial |
| Qwen3-235B-A22B | $0.180 | $0.540 | ✓ | Pricebook (LiteLLM) ↗ | Tabela oficial |
| DeepSeek-R1-Distill-Qwen-32B | $0.270 | $0.270 | — | Pricebook (LiteLLM) ↗ | Tabela oficial |
| DeepSeek-V3.2 | $0.260 | $0.380 | — | Pricebook (LiteLLM) ↗ | Tabela oficial |
| Qwen2.5-VL-32B-Instruct | $0.200 | $0.600 | ✓ | Pricebook (LiteLLM) ↗ | Tabela oficial |
| DeepSeek-R1-Distill-Llama-70B | $0.200 | $0.600 | ✓ | Pricebook (LiteLLM) ↗ | Tabela oficial |
| Qwen3.6-35B-A3B | $0.100 | $0.950 | — | Pricebook (LiteLLM) ↗ | Tabela oficial |
| Qwen3-Next-80B-A3B-Instruct | $0.090 | $1.10 | ✓ | Pricebook (LiteLLM) ↗ | Tabela oficial |
| Llama-4-Maverick-17B-128E-Instruct-FP8 | $0.200 | $0.800 | — | Pricebook (LiteLLM) ↗ | Tabela oficial |
| Qwen3.5-35B-A3B | $0.140 | $1.00 | — | Pricebook (LiteLLM) ↗ | Tabela oficial |
| Qwen2.5-72B-Instruct | $0.360 | $0.400 | — | Pricebook (LiteLLM) ↗ | Tabela oficial |
| Qwen3-VL-235B-A22B-Instruct | $0.200 | $0.880 | ✓ | Pricebook (LiteLLM) ↗ | Tabela oficial |
| gpt-oss-120b-Ultra | $0.200 | $0.950 | ✓ | Pricebook (LiteLLM) ↗ | Tabela oficial |
| MiniMax M3 | $0.224 | $0.880 | ✓ | OpenRouter ↗ | Medido por API |
| gemma-4-31B-it-Ultra | $0.270 | $0.760 | ✓ | Pricebook (LiteLLM) ↗ | Tabela oficial |
| MythoMax-L2-13b | $0.400 | $0.400 | — | Pricebook (LiteLLM) ↗ | Tabela oficial |
| Meta-Llama-3.1-70B-Instruct | $0.400 | $0.400 | — | Pricebook (LiteLLM) ↗ | Tabela oficial |
| Meta-Llama-3.1-70B-Instruct-Turbo | $0.400 | $0.400 | ✓ | Pricebook (LiteLLM) ↗ | Tabela oficial |
| Mixtral-8x7B-Instruct-v0.1 | $0.400 | $0.400 | — | Pricebook (LiteLLM) ↗ | Tabela oficial |
| DeepSeek-V3-0324 | $0.240 | $0.900 | — | Pricebook (LiteLLM) ↗ | Tabela oficial |
| DeepSeek-V3.1 | $0.250 | $0.950 | — | Pricebook (LiteLLM) ↗ | Tabela oficial |
| MiniMax-M2.7 | $0.250 | $1.00 | — | Pricebook (LiteLLM) ↗ | Tabela oficial |
| Step-3.7-Flash | $0.200 | $1.15 | ✓ | Pricebook (LiteLLM) ↗ | Tabela oficial |
| DeepSeek-V3.1-Terminus | $0.270 | $0.950 | ✓ | HuggingFace Router ↗ | Medido por API |
| Qwen3-Next-80B-A3B-Thinking | $0.140 | $1.40 | — | Pricebook (LiteLLM) ↗ | Tabela oficial |
| DeepSeek-V3 | $0.320 | $0.890 | — | HuggingFace Router ↗ | Medido por API |
| Qwen3-Coder-480B-A35B-Instruct-Turbo | $0.300 | $1.00 | — | Pricebook (LiteLLM) ↗ | Tabela oficial |
| WizardLM-2-8x22B | $0.480 | $0.480 | ✓ | Pricebook (LiteLLM) ↗ | Tabela oficial |
| Muse-Glimmer-30B | $0.300 | $1.20 | ✓ | Pricebook (LiteLLM) ↗ | Tabela oficial |
| gemini-3.1-flash-lite | $0.250 | $1.50 | — | Pricebook (LiteLLM) ↗ | Tabela oficial |
| olmOCR-7B-0725-FP8 | $0.270 | $1.50 | ✓ | Pricebook (LiteLLM) ↗ | Tabela oficial |
| Qwen3.8 27B | $0.150 | $1.88 | — | OpenRouter ↗ | Medido por API |
| Llama-3.1-Nemotron-70B-Instruct | $0.600 | $0.600 | ✓ | Pricebook (LiteLLM) ↗ | Tabela oficial |
| Inkling-Small | $0.450 | $1.20 | ✓ | Pricebook (LiteLLM) ↗ | Tabela oficial |
| DeepSeek-V4-Flash-Vision-Exp | $0.440 | $1.32 | — | HuggingFace Router ↗ | Medido por API |
| L3.3-70B-Euryale-v2.3 | $0.650 | $0.750 | ✓ | Pricebook (LiteLLM) ↗ | Tabela oficial |
| Seed-1.8 | $0.250 | $2.00 | ✓ | Pricebook (LiteLLM) ↗ | Tabela oficial |
| GLM 5.2 | $0.450 | $1.44 | — | OpenRouter ↗ | Medido por API |
| Hermes-3-Llama-3.1-70B | $0.700 | $0.700 | — | Pricebook (LiteLLM) ↗ | Tabela oficial |
| Qwen3-Coder-480B-A35B-Instruct | $0.400 | $1.60 | — | Pricebook (LiteLLM) ↗ | Tabela oficial |
| GLM-4.5 | $0.400 | $1.60 | ✓ | Pricebook (LiteLLM) ↗ | Tabela oficial |
| GLM 4.6 | $0.400 | $1.60 | ✓ | OpenRouter ↗ | Medido por API |
| MiniMax-M2.7-Turbo | $0.380 | $1.70 | ✓ | Pricebook (LiteLLM) ↗ | Tabela oficial |
| GLM-4.7 | $0.400 | $1.75 | ✓ | Pricebook (LiteLLM) ↗ | Tabela oficial |
| Qwen3-235B-A22B-Thinking-2507 | $0.230 | $2.30 | — | HuggingFace Router ↗ | Medido por API |
| Qwen3.5-122B-A10B | $0.290 | $2.40 | — | Pricebook (LiteLLM) ↗ | Tabela oficial |
| Qwen3.5-27B | $0.260 | $2.60 | — | Pricebook (LiteLLM) ↗ | Tabela oficial |
| L3.1-70B-Euryale-v2.2 | $0.850 | $0.850 | ✓ | Pricebook (LiteLLM) ↗ | Tabela oficial |
| gemini-2.5-flash | $0.300 | $2.50 | — | Pricebook (LiteLLM) ↗ | Tabela oficial |
| Kimi-K2-Instruct | $0.500 | $2.00 | ✓ | Pricebook (LiteLLM) ↗ | Tabela oficial |
| Kimi-K2-Instruct-0905 | $0.500 | $2.00 | ✓ | Pricebook (LiteLLM) ↗ | Tabela oficial |
| Kimi-K2.5 | $0.450 | $2.25 | ✓ | Pricebook (LiteLLM) ↗ | Tabela oficial |
| DeepSeek-R1-0528 | $0.500 | $2.15 | — | Pricebook (LiteLLM) ↗ | Tabela oficial |
| NVIDIA-Nemotron-3-Ultra-550B-A55B | $0.500 | $2.20 | — | Pricebook (LiteLLM) ↗ | Tabela oficial |
| GLM-5 | $0.600 | $2.08 | — | Pricebook (LiteLLM) ↗ | Tabela oficial |
| Hermes-3-Llama-3.1-405B | $1.00 | $1.00 | ✓ | Pricebook (LiteLLM) ↗ | Tabela oficial |
| Qwen3.6-27B | $0.320 | $3.20 | — | Pricebook (LiteLLM) ↗ | Tabela oficial |
| GLM 5.3 (batch) | $0.563 | $2.50 | — | OpenRouter ↗ | Medido por API |
| Qwen3.5-397B-A17B | $0.450 | $3.00 | — | Pricebook (LiteLLM) ↗ | Tabela oficial |
| DeepSeek-R1 | $0.700 | $2.40 | — | Pricebook (LiteLLM) ↗ | Tabela oficial |
| Seed-2.0-code | $0.500 | $3.00 | ✓ | Pricebook (LiteLLM) ↗ | Tabela oficial |
| Seed-2.0-pro | $0.500 | $3.00 | ✓ | Pricebook (LiteLLM) ↗ | Tabela oficial |
| Hy4-preview | $0.834 | $2.50 | ✓ | HuggingFace Router ↗ | Medido por API |
| Kimi-K2.7-Code | $0.680 | $3.40 | — | Pricebook (LiteLLM) ↗ | Tabela oficial |
| Kimi-K2.6 | $0.750 | $3.50 | — | Pricebook (LiteLLM) ↗ | Tabela oficial |
| DeepSeek-R1-0528-Turbo | $1.00 | $3.00 | ✓ | Pricebook (LiteLLM) ↗ | Tabela oficial |
| DeepSeek-R1-Turbo | $1.00 | $3.00 | — | Pricebook (LiteLLM) ↗ | Tabela oficial |
| gemini-3.7-flash | $0.750 | $3.75 | — | Pricebook (LiteLLM) ↗ | Tabela oficial |
| MiMo-V2.5-Pro | $1.00 | $3.00 | — | Pricebook (LiteLLM) ↗ | Tabela oficial |
| DeepSeek-V4-Pro-0813 | $1.30 | $2.60 | — | HuggingFace Router ↗ | Medido por API |
| DeepSeek-V4-Pro | $1.30 | $2.60 | — | HuggingFace Router ↗ | Medido por API |
| GLM-5.1 | $1.05 | $3.50 | — | Pricebook (LiteLLM) ↗ | Tabela oficial |
| Inkling | $0.950 | $4.05 | ✓ | Pricebook (LiteLLM) ↗ | Tabela oficial |
| claude-haiku-4-5 | $1.00 | $5.00 | ✓ | Pricebook (LiteLLM) ↗ | Tabela oficial |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 | $1.00 | $5.00 | ✓ | HuggingFace Router ↗ | Medido por API |
| Qwen3-Max | $1.20 | $6.00 | — | Pricebook (LiteLLM) ↗ | Tabela oficial |
| Qwen3-Max-Thinking | $1.20 | $6.00 | ✓ | Pricebook (LiteLLM) ↗ | Tabela oficial |
| Qwen3.8-Max | $1.65 | $4.95 | ✓ | Pricebook (LiteLLM) ↗ | Tabela oficial |
| Qwen3.8-2.4T-A95B | $2.00 | $6.00 | ✓ | Pricebook (LiteLLM) ↗ | Tabela oficial |
| gemini-3.5-flash | $1.50 | $9.00 | — | Pricebook (LiteLLM) ↗ | Tabela oficial |
| gemini-2.5-pro | $1.25 | $10.00 | — | Pricebook (LiteLLM) ↗ | Tabela oficial |
| Qwen3.7-Max | $2.50 | $7.50 | — | Pricebook (LiteLLM) ↗ | Tabela oficial |
| claude-sonnet-5 | $2.00 | $10.00 | ✓ | Pricebook (LiteLLM) ↗ | Tabela oficial |
| gemini-3.1-pro | $2.00 | $12.00 | ✓ | Pricebook (LiteLLM) ↗ | Tabela oficial |
| Kimi K3 (batch) | $2.85 | $14.25 | — | OpenRouter ↗ | Medido por API |
| claude-sonnet-4-6 | $3.00 | $15.00 | ✓ | Pricebook (LiteLLM) ↗ | Tabela oficial |
| claude-3-7-sonnet-latest | $3.30 | $16.50 | ✓ | Pricebook (LiteLLM) ↗ | Tabela oficial |
| claude-4-sonnet | $3.30 | $16.50 | — | Pricebook (LiteLLM) ↗ | Tabela oficial |
| claude-opus-4-8 | $5.00 | $25.00 | ✓ | Pricebook (LiteLLM) ↗ | Tabela oficial |
| claude-opus-5 | $5.00 | $25.00 | ✓ | Pricebook (LiteLLM) ↗ | Tabela oficial |
| claude-opus-4-7 | $5.00 | $25.00 | ✓ | Pricebook (LiteLLM) ↗ | Tabela oficial |
| claude-fable-5 | $10.00 | $50.00 | ✓ | Pricebook (LiteLLM) ↗ | Tabela oficial |
| claude-4-opus | $16.50 | $82.50 | — | Pricebook (LiteLLM) ↗ | Tabela oficial |