DeepInfra logo

DeepInfra

Agregador de Modelos

DeepInfra is a serverless inference marketplace running open models (Llama, Qwen, DeepSeek, GLM, Kimi and more) on managed GPUs, billed per token with no idle cost — among the cheapest hosted open-model APIs.

Modelos
165
Caché de Prompts
Descuento por Lotes
Tool Calling
Modelo165
anthropic/claude-fable-5€8.58€42.91
anthropic/claude-haiku-4-5€0.8582€4.29
anthropic/claude-opus-4-7€4.29€21.46
anthropic/claude-opus-4-8€4.29€21.46
anthropic/claude-opus-5€4.29€21.46
anthropic/claude-sonnet-4-6€2.57€12.87
anthropic/claude-sonnet-5€2.57€12.87
Audio8/Audio8-TTS-Preview-0.6b€4.29/1M caracteres
BAAI/bge-base-en-v1.5€0.004291
BAAI/bge-en-icl€0.008582
BAAI/bge-large-en-v1.5€0.008582
BAAI/bge-m3€0.008582
BAAI/bge-m3-multi€0.008582
BAAI/bge-m3-multi-8k€0.008582
bosonai/HiggsAudioV2.5€17.16/1M caracteres
ByteDance/Seed-1.8€0.2146€1.72
ByteDance/Seed-2.0-code€0.4291€2.57
ByteDance/Seed-2.0-mini€0.0858€0.3433
ByteDance/Seed-2.0-pro€0.4291€2.57
ByteDance/Seedance-1.5-Pro€1.03
ByteDance/Seedance-2.0€4.03
canopylabs/orpheus-3b-0.1-ft€6.01/1M caracteres
deepseek-ai/DeepSeek-R1-0528DeepSeek€0.4291€1.85
deepseek-ai/DeepSeek-V3DeepSeek€0.2746€0.7638
deepseek-ai/DeepSeek-V3-0324DeepSeek€0.206€0.7724
deepseek-ai/DeepSeek-V3.1DeepSeek€0.2146€0.8153
deepseek-ai/DeepSeek-V3.1-TerminusDeepSeek€0.2317€0.8153
deepseek-ai/DeepSeek-V3.2DeepSeek€0.2231€0.3261
deepseek-ai/DeepSeek-V4-FlashDeepSeek€0.0772€0.1545
deepseek-ai/DeepSeek-V4-Flash-0731DeepSeek€0.0515€0.1545
deepseek-ai/DeepSeek-V4-Flash-Vision-ExpDeepSeek€0.3776€1.13
deepseek-ai/DeepSeek-V4-ProDeepSeek€1.12€2.23
deepseek-ai/DeepSeek-V4-Pro-0813DeepSeek€1.12€2.23
deepseek-ai/DeepSeek-V4.1-FlashDeepSeek€0.2575€1.03
google/embeddinggemma-300mGemma€0.001716
google/gemini-2.5-flash€0.2575€2.15
google/gemini-2.5-pro€1.07€8.58
google/gemini-3-pro-image€102.99
google/gemini-3.1-flash-lite€0.2146€1.29
google/gemini-3.1-pro€1.72€10.3
google/gemini-3.5-flash€1.29€7.72
google/gemini-3.7-flash€0.6437€3.22
google/gemma-3-12b-itGemma€0.0429€0.1287
google/gemma-3-27b-itGemma€0.0687€0.1373
google/gemma-3-4b-itGemma€0.0429€0.0858
google/gemma-4-26B-A4B-itGemma€0.0601€0.2918
google/gemma-4-31B-itGemma€0.1116€0.3261
google/gemma-4-31B-it-turboGemma€0.0772€0.2918
google/gemma-4-31B-it-UltraGemma€0.2317€0.6522
google/gemma-4-E4B-itGemma€0.0172€0.0858
google/nano-banana-2€51.49
google/nano-banana-2-lite€25.75
google/nano-banana-pro€102.99
Gryphe/MythoMax-L2-13b€0.3433€0.3433
hexgrad/Kokoro-82M€0.5321/1M caracteres
ibm-granite/granite-4.2-30b€0.1373€0.5578
ibm-granite/granite-4.2-3b€0.0257€0.103
ibm-granite/granite-4.2-8b€0.0515€0.2146
inclusionAI/Ling-3.0-flash€0.0515€0.1545
inclusionAI/Ling-3.0-flash-Fin€0.0515€0.1545
inclusionAI/Ling-3.0-flash-VL€0.0515€0.1545
intfloat/e5-base-v2€0.004291
intfloat/e5-large-v2€0.008582
intfloat/multilingual-e5-large€0.008582
intfloat/multilingual-e5-large-instruct€0.008582
inworld-ai/realtime-tts-1.5-max€42.91/1M caracteres
inworld-ai/realtime-tts-1.5-mini€21.46/1M caracteres
inworld-ai/realtime-tts-2€30.04/1M caracteres
meta-llama/Llama-3.3-70B-Instruct-TurboLlama€0.0858€0.2746
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8Llama€0.1716€0.6866
meta-llama/Llama-4-Scout-17B-16E-InstructLlama€0.0858€0.2575
meta-llama/Llama-Guard-4-12BLlama€0.1545€0.1545
meta-llama/Meta-Llama-3.1-70B-Instruct-TurboLlama€0.3433€0.3433
meta-llama/Meta-Llama-3.1-8B-Instruct-TurboLlama€0.0172€0.0343
meta-models/Muse-Glimmer-30B€0.2575€1.03
microsoft/phi-4Phi€0.0601€0.1202
MiniMaxAI/MiniMax-M2.7MiniMax€0.2146€0.8582
MiniMaxAI/MiniMax-M2.7-TurboMiniMax€0.3261€1.46
MiniMaxAI/MiniMax-M3MiniMax€0.2403€0.944
mistralai/Mistral-Nemo-Instruct-2407Mistral€0.0163€0.0257
mistralai/Mistral-Small-24B-Instruct-2501Mistral€0.0429€0.0687
mistralai/Mistral-Small-3.2-24B-Instruct-2506Mistral€0.0644€0.1716
moonshotai/Kimi-K2.5Kimi€0.3862€1.93
moonshotai/Kimi-K2.6Kimi€0.6437€3
moonshotai/Kimi-K2.7-CodeKimi€0.5836€2.92
moonshotai/Kimi-K3Kimi€2.45€12.23
NousResearch/Hermes-3-Llama-3.1-405BLlama€0.8582€0.8582
NousResearch/Hermes-3-Llama-3.1-70BLlama€0.6008€0.6008
nvidia/llama-nemotron-embed-vl-1b-v2Llama€0.008582
nvidia/llama-nemotron-rerank-vl-1b-v2Llama€0.008582
nvidia/Nemotron-3-Embed-1B-BF16Nemotron€0.0129
nvidia/Nemotron-3-Embed-1B-NVFP4Nemotron€0.008582
nvidia/Nemotron-3-Embed-8BNemotron€0.03
nvidia/Nemotron-3-Nano-30B-A3BNemotron€0.0429€0.1716
nvidia/Nemotron-Content-Safety-3.5Nemotron€0.1716€0.1716
nvidia/NVIDIA-Nemotron-3-Super-120B-A12BNemotron€0.0729€0.3433
nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55BNemotron€0.4291€1.89
nvidia/NVIDIA-Nemotron-3.5-LightningNemotron€0.0687€0.1716
openai/gpt-oss-120bGPT-OSS€0.0318€0.1459
openai/gpt-oss-120b-TurboGPT-OSS€0.1287€0.5149
openai/gpt-oss-120b-UltraGPT-OSS€0.1716€0.8153
openai/gpt-oss-20bGPT-OSS€0.0257€0.1202
Qwen/Qwen2.5-72B-InstructQwen€0.309€0.3433
Qwen/Qwen3-14BQwen€0.103€0.206
Qwen/Qwen3-235B-A22B-Instruct-2507Qwen€0.0772€0.472
Qwen/Qwen3-235B-A22B-Thinking-2507Qwen€0.1974€1.97
Qwen/Qwen3-30B-A3BQwen€0.103€0.4291
Qwen/Qwen3-32BQwen€0.0687€0.2403
Qwen/Qwen3-Coder-480B-A35B-Instruct-TurboQwen€0.2575€0.8582
Qwen/Qwen3-Embedding-0.6BQwen€0.008582
Qwen/Qwen3-Embedding-4BQwen€0.0172
Qwen/Qwen3-Embedding-8BQwen€0.008582
Qwen/Qwen3-MaxQwen€1.03€5.15
Qwen/Qwen3-Max-ThinkingQwen€1.03€5.15
Qwen/Qwen3-Next-80B-A3B-InstructQwen€0.0772€0.944
Qwen/Qwen3-Reranker-0.6BQwen€0.008582
Qwen/Qwen3-Reranker-4BQwen€0.0215
Qwen/Qwen3-Reranker-8BQwen€0.0429
Qwen/Qwen3-TTSQwen€17.16/1M caracteres
Qwen/Qwen3-TTS-VoiceDesignQwen€17.16/1M caracteres
Qwen/Qwen3-VL-235B-A22B-InstructQwen€0.1716€0.7552
Qwen/Qwen3-VL-30B-A3B-InstructQwen€0.1287€0.5149
Qwen/Qwen3.5-122B-A10BQwen€0.2489€2.06
Qwen/Qwen3.5-27BQwen€0.2231€2.23
Qwen/Qwen3.5-35B-A3BQwen€0.1202€0.8582
Qwen/Qwen3.5-397B-A17BQwen€0.3862€2.57
Qwen/Qwen3.5-9BQwen€0.0858€0.1287
Qwen/Qwen3.6-27BQwen€0.2746€2.75
Qwen/Qwen3.6-35B-A3BQwen€0.0858€0.8153
Qwen/Qwen3.7-MaxQwen€2.15€6.44
Qwen/Qwen3.8-2.4T-A95BQwen€1.72€5.15
Qwen/Qwen3.8-27BQwen€0.3433€2.57
Qwen/Qwen3.8-MaxQwen€1.42€4.25
ResembleAI/chatterbox-multilingual€0.8582/1M caracteres
ResembleAI/chatterbox-turbo€0.8582/1M caracteres
Sao10K/L3-8B-Lunaris-v1-Turbo€0.0343€0.0429
Sao10K/L3.1-70B-Euryale-v2.2€0.7295€0.7295
sentence-transformers/all-MiniLM-L12-v2€0.004291
sentence-transformers/all-MiniLM-L6-v2€0.004291
sentence-transformers/all-mpnet-base-v2€0.004291
sentence-transformers/clip-ViT-B-32€0.004291
sentence-transformers/clip-ViT-B-32-multilingual-v1€0.004291
sentence-transformers/multi-qa-mpnet-base-dot-v1€0.004291
sentence-transformers/paraphrase-MiniLM-L6-v2€0.004291
sesame/csm-1b€6.01/1M caracteres
shibing624/text2vec-base-chinese€0.004291
stepfun-ai/Step-3.7-Flash€0.1716€0.987
tencent/Hy3€0.1202€0.4978
thenlper/gte-base€0.004291
thenlper/gte-large€0.008582
thinkingmachines/Inkling€0.8153€3.48
thinkingmachines/Inkling-Small€0.3862€1.03
XiaomiMiMo/MiMo-V2.5€0.3433€1.72
XiaomiMiMo/MiMo-V2.5-Pro€0.8582€2.57
XiaomiMiMo/MiMo-V2.5-ttsFree/1M caracteres
XiaomiMiMo/MiMo-V2.5-tts-voicecloneFree/1M caracteres
XiaomiMiMo/MiMo-V2.5-tts-voicedesignFree/1M caracteres
zai-org/GLM-4.6GLM€0.4291€1.72
zai-org/GLM-4.7GLM€0.3433€1.5
zai-org/GLM-4.7-FlashGLM€0.0515€0.3433
zai-org/GLM-5GLM€0.5149€1.79
zai-org/GLM-5.1GLM€0.9011€3
zai-org/GLM-5.2GLM€0.6437€2.06
zai-org/GLM-5.3GLM€1.03€3.43
zai-org/GLM-5.3-FlashGLM€0.1287€0.4291