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
137
Caché de Prompts
Descuento por Lotes
Tool Calling
Modelo137
ModeloPrecio de EntradaPrecio de Salida
anthropic/claude-fable-5€8.78€43.89
anthropic/claude-haiku-4-5€0.8778€4.39
anthropic/claude-opus-4-7€4.39€21.95
anthropic/claude-opus-4-8€4.39€21.95
anthropic/claude-sonnet-4-6€2.63€13.17
anthropic/claude-sonnet-5€1.76€8.78
BAAI/bge-base-en-v1.5€0.004389
BAAI/bge-en-icl€0.008778
BAAI/bge-large-en-v1.5€0.008778
BAAI/bge-m3€0.008778
BAAI/bge-m3-multi€0.008778
bosonai/HiggsAudioV2.5€17.56/1M caracteres
ByteDance/Seed-1.8€0.2195€1.76
ByteDance/Seed-2.0-code€0.4389€2.63
ByteDance/Seed-2.0-mini€0.0878€0.3511
ByteDance/Seed-2.0-pro€0.4389€2.63
ByteDance/Seedance-1.5-Pro€1.05
ByteDance/Seedance-2.0€4.13
canopylabs/orpheus-3b-0.1-ft€6.14/1M caracteres
deepseek-ai/DeepSeek-R1-0528DeepSeek€0.4389€1.89
deepseek-ai/DeepSeek-V3DeepSeek€0.2809€0.7813
deepseek-ai/DeepSeek-V3-0324DeepSeek€0.2107€0.79
deepseek-ai/DeepSeek-V3.1DeepSeek€0.2195€0.8339
deepseek-ai/DeepSeek-V3.1-TerminusDeepSeek€0.237€0.8339
deepseek-ai/DeepSeek-V3.2DeepSeek€0.2282€0.3336
deepseek-ai/DeepSeek-V4-FlashDeepSeek€0.079€0.158
deepseek-ai/DeepSeek-V4-ProDeepSeek€1.14€2.28
google/embeddinggemma-300mGemma€0.001756
google/gemini-2.5-flash€0.2633€2.19
google/gemini-2.5-pro€1.1€8.78
google/gemini-3.1-flash-lite€0.2195€1.32
google/gemini-3.1-pro€1.76€10.53
google/gemini-3.5-flash€1.32€7.9
google/gemini-3-pro-image€105.34
google/gemma-3-12b-itGemma€0.0439€0.1317
google/gemma-3-27b-itGemma€0.0702€0.1404
google/gemma-3-4b-itGemma€0.0439€0.0878
google/gemma-4-26B-A4B-itGemma€0.0614€0.2985
google/gemma-4-31B-itGemma€0.1141€0.3336
google/gemma-4-31B-it-turboGemma€0.1053€0.3248
google/gemma-4-E4B-itGemma€0.0176€0.0878
Gryphe/MythoMax-L2-13b€0.3511€0.3511
hexgrad/Kokoro-82M€0.5442/1M caracteres
intfloat/e5-base-v2€0.004389
intfloat/e5-large-v2€0.008778
intfloat/multilingual-e5-large€0.008778
intfloat/multilingual-e5-large-instruct€0.008778
inworld-ai/realtime-tts-1.5-max€43.89/1M caracteres
inworld-ai/realtime-tts-1.5-mini€21.95/1M caracteres
inworld-ai/realtime-tts-2€30.72/1M caracteres
meta-llama/Llama-3.3-70B-Instruct-TurboLlama€0.0878€0.2809
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8Llama€0.1756€0.7022
meta-llama/Llama-4-Scout-17B-16E-InstructLlama€0.0878€0.2633
meta-llama/Llama-Guard-4-12BLlama€0.158€0.158
meta-llama/Meta-Llama-3.1-70B-Instruct-TurboLlama€0.3511€0.3511
meta-llama/Meta-Llama-3.1-8B-Instruct-TurboLlama€0.0176€0.0351
microsoft/phi-4Phi€0.0614€0.1229
MiniMaxAI/MiniMax-M2.7MiniMax€0.2195€0.8778
MiniMaxAI/MiniMax-M2.7-TurboMiniMax€0.3336€1.49
MiniMaxAI/MiniMax-M3MiniMax€0.2633€1.05
mistralai/Mistral-Nemo-Instruct-2407Mistral€0.0167€0.0263
mistralai/Mistral-Small-24B-Instruct-2501Mistral€0.0439€0.0702
mistralai/Mistral-Small-3.2-24B-Instruct-2506Mistral€0.0658€0.1756
moonshotai/Kimi-K2.5Kimi€0.395€1.98
moonshotai/Kimi-K2.6Kimi€0.6584€3.07
moonshotai/Kimi-K2.7-CodeKimi€0.6496€3.07
NousResearch/Hermes-3-Llama-3.1-405BLlama€0.8778€0.8778
NousResearch/Hermes-3-Llama-3.1-70BLlama€0.6145€0.6145
nvidia/llama-nemotron-embed-vl-1b-v2Llama€0.008778
nvidia/llama-nemotron-rerank-vl-1b-v2Llama€0.008778
nvidia/Nemotron-3-Embed-1B-BF16Nemotron€0.0132
nvidia/Nemotron-3-Embed-1B-NVFP4Nemotron€0.008778
nvidia/Nemotron-3-Embed-8BNemotron€0.0307
nvidia/Nemotron-3-Nano-30B-A3BNemotron€0.0439€0.1756
nvidia/Nemotron-Content-Safety-3.5Nemotron€0.1756€0.1756
nvidia/NVIDIA-Nemotron-3-Super-120B-A12BNemotron€0.0746€0.3511
nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55BNemotron€0.4389€1.93
openai/gpt-oss-120bGPT-OSS€0.0325€0.1492
openai/gpt-oss-120b-TurboGPT-OSS€0.1317€0.5267
openai/gpt-oss-20bGPT-OSS€0.0263€0.1229
Qwen/Qwen2.5-72B-InstructQwen€0.316€0.3511
Qwen/Qwen3-14BQwen€0.1053€0.2107
Qwen/Qwen3-235B-A22B-Instruct-2507Qwen€0.079€0.4828
Qwen/Qwen3-235B-A22B-Thinking-2507Qwen€0.2019€2.02
Qwen/Qwen3-30B-A3BQwen€0.1053€0.4389
Qwen/Qwen3-32BQwen€0.0702€0.2458
Qwen/Qwen3.5-122B-A10BQwen€0.2546€2.11
Qwen/Qwen3.5-27BQwen€0.2282€2.28
Qwen/Qwen3.5-35B-A3BQwen€0.1229€0.8778
Qwen/Qwen3.5-397B-A17BQwen€0.395€2.63
Qwen/Qwen3.5-9BQwen€0.0878€0.1317
Qwen/Qwen3.6-27BQwen€0.2809€2.81
Qwen/Qwen3.6-35B-A3BQwen€0.1317€0.8339
Qwen/Qwen3.7-MaxQwen€2.19€6.58
Qwen/Qwen3-Coder-480B-A35B-Instruct-TurboQwen€0.2633€0.8778
Qwen/Qwen3-Embedding-0.6BQwen€0.008778
Qwen/Qwen3-Embedding-4BQwen€0.0176
Qwen/Qwen3-Embedding-8BQwen€0.008778
Qwen/Qwen3-MaxQwen€1.05€5.27
Qwen/Qwen3-Max-ThinkingQwen€1.05€5.27
Qwen/Qwen3-Next-80B-A3B-InstructQwen€0.079€0.9656
Qwen/Qwen3-Reranker-0.6BQwen€0.008778
Qwen/Qwen3-Reranker-4BQwen€0.0219
Qwen/Qwen3-Reranker-8BQwen€0.0439
Qwen/Qwen3-TTSQwen€17.56/1M caracteres
Qwen/Qwen3-TTS-VoiceDesignQwen€17.56/1M caracteres
Qwen/Qwen3-VL-235B-A22B-InstructQwen€0.1756€0.7725
Qwen/Qwen3-VL-30B-A3B-InstructQwen€0.1317€0.5267
ResembleAI/chatterbox-multilingual€0.8778/1M caracteres
ResembleAI/chatterbox-turbo€0.8778/1M caracteres
Sao10K/L3.1-70B-Euryale-v2.2€0.7461€0.7461
Sao10K/L3-8B-Lunaris-v1-Turbo€0.0351€0.0439
sentence-transformers/all-MiniLM-L12-v2€0.004389
sentence-transformers/all-MiniLM-L6-v2€0.004389
sentence-transformers/all-mpnet-base-v2€0.004389
sentence-transformers/clip-ViT-B-32€0.004389
sentence-transformers/clip-ViT-B-32-multilingual-v1€0.004389
sentence-transformers/multi-qa-mpnet-base-dot-v1€0.004389
sentence-transformers/paraphrase-MiniLM-L6-v2€0.004389
sesame/csm-1b€6.14/1M caracteres
shibing624/text2vec-base-chinese€0.004389
stepfun-ai/Step-3.7-Flash€0.1756€1.01
tencent/Hy3€0.1229€0.5091
thenlper/gte-base€0.004389
thenlper/gte-large€0.008778
thinkingmachines/Inkling€0.8778€3.56
XiaomiMiMo/MiMo-V2.5€0.3511€1.76
XiaomiMiMo/MiMo-V2.5-Pro€0.8778€2.63
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€0.4389€1.76
zai-org/GLM-4.7GLM€0.3511€1.54
zai-org/GLM-4.7-FlashGLM€0.0527€0.3511
zai-org/GLM-5GLM€0.5267€1.83
zai-org/GLM-5.1GLM€0.9217€3.07
zai-org/GLM-5.2GLM€0.8164€2.63