LLMRates.ai
DeepInfra logo

DeepInfra

模型集成商

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.

模型
137
提示缓存
✓
批量折扣
—
Tool Calling
✓
访问官网 →查看官方价格 →
模型137
模型输入价格输出价格
anthropic/claude-fable-5¥67.7¥338.51
anthropic/claude-haiku-4-5¥6.77¥33.85
anthropic/claude-opus-4-7¥33.85¥169.26
anthropic/claude-opus-4-8¥33.85¥169.26
anthropic/claude-sonnet-4-6¥20.31¥101.55
anthropic/claude-sonnet-5¥13.54¥67.7
BAAI/bge-base-en-v1.5¥0.0339—
BAAI/bge-en-icl¥0.0677—
BAAI/bge-large-en-v1.5¥0.0677—
BAAI/bge-m3¥0.0677—
BAAI/bge-m3-multi¥0.0677—
bosonai/HiggsAudioV2.5¥135.41/百万字符—
ByteDance/Seed-1.8¥1.69¥13.54
ByteDance/Seed-2.0-code¥3.39¥20.31
ByteDance/Seed-2.0-mini¥0.677¥2.71
ByteDance/Seed-2.0-pro¥3.39¥20.31
ByteDance/Seedance-1.5-Pro¥8.12—
ByteDance/Seedance-2.0¥31.82—
canopylabs/orpheus-3b-0.1-ft¥47.39/百万字符—
deepseek-ai/DeepSeek-R1-0528DeepSeek¥3.39¥14.56
deepseek-ai/DeepSeek-V3DeepSeek¥2.17¥6.03
deepseek-ai/DeepSeek-V3-0324DeepSeek¥1.62¥6.09
deepseek-ai/DeepSeek-V3.1DeepSeek¥1.69¥6.43
deepseek-ai/DeepSeek-V3.1-TerminusDeepSeek¥1.83¥6.43
deepseek-ai/DeepSeek-V3.2DeepSeek¥1.76¥2.57
deepseek-ai/DeepSeek-V4-FlashDeepSeek¥0.6093¥1.22
deepseek-ai/DeepSeek-V4-ProDeepSeek¥8.8¥17.6
google/embeddinggemma-300mGemma¥0.0135—
google/gemini-2.5-flash¥2.03¥16.93
google/gemini-2.5-pro¥8.46¥67.7
google/gemini-3.1-flash-lite¥1.69¥10.16
google/gemini-3.1-pro¥13.54¥81.24
google/gemini-3.5-flash¥10.16¥60.93
google/gemini-3-pro-image¥812.44—
google/gemma-3-12b-itGemma¥0.3385¥1.02
google/gemma-3-27b-itGemma¥0.5416¥1.08
google/gemma-3-4b-itGemma¥0.3385¥0.677
google/gemma-4-26B-A4B-itGemma¥0.4739¥2.3
google/gemma-4-31B-itGemma¥0.8801¥2.57
google/gemma-4-31B-it-turboGemma¥0.8124¥2.51
google/gemma-4-E4B-itGemma¥0.1354¥0.677
Gryphe/MythoMax-L2-13b¥2.71¥2.71
hexgrad/Kokoro-82M¥4.2/百万字符—
intfloat/e5-base-v2¥0.0339—
intfloat/e5-large-v2¥0.0677—
intfloat/multilingual-e5-large¥0.0677—
intfloat/multilingual-e5-large-instruct¥0.0677—
inworld-ai/realtime-tts-1.5-max¥338.51/百万字符—
inworld-ai/realtime-tts-1.5-mini¥169.26/百万字符—
inworld-ai/realtime-tts-2¥236.96/百万字符—
meta-llama/Llama-3.3-70B-Instruct-TurboLlama¥0.677¥2.17
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8Llama¥1.35¥5.42
meta-llama/Llama-4-Scout-17B-16E-InstructLlama¥0.677¥2.03
meta-llama/Llama-Guard-4-12BLlama¥1.22¥1.22
meta-llama/Meta-Llama-3.1-70B-Instruct-TurboLlama¥2.71¥2.71
meta-llama/Meta-Llama-3.1-8B-Instruct-TurboLlama¥0.1354¥0.2708
microsoft/phi-4Phi¥0.4739¥0.9478
MiniMaxAI/MiniMax-M2.7MiniMax¥1.69¥6.77
MiniMaxAI/MiniMax-M2.7-TurboMiniMax¥2.57¥11.51
MiniMaxAI/MiniMax-M3MiniMax¥2.03¥8.12
mistralai/Mistral-Nemo-Instruct-2407Mistral¥0.1286¥0.2031
mistralai/Mistral-Small-24B-Instruct-2501Mistral¥0.3385¥0.5416
mistralai/Mistral-Small-3.2-24B-Instruct-2506Mistral¥0.5078¥1.35
moonshotai/Kimi-K2.5Kimi¥3.05¥15.23
moonshotai/Kimi-K2.6Kimi¥5.08¥23.7
moonshotai/Kimi-K2.7-CodeKimi¥5.01¥23.7
NousResearch/Hermes-3-Llama-3.1-405BLlama¥6.77¥6.77
NousResearch/Hermes-3-Llama-3.1-70BLlama¥4.74¥4.74
nvidia/llama-nemotron-embed-vl-1b-v2Llama¥0.0677—
nvidia/llama-nemotron-rerank-vl-1b-v2Llama¥0.0677—
nvidia/Nemotron-3-Embed-1B-BF16Nemotron¥0.1016—
nvidia/Nemotron-3-Embed-1B-NVFP4Nemotron¥0.0677—
nvidia/Nemotron-3-Embed-8BNemotron¥0.237—
nvidia/Nemotron-3-Nano-30B-A3BNemotron¥0.3385¥1.35
nvidia/Nemotron-Content-Safety-3.5Nemotron¥1.35¥1.35
nvidia/NVIDIA-Nemotron-3-Super-120B-A12BNemotron¥0.5755¥2.71
nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55BNemotron¥3.39¥14.89
openai/gpt-oss-120bGPT-OSS¥0.2505¥1.15
openai/gpt-oss-120b-TurboGPT-OSS¥1.02¥4.06
openai/gpt-oss-20bGPT-OSS¥0.2031¥0.9478
Qwen/Qwen2.5-72B-InstructQwen¥2.44¥2.71
Qwen/Qwen3-14BQwen¥0.8124¥1.62
Qwen/Qwen3-235B-A22B-Instruct-2507Qwen¥0.6093¥3.72
Qwen/Qwen3-235B-A22B-Thinking-2507Qwen¥1.56¥15.57
Qwen/Qwen3-30B-A3BQwen¥0.8124¥3.39
Qwen/Qwen3-32BQwen¥0.5416¥1.9
Qwen/Qwen3.5-122B-A10BQwen¥1.96¥16.25
Qwen/Qwen3.5-27BQwen¥1.76¥17.6
Qwen/Qwen3.5-35B-A3BQwen¥0.9478¥6.77
Qwen/Qwen3.5-397B-A17BQwen¥3.05¥20.31
Qwen/Qwen3.5-9BQwen¥0.677¥1.02
Qwen/Qwen3.6-27BQwen¥2.17¥21.66
Qwen/Qwen3.6-35B-A3BQwen¥1.02¥6.43
Qwen/Qwen3.7-MaxQwen¥16.93¥50.78
Qwen/Qwen3-Coder-480B-A35B-Instruct-TurboQwen¥2.03¥6.77
Qwen/Qwen3-Embedding-0.6BQwen¥0.0677—
Qwen/Qwen3-Embedding-4BQwen¥0.1354—
Qwen/Qwen3-Embedding-8BQwen¥0.0677—
Qwen/Qwen3-MaxQwen¥8.12¥40.62
Qwen/Qwen3-Max-ThinkingQwen¥8.12¥40.62
Qwen/Qwen3-Next-80B-A3B-InstructQwen¥0.6093¥7.45
Qwen/Qwen3-Reranker-0.6BQwen¥0.0677—
Qwen/Qwen3-Reranker-4BQwen¥0.1693—
Qwen/Qwen3-Reranker-8BQwen¥0.3385—
Qwen/Qwen3-TTSQwen¥135.41/百万字符—
Qwen/Qwen3-TTS-VoiceDesignQwen¥135.41/百万字符—
Qwen/Qwen3-VL-235B-A22B-InstructQwen¥1.35¥5.96
Qwen/Qwen3-VL-30B-A3B-InstructQwen¥1.02¥4.06
ResembleAI/chatterbox-multilingual¥6.77/百万字符—
ResembleAI/chatterbox-turbo¥6.77/百万字符—
Sao10K/L3.1-70B-Euryale-v2.2¥5.75¥5.75
Sao10K/L3-8B-Lunaris-v1-Turbo¥0.2708¥0.3385
sentence-transformers/all-MiniLM-L12-v2¥0.0339—
sentence-transformers/all-MiniLM-L6-v2¥0.0339—
sentence-transformers/all-mpnet-base-v2¥0.0339—
sentence-transformers/clip-ViT-B-32¥0.0339—
sentence-transformers/clip-ViT-B-32-multilingual-v1¥0.0339—
sentence-transformers/multi-qa-mpnet-base-dot-v1¥0.0339—
sentence-transformers/paraphrase-MiniLM-L6-v2¥0.0339—
sesame/csm-1b¥47.39/百万字符—
shibing624/text2vec-base-chinese¥0.0339—
stepfun-ai/Step-3.7-Flash¥1.35¥7.79
tencent/Hy3¥0.9478¥3.93
thenlper/gte-base¥0.0339—
thenlper/gte-large¥0.0677—
thinkingmachines/Inkling¥6.77¥27.42
XiaomiMiMo/MiMo-V2.5¥2.71¥13.54
XiaomiMiMo/MiMo-V2.5-Pro¥6.77¥20.31
XiaomiMiMo/MiMo-V2.5-ttsFree/百万字符—
XiaomiMiMo/MiMo-V2.5-tts-voicecloneFree/百万字符—
XiaomiMiMo/MiMo-V2.5-tts-voicedesignFree/百万字符—
zai-org/GLM-4.6GLM¥3.39¥13.54
zai-org/GLM-4.7GLM¥2.71¥11.85
zai-org/GLM-4.7-FlashGLM¥0.4062¥2.71
zai-org/GLM-5GLM¥4.06¥14.08
zai-org/GLM-5.1GLM¥7.11¥23.7
zai-org/GLM-5.2GLM¥6.3¥20.31