aggregatorcommon.labs_models

Deep Infra

68 published models are listed on Deep Infra. Prices shown are this provider's own listings and may differ from first-party.

deepinfra/docs ↗DEEPINFRA_API_KEY@ai-sdk/deepinfra
Models
68
Labs
12
Free tier
0
Changes 30d
23
01Catalog

All 68 models on Deep Infra

Filter by lab. Click a row for the model's full profile.

ModelLabInputOutputContextFlags
Gemma 4 E4B IT
google/gemma-4-E4B-it
Google$0.02$0.10131,072reasoningopen weights
gpt-oss-20b
openai/gpt-oss-20b
OpenAI$0.03$0.14131,072reasoningopen weights
GPT OSS 120B
openai/gpt-oss-120b
OpenAI$0.04$0.17131,072reasoningopen weights
Gemma 3 12B IT
google/gemma-3-12b-it
Google$0.05$0.15131,072open weights
Gemma 3 4B IT
google/gemma-3-4b-it
Google$0.05$0.10131,072open weights
nemotron-3-nano-30b-a3b
nvidia/Nemotron-3-Nano-30B-A3B
NVIDIA$0.05$0.20262,144reasoningopen weights
DeepSeek V4 Flash 0731
deepseek-ai/DeepSeek-V4-Flash-0731
DeepSeek$0.06$0.181,048,576reasoningopen weights
GLM-4.7-Flash
zai-org/GLM-4.7-Flash
Zhipu AI$0.06$0.40202,752reasoningopen weights
Gemma 4 26B A4B IT
google/gemma-4-26B-A4B-it
Google$0.07$0.34262,144reasoningopen weights
Gemma 3 27B IT
google/gemma-3-27b-it
Google$0.08$0.16131,072open weights
Qwen3 32B
Qwen/Qwen3-32B
Alibaba$0.08$0.2840,960reasoningopen weights
DeepSeek V4 Flash
deepseek-ai/DeepSeek-V4-Flash
DeepSeek$0.09$0.181,048,576reasoningopen weights
qwen3-235b-a22b-instruct-2507
Qwen/Qwen3-235B-A22B-Instruct-2507
Alibaba$0.09$0.55262,144
Qwen3-Next 80B-A3B Instruct
Qwen/Qwen3-Next-80B-A3B-Instruct
Alibaba$0.09$1.10262,144open weights
Llama 3.3 70B Turbo
meta-llama/Llama-3.3-70B-Instruct-Turbo
Meta$0.10$0.32131,072open weights
Llama 4 Scout 17B 16E Instruct
meta-llama/Llama-4-Scout-17B-16E-Instruct
Meta$0.10$0.30327,680open weights
Qwen3.5 9B
Qwen/Qwen3.5-9B
Alibaba$0.10$0.15262,144reasoningopen weights
Qwen3.6 35B-A3B
Qwen/Qwen3.6-35B-A3B
Alibaba$0.10$0.95262,144reasoningopen weights
Seed 2.0 Mini
ByteDance/Seed-2.0-mini
Independent$0.10$0.40256,000reasoning
Qwen3.8 Flash
Qwen/Qwen3.8-Flash
Alibaba$0.11$0.381,000,000reasoning
Qwen3-30B-A3B
Qwen/Qwen3-30B-A3B
Alibaba$0.12$0.5040,960
Gemma 4 31B IT
google/gemma-4-31B-it
Google$0.13$0.38262,144reasoningopen weights
Hy3
tencent/Hy3
Tencent$0.14$0.58262,144reasoningopen weights
MiMo-V2.5
XiaomiMiMo/MiMo-V2.5
Xiaomi$0.14$0.28262,144reasoningopen weights
Qwen3.5 35B-A3B
Qwen/Qwen3.5-35B-A3B
Alibaba$0.14$1.00262,144reasoningopen weights
GLM-5.3-Flash
zai-org/GLM-5.3-Flash
Zhipu AI$0.15$0.501,048,576reasoningopen weights
MiniMax-M2.5
MiniMaxAI/MiniMax-M2.5
MiniMax$0.15$1.15196,608reasoningopen weights
DeepSeek V4.1 Flash
deepseek-ai/DeepSeek-V4.1-Flash
DeepSeek$0.20$0.601,048,576reasoningopen weights
Llama 4 Maverick 17B Instruct
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
Meta$0.20$0.801,048,576open weights
Nemotron 3 Nano Omni
nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning
NVIDIA$0.20$0.80262,144reasoningopen weights
Qwen3.8 27B
Qwen/Qwen3.8-27B
Alibaba$0.20$2.50262,144reasoningopen weights
Qwen3 VL 235B A22B Instruct
Qwen/Qwen3-VL-235B-A22B-Instruct
Alibaba$0.20$0.88262,144open weights
Step 3.7 Flash
stepfun-ai/Step-3.7-Flash
StepFun$0.20$1.15262,144reasoningopen weights
siliconflow/deepseek-v3-0324
deepseek-ai/DeepSeek-V3-0324
DeepSeek$0.24$0.90163,840
DeepSeek V3.1
deepseek-ai/DeepSeek-V3.1
DeepSeek$0.25$0.95163,840reasoningopen weights
MiniMax-M2.7
MiniMaxAI/MiniMax-M2.7
MiniMax$0.25$1.00196,608reasoningopen weights
deepseek-v3.2
deepseek-ai/DeepSeek-V3.2
DeepSeek$0.26$0.38163,840
Qwen3.5 27B
Qwen/Qwen3.5-27B
Alibaba$0.26$2.60262,144reasoningopen weights
MiniMax-M3
MiniMaxAI/MiniMax-M3
MiniMax$0.28$1.10524,288reasoningopen weights
Qwen3.5 122B-A10B
Qwen/Qwen3.5-122B-A10B
Alibaba$0.29$2.40262,144reasoningopen weights
Showing 40 of 68 models · sorted by input price
02Activity

Recent changes on Deep Infra

Full feed →
2026-09-15Price cutQwen3.8 27Binput / 1M $0.40 → $0.20
2026-09-15Price cutQwen3.8 27Boutput / 1M $3.00 → $2.50
2026-09-14AddedQwen3.8 Flashoffering → new
2026-09-11Price cutDeepSeek V4.1 Flashinput / 1M $0.30 → $0.20
2026-09-11Price cutDeepSeek V4.1 Flashoutput / 1M $1.20 → $0.60
2026-09-11AddedGemma 3 12B IToffering → new
2026-09-11AddedGemma 3 27B IToffering → new
2026-09-11AddedGemma 3 4B IToffering → new
2026-09-11Price cutMiMo-V2.5input / 1M $0.40 → $0.14
2026-09-11Price cutMiMo-V2.5output / 1M $2.00 → $0.28
2026-09-10AddedDeepSeek V4.1 Flashoffering → new
2026-09-10DeprecatedGLM-4.7-FlashStatus → deprecated
2026-09-10DeprecatedGLM-5Status → deprecated
2026-09-10DeprecatedMiniMax-M2.7Status → deprecated
2026-09-08DeprecatedKimi K2.5Status → deprecated
2026-09-06Price cutDeepSeek V4 Flash 0731input / 1M $0.08 → $0.06
2026-09-03AddedDeepSeek V4 Flash Vision Expoffering → new
2026-08-29Price cutGLM-5.3input / 1M $1.40 → $1.20
2026-08-29Price cutGLM-5.3output / 1M $4.40 → $4.00
2026-08-28AddedGLM-5.3offering → new
as of 2026-09-16
About ·Corrections ·Contact ·Privacy ·EN / 中文 / 繁體
HomeModelsLabsProvidersToolsRankingsChangesNews