LLM Pricing
PricingLeaderboardsToolsProvidersReleasesGuides

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Providers

Deep Infra

deepinfra·Cloud·71 models·Official docs ↗

Deep Infra is a cloud platform that resells models with its own infrastructure, billing and regional hosting. Its prices tend to track the first-party rate, with the platform's own quotas and service-level terms attached.

It lists 71 models on this page. Coverage spans text and chat (71). The lowest-priced model hosted here is Gemma 4 E4B IT.

Deep Infra is the lowest paid channel for 12 models that have at least two competing paid hosts, which is where its pricing genuinely leads rather than being the only option.

Coverage & pricing
Models hosted71With public price 71
Cheapest anywhere12
Model typesText / Chat 71
Cheapest model hereGemma 4 E4B IT
SDK package@ai-sdk/deepinfra
API—

Hosted models by blended price asc

⌕
71 of 71
Cheapest here?
Gemma 4 E4B ITgoogle/gemma-4-E4B-it$0.02$0.10—131,072Lowest anywhere
GPT OSS 20Bopenai/gpt-oss-20b$0.03$0.14—131,0721.6× pricier
Gemma 3 4B ITgoogle/gemma-3-4b-it$0.05$0.10—131,0721.3× pricier
GPT OSS 120Bopenai/gpt-oss-120b$0.037$0.17—131,0721.2× pricier
Gemma 3 12B ITgoogle/gemma-3-12b-it$0.05$0.15—131,0721.2× pricier
Nemotron 3 Nano 30B A3Bnvidia/Nemotron-3-Nano-30B-A3B$0.05$0.20$0.025262,144Lowest anywhere
DeepSeek V4 Flash 0731deepseek-ai/DeepSeek-V4-Flash-0731$0.06$0.18$0.0151,048,5762.1× pricier
Gemma 3 27B ITgoogle/gemma-3-27b-it$0.08$0.16—131,072Lowest anywhere
DeepSeek V4 Flashdeepseek-ai/DeepSeek-V4-Flash$0.09$0.18$0.0181,048,5762.6× pricier
Qwen3.5 9BQwen/Qwen3.5-9B$0.10$0.15—262,1441.7× pricier
Qwen3 32BQwen/Qwen3-32B$0.08$0.28—40,960Lowest anywhere
Gemma 4 26B A4B ITgoogle/gemma-4-26B-A4B-it$0.07$0.34—262,1441.6× pricier
GLM-4.7-Flashzai-org/GLM-4.7-Flash$0.06$0.40$0.01202,752Lowest anywhere
Llama 4 Scout 17B 16E Instructmeta-llama/Llama-4-Scout-17B-16E-Instruct$0.10$0.30—327,680Lowest anywhere
Llama 3.3 70B Turbometa-llama/Llama-3.3-70B-Instruct-Turbo$0.10$0.32—131,072Only channel
MiMo-V2.5XiaomiMiMo/MiMo-V2.5$0.14$0.28$0.0028262,144Lowest anywhere
MiMo-V2.6-FlashXiaomiMiMo/MiMo-V2.6-Flash$0.14$0.28$0.00281,048,5761.3× pricier
bySeed 2.0 MiniByteDance/Seed-2.0-mini$0.10$0.40$0.02256,0001.8× pricier
Qwen3.8 FlashQwen/Qwen3.8-Flash$0.11$0.38$0.0141,000,0001.0× pricier
Qwen3 235B-A22B Instruct 2507Qwen/Qwen3-235B-A22B-Instruct-2507$0.09$0.55—262,1441.3× pricier
Qwen3 30B A3BQwen/Qwen3-30B-A3B$0.12$0.50—40,9601.6× pricier
Hy3tencent/Hy3$0.13$0.53$0.033262,1442.0× pricier
GLM-5.3-Flashzai-org/GLM-5.3-Flash$0.15$0.50$0.031,048,5765.0× pricier
Gemma 4 31B ITgoogle/gemma-4-31B-it$0.20$0.40—262,1441.8× pricier
DeepSeek V3.2deepseek-ai/DeepSeek-V3.2$0.26$0.38$0.13163,8401.3× pricier
DeepSeek V4.1 Flashdeepseek-ai/DeepSeek-V4.1-Flash$0.20$0.60$0.0061,048,5766.0× pricier
Qwen3.6 35B-A3BQwen/Qwen3.6-35B-A3B$0.10$0.95$0.10262,1442.9× pricier
Qwen3-Next 80B-A3B InstructQwen/Qwen3-Next-80B-A3B-Instruct$0.09$1.10—262,1441.4× pricier
Nemotron 3 Nano Omni 30B A3B Reasoningnvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning$0.20$0.80—262,1442.5× pricier
Llama 4 Maverick 17B 128E Instruct FP8meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8$0.20$0.80—1,048,576Lowest anywhere
Qwen3.5 35B-A3BQwen/Qwen3.5-35B-A3B$0.14$1.00$0.05262,1442.3× pricier
Qwen3 VL 235B A22B InstructQwen/Qwen3-VL-235B-A22B-Instruct$0.20$0.88$0.11262,144Lowest anywhere
MiniMax-M2.5MiniMaxAI/MiniMax-M2.5$0.15$1.15$0.03196,6081.0× pricier
Llama 3.3 Nemotron Super 49B v1.5nvidia/Llama-3.3-Nemotron-Super-49B-v1.5$0.40$0.40—131,072Only channel
DeepSeek V3 0324deepseek-ai/DeepSeek-V3-0324$0.24$0.90$0.14163,8401.2× pricier
DeepSeek-V3.1deepseek-ai/DeepSeek-V3.1$0.25$0.95$0.13163,8401.3× pricier
MiniMax-M2.7MiniMaxAI/MiniMax-M2.7$0.25$1.00$0.05196,6083.1× pricier
Step 3.7 Flashstepfun-ai/Step-3.7-Flash$0.20$1.15$0.04262,1441.1× pricier
DeepSeek-V3deepseek-ai/DeepSeek-V3$0.32$0.89—163,8401.1× pricier
Qwen3 Coder 480B A35B Instruct TurboQwen/Qwen3-Coder-480B-A35B-Instruct-Turbo$0.30$1.00$0.10262,1441.2× pricier
MiniMax-M3MiniMaxAI/MiniMax-M3$0.28$1.10$0.056524,2881.3× pricier
MiMo-V2.6-ProXiaomiMiMo/MiMo-V2.6-Pro$0.43$0.87$0.00361,048,5761.1× pricier
Inkling Smallthinkingmachines/Inkling-Small$0.45$1.20$0.10524,288Lowest anywhere
DeepSeek V4 Flash Vision Expdeepseek-ai/DeepSeek-V4-Flash-Vision-Exp$0.44$1.32$0.0141,048,5766.0× pricier
GLM-4.7zai-org/GLM-4.7$0.40$1.75$0.08202,7522.1× pricier
Qwen3.8 27BQwen/Qwen3.8-27B$0.20$2.50$0.05262,1446.8× pricier
Qwen3.5 122B-A10BQwen/Qwen3.5-122B-A10B$0.29$2.40—262,1442.6× pricier
Qwen3.5 27BQwen/Qwen3.5-27B$0.26$2.60—262,1443.6× pricier
GLM-4.6zai-org/GLM-4.6$0.50$2.00$0.10202,7521.8× pricier
Kimi K2.5moonshotai/Kimi-K2.5$0.45$2.25$0.07262,1441.3× pricier
DeepSeek R1 0528deepseek-ai/DeepSeek-R1-0528$0.50$2.15$0.35163,840Lowest anywhere
GLM-5zai-org/GLM-5$0.60$2.08$0.12202,7521.3× pricier
Qwen3.6 27BQwen/Qwen3.6-27B$0.32$3.20—262,1442.0× pricier
Qwen3.5 397B-A17BQwen/Qwen3.5-397B-A17B$0.45$3.00$0.22262,1442.9× pricier
bySeed 2.0 CodeByteDance/Seed-2.0-code$0.50$3.00$0.10256,0001.3× pricier
bySeed 2.0 ProByteDance/Seed-2.0-pro$0.50$3.00$0.10256,0001.2× pricier
GLM-5.2zai-org/GLM-5.2$0.75$2.40$0.141,048,5762.4× pricier
Hy4 previewtencent/Hy4-preview$0.83$2.50$0.0421,048,5761.2× pricier
Kimi K2.7 Codemoonshotai/Kimi-K2.7-Code$0.68$3.40$0.14262,1442.8× pricier
Kimi K2.6moonshotai/Kimi-K2.6$0.75$3.50$0.15262,1443.0× pricier
MiMo-V2.5-ProXiaomiMiMo/MiMo-V2.5-Pro$1.00$3.00$0.201,048,5763.0× pricier
DeepSeek V4 Prodeepseek-ai/DeepSeek-V4-Pro$1.30$2.60$0.101,048,5766.2× pricier
DeepSeek V4 Pro 0813deepseek-ai/DeepSeek-V4-Pro-0813$1.30$2.60$0.101,048,5763.5× pricier
GLM-5.1zai-org/GLM-5.1$1.05$3.50$0.21202,7521.9× pricier
GLM-5.3zai-org/GLM-5.3$0.90$4.00$0.201,048,5762.6× pricier
Inklingthinkingmachines/Inkling$0.95$4.05$0.16524,288Lowest anywhere
Qwen3 MaxQwen/Qwen3-Max$1.20$6.00$0.24256,0003.8× pricier
Qwen3.8 MaxQwen/Qwen3.8-Max$1.65$4.95$0.21256,0001.0× pricier
Qwen3.8 2.4T A95BQwen/Qwen3.8-2.4T-A95B$2.00$6.00$0.20262,1441.0× pricier
Qwen3.7 MaxQwen/Qwen3.7-Max$2.50$7.50$0.50256,0003.0× pricier
Kimi K3moonshotai/Kimi-K3$2.85$14.25$0.291,048,5761.6× pricier