XiaomiMiMo/text-generation
MiMo-V2.6-Flash
An efficiency-balanced model in Xiaomi's MiMo-V2.6 series, built for agentic workloads.
$0.003 cached, $0.14 in, $0.28 out / 1M
ZDRfp81024k
FAST
deepinfra
AI Inference
Flexible AI inference, ready when you are.
VercelAdobeUBISOFTIconic HeartsLATITUDECupidBot.ai
Announcement · May 2026
We've raised $107M Series B
to scale the inference cloud
Co-led by 500 Global and Georges Harik, with participation from A.Capital Ventures, Crescent Cove, Felicis, NVIDIA, Peak6, Samsung Next, Supermicro, and Upper90.
Explore what's possible Built for what comes next.
$107MSeries B funding
25xtoken volume since Series A
Scale to trillions of tokens without breaking the bank
Low pay-as-you-go pricing—no long-term contracts, no hidden fees, no surprises. Startup? Enterprise? We can scale. We're here for you with simple APIs and hands-on technical support.
Inference Tailored to You
An inference partner that meets your needs. Whether you're optimizing for cost, latency, throughput or scale, we design the solution around your priorities. Deepinfra provides 100+ models to cover your needs.
Zero Retention. Compliant.
Secure.
With our zero retention policy, your inputs, outputs and user data stay private. Deepinfra is SOC 2 and ISO 27001 certified. We follow best practices in information security and privacy.
Our Hardware. Our Data Centers. Your Performance Edge.
Deepinfra runs on our own cutting-edge, inference-optimized infrastructure in secure US-based data centers. Better performance and reliability for you.
Models
Explore our Featured Models
View All
text-generation
text-to-speech
text-to-image
XiaomiMiMo/text-generation
MiMo-V2.6-Pro
The flagship MiMo-V2.6 model for demanding long-horizon coding and multi-tool agents.
$0.004 cached, $0.435 in, $0.87 out / 1M
ZDRfp81024k
deepseek-ai/text-generation
DeepSeek-V4.1-Flash
A multimodal mixture-of-experts model with support for long contexts.
$0.004 cached, $0.14 in, $0.42 out / 1M
ZDRPriorityFlex1024k
zai-org/text-generation
GLM-5.3
A large-scale reasoning model for complex software engineering and long tasks.
$0.125 cached, $0.563 in, $2.50 out / 1M
ZDRFlex1024k
zai-org/text-generation
GLM-5.3-Flash
A fast model suited to efficient coding and long-horizon agent tasks.
$0.015 cached, $0.075 in, $0.25 out / 1M
ZDRfp41024k
moonshotai/text-generation
Kimi-K3
Moonshot AI's open-weight multimodal reasoning model, built for complex coding.
$0.285 cached, $2.85 in, $14.25 out / 1M
ZDRCache retention1024k
Qwen/text-generation
Qwen3.8-2.4T-A95B
An open-weight sparse mixture-of-experts model from Qwen.
$0.20 cached, $2.00 in, $6.00 out / 1M
ZDRfp41024k
deepseek-ai/text-generation
DeepSeek-V4-Pro-0813
A DeepSeek-V4-Pro release for demanding reasoning and agentic work.
$0.20 cached, $1.30 in, $2.60 out / 1M
ZDRPriorityFlex
deepseek-ai/text-generation
DeepSeek-V4-Flash-0731
An efficient DeepSeek-V4-Flash release for everyday inference.
$0.015 cached, $0.06 in, $0.18 out / 1M
ZDRPriorityFlex
zai-org/text-generation
GLM-5.2
A flagship model for long-horizon tasks and agentic applications.
$0.105 cached, $0.563 in, $1.80 out / 1M
ZDRPriorityFlex
nvidia/text-generation
NVIDIA-Nemotron-3-Ultra-550B-A55B
Built for frontier reasoning, orchestration, coding agents and deep research.
$0.10 cached, $0.50 in, $2.20 out / 1M
ZDRPriorityFlex
deepseek-ai/text-generation
DeepSeek-V4-Flash
An efficiency-focused mixture-of-experts model for responsive applications.
$0.018 cached, $0.09 in, $0.18 out / 1M
ZDRPriorityFlex
AI Inference Metrics
The measures that matter for speed, scale, stability and spend
Throughput
Tokens per second
Responsiveness
Time to first token
Capacity
Requests per second
Compute
Infrastructure at scale
DeepCluster
Your own NVIDIA B300
GPU cluster
Dedicated hardware, procured and operated by Deepinfra. Full ownership, Tier 3 datacenter, 99.982% uptime SLA.
Explore GPU clustersNVIDIA B300 · 5-year term
$1.98/GPU-hr
vs $6.50 /GPU-hr on public cloud
70%cheaper than cloud
288 GBHBM3e per GPU
256–5,000GPUs available