We use essential cookies to make our site work. With your consent, we may also use non-essential cookies to improve user experience and analyze website traffic…

🚀 New models by Bria.ai, generate and edit images at scale 🚀

FAST
SIMPLE
RELIABLE
LOW-COST

AI Inference

Accelerate your AI with developer-friendly APIs designed for performance and cost-efficiency.

Let's GoBook a consultation
deepseek-ai logo
deepseek-aitext-generation
DeepSeek-OCR
$0.03/M in • $0.10/M out
allenai logo
allenaitext-generation
olmOCR-2-7B-1025
$0.09/M in • $0.19/M out
PaddlePaddle logo
PaddlePaddletext-generation
PaddleOCR-VL-0.9B
$0.14/M in • $0.80/M out
NVIDIA logo
NVIDIAgpu-rental
On-Demand DGX B200 GPUs
$2.49 / instance-hour
Qwen logo
Qwentext-generation
Qwen3-Coder-30B-A3B-Instruct
$0.07/M in • $0.26/M out
zai-org logo
zai-orgtext-generation
GLM-4.6
$0.45/M in • $1.90/M out
deepseek-ai logo
deepseek-aitext-generation
DeepSeek-V3.2-Exp
$0.27/M in • $0.40/M out
deepseek-ai logo
deepseek-aitext-generation
DeepSeek-V3.1-Terminus
$0.27/M in • $1.00/M out
Qwen logo
Qwentext-generation
Qwen3-Next-80B-A3B-Instruct
$0.14/M in • $1.10/M out
moonshotai logo
moonshotaitext-generation
Kimi-K2-Instruct-0905
$0.50/M in • $2.00/M out
deepseek-ai logo
deepseek-aitext-generation
DeepSeek-V3.1
$0.27/M in • $1.00/M out
openai logo
openaitext-generation
gpt-oss-120b
$0.05/M in • $0.24/M out
openai logo
openaitext-generation
gpt-oss-20b
$0.03/M in • $0.14/M out
Qwen logo
Qwentext-generation
Qwen3-Coder-480B-A35B-Instruct-Turbo
$0.29/M in • $1.20/M out
Qwen logo
Qwentext-generation
Qwen3-235B-A22B-Thinking-2507
$0.30/M in • $2.90/M out
Qwen logo
Qwentext-generation
Qwen3-Coder-480B-A35B-Instruct
$0.40/M in • $1.60/M out
deepseek-ai logo
deepseek-aitext-generation
DeepSeek-OCR
$0.03/M in • $0.10/M out
allenai logo
allenaitext-generation
olmOCR-2-7B-1025
$0.09/M in • $0.19/M out
PaddlePaddle logo
PaddlePaddletext-generation
PaddleOCR-VL-0.9B
$0.14/M in • $0.80/M out
NVIDIA logo
NVIDIAgpu-rental
On-Demand DGX B200 GPUs
$2.49 / instance-hour
Qwen logo
Qwentext-generation
Qwen3-Coder-30B-A3B-Instruct
$0.07/M in • $0.26/M out
zai-org logo
zai-orgtext-generation
GLM-4.6
$0.45/M in • $1.90/M out
deepseek-ai logo
deepseek-aitext-generation
DeepSeek-V3.2-Exp
$0.27/M in • $0.40/M out
deepseek-ai logo
deepseek-aitext-generation
DeepSeek-V3.1-Terminus
$0.27/M in • $1.00/M out
Qwen logo
Qwentext-generation
Qwen3-Next-80B-A3B-Instruct
$0.14/M in • $1.10/M out
moonshotai logo
moonshotaitext-generation
Kimi-K2-Instruct-0905
$0.50/M in • $2.00/M out
deepseek-ai logo
deepseek-aitext-generation
DeepSeek-V3.1
$0.27/M in • $1.00/M out
openai logo
openaitext-generation
gpt-oss-120b
$0.05/M in • $0.24/M out
openai logo
openaitext-generation
gpt-oss-20b
$0.03/M in • $0.14/M out
Qwen logo
Qwentext-generation
Qwen3-Coder-480B-A35B-Instruct-Turbo
$0.29/M in • $1.20/M out
Qwen logo
Qwentext-generation
Qwen3-235B-A22B-Thinking-2507
$0.30/M in • $2.90/M out
Qwen logo
Qwentext-generation
Qwen3-Coder-480B-A35B-Instruct
$0.40/M in • $1.60/M out
Let's GoBook a consultation
Abacus.AI
Hugging Face
interface.ai
Salesforce
Requesty
Abacus.AI
Hugging Face
interface.ai
Salesforce
Requesty

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 are there for you with our 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 all your needs.

Zero Retention. Compliant. Secure.

With our zero retention policy your inputs, your outputs, and your user data stay private. DeepInfra is SOC 2 and ISO 27001 certified. We follow the best practices in information security and privacy.

Our Hardware. Our Data Centers. Your Performance Edge.

DeepInfra runs on our own cutting-edge inference optimised infrastructure, in secure US-based data centers. Better performance and reliability for you.

Models

Explore our Featured Models

text-generation
deepseek-ai logo
deepseek-ai/
DeepSeek-OCR
deepseek-ai/DeepSeek-OCR cover image
DeepSeek-OCR as an initial investigation into the feasibility of compressing long contexts via optical 2D mapping. DeepSeek-OCR consists of two components: DeepEncoder and DeepSeek3B-MoE-A570M as the decoder. Specifically, DeepEncoder serves as the core engine, designed to maintain low activations under high-resolution input while achieving high compression ratios to ensure an optimal and manageable number of vision tokens. Experiments show that when the number of text tokens is within 10 times that of vision tokens (i.e., a compression ratio < 10x), the model can achieve decoding (OCR) precision of 97%. Even at a compression ratio of 20x, the OCR accuracy still remains at about 60%. This shows considerable promise for research areas such as historical long-context compression and memory forgetting mechanisms in LLMs.
bfloat16
8k
$0.03 in, $0.10 out / 1M
text-generation
allenai logo
allenai/
olmOCR-2-7B-1025
allenai/olmOCR-2-7B-1025 cover image
olmOCR is a specialized AI tool that converts PDF documents into clean, structured text while preserving important formatting and layout information. What makes olmOCR particularly valuable for developers is its ability to handle challenging PDFs that traditional OCR tools struggle with—including complex layouts, poor-quality scans, handwritten text, and documents with mixed content types. Built on a fine-tuned 7B vision-language model, olmOCR provides enterprise-grade PDF processing at a fraction of the cost of proprietary solutions.
fp8
16k
$0.09 in, $0.19 out / 1M
text-generation
PaddlePaddle logo
PaddlePaddle/
PaddleOCR-VL-0.9B
PaddlePaddle/PaddleOCR-VL-0.9B cover image
PaddleOCR-VL is a SOTA and resource-efficient model tailored for document parsing. Its core component is PaddleOCR-VL-0.9B, a compact yet powerful vision-language model (VLM) that integrates a NaViT-style dynamic resolution visual encoder with the ERNIE-4.5-0.3B language model to enable accurate element recognition. This innovative model efficiently supports 109 languages and excels in recognizing complex elements (e.g., text, tables, formulas, and charts), while maintaining minimal resource consumption. Through comprehensive evaluations on widely used public benchmarks and in-house benchmarks, PaddleOCR-VL achieves SOTA performance in both page-level document parsing and element-level recognition. It significantly outperforms existing solutions, exhibits strong competitiveness against top-tier VLMs, and delivers fast inference speeds. These strengths make it highly suitable for practical deployment in real-world scenarios.
bfloat16
16k
$0.14 in, $0.80 out / 1M
text-generation
Qwen logo
Qwen/
Qwen3-Coder-30B-A3B-Instruct
Qwen/Qwen3-Coder-30B-A3B-Instruct cover image
Qwen3-Coder-30B-A3B-Instruct is a high-performance code generation model optimized for agentic coding and complex programming tasks. With 30.5B total parameters and 3.3B activated through Mixture-of-Experts architecture, it delivers exceptional efficiency. The model features native support for 256K token context (extendable to 1M), making it ideal for repository-scale code understanding. It excels at tool calling, browser automation, and multi-step coding workflows.
fp8
256k
$0.07 in, $0.26 out / 1M
text-generation
zai-org logo
zai-org/
GLM-4.6
zai-org/GLM-4.6 cover image
Compared with GLM-4.5, GLM-4.6 brings several key improvements: Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex agentic tasks. Superior coding performance: The model achieves higher scores on code benchmarks and demonstrates better real-world performance in applications such as Claude Code、Cline、Roo Code and Kilo Code, including improvements in generating visually polished front-end pages. Advanced reasoning: GLM-4.6 shows a clear improvement in reasoning performance and supports tool use during inference, leading to stronger overall capability. More capable agents: GLM-4.6 exhibits stronger performance in tool using and search-based agents, and integrates more effectively within agent frameworks. Refined writing: Better aligns with human preferences in style and readability, and performs more naturally in role-playing scenarios.
fp4
198k
$0.11 cached, $0.45 in, $1.90 out / 1M
text-generation
deepseek-ai logo
deepseek-ai/
DeepSeek-V3.2-Exp
deepseek-ai/DeepSeek-V3.2-Exp cover image
DeepSeek-V3.2-Exp is an intermediate step toward the next-generation architecture of the DeepSeek models by introducing DeepSeek Sparse Attention—a sparse attention mechanism designed to explore and validate optimizations for training and inference efficiency in long-context scenarios.
fp4
160k
$0.27 in, $0.40 out / 1M
text-generation
deepseek-ai logo
deepseek-ai/
DeepSeek-V3.1-Terminus
deepseek-ai/DeepSeek-V3.1-Terminus cover image
DeepSeek-V3.1 Terminus is an update to DeepSeek V3.1 that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's performance in coding and search agents. It is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes. It extends the DeepSeek-V3 base with a two-phase long-context training process. Users can control the reasoning behaviour with the reasoning enabled boolean. Learn more in our docs The model improves tool use, code generation, and reasoning efficiency, achieving performance comparable to DeepSeek-R1 on difficult benchmarks while responding more quickly. It supports structured tool calling, code agents, and search agents, making it suitable for research, coding, and agentic workflows.
fp4
160k
$0.216 cached, $0.27 in, $1.00 out / 1M
text-generation
Qwen logo
Qwen/
Qwen3-Next-80B-A3B-Instruct
Qwen/Qwen3-Next-80B-A3B-Instruct cover image
Over the past few months, we have observed increasingly clear trends toward scaling both total parameters and context lengths in the pursuit of more powerful and agentic artificial intelligence (AI). We are excited to share our latest advancements in addressing these demands, centered on improving scaling efficiency through innovative model architecture. We call this next-generation foundation models Qwen3-Next.
bfloat16
256k
$0.14 in, $1.10 out / 1M
text-generation
moonshotai logo
moonshotai/
Kimi-K2-Instruct-0905
moonshotai/Kimi-K2-Instruct-0905 cover image
Kimi K2 0905 is the September update of Kimi K2 0711. It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It supports long-context inference up to 256k tokens, extended from the previous 128k. This update improves agentic coding with higher accuracy and better generalization across scaffolds, and enhances frontend coding with more aesthetic and functional outputs for web, 3D, and related tasks. Kimi K2 is optimized for agentic capabilities, including advanced tool use, reasoning, and code synthesis. It excels across coding (LiveCodeBench, SWE-bench), reasoning (ZebraLogic, GPQA), and tool-use (Tau2, AceBench) benchmarks. The model is trained with a novel stack incorporating the MuonClip optimizer for stable large-scale MoE training.
fp4
256k
$0.40 cached, $0.50 in, $2.00 out / 1M
text-generation
deepseek-ai logo
deepseek-ai/
DeepSeek-V3.1
deepseek-ai/DeepSeek-V3.1 cover image
DeepSeek-V3.1 is post-trained on the top of DeepSeek-V3.1-Base, which is built upon the original V3 base checkpoint through a two-phase long context extension approach, following the methodology outlined in the original DeepSeek-V3 report. We have expanded our dataset by collecting additional long documents and substantially extending both training phases. The 32K extension phase has been increased 10-fold to 630B tokens, while the 128K extension phase has been extended by 3.3x to 209B tokens. Additionally, DeepSeek-V3.1 is trained using the UE8M0 FP8 scale data format to ensure compatibility with microscaling data formats.
fp4
160k
$0.216 cached, $0.27 in, $1.00 out / 1M
text-generation
openai logo
openai/
gpt-oss-120b
openai/gpt-oss-120b cover image
gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. The model supports configurable reasoning depth, full chain-of-thought access, and native tool use, including function calling, browsing, and structured output generation.
fp4
128k
$0.05 in, $0.24 out / 1M
text-generation
openai logo
openai/
gpt-oss-20b
openai/gpt-oss-20b cover image
gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for lower-latency inference. The model is trained in OpenAI’s Harmony response format and supports reasoning level configuration, fine-tuning, and agentic capabilities including function calling, tool use, and structured outputs.
fp4
128k
$0.03 in, $0.14 out / 1M
View full collection (100+)

Live AI Inference Metrics

End-to-end insights into speed, scale, stability and spend

0.00M
Tokens per second
0ms
Time to first token
0
Requests per second
0.00
exaFLOPS

Host your models on our servers

Low cost, high privacy to ensure you run your operations smoothly

How it works
Footer Logo
SOC 2 CertifiedISO 27001 Certified

Have questions or need a custom solution?

Contact Sales

Company

Pricing
Docs
Compare
DeepStart
About
Careers
Contact us
Trust Center
DeepGPT

Latest Models

deepseek-ai/DeepSeek-V3.1zai-org/GLM-4.6moonshotai/Kimi-K2-Instruct-0905anthropic/claude-3-7-sonnet-latestdeepseek-ai/DeepSeek-V3.2-Exp

Featured Models

deepseek-ai/DeepSeek-R1-0528Qwen/Qwen3-14Bmoonshotai/Kimi-K2-Instruct-0905deepseek-ai/DeepSeek-V3-0324Qwen/Qwen3-Coder-30B-A3B-Instruct
Built With Love in Palo Alto

© 2025 Deep Infra. All rights reserved.

Privacy PolicyTerms of Service