DeepStart | Production-Ready Machine Learning Models

DeepInfra raises $107M Series B to scale the inference cloud — read the announcement

DeepStart~50,000,000,000 free tokens*

To qualify your startup needs to meet the following

Have raised between 250K and 10M USD

Founded in the last 2 years

* at DeepSeek V4 Flash prices
Credits expire 1 year after approval

Featured models

What we loved, used, and implemented most last month

text-generation

tencent/

Hy4-preview

Hy4 preview is a 770B-parameter Mixture-of-Experts flagship model from the Tencent Hy Team, with 49B parameters activated per token and a 1M-token context window. It uses Gated DeepSeek Sparse Attention with IndexCache, and is post-trained for software engineering, office and data analysis, game development, and scientific research.

ZDR

fp8

1024k

$0.042 cached, $0.834 in, $2.501 out / 1M

text-generation

XiaomiMiMo/

MiMo-V2.6-Flash

MiMo-V2.6-Flash is the efficiency-balanced model in Xiaomi's MiMo-V2.6 series: a sparse Mixture-of-Experts model with 309B total and 15B activated parameters, natively omnimodal across text, image, video and audio, with a 1M-token context window. Trained with large-scale mixed reinforcement learning across coding, general agents, visual and cybersecurity tasks, it is built for agentic workloads such as long-horizon coding, tool use and computer use.

ZDR

fp8

1024k

$0.003 cached, $0.14 in, $0.28 out / 1M

text-generation

XiaomiMiMo/

MiMo-V2.6-Pro

MiMo-V2.6-Pro is the flagship of Xiaomi's MiMo-V2.6 series: a sparse Mixture-of-Experts model with 1.02T total and 42B activated parameters, natively omnimodal across text, image, video and audio, with a 1M-token context window. Trained with large-scale mixed reinforcement learning and groupwise agentic grading, it is built for demanding agentic work including long-horizon coding, multi-tool agents and cybersecurity tasks.

ZDR

fp8

1024k

$0.004 cached, $0.43 in, $0.87 out / 1M

text-generation

deepseek-ai/

DeepSeek-V4.1-Flash

Introduce DeepSeek-V4.1-Flash, a multimodal Mixture-of-Experts (MoE) model with 552B backbone parameters and support for contexts of up to one million tokens.

$0.004 cached, $0.14 in, $0.42 out / 1M

text-generation

zai-org/

GLM-5.3

GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves on GLM-5.2 in coding and in the balance between performance and token efficiency.

$0.125 cached, $0.563 in, $2.50 out / 1M

text-generation

zai-org/

GLM-5.3-Flash

GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while reducing compute overhead.

$0.015 cached, $0.075 in, $0.25 out / 1M

text-generation

moonshotai/

Kimi-K3

Kimi K3 is Moonshot AI's 2.8T-parameter open-weight multimodal reasoning model. Built for complex coding, knowledge work, and long-horizon agentic workflows, it excels at navigating large repositories, calling tools, debugging, and iterating on images, logs, tests, and runtime feedback. Its architecture relies on KDA and Attention Residuals for computational efficiency.

ZDR

Cache retention

1024k

$0.285 cached, $2.85 in, $14.25 out / 1M

text-generation

Qwen/

Qwen3.8-2.4T-A95B

Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of Qwen3.8 Max, with 95 billion active parameters out of 2.4 trillion total. It is suited for coding, research, complex reasoning, and agentic workflows.

ZDR

fp4

256k

$0.20 cached, $2.00 in, $6.00 out / 1M

text-generation

deepseek-ai/

DeepSeek-V4-Pro-0813

DeepSeek-V4-Pro-0813 is the official release of DeepSeek-V4-Pro, superseding the preview version, with greatly enhanced agentic capabilities and performance improvements that are especially pronounced in production environments. It is built on the DeepSeek-V4-Pro (Preview) model structure, with a DSpark speculative decoding module attached.

$0.10 cached, $1.30 in, $2.60 out / 1M

text-generation

deepseek-ai/

DeepSeek-V4-Flash-0731

DeepSeek-V4-Flash-0731 is the official release of DeepSeek-V4-Flash, superseding the preview version, with substantially enhanced agentic capabilities. DeepSeek-V4-Flash-0731 outperforms DeepSeek-V4-Pro (Preview) on benchmarks listed below despite its far smaller activated parameter count, and is broadly competitive with the strongest proprietary models available.

$0.015 cached, $0.06 in, $0.18 out / 1M

text-generation

zai-org/

GLM-5.2

GLM-5.2 is Z-AI's latest flagship model for long-horizon tasks. It marks a substantial leap in long-horizon task capability over its predecessor GLM-5.1 and, for the first time, delivers that capability on a **solid 1M-token context**.

$0.105 cached, $0.563 in, $1.80 out / 1M

text-generation

nvidia/

NVIDIA-Nemotron-3-Ultra-550B-A55B

Nemotron 3 Ultra is built for, frontier reasoning, orchestration, coding agents, deep research, and complex enterprise workflows. It delivers up to 5x faster inference and up to 30% lower cost for agentic workloads while supporting up to 1M token context.

$0.10 cached, $0.50 in, $2.20 out / 1M

View full collection (100+)

Have questions or need a custom solution?

Company

Latest Models

anthropic/claude-sonnet-5-5 tencent/Hy4-preview nvidia/Nemotron-3-Diarization anthropic/claude-opus-5-5 XiaomiMiMo/MiMo-V2.6-Pro

Featured Models

moonshotai/Kimi-K3 google/gemma-4-26B-A4B-it zai-org/GLM-5.2 XiaomiMiMo/MiMo-V2.6-Pro zai-org/GLM-5.3-Flash