DeepStart | Production-Ready Machine Learning Models | DeepInfra

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…

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

DeepStart1,000,000,000 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 V3.1 prices

Featured models

What we loved, used, and implemented most last month

text-generation

moonshotai/Kimi-K3 cover image

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.

$0.27 cached, $2.70 in, $13.50 out / 1M

text-generation

zai-org/GLM-5.2 cover image

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**.

$0.18 cached, $0.93 in, $3.00 out / 1M

text-generation

moonshotai/Kimi-K2.7-Code cover image

Kimi K2.7 Code is a coding-focused agentic model built upon Kimi K2.6. With substantial improvements on real-world long-horizon coding tasks, it strengthens end-to-end task completion across complex software engineering workflows while improving token efficiency, reducing thinking-token usage by approximately 30% compared with Kimi K2.6.

$0.15 cached, $0.74 in, $3.50 out / 1M

text-generation

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

nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B cover image

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

text-generation

DeepSeek-V4-Flash

deepseek-ai/DeepSeek-V4-Flash cover image

DeepSeek V4 Flash is an efficiency-focused MoE model with 284B total parameters (13B active) and a 1M-token context window. It's tuned for fast inference and high-throughput use cases while still holding up on reasoning and coding tasks.

$0.018 cached, $0.09 in, $0.18 out / 1M

text-generation

DeepSeek-V4-Pro

deepseek-ai/DeepSeek-V4-Pro cover image

DeepSeek V4 Pro is an MoE model with 1.6T total parameters (49B active) and a 1M-token context window. It's built for advanced reasoning, coding, and long-running agent tasks, and performs well on knowledge, math, and software engineering benchmarks.

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

text-generation

moonshotai/Kimi-K2.6 cover image

Kimi K2.6 is an open-source, native multimodal agentic model that advances practical capabilities in long-horizon coding, coding-driven design, proactive autonomous execution, and swarm-based task orchestration.

$0.15 cached, $0.75 in, $3.50 out / 1M

text-generation

XiaomiMiMo/MiMo-V2.5-Pro cover image

MiMo-V2.5-Pro is an open-source Mixture-of-Experts (MoE) language model with 1.02T total parameters and 42B active parameters. It utilizes the hybrid attention architecture and 3-layers Multi-Token Prediction (MTP) introduced in [MiMo-V2-Flash](https://github.com/XiaomiMiMo/MiMo-V2-Flash).

$0.20 cached, $1.00 in, $3.00 out / 1M

text-generation

Qwen3.6-35B-A3B

Qwen/Qwen3.6-35B-A3B cover image

Qwen3.6-35B-A3B is Alibaba's latest flagship Mixture-of-Experts model, with 35B total parameters and only 3B activated per token (256 experts, 8 routed + 1 shared). Built on direct feedback from the community, Qwen3.6 prioritizes stability and real-world utility, offering developers a more intuitive, responsive, and genuinely productive coding experience.

$0.15 in, $0.95 out / 1M

text-generation

zai-org/GLM-5.1 cover image

GLM-5.1 is Z-AI's next-generation flagship model for agentic engineering, with significantly stronger coding capabilities than its predecessor. It achieves state-of-the-art performance on SWE-Bench Pro and leads GLM-5 by a wide margin on NL2Repo (repo generation) and Terminal-Bench 2.0 (real-world terminal tasks).

$0.205 cached, $1.05 in, $3.50 out / 1M

text-generation

Qwen3.5-397B-A17B

Qwen/Qwen3.5-397B-A17B cover image

Qwen3.5-397B-A17B is Alibaba's most capable Qwen3.5 model, a Mixture-of-Experts architecture with 397B total parameters and 17B activated per token. It features a 262K token context window (extensible to 1M with YaRN), thinking/reasoning mode, tool calling with MCP integration, and support for 201 languages. Sets state-of-the-art results on reasoning, coding, math, and multimodal benchmarks.

$0.22 cached, $0.45 in, $3.00 out / 1M

text-generation

gemma-4-26B-A4B-it

google/gemma-4-26B-A4B-it cover image

Efficient, MoE variant of Gemma 4. Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input and generating text output.

$0.07 in, $0.34 out / 1M

View full collection (100+)

SOC 2 Certified

ISO 27001 Certified

Have questions or need a custom solution?

Company

Latest Models

anthropic/claude-opus-5 thinkingmachines/Inkling Qwen/Qwen3-ASR-1.7B Qwen/Qwen3-ASR-0.6B nvidia/Nemotron-3-Embed-8B

Featured Models

Qwen/Qwen3-TTS moonshotai/Kimi-K2.5 Qwen/Qwen3-TTS-VoiceDesign black-forest-labs/FLUX-2-klein-4b Qwen/Qwen3.5-397B-A17B

Built With Love in Palo Alto

© 2026 DeepInfra. All rights reserved.

Privacy Policy Terms of Service