DeepStart | Production-Ready Machine Learning Models | Deep Infra

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…

GLM-5.1 - state-of-the-art agentic engineering, now available on DeepInfra!

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

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).

$0.26 cached, $1.40 in, $4.40 out / 1M

inworld-tts-1.5-max

inworld-ai/inworld-tts-1.5-max cover image

High-quality multilingual text-to-speech model by Inworld AI with 130+ preset voices across 15 languages. Supports voice cloning, word-level timestamps, and streaming. Optimized for natural, expressive speech with <250ms time-to-first-audio.

$50.00 per 1M characters

inworld-tts-1.5-mini

inworld-ai/inworld-tts-1.5-mini cover image

Fast multilingual text-to-speech model by Inworld AI with 130+ preset voices across 15 languages. Supports voice cloning, word-level timestamps, and streaming. Optimized for low-latency applications with <130ms time-to-first-audio.

$25.00 per 1M characters

text-generation

stepfun-ai/Step-3.5-Flash cover image

Step 3.5 Flash is an open-source reasoning model by StepFun with 196B total parameters (11B active) using Mixture of Experts. It features a 256K context window, deep reasoning, tool calling, and agentic capabilities, achieving 97.3 on AIME 2025 and 74.4% on SWE-bench Verified.

$0.02 cached, $0.10 in, $0.30 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.

$0.27 cached, $0.54 in, $3.40 out / 1M

text-generation

Qwen3.5-122B-A10B

Qwen/Qwen3.5-122B-A10B cover image

Qwen3.5-122B-A10B is a large Mixture-of-Experts model from Alibaba's Qwen3.5 series with 122B total parameters and 10B activated per token. It features a 262K token context window (extensible to 1M with YaRN), thinking/reasoning mode, tool calling, and support for 201 languages. Excels at complex reasoning, coding, multimodal understanding, and agentic tasks with the efficiency of sparse activation.

$0.145 cached, $0.29 in, $2.90 out / 1M

text-generation

Qwen3.5-35B-A3B

Qwen/Qwen3.5-35B-A3B cover image

Qwen3.5-35B-A3B is an efficient Mixture-of-Experts model from Alibaba's Qwen3.5 series with 35B total parameters and only 3B activated per token. It features a 262K token context window (extensible to 1M with YaRN), thinking/reasoning mode, tool calling, and support for 201 languages. Delivers strong performance on reasoning, coding, and vision-language tasks at a fraction of the compute cost.

$0.11 cached, $0.22 in, $2.20 out / 1M

text-generation

Qwen/Qwen3.5-27B cover image

Qwen3.5-27B is Alibaba's largest dense Qwen3.5 model, delivering near-frontier quality across reasoning, coding, and instruction following. It features a 262K token context window (extensible to 1M), thinking/reasoning mode, tool calling, multi-token prediction, and support for 201 languages. Best suited for production deployments and complex enterprise tasks requiring top-tier performance.

$0.26 in, $2.60 out / 1M

text-generation

Qwen/Qwen3.5-9B cover image

Qwen3.5-9B is a high-performance model from Alibaba's Qwen3.5 series with a hybrid Gated Delta Networks and sparse MoE architecture. It features a 262K token context window, thinking/reasoning mode, tool calling, multi-token prediction, and support for 201 languages. Excels at reasoning, coding, instruction following, and long-context tasks.

$0.04 in, $0.20 out / 1M

text-generation

Qwen/Qwen3.5-4B cover image

Qwen3.5-4B is a mid-size model from Alibaba's Qwen3.5 series that delivers a strong balance of performance and efficiency. It features a 262K token context window (extensible to 1M with YaRN), thinking/reasoning mode, tool calling, and support for 201 languages. Well-suited for complex reasoning, code generation, and agentic applications.

$0.03 in, $0.15 out / 1M

text-generation

Qwen/Qwen3.5-2B cover image

Qwen3.5-2B is a compact yet capable model from Alibaba's Qwen3.5 series. It features a 262K token context window, support for 201 languages, thinking/reasoning mode, and tool calling for agentic workflows. A strong choice for prototyping, fine-tuning, and efficient multilingual deployments.

$0.02 in, $0.10 out / 1M

text-generation

Qwen/Qwen3.5-0.8B cover image

Qwen3.5-0.8B is Alibaba's smallest model in the Qwen3.5 series, featuring a hybrid Gated Delta Networks and sparse Mixture-of-Experts architecture. Despite its compact size, it supports a 262K token context window, 201 languages, thinking/reasoning mode, and tool calling. Ideal for edge deployments, resource-constrained environments, and lightweight inference tasks.

$0.01 in, $0.05 out / 1M

View full collection (100+)

SOC 2 Certified

ISO 27001 Certified

Have questions or need a custom solution?

Company

Latest Models

zai-org/GLM-5.1 deepseek-ai/DeepSeek-V3.2-Exp zai-org/GLM-4.6 anthropic/claude-3-7-sonnet-latest deepseek-ai/DeepSeek-V3.1

Featured Models

Qwen/Qwen3-Max black-forest-labs/FLUX-2-klein-4b Qwen/Qwen3.5-27B google/gemma-4-26B-A4B-it moonshotai/Kimi-K2.5

Built With Love in Palo Alto

© 2026 Deep Infra. All rights reserved.

Privacy Policy Terms of Service