Model Library

Every model, one endpoint

Browse 36+ open and frontier models on the Parasail inference cloud. Filter by category, compare specs, and call any model with a single OpenAI-compatible API.

36+
Models
1M
Max context
6
GPU types
All models

Explore the library

Filter by category to find the right model for your use case.

reasoning Z.AI | Released: 6-26

GLM-5.2

Z.AI’s next-gen model for agentic engineering with sustained execution on long-horizon tasks.

reasoningagenticlong-context
1M tokens · Text
reasoning Z.AI | Released: 4-26

GLM-5.1

Strong reasoning and coding model with a 1M context window at competitive pricing.

reasoningcodinglong-context
1M tokens · Text
reasoning Z.AI | Released: 2-26

GLM-5

Z.AI’s open model for reasoning and agentic workflows.

reasoningagentic
128K tokens · Text
reasoning MiniMax | Released: 5-26

MiniMax M3

Highly efficient MoE model delivering strong reasoning at exceptionally low cost.

reasoningefficient
1M tokens · Text
reasoning MiniMax | Released: 3-26

MiniMax M2.5

Cost-effective large model with strong general capabilities and long context.

reasoninglong-context
1M tokens · Text
reasoning DeepSeek | Released: 5-26

DeepSeek V4 Pro

Open model for reasoning and coding workloads.

reasoningcoding
128K tokens · Text
compact DeepSeek | Released: 5-26

DeepSeek V4 Flash

Ultra-fast, ultra-cheap reasoning model for high-throughput workloads.

efficientfast
128K tokens · Text
reasoning Moonshot | Released: 4-26

Kimi K2.6

Strong reasoning model with excellent long-context understanding.

reasoninglong-context
256K tokens · Text
reasoning Alibaba | Released: 5-26

Qwen3.5 397B-A17B

Large-scale MoE model with frontier reasoning and multilingual capabilities.

reasoningmultilingual
256K tokens · Text
reasoning Alibaba | Released: 7-25

Qwen3 235B-A22B

Strong open MoE model with excellent coding and reasoning at low cost.

reasoningcoding
256K tokens · Text
reasoning Trinity | Released: 4-26

Trinity Large (Thinking)

Reasoning-focused model with extended thinking for complex problem-solving.

reasoning
128K tokens · Text
reasoning NVIDIA | Released: 6-26

Nemotron 3 Ultra 550B

NVIDIA’s flagship open model optimized for enterprise reasoning workloads.

reasoningenterprise
128K tokens · Text
reasoning Meta | Released: 4-25

Llama 4 Maverick

Meta’s multimodal Llama model with native image understanding.

reasoningmultimodal
1M tokens · Text + Vision
general Meta | Released: 12-24

Llama 3.3 70B

Meta’s reliable workhorse — great quality-to-cost ratio for production.

generalproduction
128K tokens · Text
coding Moonshot | Released: 5-26

Kimi K2.7 Code

Specialized coding model optimized for software engineering and agentic coding workflows.

codingagentic
256K tokens · Text
coding Alibaba | Released: 5-26

Qwen3-Coder-Next

Code-specialized model with strong fill-in-the-middle and agentic coding support.

codingefficient
256K tokens · Text
vision Alibaba | Released: 5-26

Qwen3-VL 235B-A22B

Large vision-language model with strong document understanding and visual reasoning.

visionreasoning
256K tokens · Text + Vision
vision Alibaba | Released: 5-26

Qwen3-VL 8B

Compact vision-language model — fast and affordable for image understanding at scale.

visionefficient
128K tokens · Text + Vision
vision Alibaba | Released: 1-25

Qwen2.5-VL 72B

Proven vision-language model for OCR, document QA, and visual grounding.

visiondocument
128K tokens · Text + Vision
compact Alibaba | Released: 6-26

Qwen3.6 35B-A3B

Efficient MoE model with 3B active parameters — great price-to-performance.

efficientfast
128K tokens · Text
compact Alibaba | Released: 5-26

Qwen3.5 35B-A3B

Compact MoE model with strong reasoning at minimal cost per token.

efficient
128K tokens · Text
compact Alibaba | Released: 4-26

Qwen3-Next 80B

Balanced model with strong general capabilities at a competitive price point.

generalefficient
128K tokens · Text
compact Mistral | Released: 3-26

Mistral Small 3.2 24B

Mistral’s efficient model — excellent for high-volume, latency-sensitive workloads.

efficientfast
128K tokens · Text
compact Google | Released: 3-26

Gemma 4 26B-A4B

Google’s efficient MoE Gemma model with 4B active parameters.

efficientfast
128K tokens · Text
compact Google | Released: 3-26

Gemma 4 31B

Google’s latest open model with strong general performance and broad language support.

generalmultilingual
128K tokens · Text
compact Google | Released: 3-25

Gemma 3 27B

Proven compact model with multimodal capabilities and strong multilingual support.

multilingualefficient
128K tokens · Text
compact OpenAI | Released: 8-25

gpt-oss-120b

OpenAI’s open-weight model with strong reasoning at a low cost.

reasoningopen-weight
128K tokens · Text
compact OpenAI | Released: 8-25

gpt-oss-120b (Fast)

Optimized fast tier of gpt-oss-120b with lower latency for real-time workloads.

fastopen-weight
128K tokens · Text
compact OpenAI | Released: 8-25

gpt-oss-20b

Compact open-weight model from OpenAI — ultra-cheap, fits on a single GPU.

efficientopen-weight
128K tokens · Text
compact Xiaomi | Released: 4-26

MiMo v2.5

Xiaomi’s efficient reasoning model with strong coding capabilities.

reasoningcoding
128K tokens · Text
compact Skyfall | Released: 2-26

Skyfall 31B v4.2

Fine-tuned model optimized for creative writing and conversational tasks.

creativeconversational
128K tokens · Text
compact Skyfall | Released: 2-25

Skyfall 36B v2

Fine-tuned model with enhanced instruction-following and creative output.

creativeinstruction-tuned
128K tokens · Text
compact Cydonia | Released: 8-25

Cydonia 24B v4.1

Fine-tuned model with enhanced roleplay and character consistency.

roleplayconversational
32K tokens · Text
embeddings BAAI | Released: 1-24

BGE-M3

Multilingual, multi-functional embedding model supporting 100+ languages.

multilingualretrieval
8K tokens · Embedding
audio Resemble | Released: 4-26

Resemble TTS (English)

High-quality text-to-speech model with natural-sounding English voices.

ttsvoice
· Audio
agents ByteDance | Released: 4-25

UI-TARS 1.5 7B

GUI agent model that can operate computer interfaces autonomously.

agenticgui
128K tokens · Text + Vision
No models in this category yet.

Find the right model for your workload

Start with free credits — no credit card. Call any model in minutes with an OpenAI-compatible API.