Models

Models from leading labs, each with the providers that serve it. Open a model to see its providers' price, latency and uptime.

models.json Get a key

All2 Chat0 Image0 Video0 Decisions2

/

Open weights only Sort

Clear filters · 1 active

Input modalities

Image0File0Audio0Video0

Output modalities

Text0Image0Video0Typed answers2

Context length

Any32K+0128K+0200K+01M+0

Supported parameters

Tool calling0Reasoning0Structured outputs0JSON mode0

Data policy

Zero data retention0

Input price /1M

AnyFree0≤ $0.502≤ $12≤ $52

Labs

OpenAI0Anthropic0Google0Mistral AI0ByteDance0Qwen0DeepSeek0Krea0xAI0Morph0ScaleDown0Z.ai0Alibaba0Bespoke Labs2Black Forest Labs0Cloudflare0Ideogram0Moonshot AI0NVIDIA0RouterPlus0Tencent0Xiaomi0Fastino0Kuaishou0Levanto0Luma0Meta0MiniMax0Perplexity0Recraft0TypeSafe0

Providers1 selected

Bespoke Labs2DeepInfra29OpenAI17Krea AI16Nebius13Novita AI12Replicate12Anthropic9Mistral AI9Morph8ScaleDown3Cloudflare2RouterPlus2Fastino1Levanto1Perplexity1TypeSafe1

2 decision models

Bespoke Labs×

Decision models

POST /v1/decisions

Bespoke Nimble v4 Maxvia Bespoke Labs→

Context262K

Input /1M$0.09

Modalitytext → typed answers

bespokelabs/nimble-v4-max

Bespoke Nimble v4via Bespoke Labs→

Context262K

Input /1M$0.04

Modalitytext → typed answers

bespokelabs/nimble-v4

RouterPlus · Data policyprices USD · provider latency and uptime from the last 24h