MorphMorph
Morph Models

Fast general models for agent loops

Run the primary agent loop on fast, OpenAI-compatible coding models served on Morph's custom kernels. One API for chat, code generation, and reasoning.
Get API KeyRead the docsPrivate deployments
50/50 TESTS PASS
UPDATED
0 Tok/s
Morph Models

Frontier coding models, served on custom kernels

Output speed

Codegen-specific optimizations and custom GPU kernels. Up to 150 tok/s on DeepSeek V4 Flash, measured on private deployments with custom speculators. Public endpoints run on shared capacity.

tok/s on private deployments150DSV4 Flash100Qwen 3.6 27B80GLM-5.2 744B90MiniMax M2.7

One OpenAI-compatible API

Point your existing client at api.morphllm.com. Switch models by changing one string.

01
import OpenAI from "openai";
02
03
const client = new OpenAI({
04
  baseURL: "https://api.morphllm.com/v1",
05
  apiKey: process.env.MORPH_API_KEY,
06
});
07
08
const res = await client.chat.completions.create({
09
  model: "morph-glm52-744b",
10
  messages: [{ role: "user", content: "Refactor this function..." }],
11
});

The lineup

Open-weight frontier models with long context, served and billed per token. No per-seat fees.

01
// Available general models
02
morph-glm52-744b       // 744B MoE, 1M context
03
morph-minimax3-428b    // 428B MoE, 256k context
04
morph-minimax27-230b   // 230B MoE, agentic workflows
05
morph-dsv4flash        // 1M context, fast
06
morph-qwen36-27b       // dense, low latency

Built for production agent workloads

Inference optimized for coding agents

Every agent will write code. We bet the stack on it.

So we tune every layer for that one workload: custom GPU kernels, speculative decoding shaped around code, and serving built for the agent loop instead of general chat. Not general infrastructure with code bolted on.

Private deployments

The fastest endpoints are private deployments

The headline speeds on this page come from dedicated deployments, not the shared public endpoints. At scale we build the deployment around your traffic: speculators trained on it, caching tuned to it, and pricing well under public rates.

100B+

tokens per day served across private deployments

Custom speculators

trained on your traffic for higher acceptance rates

Custom caching

prefix and KV caching tuned to your workload

Volume pricing

large discounts over public per-token rates

Talk to us about a private deployment

Sign up and start free. No card required.

Get API Key

Add a billing method for $10 in free credits and full rate limits.