What other models does Morph offer?

Morph builds a small family of specialized models for AI coding workflows rather than general-purpose chat models. Here are some other models Morph supports:

• Morph v3 Large: the higher-accuracy apply model, tuned to merge edits reliably on larger or more complex files, at a slightly higher price of $0.90 input and $1.90 output per million tokens

• Morph Compactor: the cheapest model in the lineup at $0.20 input and $0.50 output per million tokens, built to compress long conversation or code context down to what a downstream model actually needs

• Morph Embedding: a code-focused embedding model used for retrieval over a codebase, so an agent can find the right files before it edits them

How does Morph v3 Fast differ from Morph's other models?

Morph V3 Fast sits at the speed-first end of Morph's apply lineup.

• Speed: it's the fastest apply model Morph offers, running at roughly 10,500 tokens per second, which is what makes it viable in latency-sensitive edit loops

• Accuracy vs Morph v3 Large: Morph v3 Fast targets about 96% apply accuracy; Morph v3 Large is the one to reach for when edit correctness on complex, multi-hunk changes matters more than raw speed

• Pricing: at $0.80 input and $1.20 output per million tokens, it's cheaper than Morph v3 Large and more expensive than Morph Compactor, which does a different job entirely

• Purpose: all three share a large context window (around 131K tokens), but Morph v3 Fast and Morph v3 Large apply edits while Morph Compactor compresses context

Morph v3 Fast is the right pick for the high-volume apply step in a coding agent: you hand it the original file plus a proposed edit, and it returns the merged result quickly and cheaply.

What models should I consider using alongside Morph v3 Fast?

No single model is optimal for every task. Here are models worth pairing with Morph V3 Fast depending on what your product needs:

• Claude Opus 4.8: route here to generate the actual code changes on hard, multi-file tasks, then pass the resulting edit to Morph v3 Fast to apply it fast

• DeepSeek V4 Pro: a cost-efficient generation model for producing edits at high volume before the apply step, when you want frontier-level output without frontier pricing

• GPT-4.1: for agentic, multi-step workflows that plan and emit the edits Morph v3 Fast then merges into the file

• Gemini 3 Pro: for long-context reasoning across a large repo to decide what to change, upstream of the apply step

• Codestral: a code-specialized model for generating completions and edits in tighter, lower-latency coding loops

What are the challenges of using Morph v3 Fast in my product?

Like any production LLM, Morph V3 Fast comes with tradeoffs worth planning for:

• Narrow by design: it applies edits, it doesn't author them. Morph v3 Fast merges a provided change into a file but won't reason about what to change or write code from scratch, so you always need a generation model upstream

• Accuracy ceiling on complex edits: at around 96% apply accuracy and tuned for speed, ambiguous or large multi-hunk edits can misapply, which is the exact case Morph v3 Large is built for

• Provider dependency: relying on Morph alone means an outage or a deprecated model version stalls the apply step in your pipeline

• Cost at scale: at $0.80 input and $1.20 output per million tokens, a high-volume edit pipeline compounds quickly without active budget controls

• Ecosystem maturity: Morph is a newer, specialized provider, so its tooling, documentation, and regional availability are thinner than the major labs'

Why should I use Merge Gateway to route LLM requests with Morph v3 Fast and every other model?

Using Morph v3 Fast through Merge Gateway gives you access to the model itself and the infrastructure layer around it:

• One API, every provider: reach Morph v3 Fast and every other major LLM through a single endpoint and API key. Change providers by swapping the model string, with no application code changes

• Intelligent routing and automatic failover: Merge routes around Morph outages automatically, and routing policies based on cost, latency, or quality can cut spend by 40 to 60% without touching your application code

• Cost governance: set hard or soft project budgets so Morph v3 Fast spend stays within plan, with every request attributed to a model, project, and tag in one billing dashboard across all providers

• Build Your Own Router: define what "best" means for your traffic using curated ML benchmarks or your own eval scores, and the router scores each model per request and explains why it picked the winner

• Security and compliance controls: apply DLP rules and prompt injection protection before any request reaches Morph, and enforce per-project model and region policies outside your application code

How can I start routing requests to Morph V3 Fast via Merge Gateway?

Getting Morph v3 Fast running through Merge Gateway takes a few minutes:

1. Create an account and get your API key from the dashboard.

2. Install the Merge Gateway SDK: run pip install merge-gateway-sdk (Python) or npm install merge-gateway-sdk (Node). Alternatively, if you're already using the OpenAI SDK, set base_url = "https://api-gateway.merge.dev/v1/openai" and your existing code works as-is.

3. Make your first request using the provider/model format. For Morph v3 Fast, the model string is morph/morph-v3-fast. Swap the model string to route to any other provider without changing anything else.

4. Configure a routing policy in the dashboard to set failover behavior, cost limits, and optimization strategy. Your first policy can be as simple as naming Morph v3 Fast as primary with one fallback.

Full setup instructions and SDK references are in the Merge Gateway docs.