MorphMorph
Models
Open Source Models

GLM-5.2

744B MoE, 1M context. #1 on Design Arena.

Qwen

397B MoE, 262k context.

MiniMax

230B MoE for agentic workflows.

DeepSeek

1M-context model, served fast.

Specialized

Reflex

Classify every agent trace for any behavior that matters, in under 90ms.

Fast Apply

Merge AI-generated code edits instantly.

WarpGrep

AI search subagent with sub-6s searches.

Compact

Verbatim context compaction for long-running agents.

Model Router

Auto-route each prompt to the best model.

SDK

DocsPricingMCP
Resources

Blog

Engineering deep dives and product updates.

Startup Credits

Up to $5K in API credits for startups.

Contact Us

Talk to the team about your use case.

About

How we train and deploy models.

Careers

Join a small team shipping daily.

Usage-based pricing · start free

Pricing

Per-token
usage-based billing
No limits
practically no rate limits
200 req
free every month

Open Source Models

Frontier open weights, served on custom kernels for codegen.

Chat
GLM-5.2 744BFeatured
morph-glm52-744b
Speed~80 tok/sec
Input$1.1/1M
Output$4.1/1M
Context1M
Qwen 3.5 397B
morph-qwen35-397b
Speed~180 tok/sec
Input$0.5/1M
Cache read$0.3/1M
Output$3.5/1M
Context262k
Qwen 3.6 27B
morph-qwen36-27b
Speed~100 tok/sec
Input$0.289/1M
Output$2.4/1M
Context131k
MiniMax M2.7
morph-minimax27-230b
Speed~90 tok/sec
Input$0.279/1M
Output$1.2/1M
Context196k
MiniMax M3
morph-minimax3-428b
Speed~90 tok/sec
Input$0.6/1M
Output$2.4/1M
Context256k
DeepSeek V4 Flash
morph-dsv4flash
Speed~150 tok/sec
Input$0.139/1M
Output$0.278/1M
Context1M
ModelSpeedInputCache ReadOutputContext
GLM-5.2 744BFeatured
morph-glm52-744b
~80 tok/sec$1.1/1M—$4.1/1M1M
Qwen 3.5 397B
morph-qwen35-397b
~180 tok/sec$0.5/1M$0.3/1M$3.5/1M262k
Qwen 3.6 27B
morph-qwen36-27b
~100 tok/sec$0.289/1M—$2.4/1M131k
MiniMax M2.7
morph-minimax27-230b
~90 tok/sec$0.279/1M—$1.2/1M196k
MiniMax M3
morph-minimax3-428b
~90 tok/sec$0.6/1M—$2.4/1M256k
DeepSeek V4 Flash
morph-dsv4flash
~150 tok/sec$0.139/1M—$0.278/1M1M

Specialized Models

Purpose-built APIs that offload the bottlenecks: code editing, search, context management, and per-turn classification.

Fast Apply
Fastest model
morph-v3-fast
Try
Speed10,500+ tok/sec
Price
$0.8/1M in$1.2/1M out
Context262k
Most diversePopular
morph-v3-large
Try
Speed5,000+ tok/sec
Price
$0.9/1M in$1.9/1M out
Context262k
Code Search
Fast context for agentsNew
morph-warp-grep-v2
Try
Price
$0.8/100K
Context100K (1M for Pro)
Compaction
Verbatim context compaction
morph-compact
Try
Speed< 2s P99
Price
$0.2/1M in$0.5/1M out
Context1M
Reflex
Realtime per-turn classifiers
morph-reflex-v1
Try
Speed< 90ms
Price
$0.001/event$0.0005 over 1M/mo
Context64K
Batch (offline)
morph-reflex-v1
Try
Price
$0.0005/event$0.00025 over 1M/mo
Context64K
ModelSpeedPriceContext
Fast Apply
Fastest model
morph-v3-fast
10,500+ tok/sec
$0.8/1M in$1.2/1M out
262k
Try
Most diversePopular
morph-v3-large
5,000+ tok/sec
$0.9/1M in$1.9/1M out
262k
Try
Code Search
Fast context for agentsNew
morph-warp-grep-v2
—
$0.8/100K
100K (1M for Pro)
Try
Compaction
Verbatim context compaction
morph-compact
< 2s P99
$0.2/1M in$0.5/1M out
1M
Try
Reflex
Realtime per-turn classifiers
morph-reflex-v1
< 90ms
$0.001/event$0.0005 over 1M/mo
64K
Try
Batch (offline)
morph-reflex-v1
—
$0.0005/event$0.00025 over 1M/mo
64K
Try
Router
Difficulty-based model routing
morph-router
Price$0.005/request
Context—
ModelPriceContext
Difficulty-based model routing
morph-router
$0.005/request—

Subscriptions

Prepaid credits with volume discounts. Credits apply to all models above.

Free

For testing and personal projects

$0/month
Credits250K
LimitsLow rate limits

Starter

For individuals with moderate usage

$20/month
Credits3M
LimitsGenerous rate limits

Pro

For individuals who code all day

$60/month
Credits10M
LimitsGenerous rate limits

Scale

For individuals who can't stop coding

$400/month
Credits80M
LimitsPractically no rate limits

Need higher volume or custom solutions?

Dedicated infrastructure, SSO, custom rate limits, and priority support.

Get in touch
MorphMorph

Applied research building for the future of codegen.

© 2026 AutoInfra, Inc. All rights reserved.

Y
Backed by Y Combinator
  • Documentation
  • Blog
  • Trust Center
  • CareersWe're Hiring!
  • Privacy Policy
  • Terms of Service
  • EULA
  • Service Status
  • Book a Call