Models
Every model Morph serves, always current. Frontier open weights on custom kernels, plus the specialized agent APIs that offload an agent's bottlenecks. One endpoint, one key.
Open-source coding models
Frontier open weights, served on Morph's custom kernels for codegen. Run the primary agent loop.
morph-dsv41flashVision-language MoE with thinking on by default; shared serving pool and list rates.morph-dsv41flash-1017Vision-language MoE with thinking on by default; shared serving pool and list rates.morph-dsv41flash-abliteratedDeepSeek V4.1 Flash 1017 with refusals ablated. Released to verified teams.| Model | Input | Cache Read | Output | Context | Max Out |
|---|---|---|---|---|---|
| $2.50/1M | $0.29/1M | $14.00/1M | 1M | 1M | |
| $1.19/1M | $0.20/1M | $6.00/1M | 1M | 1M | |
| $0.20/1M | $0.04/1M | $0.70/1M | 1M | 1M | |
DeepSeek V4.1 Flash morph-dsv41flashVision-language MoE with thinking on by default; shared serving pool and list rates. | $0.12/1M | $0.008/1M | $0.80/1M | 1M | 1M |
DeepSeek V4.1 Flash 1017 morph-dsv41flash-1017Vision-language MoE with thinking on by default; shared serving pool and list rates. | $0.12/1M | $0.008/1M | $0.80/1M | 1M | 1M |
DeepSeek V4.1 Flash Abliterated morph-dsv41flash-abliteratedDeepSeek V4.1 Flash 1017 with refusals ablated. Released to verified teams. | $0.30/1M | $0.03/1M | $1.20/1M | 1M | 1M |
Specialized agent models
Purpose-built APIs that offload the bottlenecks: code editing, search, context management, per-turn classification, and routing.
| Model | Product | Speed | Price | Context |
|---|---|---|---|---|
Decisions | — | $0.042 in $0.00 out /1M | 65k | |
Fast Apply | 10,500+ tok/s | $0.80 in $1.20 out /1M | 262k | |
Fast Apply | 5,000+ tok/s | $0.90 in $1.90 out /1M | 262k | |
Code Search | — | $0/100k · $1/1M req | — | |
Compaction | 33,000 tok/s | $0.20 in $0.50 out /1M | 1M | |
Router | — | $0.005/request | — |
Models we've analyzed
Deep-dives on models Morph doesn't serve on public endpoints. Architecture, benchmarks, and where to run them.
The fastest endpoints are private deployments
Morph's top speeds come from dedicated deployments, not shared public endpoints: speculators trained on your traffic, caching tuned to your workload, and volume discounts over public per-token rates. Over 1 trillion tokens per day run this way.