Morph
Fast open models and code-editing models on a custom inference stack.
Morph serves open-weight models (Kimi K3, GLM-5.3, DeepSeek V4 Flash) on its own kernels at up to a 1M-token context, alongside its own coding models: Fast Apply for merging code edits, Compact for context compression and WarpGrep for code search. Morph names models its own way (morph-glm53-744b); its published price list says which model each id is, so the site files them under the canonical ids other gateways use. Its /models lists no prices, so they come from that public price list, which Morph reprices often.
- Status
- Live
- Models in catalog
- 12
- Text / multimodal
- 9
- Publishes pricing for
- 8 models
- Largest context window
- 1M tokens
- Model id style
- Morph’s own ids (`morph-glm53-744b`, `morph-kimik3`), aligned to canonical ids (`z-ai/glm-5.3`).
- Billing
- Pay per token; a 50%-off standby tier on GLM-5.3.
- Catalog last checked
- Website
- www.morphllm.com
- Documentation
- Developer docs
12 models on Morph
The 12 most widely available are shown; the rest are searchable in the full model list. "Id on this gateway" is what Morph calls the model — where it differs from the canonical id, that difference is what a router has to translate.
Search all 12 models on Morph| Model | Vendor | Type | Id on this gateway | Available on | Context | Input / Mtok |
|---|---|---|---|---|---|---|
DeepSeek V4.1 Flash
deepseek/deepseek-v4.1-flash
|
DeepSeek | Multimodal | morph-dsv41flash |
BasetenCloudflareFireworksMorphOpenRouterOrcaRouterRampRequestySailTogetherVercel | 1M | $0.060–$0.300 |
GLM 5.3
z-ai/glm-5.3
|
Z.ai | Multimodal | morph-glm53-744b |
BasetenCloudflareFireworksMorphOpenRouterOrcaRouterRampRequestySailTogetherVercel | 1M | $0.055–$1.40 |
GLM 5.3 Flash
z-ai/glm-5.3-flash
|
Z.ai | Multimodal | morph-glm53flash |
BasetenCloudflareFireworksMorphOpenRouterOrcaRouterRampRequestySailTogetherVercel | 1M | $0.026–$0.150 |
Kimi K3
moonshotai/kimi-k3
|
Moonshot AI | Multimodal | morph-kimik3 |
BasetenCloudflareFireworksMorphOpenRouterOrcaRouterRequestySailTogetherVercel | 1M | $0.730–$3.00 |
DeepSeek V4 Flash 0731
deepseek/deepseek-v4-flash-0731
|
DeepSeek | Text | deepseek/deepseek-v4-flash-0731 |
BasetenCloudflareMorphOpenRouterOrcaRouterRequestySailTogetherVercel | 1M | $0.016–$0.220 |
DeepSeek V4 Flash 0423
deepseek/deepseek-v4-flash
|
DeepSeek | Text | deepseek/deepseek-v4-flash |
CloudflareMorphOpenRouterOrcaRouterVercel | 1M | $0.043–$0.220 |
v3 Fast Apply
morph/morph-v3-fast
|
Morph | Text | morph-v3-fast |
CloudflareMorphOpenRouterVercel | 262.1K | $0.800 |
v3 Large Apply
morph/morph-v3-large
|
Morph | Text | morph-v3-large |
CloudflareMorphOpenRouterVercel | 262.1K | $0.900 |
Kimi K3 Fast
moonshotai/kimi-k3-fast
|
Moonshot AI | Multimodal | morph-kimik3-fast |
FireworksMorphVercel | 1M | $4.50–$6.00 |
deepseek-v4-flash-20260423
deepseek/deepseek-v4-flash-20260423
|
DeepSeek | Unclassified | deepseek/deepseek-v4-flash-20260423 |
CloudflareMorph | — | — |
morph-compactor
morph-compactor
|
Morph | Unclassified | morph-compactor |
Morph | — | — |
morph-warp-grep-v2.1
morph-warp-grep-v2.1
|
Morph | Unclassified | morph-warp-grep-v2.1 |
Morph | — | — |
Lowest input prices on Morph
Ranked by what this gateway charges, not by the cheapest price anywhere.
What Morph carries
A gateway with 2,000 models is not necessarily a gateway with 2,000 chat models.
10 of these models are on other gateways too
Anything in this list can be served from somewhere other than Morph without changing the model id your application sends.
What Morph has changed lately
From the daily catalog crawl. Every line below concerns this gateway, so it is not named on each one.
All gateway changes- Cut input 51.7% to $0.029 on Morph: GLM-5.3-Flash
- Cut input 78% to $0.055 on Morph: GLM-5.3
- Raised input 42.9% to $0.060 and output 8.3% to $0.650 on Morph: DeepSeek V4.1 Flash
- Cut input 45.9% to $0.060 and raised output 33.3% to $1.00 on Morph: GLM-5.3-Flash
- Cut input 16.7% to $0.250 and raised output 127.3% to $5.00 on Morph: GLM-5.3
- Raised input 122.2% to $1.00 on Morph: Kimi K3
- Raised input 40% to $0.042 and output 100% to $0.600 on Morph: DeepSeek V4.1 Flash
- Raised input 98.2% to $0.111 on Morph: GLM-5.3-Flash
- Cut input 15.3% to $0.300 and output 63.3% to $2.20 on Morph: GLM-5.3
- Cut input 28.6% to $0.450 and output 6.9% to $14.90 on Morph: Kimi K3
- Raised input 3.4% to $0.030 and cut output 70% to $0.300 on Morph: DeepSeek V4.1 Flash
- Cut input 45.6% to $0.056 and raised output 7.1% to $0.750 on Morph: GLM-5.3-Flash
- Raised input 48.7% to $0.354 and output 60.4% to $6.00 on Morph: GLM-5.3
- Cut input 68.1% to $0.630 and raised output 14.3% to $16.00 on Morph: Kimi K3
- Cut input 42% to $0.029 and raised output 66.7% to $1.00 on Morph: DeepSeek V4.1 Flash
- Raised input 6.2% to $0.103 on Morph: GLM-5.3-Flash
- Raised input 64.1% to $0.238 on Morph: GLM-5.3
- Cut input 21% to $1.98 on Morph: Kimi K3
- Raised input 150% to $0.050 on Morph: DeepSeek V4.1 Flash
- Raised input 6.6% to $0.097 on Morph: GLM-5.3-Flash
- Raised input 9.6% to $0.091 and output 8.4% to $0.700 on Morph: GLM-5.3-Flash
- Raised input 141.7% to $0.145 and output 5.3% to $3.74 on Morph: GLM-5.3
- Raised input 300% to $2.50 and output 7.6% to $14.00 on Morph: Kimi K3
- Cut input 70.6% to $0.020 and raised output 41.5% to $0.600 on Morph: DeepSeek V4.1 Flash