Morph
Explore Morph models on TrustedRouter with current routes, token pricing, policy sources, privacy posture, regional availability, and API support.
Morphmorph
No provider claim
These privacy labels describe Morph, the upstream model provider. ZDR is a retention policy; verified confidential inference additionally requires attested provider compute and end-to-end encryption.
| Provider | Morph |
|---|---|
| Routing status | Active |
| Provider website | https://www.morphllm.com/ |
| Models | 8 public models |
| Credits routes | 8 |
| Zero data retention | not claimed |
| Verified confidential inference | Not verified |
| Policy note | Morph's public paid tier documents up to 30 days of content retention. Zero retention is reserved for enterprise contracts. Policy source |
Measured performance
36 samplesContinuously sampled across Morph's routed models: p50 TTFT, effective throughput, and success rate. Effective throughput uses provider-reported output tokens over complete request time. Unsupported route and probe-configuration rows are separated from provider downtime. No prompt or output content stored.
| p50 TTFT | 2945 ms |
|---|---|
| Effective throughput | 36 tok/s n=2 |
| Uptime | 58.33% |
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| z-ai/glm-5.2 | 1525 ms | — | 100.00% | — | 3 |
| minimax/minimax-m2.7 | 1836 ms | — | 50.00% | — | 4 |
| qwen/qwen3.6-27b | 1994 ms | — | 37.50% | — | 8 |
| morph/morph-v3-large | 2945 ms | — | 100.00% | — | 4 |
| morph/morph-v3-fast | 3078 ms | — | 100.00% | — | 3 |
| deepseek/deepseek-v4-flash | 3133 ms | 39 tok/s n=1 | 75.00% | — | 4 |
| qwen/qwen3.5-397b-a17b | 3636 ms | — | 40.00% | — | 5 |
| minimax/minimax-m3 | 25067 ms | 32 tok/s n=1 | 20.00% | — | 5 |
Morph performance history · Full provider & model leaderboard.
Models served by Morph.
Each row links to pricing, provider, benchmark, and API pages for the model.
| Model | AI IQ | Context | Input | Cached input | Output |
|---|---|---|---|---|---|
deepseek/deepseek-v4-flashDeepSeek: DeepSeek V4 Flash 0423 |
IQ 116#37 | 1,048,576 | $0.1477/1M | Not published | $0.2954/1M |
minimax/minimax-m2.7MiniMax: MiniMax M2.7 |
IQ 107#72 | 196,608 | $0.2954/1M | Not published | $1.266/1M |
minimax/minimax-m3MiniMax: MiniMax M3 |
IQ 115#45 | 524,288 | $0.633/1M | Not published | $2.532/1M |
morph/morph-v3-fastmorph-v3-fast |
— | 262,144 | $0.844/1M | Not published | $1.266/1M |
morph/morph-v3-largemorph-v3-large |
— | 262,144 | $0.9495/1M | Not published | $2.0045/1M |
qwen/qwen3.5-397b-a17bQwen: Qwen3.5 397B A17B |
— | 262,144 | $0.5275/1M | $0.3165/1M | $3.6925/1M |
qwen/qwen3.6-27bQwen: Qwen3.6 27B |
IQ 108#68 | 262,144 | $0.30595/1M | Not published | $2.532/1M |
z-ai/glm-5.2Z.ai: GLM 5.2 |
IQ 120#28 | 1,048,576 | $1.1605/1M | Not published | $4.3255/1M |
Questions
Does Morph have zero data retention?
TrustedRouter does not currently mark Morph as provider-level zero data retention. Use trustedrouter/zdr or provider.min_privacy=zdr to select a different eligible route, and review the linked policy source for changes.
Is Morph end-to-end encrypted?
TrustedRouter does not currently mark Morph as end-to-end encrypted at the provider boundary. The TrustedRouter gateway is still attested, but the selected provider normally receives the request in order to run the model. Use trustedrouter/e2e for the stronger route requirement.
Which Morph models are available through TrustedRouter?
This page currently lists 8 public Morph models, with live pricing, route count, context length, measured performance when available, and links to each model's provider and benchmark pages.