Morph
Explore Morph models on TrustedRouter with current routes, token pricing, policy sources, privacy posture, regional availability, and API support.
Morphmorph
No provider claim
| Provider | Morph |
|---|---|
| Routing status | Active |
| Provider website | https://www.morphllm.com/ |
| Models | 8 public models |
| Credits routes | 8 |
| Zero data retention | not claimed |
| Confidential compute | not claimed |
| Provider E2EE | not claimed |
| 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
40 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 | 2508 ms |
|---|---|
| Effective throughput | 38 tok/s n=4 |
| Uptime | 72.50% |
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| morph/morph-v3-fast | 906 ms | — | 33.33% | — | 6 |
| z-ai/glm-5.2 | 1620 ms | 41 tok/s n=2 | 100.00% | — | 5 |
| morph/morph-v3-large | 1816 ms | — | 100.00% | — | 4 |
| deepseek/deepseek-v4-flash | 2508 ms | 28 tok/s n=1 | 100.00% | — | 8 |
| qwen/qwen3.5-397b-a17b | 2508 ms | — | 80.00% | — | 5 |
| minimax/minimax-m2.7 | 2519 ms | — | 66.67% | — | 3 |
| qwen/qwen3.6-27b | 3126 ms | — | 33.33% | — | 6 |
| minimax/minimax-m3 | 3293 ms | 35 tok/s n=1 | 66.67% | — | 3 |
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 113#46 | 1,024,000 | $0.1477/1M | Not published | $0.2954/1M |
minimax/minimax-m2.7MiniMax: MiniMax M2.7 |
IQ 109#60 | 204,800 | $0.2954/1M | Not published | $1.266/1M |
minimax/minimax-m3MiniMax: MiniMax M3 |
IQ 114#44 | 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 111#56 | 262,144 | $0.30595/1M | Not published | $2.532/1M |
z-ai/glm-5.2Z.ai: GLM 5.2 |
IQ 120#27 | 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.