Morph V3 Large
Morph · released Jul 7, 2025
- Type
- Proprietary
- Input
- $0.90
- Output
- $1.90
- Cached
- Not published
List price · per 1M tokens · Morph at 262K context · source ↗
Our take
Written Aug 2, 2026Morph V3 Large is a hosted-only text model built for long-document work, with a 262,144-token request limit and no downloadable weights. It is a niche pick for teams that need deep context and can accept a proprietary-only, unmeasured model.
Choose this when you need to process very long documents in a single request and do not need image, audio or video input. Use Morph's own endpoint if throughput matters to your workload. Skip it if you want measured quality scores, the flexibility of open weights, or any multimodal capability.
The case for it
- Extremely large context window for long-document tasks, at 262,144 tokens.
- Direct-provider throughput of 204.5 tokens per second available from Morph's own endpoint.
The case against it
- No measured quality data to justify its price against alternatives.
- Proprietary weights with no licensing flexibility — no commercial redistribution or self-hosting possible.
- Same price on direct and third-party routing with no price advantage for either channel; only Morph offers verified throughput.
How good is it?
We hold no score for this model.
We look for every model we track on every board we watch, and none of them has turned up Morph V3 Large — so there is no intelligence, coding, agentic or writing score to show you, not a low one, none.
Or rent it from someone else
Why this differs from the header. The strip above quotes Morph's own list price. This is the cheapest live offer at the widest standard context we hold, whoever is serving it — a reseller undercutting a lab is ordinary commerce, not an error.
- per 1M tokens
- $0.90 in / $1.90 out
- Context served
- 262K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouter | $0.90 / $1.90 | 262K | not measured | Unknown | Unknown | Unknown |
| Morph | $0.90 / $1.90 | 262K | 2855 tok/s | No | No | Confirmed |
Across the 2 listings we hold: 1 say they do not train on prompts, 0 say they do and 1 do not say. 1 appear in the zero-retention registry we check; the rest are unknown to us rather than confirmed either way.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
- ✓
- Supported
- ✗
- Not supported
- Not published
- host gave no parameter list
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouter | ✗ | ✓ | ✓ |
| Morph | ✗ | ✓ | ✓ |
Tool calling: 0 of 2 listings say yes, 2 say no. JSON output: 2 of 2 listings say yes. Strict schema: 2 of 2 listings say yes.
When we formed this view
Dates behind this page
Prices last checked 9d ago
What we do not know about this model yet
- No board we watch has turned up a score, so we hold no quality figures at all.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 2 listings do not say whether they train on prompts.
- We hold no cached-input rate for any of its listings.
Licence and identifiers
What the licence allowsWe hold no licence record for this model. Inside are the identifiers you need to pull it — its Hugging Face repo where we have one, our slug and a machine-readable card.
Licence
Commercial API terms. We hold no licence record for this model, so there is nothing to summarise here.
Identifiers
- Modality record
- text->text
- Catalogue slug
- morph-morph-v3-large