Limits
Body sizes, message counts, media, rate limits, and credit, for every endpoint.
Every limit the API sets, in one place. A request over one is refused before it reaches a model, and costs nothing.
Request size
| Endpoint | Largest body |
|---|---|
| Chat completions | 32 MiB |
| Images | 32 MiB |
| Search | 64 KiB |
| Fetch | 64 KiB |
| Transcriptions | 10 MiB |
A larger body is refused with 413 request_too_large. A body that doesn't arrive within one minute is refused with 408 request_timeout.
Chat completions
| Limit | Value | Over it |
|---|---|---|
| Messages | 4,096 | too_many_messages |
| JSON values in the body | 262,144 | request_too_complex |
| Conversation length | The largest context_tokens among the tiers the request may run at | context_length_exceeded |
| Output tokens | The max_output_tokens of the tier that serves the request | Lowered to fit, or e2ee_output_limit_refused on an E2EE model |
Images
- Up to four images a request.
- Each model sets its own most reference images, and some take none.
aspect_ratiois one of1:1,16:9,9:16,4:3,3:4,3:2, or2:3, andresolutionis1kor2k.- A provider that takes more than 10 minutes ends the request with
upstream_error, and you pay nothing.
Search and fetch
- Up to three queries a search.
- A search's excerpts hold at most 8,000 characters together.
- A fetched URL is at most 2,048 characters,
httporhttps, on a public host and port 80 or 443, without credentials. - A fetched page's text is at most 100,000 characters.
truncatedsays when it was cut.
Transcription
A WAV file of 16-bit PCM, mono or stereo, at 8 to 48 kHz. At most 5 minutes long, and 10 MiB with the other fields.
Rate limits
Your plan sets requests a minute and requests in flight. Every key on the account shares them, with your own use of the Morse app.
| Plan | Requests a minute | Burst | In flight |
|---|---|---|---|
| Free | 60 | 7 | 5 |
| Pro | 120 | 13 | 8 |
| Max | 600 | 61 | 10 |
| Endpoint | Requests a minute |
|---|---|
POST /v1/search | 30 |
POST /v1/fetch | 30 |
POST /v1/audio/transcriptions | 30 |
GET /v1/models | 60, apart from your plan's |
A request over a limit gets 429 and Retry-After. See Rate limits.
Credit
A request must hold credit for the most it could cost. Below that, it's refused with 402 insufficient_balance, or key_spend_limit_reached when the key's spend limit is what ran short. Morse may instead lower the output limit so the request fits, and says so in X-Output-Limited.