Live status →

Benchmark report

Jev API thumbnail

Is the Jev API slow?

Jev response times from 6 cities, measured daily

Slow from some locations

The full answer typically came back in 112 ms from San Francisco and 335 ms from Mumbai. The first week had slow days; since 26 September every daily run has been steady.

Fastest
112 ms
San Francisco
Slowest
335 ms
Mumbai
Successful requests
100%
6 locations

Response time around the world

Amsterdam 257ms typicalSan Francisco 112ms typicalMontreal 149ms typicalSingapore 282ms typicalTokyo 190ms typicalMumbai 335ms typical
  • United StatesSan Francisco
    112 ms
  • CanadaMontreal
    149 ms
  • JapanTokyo
    190 ms
  • NetherlandsAmsterdam
    257 ms
  • SingaporeSingapore
    282 ms
  • IndiaMumbai
    335 ms

Why does Mumbai wait three times longer than San Francisco?

In the controlled run of 4 October, connecting and the secure handshake took under 25 ms in every city, each at a nearby Cloudflare site. Almost all of the time was waiting for the answer: 75 ms from San Francisco, 125 ms from Montreal, 156 ms from Tokyo, 214 ms from Amsterdam, 242 ms from Singapore and 292 ms from Mumbai. The wait grows with distance from the US West Coast, which suggests Jev answers from there and the other cities add the trip to it.

Click the location to see each stage.

ConnectTLSServer waitDownload
IndiaMumbai
304 ms
Finding the server
2 ms
Reaching the server
3 ms
Setting up security
9 ms
Waiting for the server: most of the time
292 ms
Receiving the response
0 ms
Total
304 ms

Finding the server is measured once per location, so it sits outside these bars. Open a city to see it.

Bars show the typical request, so the parts add up to its total. Why

Compare all locations

Click a city to see its stage-by-stage breakdown.

ConnectTLSServer waitDownload
NetherlandsAmsterdam
235 ms
Finding the server
171 ms
Reaching the server
8 ms
Setting up security
13 ms
Waiting for the server: most of the time
214 ms
Receiving the response
0 ms
Total
235 ms
United StatesSan Francisco
91 ms
Finding the server
14 ms
Reaching the server
4 ms
Setting up security
12 ms
Waiting for the server: most of the time
75 ms
Receiving the response
0 ms
Total
91 ms
CanadaMontreal
133 ms
Finding the server
2 ms
Reaching the server
3 ms
Setting up security
4 ms
Waiting for the server: most of the time
125 ms
Receiving the response
1 ms
Total
133 ms
SingaporeSingapore
260 ms
Finding the server
6 ms
Reaching the server
6 ms
Setting up security
11 ms
Waiting for the server: most of the time
242 ms
Receiving the response
1 ms
Total
260 ms
JapanTokyo
166 ms
Finding the server
1 ms
Reaching the server
3 ms
Setting up security
6 ms
Waiting for the server: most of the time
156 ms
Receiving the response
1 ms
Total
166 ms
IndiaMumbai
304 ms
Finding the server
2 ms
Reaching the server
3 ms
Setting up security
9 ms
Waiting for the server: most of the time
292 ms
Receiving the response
0 ms
Total
304 ms

The phases come from the controlled run of 4 October 2026. Typical and slower times pool the daily requests. 6 of 6 test locations included: Amsterdam, San Francisco, Montreal, Singapore, Tokyo, Mumbai.

Finding the server is measured once per location, so it sits outside these bars. Open a city to see it.

Bars show the typical request, so the parts add up to its total. Why

TypeSafe still feels slow?

Check TypeSafe’s status page
API incidents are posted there. A slow answer during one is not your network.
This is a full answer, not a first token
Jev does not stream, so we time the whole JSON response. The chat model pages time the first visible word of a streamed reply, which is a different measurement. We don't measure longer messages, more questions, the OpenRouter route or Cloudflare Workers AI.
The slow first week
On 21, 22, 24 and 25 September every city was slower than it has been since, most of them about twice as slow: Amsterdam's daily median was 475 to 554 ms on those days and 230 to 289 ms from 26 September on. The slower times on this page still include those days.

Response time over the last 14 days

Daily median of 5 requests per location, 21 September 2026 to 5 October 2026.
05001000 ms21 Sept5 OctAmsterdam, 21 September 2026: 537 ms, well above its usual level.Amsterdam, 22 September 2026: 554 ms, well above its usual level.Amsterdam, 24 September 2026: 553 ms, well above its usual level.San Francisco, 24 September 2026: 229 ms, well above its usual level.Montreal, 21 September 2026: 315 ms, well above its usual level.Montreal, 22 September 2026: 365 ms, well above its usual level.Montreal, 24 September 2026: 373 ms, well above its usual level.Montreal, 25 September 2026: 303 ms, well above its usual level.Singapore, 21 September 2026: 738 ms, well above its usual level.Singapore, 22 September 2026: 697 ms, well above its usual level.Singapore, 24 September 2026: 718 ms, well above its usual level.Singapore, 25 September 2026: 656 ms, well above its usual level.Tokyo, 21 September 2026: 475 ms, well above its usual level.Tokyo, 22 September 2026: 503 ms, well above its usual level.Tokyo, 24 September 2026: 512 ms, well above its usual level.Tokyo, 25 September 2026: 459 ms, well above its usual level.Mumbai, 21 September 2026: 812 ms, well above its usual level.Mumbai, 22 September 2026: 804 ms, well above its usual level.Mumbai, 24 September 2026: 785 ms, well above its usual level.Mumbai, 25 September 2026: 765 ms, well above its usual level.

A dot marks a day well above that location’s usual level.

Show the numbers
DayAmsterdamSan FranciscoMontrealSingaporeTokyoMumbai
21 September 2026537 ms ▲194 ms315 ms ▲738 ms ▲475 ms ▲812 ms ▲
22 September 2026554 ms ▲175 ms365 ms ▲697 ms ▲503 ms ▲804 ms ▲
23 September 2026254 ms169 ms229 ms286 ms188 ms353 ms
24 September 2026553 ms ▲229 ms ▲373 ms ▲718 ms ▲512 ms ▲785 ms ▲
25 September 2026475 ms135 ms303 ms ▲656 ms ▲459 ms ▲765 ms ▲
26 September 2026243 ms105 ms142 ms287 ms179 ms334 ms
27 September 2026257 ms94 ms132 ms286 ms189 ms316 ms
28 September 2026251 ms123 ms195 ms273 ms193 ms335 ms
29 September 2026245 ms113 ms166 ms245 ms201 ms306 ms
30 September 2026289 ms94 ms140 ms248 ms173 ms298 ms
1 October 2026234 ms87 ms138 ms281 ms179 ms303 ms
2 October 2026255 ms89 ms132 ms243 ms170 ms280 ms
3 October 2026259 ms93 ms128 ms282 ms165 ms315 ms
4 October 2026239 ms84 ms146 ms257 ms173 ms325 ms
5 October 2026230 ms111 ms130 ms258 ms160 ms302 ms

About this measurement

POST api.typesafe.ai/v1/systemone · 75 requests per location over 15 daily runs · 21 September 2026 to 5 October 2026

What we tested · AI decision. Whole JSON response from jev-1.13.0 to one yes/no question on a two-sentence support message: POST api.typesafe.ai/v1/systemone, no stream, paid key.

How LatencyRadar measures response time →

Technical details

Doesn’t measure: Time to first token (Jev has none), the Requesty or OpenRouter routes, Cloudflare Workers AI, longer states, more questions or the SDK retry layer.

One TypeSafe surface: POST api.typesafe.ai/v1/systemone with the jev-1.13.0 model, a two-sentence support message and one yes/no question, paid key. Jev returns its answers as one JSON document instead of a stream of tokens, so the number here is the time to the complete answer on a new connection. Your code waits that long before it can act on the decision.

Not measured: time to first token (Jev has none), longer messages or several questions in one request, the OpenRouter and Requesty routes, Cloudflare Workers AI, or the retries TypeSafe's SDK adds. The chat model pages time the first visible word of a streamed reply. That is a different measurement, and this page does not rank Jev against them.

Between 21 September and 5 October 2026 the typical time was 112 ms in San Francisco, 149 ms in Montreal, 190 ms in Tokyo, 257 ms in Amsterdam, 282 ms in Singapore and 335 ms in Mumbai. The first week was uneven: on four of the first five days every city was slower, most of them about twice as slow. Since 26 September the daily medians have stayed between 84 and 123 ms in San Francisco and between 280 and 335 ms in Mumbai.

Test locationTypical response timeSlower response timeRequests
Amsterdam257 ms606 ms20
San Francisco112 ms260 ms20
Montreal149 ms373 ms20
Singapore282 ms767 ms20
Tokyo190 ms554 ms20
Mumbai335 ms826 ms20

Typical: half of the requests finished within this time (technical: p50). Slower: 95% of requests finished within this time (technical: p95). Statistics

Request
POST api.typesafe.ai/v1/systemone
Measured from
Amsterdam · San Francisco · Montreal · Singapore · Tokyo · Mumbai
Requests
Daily measurements from 21 September 2026 to 5 October 2026. 6 of 6 test locations included: Amsterdam, San Francisco, Montreal, Singapore, Tokyo, Mumbai. · 21 September 2026 to 5 October 2026
Model
jev-1.13.0, pinned (not jev-latest) · no streaming · whole JSON response timed
Request
One yes/no question ("The customer is explicitly asking for a refund") about a two-sentence support message asking for a duplicate charge to be refunded. Identical in every city and on every day
Timings taken
DNS, connect, TLS, waiting for the server, download
Report coverage
6 of 6 test locations included: Amsterdam, San Francisco, Montreal, Singapore, Tokyo, Mumbai.
Daily requests in each location
Amsterdam: 75 · San Francisco: 75 · Montreal: 75 · Singapore: 75 · Tokyo: 75 · Mumbai: 75
Typical response time
Median of the eligible daily requests in each included location.
Slower response time
The 95th percentile of the same eligible daily requests in each included location.

Jev API

https://api.typesafe.ai/v1/systemone

Independent measurement by LatencyRadar. Not affiliated with TypeSafe. · How we measure (v1.3)

How fast is your API compared to Jev?

Run a free speed test from multiple cities and find out where your users are waiting. No setup, no account required.

Test my API

No account required · Takes about 30 seconds.

More benchmarks

All benchmarks →