Benchmark report
Is the Mistral API slow?
Mistral Medium time to first token from 6 cities, measured daily
Uneven around the world
First visible token arrived in 214 ms from Amsterdam and 435 ms from Singapore and Tokyo, with every city under half a second. The gap grows with distance from Europe, which suggests the model is served from there.
- Fastest
- 214 ms
- Amsterdam
- Slowest
- 435 ms
- Tokyo
- Successful requests
- 100%
- 6 locations
Response time around the world
Amsterdam214 ms
Montreal277 ms
Mumbai326 ms
San Francisco333 ms
Singapore435 ms
Tokyo435 ms
No thinking phase, so the stream opens with the answer
In the controlled run of 27 September the stream opened at the same moment the first visible token arrived, within a millisecond, in every city, and the one-word reply was complete 15 to 24 ms later. Connecting took 3 to 9 ms and the secure handshake 6 to 13 ms; the rest was waiting: 215 ms in Amsterdam, 263 in Montreal, 305 in San Francisco, 334 in Mumbai, 417 in Tokyo and 468 in Singapore. Every city reached the same Cloudflare address through a nearby point of presence (London for Amsterdam), so the wait is the trip from that edge to Mistral plus the time the model takes to produce its first token. About a fifth of a second of it is there even in Amsterdam, and the rest grows with distance from Europe.
Click the location to see each stage.
Tokyo454 ms
Tokyo- Finding the server
- 1 ms
- Reaching the server
- 3 ms
- Setting up security
- 8 ms
- Waiting for the server: most of the time
- 417 ms
- Receiving the response
- 26 ms
- Total
- 454 ms
- Response opened
- 430 ms
- First visible word
- 430 ms
- Answer complete
- 454 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 locationsHide the comparison
Click a city to see its stage-by-stage breakdown.
Amsterdam253 ms
Amsterdam- Finding the server
- 1 ms
- Reaching the server
- 9 ms
- Setting up security
- 13 ms
- Waiting for the server: most of the time
- 215 ms
- Receiving the response
- 16 ms
- Total
- 253 ms
- Response opened
- 237 ms
- First visible word
- 238 ms
- Answer complete
- 253 ms
San Francisco333 ms
San Francisco- Finding the server
- 11 ms
- Reaching the server
- 4 ms
- Setting up security
- 6 ms
- Waiting for the server: most of the time
- 305 ms
- Receiving the response
- 18 ms
- Total
- 333 ms
- Response opened
- 313 ms
- First visible word
- 313 ms
- Answer complete
- 333 ms
Montreal291 ms
Montreal- Finding the server
- 4 ms
- Reaching the server
- 3 ms
- Setting up security
- 6 ms
- Waiting for the server: most of the time
- 263 ms
- Receiving the response
- 19 ms
- Total
- 291 ms
- Response opened
- 272 ms
- First visible word
- 273 ms
- Answer complete
- 291 ms
Singapore499 ms
Singapore- Finding the server
- 6 ms
- Reaching the server
- 3 ms
- Setting up security
- 11 ms
- Waiting for the server: most of the time
- 468 ms
- Receiving the response
- 17 ms
- Total
- 499 ms
- Response opened
- 482 ms
- First visible word
- 483 ms
- Answer complete
- 499 ms
Tokyo454 ms
Tokyo- Finding the server
- 1 ms
- Reaching the server
- 3 ms
- Setting up security
- 8 ms
- Waiting for the server: most of the time
- 417 ms
- Receiving the response
- 26 ms
- Total
- 454 ms
- Response opened
- 430 ms
- First visible word
- 430 ms
- Answer complete
- 454 ms
Mumbai364 ms
Mumbai- Finding the server
- 2 ms
- Reaching the server
- 3 ms
- Setting up security
- 7 ms
- Waiting for the server: most of the time
- 334 ms
- Receiving the response
- 20 ms
- Total
- 364 ms
- Response opened
- 344 ms
- First visible word
- 344 ms
- Answer complete
- 364 ms
The phases come from the controlled run of 27 September 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
Mistral still feels slow?
- Check Mistral’s status page
- Elevated latency and error rates are posted there. A slow first token during an incident is not your region.
- Short everywhere, a little longer far from Europe
- Amsterdam waited 215 ms in the controlled run; Montreal about 50 ms more, San Francisco about 90 ms more, Mumbai about 120 ms more, Tokyo about 200 ms more and Singapore about 250 ms more. The single Cloudflare address does not say where the model runs, but the pattern suggests the origin is in Europe. For users in Asia, most of the extra 200 to 250 ms is probably distance.
Response time over the last 29 days
Show the numbers
| Day | Amsterdam | San Francisco | Montreal | Singapore | Tokyo | Mumbai |
|---|---|---|---|---|---|---|
| 11 September 2026 | 248 ms | 357 ms | 310 ms | 415 ms | 460 ms | 366 ms |
| 12 September 2026 | 200 ms | 338 ms | 279 ms | 373 ms | 410 ms | 324 ms |
| 13 September 2026 | 245 ms | 332 ms | 258 ms | 400 ms | 414 ms | 322 ms |
| 14 September 2026 | 262 ms | 346 ms | 329 ms | 375 ms | 486 ms | 354 ms |
| 15 September 2026 | 220 ms | 361 ms | 552 ms | 361 ms | 455 ms | 312 ms |
| 16 September 2026 | 227 ms | 373 ms | 317 ms | 343 ms | 429 ms | 295 ms |
| 17 September 2026 | 242 ms | 357 ms | 332 ms | 394 ms | 388 ms | 382 ms |
| 18 September 2026 | 244 ms | 321 ms | 334 ms | 520 ms | 453 ms | 372 ms |
| 19 September 2026 | 241 ms | 319 ms | 313 ms | 357 ms | 410 ms | 296 ms |
| 20 September 2026 | 224 ms | 373 ms | 307 ms | 416 ms | 446 ms | 349 ms |
| 21 September 2026 | 299 ms | 336 ms | 291 ms | 393 ms | 404 ms | 308 ms |
| 22 September 2026 | 238 ms | 344 ms | 260 ms | 382 ms | 454 ms | 380 ms |
| 23 September 2026 | 238 ms | 351 ms | 286 ms | 379 ms | 434 ms | 338 ms |
| 24 September 2026 | 264 ms | 393 ms | 263 ms | 376 ms | 409 ms | 376 ms |
| 25 September 2026 | 218 ms | 355 ms | 314 ms | 380 ms | 412 ms | 335 ms |
| 26 September 2026 | 276 ms | 354 ms | 295 ms | 369 ms | 430 ms | 343 ms |
| 27 September 2026 | 210 ms | 307 ms | 265 ms | 404 ms | 398 ms | 297 ms |
| 28 September 2026 | 233 ms | 339 ms | 297 ms | 463 ms | 442 ms | 353 ms |
| 29 September 2026 | 200 ms | 331 ms | 266 ms | 530 ms | 429 ms | 354 ms |
| 30 September 2026 | 221 ms | 340 ms | 264 ms | 492 ms | 442 ms | 317 ms |
| 1 October 2026 | 200 ms | 321 ms | 273 ms | 503 ms | 396 ms | 302 ms |
| 2 October 2026 | 255 ms | 354 ms | 253 ms | 516 ms | 402 ms | 294 ms |
| 3 October 2026 | 214 ms | 316 ms | 256 ms | 524 ms | 409 ms | 331 ms |
| 4 October 2026 | 200 ms | 310 ms | 267 ms | 333 ms | 418 ms | 322 ms |
| 5 October 2026 | 214 ms | 329 ms | 294 ms | 388 ms | 450 ms | 346 ms |
| 6 October 2026 | 208 ms | 371 ms | 275 ms | 378 ms | 424 ms | 382 ms |
| 7 October 2026 | 204 ms | 330 ms | 280 ms | 351 ms | 438 ms | 308 ms |
| 9 October 2026 | 282 ms | 368 ms | 304 ms | 389 ms | 446 ms | 351 ms |
| 10 October 2026 | 296 ms | 307 ms | 307 ms | 370 ms | 451 ms | 304 ms |
About this measurement
POST api.mistral.ai/v1/chat/completions · 65 requests per location over 13 daily runs · 27 September 2026 to 10 October 2026
What we tested · AI response. Time to first visible token from mistral-medium-latest on a one-word prompt: streaming, 256 max tokens, no reasoning setting, paid key.
How LatencyRadar measures response time →
Technical details
Doesn’t measure: Le Chat, tokens per second, long prompts, or other Mistral models.
One Mistral surface: time to first visible token from mistral-medium-latest at api.mistral.ai/v1/chat/completions, a one-word prompt, streaming, 256 max tokens, paid key. The request sets no reasoning option because Mistral Medium answers directly; there is no thinking phase to include or leave out, and Mistral's Magistral reasoning models are not measured here. Mistral's API uses the OpenAI-compatible event format, so the same parser that reads ChatGPT's stream reads this one.
The ChatGPT, Claude and Grok figures on this page are the same prompt on the same days at low reasoning effort. Their daily medians ran 0.6 to 1.7 seconds (ChatGPT), 0.8 to 2.1 seconds (Claude) and 1.7 to 4.2 seconds (Grok) while Mistral's ran 0.20 to 0.53 seconds. Part of that gap is thinking Mistral Medium never does, so the two sets of numbers describe different requests and are not a ranking.
The published measurements cover 27 September to 10 October 2026. Typical first-token times are 214 ms in Amsterdam to 435 ms in Singapore and Tokyo, with Montreal at 277 ms, Mumbai at 326 ms and San Francisco at 333 ms. Daily medians moved inside a band of less than 100 ms in five cities; Singapore's ranged from 333 to 530 ms. The slower times sit furthest above the typical in Mumbai (748 ms) and Montreal (653 ms), so budget for the tail there even though the typical wait is short.
| Test location | Typical response time | Slower response time | Requests |
|---|---|---|---|
| Amsterdam | 214 ms | 490 ms | 65 |
| San Francisco | 333 ms | 495 ms | 65 |
| Montreal | 277 ms | 653 ms | 65 |
| Singapore | 435 ms | 652 ms | 65 |
| Tokyo | 435 ms | 508 ms | 65 |
| Mumbai | 326 ms | 748 ms | 65 |
Typical: half of the requests finished within this time (technical: p50 of time to first visible token). Slower: 95% of requests finished within this time (technical: p95). Statistics
- Request
- Authenticated streaming POST to api.mistral.ai/v1/chat/completions
- Measured from
- Amsterdam · San Francisco · Montreal · Singapore · Tokyo · Mumbai
- Requests
- Daily measurements from 27 September 2026 to 10 October 2026. 6 of 6 test locations included: Amsterdam, San Francisco, Montreal, Singapore, Tokyo, Mumbai. · 27 September 2026 to 10 October 2026
- Model
- mistral-medium-latest · no reasoning option (the model answers directly) · max_tokens 256 · default temperature
- Prompt
- "Say 'ok' and nothing else." Identical across every city and every LLM API we benchmark
- Comparison figures
- ChatGPT (gpt-5.6-sol), Claude (claude-opus-5) and Grok (grok-4.6), all at low reasoning effort, from the same daily collection between 27 September and 10 October 2026. Those three think briefly before the first token; Mistral Medium does not
- Timings taken
- Parsed from the token stream: stream open, first visible token, completion, plus DNS, connect and TLS
- Report coverage
- 6 of 6 test locations included: Amsterdam, San Francisco, Montreal, Singapore, Tokyo, Mumbai.
- Coverage changes
- Mumbai (measured since 8 September 2026) joined this report on 27 September 2026. Earlier daily bands keep their previous location set.
- Daily requests in each location
- Amsterdam: 65 · San Francisco: 65 · Montreal: 65 · Singapore: 65 · Tokyo: 65 · Mumbai: 65
- 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.
Mistral API
https://api.mistral.ai/v1/chat/completions
Independent measurement by LatencyRadar. Not affiliated with Mistral AI. · How we measure (v1.3)
How fast is your API compared to Mistral's?
Run a free speed test from multiple cities and find out where your users are waiting. No setup, no account required.
No account required · Takes about 30 seconds.
