Get started

GLM 5V Turbo

Timed at 35 tok/s, on 21 Design Arena boards, and not scored by Artificial Analysis.

retrieved sha256 · 0bb53a77713f

Models/Z.ai/GLM 5V TurboUSD per 1M tokens · as OpenRouter routes it
z-ai/glm-5v-turboZ.ai · base listing · Other tokenizer
OpenRouter list price · the routed rate, as the catalog carried itretrieved 17 Nov 16:29 UTC from openrouter.ai ↗
Input$1.20per 1M tokens
Output$4.00per 1M tokens
Cached input$0.24per 1M tokens
Context203k202,752 tokens
What the list says · the fields OpenRouter publishes for this id9 fields
AuthorZ.ai
Listed
Canonical idz-ai/glm-5v-turbo-20260401
Context202,752 tokens
Max output131,072 tokens
Modalitiesimage, text, video → text
TokenizerOther
Reasoningoptional, on by default
Moderationnot moderated by OpenRouter

Measured speed

335 requests · 1 endpoint · 30-minute window
Throughput35 tok/sMedian output rate, weighted across the one endpoint serving it by the requests each answered.the speed board
First token1.24sMedian wait before the first token, over the same window and weighted the same way.how Vitna reads a figure
Endpoint spreadone routeOne endpoint served this model in the window, so the headline is that endpoint's own figure rather than a blend.the board, fastest first

OpenRouter's own timing of its routed traffic, weighted by requests, over one 30-minute window read . Every route is on the endpoint ledger below.

Every endpoint

1 priced · 1 timed · cheapest first
  1. Z.AIz-ai/fp8 · listed$1.20$4.00$0.24fp8131k35 tok/s17.71.24s335 req100%

Uptime is OpenRouter's own figure for each seller over the trailing day, read once a day, and the column prints the latest reading, taken . The one seller with a reading, Z.AI at 98.95% on 3 Nov 2026, fell under 99% on at least one of the 23 days held, 23 Oct 2026 to 21 Nov 2026. Source: OpenRouter's public endpoints API, one reading a day for each seller: 1,211 sellers carried one on the latest of the 23 days held.

Source: OpenRouter's public endpoints API. 1257 sellers across 359 models when the mirror ran, 186 of them served by more than one. List prices, not what anybody paid; a discount is the seller's own. Read . Speed is OpenRouter's own timing over one 30-minute window, read .

What each seller accepts

9 parameters · 1 seller
  1. include_reasoningevery seller
  2. max_tokensevery seller
  3. reasoningevery seller
  4. response_formatevery seller
  5. temperatureevery seller
  6. tool_choiceevery seller
  7. toolsevery seller
  8. top_kevery seller
  9. top_pevery seller

The one seller that publishes a list accepts these 9. Each list is the seller's own declaration in OpenRouter's endpoints API, read , and nothing here tested one.

Price position

342 priced models

Blended $1.90 per million tokens, 3 in to 1 out: cheaper than 107 of the 342 priced models in the catalog. Each bar is one stretch of the catalog on a logarithmic price scale; the mark is this listing.

Measured quality

145 models with an index · 132 on a design arena board

Each mark is one board this model stands on, placed at the share of that board it scores above, and led to its number in the list under the rule. The columns and the ledger below carry the figures.

Intelligence Indexnot scoredArtificial Analysis has not scored this model on its Intelligence Index.the intelligence leaderboard
Coding Indexnot scoredArtificial Analysis has not scored this model on its Coding Index.the coding leaderboard
Agentic Indexnot scoredArtificial Analysis has not scored this model on its Agentic Index.the agentic leaderboard
  1. Agentic game development · Agents1048 Elowin rate 42.6% · source rank 24the board, 25 ranked
  2. Agentic HTML slides · Agents1134 Elowin rate 41.7% · source rank 7the board, 9 ranked
  3. Agentic slides · Agents1171 Elowin rate 51.6% · source rank 5the board, 9 ranked
  4. Agentic slides, HTML · Agents1137 Elowin rate 41.8% · source rank 7the board, 9 ranked
  5. Agentic slides, python-pptx · Agents1183 Elowin rate 53.9% · source rank 5the board, 9 ranked
  6. Android native · Agents1267 Elowin rate 54.8% · source rank 5the board, 41 ranked
  7. Full stack · Agents1123 Elowin rate 52.1% · source rank 29the board, 44 ranked
  8. Godot game development · Agents928 Elowin rate 26.9% · source rank 35the board, 34 ranked
  9. HTML slides · Agents1017 Elowin rate 44.6% · source rank 23the board, 25 ranked
  10. Mobile apps · Agents1127 Elowin rate 50.5% · source rank 40the board, 49 ranked
  11. PPTX slides · Agents1164 Elowin rate 52.1% · source rank 5the board, 8 ranked
  12. python-pptx slides · Agents1165 Elowin rate 51.9% · source rank 17the board, 29 ranked
  13. Web apps · Agents1105 Elowin rate 44.7% · source rank 38the board, 47 ranked
  14. 3D scenes · Models1189 Elowin rate 52.3% · source rank 54the board, 113 ranked
  15. ASCII art · Models1103 Elowin rate 42.4% · source rank 60the board, 67 ranked
  16. Code · Models1217 Elowin rate 49.5% · source rank 60the board, 120 ranked
  17. Data visualisation · Models1198 Elowin rate 47.6% · source rank 62the board, 110 ranked
  18. Game development · Models1206 Elowin rate 49.3% · source rank 52the board, 120 ranked
  19. SVG · Models1138 Elowin rate 48.0% · source rank 55the board, 83 ranked
  20. UI components · Models1200 Elowin rate 47.8% · source rank 62the board, 116 ranked
  21. Websites · Models1221 Elowin rate 48.9% · source rank 60the board, 126 ranked
Epoch Capabilities Index · a fit by a third party over every benchmark this model has results onthe whole index, with intervals

Epoch AI has not placed GLM 5V Turbo on its Capabilities Index, or places it under a name the pairing does not reach. Epoch places a model once four of its benchmarks carry a result.

Benchmark results

none of 6 boards

None of the 6 openly licensed boards Vitna mirrors has published a result for GLM 5V Turbo under a name that matches its listing, and names are matched to the catalog exactly and never guessed. Every board, with its licence and what its publisher measures, is on /benchmarks.

Sources

Source: OpenRouter (openrouter.ai/models), as of 17 Nov 16:29 UTC. sha256 0bb53a77713f over 853,270 bytes.
Catalog: OpenRouter's public model list.
Intelligence, coding and agentic indexes: Artificial Analysis, as published by OpenRouter.
Elo, win rate and rank: Design Arena, as published by OpenRouter.
Vitna ran none of these evaluations and adjusted none of these figures.