Get started

GLM 4.7 Flash

Sold by 2 sellers, timed at 36.4 tok/s, on 7 Design Arena boards, with results on 1 openly licensed board, and not scored by Artificial Analysis.

retrieved sha256 · 0bb53a77713f

Models/Z.ai/GLM 4.7 FlashUSD per 1M tokens · as OpenRouter routes it
z-ai/glm-4.7-flashZ.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$0.0605per 1M tokens
Output$0.40per 1M tokens
Cached inputnot listedper 1M tokens
Context200k200,000 tokens
What Vitna read · 2 providers, each from its own pricing page, kept as dated recordsin / out per 1M tokens
AWSopen weights$0.07 / $0.40confirmed 22 Nov 2026
Novita AIopen weights$0.07 / $0.40confirmed 22 Nov 2026

The same weights served by 2 providers, each at its own list price. OpenRouter's rate is its routed rate across whichever of them it uses, and it need not match any one of them.

What the list says · the fields OpenRouter publishes for this id10 fields
AuthorZ.ai
Listed
Canonical idz-ai/glm-4.7-flash-20260119
Context200,000 tokens
Max output117,964 tokens
Modalitiestext → text
TokenizerOther
Reasoningoptional, on by default
Moderationnot moderated by OpenRouter
What the weights say · read from the model's own repository on Hugging Faceretrieved from huggingface.co ↗
Licencemit
Parameters31.2B · 31,221,488,576 declared
Model classGlm4MoeLiteForCausalLM
Downloadnot gated
Published

What sellers charge

2 sellers · 1.16x from cheapest to dearest

One tick per seller, on a log scale of input price per million from $0.0605 at Cloudflare to $0.07 at Novita. The $0.0605 listed is the cheapest on offer; 1 seller is dearer. A faint tick declares no number format. Every seller is named on the endpoint ledger below.

Measured speed

8,273 requests · 2 endpoints · 30-minute window
Throughput36.4 tok/sMedian output rate, weighted across the 2 endpoints serving it by the requests each answered.the speed board
First token559msMedian wait before the first token, over the same window and weighted the same way.how Vitna reads a figure
Endpoint spread32 to 57The slowest and the fastest route serving this model, in tokens per second. Speed is a property of the route, not of the weights.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

2 priced · 2 timed · cheapest first
  1. Cloudflarecloudflare · listed$0.0605$0.40not listednot declared118k32 tok/s10473ms6,825 req85.25%
  2. Novitanovita/bf16$0.07$0.40$0.01bf16128k57 tok/s22962ms1,448 req8.19%

Each track runs from a route's p90, the rate nine in ten of its requests met or beat, up to its median. Weighted by requests, the figure above reports where the traffic went rather than what one route does: 1 of the 2 timed routes are slower than it, and the middle route runs at 44.5 tok/s. The widest median-to-p90 gap is Cloudflare's, 3.2x.

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 . 2 of the 2 sellers with a reading fell under 99% on at least one of the 23 days held, 23 Oct 2026 to 21 Nov 2026: Novita at 1.04% on 24 Oct 2026 and Cloudflare at 85.25% on 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

19 parameters · 2 sellers
  1. frequency_penaltyevery seller
  2. include_reasoningevery seller
  3. max_tokensevery seller
  4. presence_penaltyevery seller
  5. reasoningevery seller
  6. repetition_penaltyevery seller
  7. response_formatevery seller
  8. seedevery seller
  9. stopevery seller
  10. temperatureevery seller
  11. tool_choiceevery seller
  12. toolsevery seller
  13. top_kevery seller
  14. top_pevery seller
  15. logit_bias1 of 2not Novita
  16. logprobs1 of 2not Novita
  17. min_p1 of 2not Novita
  18. structured_outputs1 of 2not Novita
  19. top_logprobs1 of 2not Novita

14 of these 19 are accepted by every one of the 2 sellers that publish a list; the other 5 are declared by some sellers and not others, so what a request sending one of them gets depends on which seller serves it. 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 $0.145 per million tokens, 3 in to 1 out: cheaper than 291 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. 3D scenes · Models1100 Elowin rate 51.2% · source rank 94the board, 113 ranked
  2. Code · Models1166 Elowin rate 53.1% · source rank 75the board, 120 ranked
  3. Data visualisation · Models1119 Elowin rate 45.3% · source rank 98the board, 110 ranked
  4. Game development · Models1124 Elowin rate 49.7% · source rank 91the board, 120 ranked
  5. SVG · Models1027 Elowin rate 44.2% · source rank 87the board, 83 ranked
  6. UI components · Models1196 Elowin rate 57.6% · source rank 65the board, 116 ranked
  7. Websites · Models1185 Elowin rate 54.0% · source rank 72the 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 4.7 Flash 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

1 of 6 boards · 4 results
Epoch AI Benchmarking Hub · publisher-run, CC-BY-4.02 of 22 tasks
TaskAll runsEffortScore
GPQA diamond342none0.45
unstated0.61
OTIS Mock AIME 2024-2025319none0.25
unstated0.58

Mean accuracy, 0 to 1, on the task the row names, as Epoch AI runs it and averaged over repeated runs. All eighteen of their tasks, including the held-out FrontierMath tiers, named as they name them. The model id carries the effort setting the run used. Epoch AI Benchmarking Hub names these runs glm-4.7-flash_none and glm-4.7-flash, and the effort beside each score says which run it is, unstated where the publisher wrote none. All runs is how many runs the publisher scored on the task, every model's. Read from epoch.ai ↗, which dates its own data . Epoch AI Benchmarking Hub data, by Epoch AI, under CC BY 4.0.

1 of the 6 openly licensed boards Vitna mirrors carries a result for GLM 4.7 Flash, each printed as its publisher published it and none added to another. MTEB, LiveBench, HELM, Vectara hallucination leaderboard and Aider polyglot have not published one under a name that matches its listing, and names are matched to the catalog exactly and never guessed. A task that is a link opens its column on /capability, with every run scored on it. 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.
Source: each model's own Hugging Face repository (huggingface.co), as of 20 Nov 2026. 162 repositories read, 4 did not answer.
Licence, parameter count, model class and gating: each model's own Hugging Face repository, the one OpenRouter names for the listing.
A licence is the tag the uploader put on the repository, read from nothing else and verified by nobody.
A parameter count is the total the repository's safetensors files declare; for a mixture of experts that is every expert, not the share one token runs through.
Vitna ran none of these evaluations and adjusted none of these figures.