Context
131K
Max output
33K
Serving providers
1
Cheapest input
$0.30 /1M
Prices are on-demand list rates. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.

Benchmarks

independent evaluations · source: Artificial Analysis
Speed & latency
Output speed
36 t/s
tokens / second
Time to first token
23.46s
latency
Headline indices
Individual benchmarks · click a row for effort variants
BenchmarkBest scoreEffortCost / task
CritPt0%reasoning: true
EvalComputeProxy24.4reasoning: true
GPQA Diamond72%reasoning: true
Humanity's Last Exam9%reasoning: true
IFBench30%reasoning: true
LiveCodeBench41%default
Long-Context Reasoning40%reasoning: true
MMLU-Pro80%reasoning: true
MMMU-Pro49%reasoning: true
Omniscience-26.5reasoning: true
SciCode30%reasoning: true
TerminalBench Hard14%reasoning: true
τ²-bench32%reasoning: true

Pricing by serving provider

standard tier · per 1M tokens · click a provider to expand
Serving providerInput /1MOutput /1MEndpoints
NovitaCheapest$0.30$0.901
ComponentUnitStandardBatchCached
Text cached in/1M tok$0.0550
Text input/1M tok$0.3000
Text output/1M tok$0.9000

Price history

input + output $/1M since we started tracking
Input Output
$0.000$0.500$1.00Jan 13Jun 22$0.900$0.300

Cost calculator

estimate your monthly spend on this model
$132
estimated / month

Model IDs

copy the exact identifier for your platform
novita/zai-org/glm-4.6v

Frequently asked questions

GLM 4.6V pricing, context and availability

How much does GLM 4.6V cost?

GLM 4.6V costs $0.30 per 1M input tokens and $0.90 per 1M output tokens at its cheapest provider via Novita.

What is the context window of GLM 4.6V?

GLM 4.6V accepts up to 131K tokens of context and can return up to 33K output tokens.

What can GLM 4.6V do?

GLM 4.6V supports image input (vision), tool use, reasoning and structured output.

Other Zhipu models

compare pricing across the Zhipu lineup
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI