BroadRouter

GLM 4.7 vs GLM 4.6 API pricing

Updated

GLM 4.7: USD 0.40 input, USD 1.75 output per 1M tokens (DeepInfra). GLM 4.6: USD 0.43 input, USD 1.75 output per 1M tokens (Venice). At 3 input tokens per output token, GLM 4.6 costs 3.1% more than GLM 4.7 (USD 0.76 vs USD 0.7375 per 1M).

GLM 4.6 is the release before GLM 4.7 in the same Z.ai line (by version in the name), so this page shows what the newer release costs. Price only: every number is computed from prices read from each provider's own pricing page (linked per cell, newest check 2026-11-15), with no claim about quality, speed or accuracy.

How do GLM 4.7 and GLM 4.6 differ on price?

GLM 4.7 and GLM 4.6 prices side by side

USD per 1M tokens, standard tier. "Cheapest" is the lowest price at 3 input tokens to 1 output token; each line can come from a different provider.

GLM 4.7 and GLM 4.6 API prices compared
PriceGLM 4.7GLM 4.6
Model pageGLM 4.7
Z.ai · 8 providers
GLM 4.6
Z.ai · 6 providers
Cheapest standard price, blended 3:1USD 0.7375 lower
USD 0.40 in / USD 1.75 out at DeepInfra
DeepInfra page checked 2026-11-14
USD 0.76
USD 0.43 in / USD 1.75 out at Venice
Venice page checked 2026-11-15
Cheapest inputUSD 0.40 lower
DeepInfra source
USD 0.43
Venice source
Cheapest cached inputUSD 0.06 lower
Google Vertex AI source
USD 0.08
Venice source
Cheapest outputUSD 1.75 tie
DeepInfra source
USD 1.75 tie
Venice source
Maker's own APIUSD 0.60 / USD 2.20
Z.ai source
USD 0.60 / USD 2.20
Z.ai source
Median standard priceUSD 0.60 / USD 2.20
input / output, 8 prices
USD 0.55 / USD 2.10
input / output, 6 prices
Context window204,800 tokens, largest stated; from 198,000 at some providers204,800 tokens, largest stated; from 198,000 at some providers
Providers with a standard price86

Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).

What do GLM 4.7 and GLM 4.6 cost for a real workload?

30 days at each model's cheapest standard price for the workload (presets of the cost calculator; cached input at the cached price where listed).

Monthly cost of three workloads on GLM 4.7 and GLM 4.6
WorkloadGLM 4.7GLM 4.6Difference
Support chatbot
2,000 requests a day, 1,500 input tokens (60% cached), 300 output
USD 50.22
DeepInfra
USD 51.30
Venice
USD 1.08
GLM 4.7 lower
RAG over documents
1,000 requests a day, 8,000 input tokens (30% cached), 500 output
USD 99.21
DeepInfra
USD 104.25
Venice
USD 5.04
GLM 4.7 lower
Coding agent (one developer)
1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning
USD 387.90
DeepInfra
USD 396.00
Venice
USD 8.10
GLM 4.7 lower

GLM 4.7 is cheaper on all three workloads. The widest gap is on RAG over documents: the dearer model costs 5.1% more than the cheaper one.

Does the cheaper model change with your input:output ratio?

GLM 4.7 is cheaper at every mix of input and output tokens, before cache discounts: its cheapest input price and its cheapest output price are both at or below GLM 4.6's, so the input:output ratio never changes the answer. On output price alone they tie.

Price per 1M tokens of GLM 4.7 and GLM 4.6 at different input:output mixes
Input : output tokensGLM 4.7GLM 4.6
1 : 3 (long answers)USD 1.413 lower
DeepInfra
USD 1.42
Venice
1 : 1USD 1.075 lower
DeepInfra
USD 1.09
Venice
3 : 1 (the site’s blend)USD 0.7375 lower
DeepInfra
USD 0.76
Venice
10 : 1 (retrieval, long prompts)USD 0.5227 lower
DeepInfra
USD 0.55
Venice
30 : 1 (agents, big contexts)USD 0.4435 lower
DeepInfra
USD 0.4726
Venice

USD per 1M tokens at the cheapest standard provider for each mix, before cache discounts. Thinking tokens bill as output.

What do GLM 4.7 and GLM 4.6 cost per character in other languages?

Not measured: the real cost by language dataset covers only tokenizers we could measure from published files, and GLM 4.7 and GLM 4.6 are not among them. Count tokens on your own text with the counters below.

Check it on your own traffic

More comparisons: GLM 5 vs GLM 4.7 · GLM 4.7 Flash vs GLM 4.7 · GLM 4.6 vs GLM-4.5-FP8 · every GLM 4.7 comparison · every GLM 4.6 comparison · all 662 price comparisons

Questions

Is GLM 4.7 cheaper than GLM 4.6?

Yes. On a blend of 3 input tokens to 1 output token, GLM 4.7 costs USD 0.7375 per 1M tokens and GLM 4.6 USD 0.76, at each model's cheapest standard price. For input alone, GLM 4.7 is cheaper (USD 0.40 against USD 0.43 per 1M); for output alone, both start at USD 1.75. This compares price only, not quality.

What do GLM 4.7 and GLM 4.6 cost per 1M tokens?

GLM 4.7: from USD 0.40 input and USD 1.75 output at DeepInfra; Z.ai's own API charges USD 0.60 / USD 2.20; median of 8 standard prices USD 0.60 / USD 2.20. GLM 4.6: from USD 0.43 input and USD 1.75 output at Venice; Z.ai's own API charges USD 0.60 / USD 2.20; median of 6 standard prices USD 0.55 / USD 2.10. Each price is read from the provider's own pricing page; the source is linked in the table.

Which providers sell both GLM 4.7 and GLM 4.6?

6 providers have a standard price for both: DeepInfra (USD 0.7375 and USD 0.875 at 3:1), Venice (USD 1.075 and USD 0.76 at 3:1), Featherless (USD 0.9625 and USD 0.9625 at 3:1), GMI Cloud (USD 1 and USD 0.95 at 3:1), Novita AI (USD 1 and USD 0.9625 at 3:1), Z.ai (USD 1 and USD 1 at 3:1). The first is the lowest combined price. Buying each model from its own cheapest provider costs USD 0.7375 and USD 0.76.

Which is cheaper for a coding agent or a chatbot, GLM 4.7 or GLM 4.6?

For a coding agent (1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning): USD 387.90 a month on GLM 4.7 (DeepInfra) against USD 396.00 on GLM 4.6 (Venice), a difference of USD 8.10. For a support chatbot (2,000 requests a day, 1,500 input tokens (60% cached), 300 output): USD 50.22 a month on GLM 4.7 (DeepInfra) against USD 51.30 on GLM 4.6 (Venice), a difference of USD 1.08. Each uses the cheapest standard price for that workload, cached input included. Try your own numbers.

At what input:output ratio does the cheaper of GLM 4.7 and GLM 4.6 change?

GLM 4.7 is cheaper at every mix of input and output tokens, before cache discounts: its cheapest input price and its cheapest output price are both at or below GLM 4.6's, so the input:output ratio never changes the answer. On output price alone they tie.

Do GLM 4.7 and GLM 4.6 have cached input pricing?

GLM 4.7 from USD 0.06 per 1M cached input tokens (Google Vertex AI; 7 of 8 standard prices list a discount). GLM 4.6 from USD 0.08 per 1M cached input tokens (Venice; 5 of 6 standard prices list a discount). Cached tokens are billed at the input price where no cache price is published.

Which has the larger context window, GLM 4.7 or GLM 4.6?

Both go up to 204,800 tokens on the providers that state it.

Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity