BroadRouter

DeepSeek V3.1 vs GLM 4.6V API pricing

Updated

DeepSeek V3.1: USD 0.25 input, USD 0.95 output per 1M tokens (DeepInfra). GLM 4.6V: USD 0.30 input, USD 0.90 output per 1M tokens (Z.ai and 1 other). At 3 input tokens per output token, GLM 4.6V costs 5.9% more than DeepSeek V3.1 (USD 0.45 vs USD 0.425 per 1M).

Picked by the same-tier rule: both are in the second quarter of the indexed models by price (USD 0.1556 to USD 0.4512 per 1M tokens at 3:1) and in the same size class, mid-size (no tier word, 40B to 200B parameters or no size in the name). DeepSeek V3.1 is the 4th-closest-priced model from another maker to GLM 4.6V in that bucket. 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 DeepSeek V3.1 and GLM 4.6V differ on price?

DeepSeek V3.1 and GLM 4.6V 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.

DeepSeek V3.1 and GLM 4.6V API prices compared
PriceDeepSeek V3.1GLM 4.6V
Model pageDeepSeek V3.1
DeepSeek · 7 providers
GLM 4.6V
Z.ai · 2 providers
Cheapest standard price, blended 3:1USD 0.425 lower
USD 0.25 in / USD 0.95 out at DeepInfra
DeepInfra page checked 2026-11-14
USD 0.45
USD 0.30 in / USD 0.90 out at Z.ai and 1 other
Z.ai page checked 2026-11-14
Cheapest inputUSD 0.25 lower
DeepInfra source
USD 0.30
Z.ai source
Cheapest cached inputUSD 0.06
Google Vertex AI source
USD 0.05 lower
Z.ai source
Cheapest outputUSD 0.95
DeepInfra source
USD 0.90 lower
Z.ai source
Maker's own APIDeepSeek publishes no paid standard price on its own API that we found.USD 0.30 / USD 0.90
Z.ai source
Median standard priceUSD 0.285 / USD 1
input / output, 7 prices
USD 0.30 / USD 0.90
input / output, 2 prices
Context window163,840 tokens, largest stated; from 131,072 at some providers131,072 tokens, largest stated
Providers with a standard price72

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

What do DeepSeek V3.1 and GLM 4.6V 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 DeepSeek V3.1 and GLM 4.6V
WorkloadDeepSeek V3.1GLM 4.6VDifference
Support chatbot
2,000 requests a day, 1,500 input tokens (60% cached), 300 output
USD 33.12
DeepInfra
USD 29.70
Z.ai
USD 3.42
GLM 4.6V lower
RAG over documents
1,000 requests a day, 8,000 input tokens (30% cached), 500 output
USD 65.61
DeepInfra
USD 67.50
Z.ai
USD 1.89
DeepSeek V3.1 lower
Coding agent (one developer)
1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning
USD 351.90
DeepInfra
USD 238.50
Z.ai
USD 113.40
GLM 4.6V lower

The cheaper model depends on the workload: GLM 4.6V for Support chatbot, DeepSeek V3.1 for RAG over documents, GLM 4.6V for Coding agent (one developer). Cache-heavy work rewards a low cached-input price. The widest gap is on Coding agent (one developer): the dearer model costs 48% more than the cheaper one.

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

The cheaper model changes with the mix: below 1 input token per output token, GLM 4.6V is cheaper; above 1, DeepSeek V3.1 is cheaper. At the site's 3:1 blend, DeepSeek V3.1 is cheaper. More input per output token, as with retrieval or agents that resend long contexts, favours the lower input price; long answers favour the lower output price.

Price per 1M tokens of DeepSeek V3.1 and GLM 4.6V at different input:output mixes
Input : output tokensDeepSeek V3.1GLM 4.6V
1 : 3 (long answers)USD 0.775
DeepInfra
USD 0.75 lower
Z.ai
1 : 1USD 0.60 tie
DeepInfra
USD 0.60 tie
Z.ai
3 : 1 (the site’s blend)USD 0.425 lower
DeepInfra
USD 0.45
Z.ai
10 : 1 (retrieval, long prompts)USD 0.3136 lower
DeepInfra
USD 0.3545
Z.ai
30 : 1 (agents, big contexts)USD 0.2726 lower
DeepInfra
USD 0.3194
Z.ai

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

What do DeepSeek V3.1 and GLM 4.6V 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 4.6V is not among them. Count tokens on your own text with the counters below.

Check it on your own traffic

More comparisons: DeepSeek V3.1 vs DeepSeek V3 · DeepSeek V3.2 vs DeepSeek V3.1 · GLM 4.6V vs GLM 4.5V · every DeepSeek V3.1 comparison · every GLM 4.6V comparison · all 662 price comparisons

Questions

Is DeepSeek V3.1 cheaper than GLM 4.6V?

Yes. On a blend of 3 input tokens to 1 output token, DeepSeek V3.1 costs USD 0.425 per 1M tokens and GLM 4.6V USD 0.45, at each model's cheapest standard price. For input alone, DeepSeek V3.1 is cheaper (USD 0.25 against USD 0.30 per 1M); for output alone, GLM 4.6V is (USD 0.90 against USD 0.95). This compares price only, not quality.

What do DeepSeek V3.1 and GLM 4.6V cost per 1M tokens?

DeepSeek V3.1: from USD 0.25 input and USD 0.95 output at DeepInfra; median of 7 standard prices USD 0.285 / USD 1. GLM 4.6V: from USD 0.30 input and USD 0.90 output at Z.ai and 1 other; Z.ai's own API charges USD 0.30 / USD 0.90; median of 2 standard prices USD 0.30 / USD 0.90. Each price is read from the provider's own pricing page; the source is linked in the table.

Which providers sell both DeepSeek V3.1 and GLM 4.6V?

None of the providers we track sells both at a standard price. DeepSeek V3.1 is cheapest at DeepInfra and GLM 4.6V at Z.ai and 1 other, so running both means two accounts.

Which is cheaper for a coding agent or a chatbot, DeepSeek V3.1 or GLM 4.6V?

For a coding agent (1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning): USD 351.90 a month on DeepSeek V3.1 (DeepInfra) against USD 238.50 on GLM 4.6V (Z.ai), a difference of USD 113.40. For a support chatbot (2,000 requests a day, 1,500 input tokens (60% cached), 300 output): USD 33.12 a month on DeepSeek V3.1 (DeepInfra) against USD 29.70 on GLM 4.6V (Z.ai), a difference of USD 3.42. 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 DeepSeek V3.1 and GLM 4.6V change?

The cheaper model changes with the mix: below 1 input token per output token, GLM 4.6V is cheaper; above 1, DeepSeek V3.1 is cheaper. At the site's 3:1 blend, DeepSeek V3.1 is cheaper. More input per output token, as with retrieval or agents that resend long contexts, favours the lower input price; long answers favour the lower output price.

Do DeepSeek V3.1 and GLM 4.6V have cached input pricing?

DeepSeek V3.1 from USD 0.06 per 1M cached input tokens (Google Vertex AI; 3 of 7 standard prices list a discount). GLM 4.6V from USD 0.05 per 1M cached input tokens (Z.ai; 2 of 2 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, DeepSeek V3.1 or GLM 4.6V?

DeepSeek V3.1: up to 163,840 tokens, against 131,072 for GLM 4.6V, as stated on providers' pricing pages. Some providers offer less than the maximum; check the model pages before you pick the cheapest row for long prompts.

Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity