GLM 4.7 vs L3.1-70B-Euryale-v2.2 API pricing
Updated
GLM 4.7's lowest standard price we found is USD 0.40 per 1M input tokens and USD 1.75 per 1M output tokens (DeepInfra). L3.1-70B-Euryale-v2.2's lowest standard price we found is USD 0.72 per 1M input tokens and USD 0.72 per 1M output tokens (Featherless). At 3 input tokens per output token, GLM 4.7 costs 2.4% more than L3.1-70B-Euryale-v2.2 (USD 0.7375 vs USD 0.72 per 1M).
How do GLM 4.7 and L3.1-70B-Euryale-v2.2 differ on price?
- Cheapest input price: GLM 4.7 USD 0.40 against USD 0.72 per 1M tokens, so L3.1-70B-Euryale-v2.2 costs 1.8× as much (80% more).
- Cheapest output price: L3.1-70B-Euryale-v2.2 USD 0.72 against USD 1.75 per 1M tokens, so GLM 4.7 costs 2.4× as much.
- Among the 201 indexed models, GLM 4.7 ranks 115th cheapest and L3.1-70B-Euryale-v2.2 113th on the 3:1 blend.
- The cheaper model changes at 3.2 input tokens per output token.
- Only GLM 4.7 lists a cached-input discount: GLM 4.7 at 7 standard prices of 8, from USD 0.06 (Google Vertex AI, 90% below that provider's input price). L3.1-70B-Euryale-v2.2's cached tokens bill at the input price.
- GLM 4.7 states up to 204,800 tokens of context, 1.56× the 131,072 of L3.1-70B-Euryale-v2.2.
- GLM 4.7 has 8 providers with a standard price, 6 more than L3.1-70B-Euryale-v2.2; 2 providers sell both (DeepInfra and Featherless).
- On one account, DeepInfra charges USD 0.7375 for GLM 4.7 (its cheapest price) and USD 0.85 for L3.1-70B-Euryale-v2.2 (1.18× its cheapest price) at 3:1, the lowest combined price among the providers that sell both.
- Shopping around matters more for GLM 4.7: its dearest standard price is 1.46× its cheapest, against 1.18× for L3.1-70B-Euryale-v2.2.
- Z.ai's own API charges USD 1 for GLM 4.7 at 3:1, 36% above the cheapest provider (DeepInfra).
- For the one-developer coding agent preset, the gap is USD 14,623 a year in GLM 4.7's favour (GLM 4.7 USD 387.90 a month, L3.1-70B-Euryale-v2.2 USD 1,607).
GLM 4.7 and L3.1-70B-Euryale-v2.2 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.
| Price | GLM 4.7 | L3.1-70B-Euryale-v2.2 |
|---|---|---|
| Model page | GLM 4.7 Z.ai · 8 providers | L3.1-70B-Euryale-v2.2 Sao10K · 2 providers |
| Cheapest standard price, blended 3:1 | USD 0.7375 USD 0.40 in / USD 1.75 out at DeepInfra DeepInfra page checked 2026-11-14 | USD 0.72 lower USD 0.72 in / USD 0.72 out at Featherless Featherless page checked 2026-11-15 |
| Cheapest input | USD 0.40 lower DeepInfra source | USD 0.72 Featherless source |
| Cheapest cached input | USD 0.06 Google Vertex AI source | No standard price lists a cache price; cached tokens bill at the input price. |
| Cheapest output | USD 1.75 DeepInfra source | USD 0.72 lower Featherless source |
| Maker's own API | USD 0.60 / USD 2.20 Z.ai source | Sao10K publishes no paid standard price on its own API that we found. |
| Median standard price | USD 0.60 / USD 2.20 input / output, 8 prices | USD 0.785 / USD 0.785 input / output, 2 prices |
| Context window | 204,800 tokens, largest stated; from 198,000 at some providers | 131,072 tokens, largest stated; from 32,768 at some providers |
| Providers with a standard price | 8 | 2 |
- Lower marks the lower price on a line; tie, equal prices. Other tiers and free rows are on the model pages.
Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).
What do GLM 4.7 and L3.1-70B-Euryale-v2.2 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).
| Workload | GLM 4.7 | L3.1-70B-Euryale-v2.2 | Difference |
|---|---|---|---|
| Support chatbot 2,000 requests a day, 1,500 input tokens (60% cached), 300 output | USD 50.22 DeepInfra | USD 77.76 Featherless | USD 27.54 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 183.60 Featherless | USD 84.39 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 1,607 DeepInfra | USD 1,219 GLM 4.7 lower |
GLM 4.7 is cheaper on all three workloads. The widest gap is on Coding agent (one developer): the dearer model costs 4.1× as much as the cheaper one.
Does the cheaper model change with your input:output ratio?
The cheaper model changes with the mix: below 3.2 input tokens per output token, L3.1-70B-Euryale-v2.2 is cheaper; above 3.2, GLM 4.7 is cheaper. At the site's 3:1 blend, L3.1-70B-Euryale-v2.2 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.
| Input : output tokens | GLM 4.7 | L3.1-70B-Euryale-v2.2 |
|---|---|---|
| 1 : 3 (long answers) | USD 1.413 DeepInfra | USD 0.72 lower Featherless |
| 1 : 1 | USD 1.075 DeepInfra | USD 0.72 lower Featherless |
| 3 : 1 (the site’s blend) | USD 0.7375 DeepInfra | USD 0.72 lower Featherless |
| 10 : 1 (retrieval, long prompts) | USD 0.5227 lower DeepInfra | USD 0.72 Featherless |
| 30 : 1 (agents, big contexts) | USD 0.4435 lower DeepInfra | USD 0.72 Featherless |
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 L3.1-70B-Euryale-v2.2 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 L3.1-70B-Euryale-v2.2 are not among them. Count tokens on your own text with the counters below.
Check it on your own traffic
- GLM 4.7 API pricing: all 8 providers and other tiers.
- L3.1-70B-Euryale-v2.2 API pricing: all 2 providers and other tiers.
- Cost calculator with GLM 4.7 and L3.1-70B-Euryale-v2.2 preloaded
- GLM token counter
- Token counter
- Prompt caching calculator
More comparisons: GLM 4.7 vs GLM 4.6 · GLM 5 vs GLM 4.7 · GLM 4.7 Flash vs GLM 4.7 · every GLM 4.7 comparison · every L3.1-70B-Euryale-v2.2 comparison · all 662 price comparisons
Questions
Is GLM 4.7 cheaper than L3.1-70B-Euryale-v2.2?
No. On a blend of 3 input tokens to 1 output token, L3.1-70B-Euryale-v2.2 costs USD 0.72 per 1M tokens and GLM 4.7 USD 0.7375, at each model's cheapest standard price. For input alone, GLM 4.7 is cheaper (USD 0.40 against USD 0.72 per 1M); for output alone, L3.1-70B-Euryale-v2.2 is (USD 0.72 against USD 1.75). This compares price only, not quality.
What do GLM 4.7 and L3.1-70B-Euryale-v2.2 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. L3.1-70B-Euryale-v2.2: from USD 0.72 input and USD 0.72 output at Featherless; median of 2 standard prices USD 0.785 / USD 0.785. 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 L3.1-70B-Euryale-v2.2?
2 providers have a standard price for both: DeepInfra (USD 0.7375 and USD 0.85 at 3:1), Featherless (USD 0.9625 and USD 0.72 at 3:1). The first is the lowest combined price. Buying each model from its own cheapest provider costs USD 0.7375 and USD 0.72.
Which is cheaper for a coding agent or a chatbot, GLM 4.7 or L3.1-70B-Euryale-v2.2?
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 1,607 on L3.1-70B-Euryale-v2.2 (DeepInfra), a difference of USD 1,219. 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 77.76 on L3.1-70B-Euryale-v2.2 (Featherless), a difference of USD 27.54. 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 L3.1-70B-Euryale-v2.2 change?
The cheaper model changes with the mix: below 3.2 input tokens per output token, L3.1-70B-Euryale-v2.2 is cheaper; above 3.2, GLM 4.7 is cheaper. At the site's 3:1 blend, L3.1-70B-Euryale-v2.2 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 GLM 4.7 and L3.1-70B-Euryale-v2.2 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). L3.1-70B-Euryale-v2.2: no standard price lists a cached-input 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 L3.1-70B-Euryale-v2.2?
GLM 4.7: up to 204,800 tokens, against 131,072 for L3.1-70B-Euryale-v2.2, 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.