01000001 01010000 01001001QWEN-3.8-MAXDEDICATEDQWEN-3.7-PLUS01001110 01000110 01011001QWEN-3.8-27BFRONTIERDEEPSEEK-V4-FLASHGLM-5.2NO-FOREX-MARKUP01000001 01010000 01001001QWEN-3.8-MAXDEDICATEDQWEN-3.7-PLUS01001110 01000110 01011001QWEN-3.8-27BFRONTIERDEEPSEEK-V4-FLASHGLM-5.2NO-FOREX-MARKUP
DOC. APF-009·FRONTIER APIS·LIVE

The open frontier,
priced in rupees.

// vs a USD-billing gateway, all-in
19.6%
Same weights. Same throughput.

Buying the same model in dollars, you pay a 5–7% forex markup and 18% GST on the conversion before the model has run. We hold the provider accounts and bill you rupee-native, so neither exists on your bill.

₹95.5 interbank × 1.06 forex × 1.18 GST vs ₹96.0 flat
▸ See the full comparison

6 of the strongest open-weight models on the market, served through accounts we hold, billed at a flat rupee rate with a reclaimable GST invoice. One key instead of 6 provider logins — and roughly 20% less than the same models cost you through a foreign gateway.

These models run on the provider's infrastructure, not ours. That is why no India-residency claim appears against them anywhere on this page — the receipt still names the model and the region every call actually ran on.

§ 01 — PRICE ADVANTAGE
// Same model · same provider weights · lower bill

Every frontier model, cheaper in rupees.

The upstream dollar rate is printed against every row, because the only way to show a discount is real is to show what you are being discounted from.

PER 1M TOKENS · INDIAN DEVELOPER · ALL-IN ₹ · EXACT IN / OUTvs a USD gateway
MODELVIA A USD GATEWAY* (in / out)VIA APINFY (in / out)SAVE
Qwen 3.8 Max$2.00 / $6.00₹238.90 / ₹716.71₹192 / ₹57619.6%
Qwen 3.7 Plus$0.47 / $1.41₹56.14 / ₹168.43₹45 / ₹13519.6%
DeepSeek V4 Flash$0.44 / $1.32₹52.56 / ₹157.68₹42 / ₹12719.6%
Kimi K2.7 Code$0.95 / $4.00₹113.48 / ₹477.81₹91 / ₹38419.6%
Qwen 3.7 Max$1.25 / $3.75₹149.31 / ₹447.94₹120 / ₹36019.6%
GLM-5.2$1.40 / $4.40₹167.23 / ₹525.59₹134 / ₹42219.6%
*A USD-billing gateway, or a provider direct, costs an Indian developer USD × interbank (₹95.5) × 1.06 forex markup × 1.18 GST — the real all-in cost once the card statement lands. apinfy bills USD × ₹96.0 flat (interbank + ₹0.50 spread) in rupees, with a GST invoice you reclaim, so the forex markup and the conversion-GST do not exist on your bill. On ₹10,00,000/mo of frontier spend that is ₹23,55,910 saved per year. Rates provisional until launch.
What each rate is quoted against. Qwen rows are the International (Singapore) endpoint — the one we resell. Alibaba publishes a separate Chinese Mainland (Beijing) rate card that runs 60–70% cheaper, so a Qwen price without its endpoint cannot be checked against anything. DeepSeek V4 Flash is quoted at the peak rate; DeepSeek bills peak/off-peak since 16 Aug 2026. Its peak windows land inside the Indian working day, so peak is the rate that holds for the traffic we actually serve. // The whole table rests on the interbank rate (₹95.5), which moves every day; last checked 25 August 2026, and re-confirmed against the live rate before billing starts.
§ 02 — WHY ONE KEY
// Six providers. One account. One invoice.

Six providers. One account. One invoice.

Every foreign gateway bills in US dollars. By the time it reaches your card you have paid a 5–7% forex markup and 18% GST on the conversion — roughly a 25% stack on top of the sticker price. We hold the provider accounts and bill you rupee-native, so that stack does not exist. Same weights, same throughput, one flat rupee rate, and a GST invoice you can actually reclaim.

§ 03 — THE MODELS
// 6 models · ₹ in / out per 1M tokens

The open frontier, on one key.

The same weights the labs publish. The dollar rate under each price is the provider's own, shown so the rupee figure above it can be checked rather than believed.

Qwen 3.8 Max
Newest flagship · live now
₹192 / ₹576 in/out per 1M
provider rate $2.00 / $6.00
Qwen 3.7 Plus
Fast mid-tier · reasoning built in
₹45 / ₹135 in/out per 1M
provider rate $0.47 / $1.41
DeepSeek V4 Flash
Updated · cheapest frontier
₹42 / ₹127 in/out per 1M
provider rate $0.44 / $1.32
Kimi K2.7 Code
Long-horizon agentic
₹91 / ₹384 in/out per 1M
provider rate $0.95 / $4.00
Qwen 3.7 Max
Flagship agent model
₹120 / ₹360 in/out per 1M
provider rate $1.25 / $3.75
GLM-5.2
Highest open GDPval
₹134 / ₹422 in/out per 1M
provider rate $1.40 / $4.40

Rates provisional until launch. They are derived from the provider's published dollar rate at the interbank assumption stated above and are re-confirmed against the live rate before billing starts. Every response discloses the exact model that answered.

§ 04 — BENCHMARK READOUT
// Prove it, don't claim it

Where the open frontier lands against the closed one.

Published scores for the frontier models we serve, next to the closed frontier, with the price column beside them. Gaps shown honestly.

ModelLaneSWE-bench VerifiedSWE-bench Pro₹/M out
DeepSeek V4 Flash▸FRONTIERFrontier78.055.4₹22
Kimi K2.7 Code▸FRONTIERFrontier80.258.6₹330
GLM-5.2▸FRONTIERFrontier80.658.4₹355
Claude Opus 4.8Closed88.6₹2,075
GPT-5.6 SolClosed96.2₹2,490
SRC: published cards + independent SWE-bench Pro (Scale) / Vals AI · JUL 2026. SWE-bench is scaffold-sensitive (~20pt swing) — Pro is the fairer cross-model read. ~8–16pt behind absolute frontier on Verified, at 1/6th–1/100th the price.
§ 05 — INTEGRATION
// Drop-in

Change one line. Keep your code.

▸ frontier.pyPYTHON 3 // OPENAI-COMPATIBLE
# pip install openai — then change the base_url client = OpenAI(base_url="https://apinfy.com/v1", api_key="kk_live_...") # any of the frontier models above, by name, on the one key r = client.chat.completions.create(model="glm-5.2", messages=[...]) print(r.receipt.model, r.receipt.lane, r.receipt.region) # → glm-5.2 frontier ✓ signed
▸ Get your API keyRead the docs

The open frontier. Always in rupees.

One key, one invoice, no forex markup. Top up by UPI when you are ready.

▸ Get your API keySee pricing