provider price index

DeepSeek V4.1 Flash 1017provider price index

Effective input, cache, and output economics for DeepSeek V4.1 Flash 1017 across 5 gateways. Compare the best current price from every inference provider, with ZDR status, gateway fees, discounts, and the evidence behind every number.

24 hours5-minute bucketsself-hostedOpenRouterVercel AI GatewayRequestyOpperTrustedRouter

Last update Nov 21 2026, 18:40 UTC/data age 2m ago/tracking since Nov 21 2026, 18:28 UTC

Cheapest standard$0.0048per 1M · default mixAmbient · OpenRouter
Offers tracked144across 5 gateways130 Standard
Strict ZDR offers8861% of tracked offersprovider-reported
24 hours coverage1.4%4/288 buckets10m fill · gaps stay gaps
Range
Tier
Display
Coverage
1.4%4/288 · 5m bucketstracking since Nov 21 2026, 18:28 UTC
Gateways
ZDR
Usage mix always sums to 100.0%
2.5%
%
97.0%
%
0.5%
%
Total 100.0% — effective mix

Effective blend = input × 2.5% + cache × 97.0% + output × 0.5%. Fees are PAYG estimates; BYOK and enterprise contracts may differ.

offers 81

Providers by price

Best current price

5/12 selected
44 / 44 providers

Each line is the selected provider’s current best offer. Use the gateway menu to pin a different route.

Effective blended price

Price over 24 hours

5 lines1.4% coverageUSD / 1M
Updated Nov 21 2026, 18:40 UTC · data age 2m agoLive

Full snapshot · server-rendered

Every offer, with its evidence

81 offersUSD / 1M

Rows are sorted by effective blended price using the current mix (2.5% Input · 97.0% Cache · 0.5% Output). List price is reconstructed from the gateway discount; peak badges use the UTC window at collection time. TPS is shown only when the source reports a positive p50.

Every offer, with its evidence · USD/1M
#PlotProviderGatewayAttributesListDiscountQuotedPeakEffective blendInputCacheOutputTPS p50Latency p50Uptime
01★Pearl ResearchOpenRouterZDRfp8$0.00566—$0.00566—$0.00566per 1M tokens$0.05$0.003$0.3140Model page · 30mn/a30m100.00%30m · 1d 100.00%
02★MorphVercel AI GatewayZDRfp8$0.00643—$0.00643—$0.00643per 1M tokens$0.022$0.004$0.4133API · 60m634 ms60m100.00%60m · 1d 100.00%
03★DeepInfraOpenRouterZDRfp8$0.0138-51%$0.006772—$0.006772per 1M tokens$0.098$0.00294$0.294117Model page · 30mn/a30m100.00%30m · 1d 100.00%
04DeepInfraRequestyZDRfp8$0.006772—$0.006772—$0.006772per 1M tokens$0.098$0.00294$0.294n/an/an/an/an/an/a · 1d n/a
05★OpenInferenceOpenRouterZDRfp4$0.00694—$0.00694—$0.00694per 1M tokens$0.05$0.002$0.75169Model page · 30mn/a30m100.00%30m · 1d 100.00%
06★CohereOpenRouterZDRfp8$0.0073—$0.0073—$0.0073per 1M tokens$0.115$0.0025$0.4133Model page · 30mn/a30m100.00%30m · 1d 100.00%
07★Ant DigitalOpenRouterZDRfp8$0.0193-60%$0.007728—$0.007728per 1M tokens$0.12$0.0024$0.4897Model page · 30mn/a30m100.00%30m · 1d 100.00%
08★RiverOpenRouterZDR$0.007728—$0.007728—$0.007728per 1M tokens$0.12$0.0024$0.4875Model page · 30mn/a30m100.00%30m · 1d 100.00%
09★Prime IntellectOpenRouterZDR$0.007946—$0.007946—$0.007946per 1M tokens$0.0568$0.00312$0.7126Model page · 30mn/a30m100.00%30m · 1d 99.9%
10★Sail ResearchOpenRouterZDRUSfp4$0.00829—$0.00829—$0.00829per 1M tokens$0.04$0.007$0.1119Model page · 30mn/a30m100.00%30m · 1d 99.8%
11★Cloudflare Workers AIOpenRouterZDR$0.00841—$0.00841—$0.00841per 1M tokens$0.1$0.003$0.694Model page · 30mn/a30m100.00%30m · 1d 100.00%
12★DekaLLMOpenRouterZDR$0.00841—$0.00841—$0.00841per 1M tokens$0.1$0.003$0.6132Model page · 30mn/a30m100.00%30m · 1d 100.00%
13★RelaceOpenRouterZDRfp4$0.00841—$0.00841—$0.00841per 1M tokens$0.12$0.003$0.5141Model page · 30mn/a30m100.00%30m · 1d 99.93%
14RelaceVercel AI GatewayZDR$0.00841—$0.00841—$0.00841per 1M tokens$0.12$0.003$0.5248API · 60m1,215 ms60m100.00%60m · 1d 99.97%
15MorphOpenRouterZDRfp8$0.008925—$0.008925—$0.008925per 1M tokens$0.059$0.005$0.52112Model page · 30mn/a30m100.00%30m · 1d 98.7%
16★Alibaba CloudVercel AI GatewayZDR$0.00966—$0.00966off-peak$0.00966per 1M tokens$0.15$0.003$0.6253API · 60m5,637 ms60m100.00%60m · 1d 100.00%
17★DigitalOceanOpenRouterZDR$0.00966—$0.00966—$0.00966per 1M tokens$0.15$0.003$0.6175Model page · 30mn/a30m100.00%30m · 1d 100.00%
18★WaferOpenRouterZDRmxfp4$0.0105—$0.0105—$0.0105per 1M tokens$0.066$0.0065$0.5167Model page · 30mn/a30m100.00%30m · 1d 100.00%
19WaferVercel AI GatewayZDRUS$0.0105—$0.0105—$0.0105per 1M tokens$0.066$0.0065$0.5186API · 60m359 ms60m100.00%60m · 1d 99.99%
20★InceptronOpenRouterZDRfp4$0.0113—$0.0113—$0.0113per 1M tokens$0.1$0.006$0.6125Model page · 30mn/a30m100.00%30m · 1d 99.0%
21★ModalOpperZDREU$0.0116—$0.0116—$0.0116per 1M tokens$0.18$0.0036$0.72n/an/an/an/an/an/a · 1d n/a
22★NebiusOpenRouterZDRfp4$0.0193-40%$0.0116—$0.0116per 1M tokens$0.18$0.0036$0.72230Model page · 30mn/a30m100.00%30m · 1d 100.00%
23RelaceRequestyZDRfp4$0.012—$0.012—$0.012per 1M tokens$0.07$0.008$0.5n/an/an/an/an/an/a · 1d n/a
24★EntrimOpperZDREUfp8$0.0128—$0.0128—$0.0128per 1M tokens$0.2$0.005$0.6n/an/an/an/an/an/a · 1d n/a
25★InferenceNetOpenRouterZDRUSfp8$0.0131—$0.0131—$0.0131per 1M tokens$0.08$0.008$0.666146Model page · 30mn/a30m100.00%30m · 1d 100.00%
26WaferOpenRouterZDRUSmxfp4$0.0131—$0.0131—$0.0131per 1M tokens$0.036$0.01$0.5157Model page · 30mn/a30m100.00%30m · 1d 100.00%
27★ModelRunOpenRouterZDRfp4$0.0134—$0.0134—$0.0134per 1M tokens$0.17$0.006$0.67177Model page · 30mn/a30m100.00%30m · 1d 100.00%
28★MakoraOpenRouterZDRfp8$0.0136—$0.0136—$0.0136per 1M tokens$0.15$0.006$0.8125Model page · 30mn/a30m100.00%30m · 1d 100.00%
29Sail ResearchTrustedRouterZDRfp8$0.0137—$0.0137—$0.0137per 1M tokens$0.095$0.01$0.3165n/an/an/an/an/an/a · 1d n/a
30★Prima LabsOpenRouterZDR$0.0155—$0.0155—$0.0155per 1M tokens$0.24$0.0048$0.96139Model page · 30mn/a30m100.00%30m · 1d 99.5%
31InceptronTrustedRouterZDR$0.0155—$0.0155—$0.0155per 1M tokens$0.1055$0.01$0.633n/an/an/an/an/an/a · 1d n/a
32WaferTrustedRouterZDR$0.0158—$0.0158—$0.0158per 1M tokens$0.1372$0.01$0.5275n/an/an/an/an/an/a · 1d n/a
33WaferTrustedRouterZDR$0.0158—$0.0158—$0.0158per 1M tokens$0.1372$0.01$0.5275n/an/an/an/an/an/a · 1d n/a
34ModalOpenRouterZDR$0.0161—$0.0161—$0.0161per 1M tokens$0.25$0.005$1109Model page · 30mn/a30m100.00%30m · 1d 100.00%
35★RunwareRequestyZDR$0.0165—$0.0165—$0.0165per 1M tokens$0.15$0.01$0.6n/an/an/an/an/an/a · 1d n/a
36★IonstreamOpenRouterZDR$0.0185—$0.0185—$0.0185per 1M tokens$0.21$0.0105$0.62195Model page · 30mn/a30m100.00%30m · 1d 99.9%
37★CoreWeaveOpenRouterZDRfp8$0.0193—$0.0193—$0.0193per 1M tokens$0.3$0.006$1.2241Model page · 30mn/a30m100.00%30m · 1d 100.00%
38DigitalOceanVercel AI GatewayZDR$0.0193—$0.0193—$0.0193per 1M tokens$0.3$0.006$1.2264API · 60m608 ms60m100.00%60m · 1d 99.99%
39★Fireworks AIOpenRouterZDR$0.0193—$0.0193—$0.0193per 1M tokens$0.3$0.006$1.2187Model page · 30mn/a30m100.00%30m · 1d 100.00%
40Fireworks AIRequestyZDR$0.0193—$0.0193—$0.0193per 1M tokens$0.3$0.006$1.2n/an/an/an/an/an/a · 1d n/a
41Fireworks AIVercel AI GatewayZDR$0.0193—$0.0193—$0.0193per 1M tokens$0.3$0.006$1.2289API · 60m1,159 ms60m100.00%60m · 1d 100.00%
42★NEAR AIOpenRouterZDR$0.0193—$0.0193—$0.0193per 1M tokens$0.3$0.006$1.246Model page · 30mn/a30mn/a30m · 1d 100.00%
43NebiusRequestyZDRUSfp4$0.0193—$0.0193—$0.0193per 1M tokens$0.3$0.006$1.2n/an/an/an/an/an/a · 1d n/a
44NebiusVercel AI GatewayZDRfp8$0.0193—$0.0193—$0.0193per 1M tokens$0.3$0.006$1.2n/aAPI · 60m452 ms60m100.00%60m · 1d 99.90%
45★Novita AIRequestyZDRfp8$0.0193—$0.0193—$0.0193per 1M tokens$0.3$0.006$1.2n/an/an/an/an/an/a · 1d n/a
46★ParasailOpenRouterZDRfp8$0.0193—$0.0193—$0.0193per 1M tokens$0.3$0.006$1.2207Model page · 30mn/a30m100.00%30m · 1d 100.00%
47ParasailVercel AI GatewayZDR$0.0193—$0.0193—$0.0193per 1M tokens$0.3$0.006$1.2n/aAPI · 60m367 ms60m100.00%60m · 1d 100.00%
48★RekaOpenRouterZDR$0.0193—$0.0193—$0.0193per 1M tokens$0.3$0.006$1.2159Model page · 30mn/a30m100.00%30m · 1d 99.93%
49★Together AIOpenRouterZDR$0.0193—$0.0193—$0.0193per 1M tokens$0.3$0.006$1.2169Model page · 30mn/a30m100.00%30m · 1d 100.00%
50Together AIRequestyZDR$0.0193—$0.0193—$0.0193per 1M tokens$0.3$0.006$1.2n/an/an/an/an/an/a · 1d n/a
51Together AIVercel AI GatewayZDR$0.0193—$0.0193—$0.0193per 1M tokens$0.3$0.006$1.2265API · 60m975 ms60m100.00%60m · 1d 100.00%
52★CrusoeOpenRouterZDRfp8$0.02—$0.02—$0.02per 1M tokens$0.29$0.007$1.2198Model page · 30mn/a30m100.00%30m · 1d 100.00%
53★BasetenOpenRouterZDR$0.0203—$0.0203—$0.0203per 1M tokens$0.3$0.007$1.2157Model page · 30mn/a30m100.00%30m · 1d 100.00%
54BasetenVercel AI GatewayZDRUS$0.0203—$0.0203—$0.0203per 1M tokens$0.3$0.007$1.2202API · 60m713 ms60m100.00%60m · 1d 99.97%
55★MistralOpenRouterZDRfp8$0.0203—$0.0203—$0.0203per 1M tokens$0.3$0.007$1.2169Model page · 30mn/a30m100.00%30m · 1d 99.2%
56MistralOpperZDR$0.0203—$0.0203—$0.0203per 1M tokens$0.3$0.007$1.2n/an/an/an/an/an/a · 1d n/a
57MistralVercel AI GatewayZDR$0.0203—$0.0203—$0.0203per 1M tokens$0.3$0.007$1.2312API · 60m2,137 ms60m100.00%60m · 1d 99.6%
58★VeniceOpenRouterZDRfp8$0.0208—$0.0208—$0.0208per 1M tokens$0.3$0.0075$1.2111Model page · 30mn/a30mn/a30m · 1d 99.6%
59MistralOpperZDREU$0.0223—$0.0223—$0.0223per 1M tokens$0.33$0.0077$1.32n/an/an/an/an/an/a · 1d n/a
60MistralVercel AI GatewayZDREU$0.0223—$0.0223—$0.0223per 1M tokens$0.33$0.0077$1.32312API · 60m2,137 ms60m100.00%60m · 1d 99.6%
61BasetenTrustedRouterZDR$0.0239—$0.0239—$0.0239per 1M tokens$0.3165$0.01$1.266n/an/an/an/an/an/a · 1d n/a
62BasetenTrustedRouterZDR$0.0239—$0.0239—$0.0239per 1M tokens$0.3165$0.01$1.266n/an/an/an/an/an/a · 1d n/a
63Cloudflare Workers AITrustedRouterZDR$0.0239—$0.0239—$0.0239per 1M tokens$0.3165$0.01$1.266n/an/an/an/an/an/a · 1d n/a
64★TelnyxTrustedRouterZDR$0.0239—$0.0239—$0.0239per 1M tokens$0.3165$0.01$1.266n/an/an/an/an/an/a · 1d n/a
65TelnyxTrustedRouterZDR$0.0239—$0.0239—$0.0239per 1M tokens$0.3165$0.01$1.266n/an/an/an/an/an/a · 1d n/a
66RunwareVercel AI GatewayZDR$0.0248—$0.0248—$0.0248per 1M tokens$0.23$0.015$0.91n/aAPI · 60m331 ms60m100.00%60m · 1d 100.00%
67Fireworks AIOpenRouterZDRUS$0.029—$0.029—$0.029per 1M tokens$0.45$0.009$1.8187Model page · 30mn/a30m100.00%30m · 1d 100.00%
68Fireworks AIVercel AI GatewayZDRUS$0.029—$0.029—$0.029per 1M tokens$0.45$0.009$1.8289API · 60m1,159 ms60m100.00%60m · 1d 100.00%
69★MeliousRequestyZDREU$0.0308—$0.0308—$0.0308per 1M tokens$0.23$0.02$1.14n/an/an/an/an/an/a · 1d n/a
70★Particle AIOpenRouterZDRUS$0.0334—$0.0334—$0.0334per 1M tokens$0.06$0.03$0.55108Model page · 30mn/a30m100.00%30m · 1d 100.00%
71★TinfoilTrustedRouterZDRfp8$0.0337—$0.0337—$0.0337per 1M tokens$0.633$0.0106$1.53n/an/an/an/an/an/a · 1d n/a
72TinfoilTrustedRouterZDRfp8$0.0337—$0.0337—$0.0337per 1M tokens$0.633$0.0106$1.53n/an/an/an/an/an/a · 1d n/a
73Particle AIVercel AI GatewayZDRUS$0.0179—$0.01792×$0.0358per 1M tokens$0.07$0.03$1n/aAPI · 60m401 ms60m100.00%60m · 1d 100.00%
74★SferenceOpperZDREEA$0.0444—$0.0444—$0.0444per 1M tokens$0.35$0.03$1.32n/an/an/an/an/an/a · 1d n/a
75SferenceRequestyZDREU$0.0444—$0.0444—$0.0444per 1M tokens$0.35$0.03$1.32n/an/an/an/an/an/a · 1d n/a
76★Confidential AITrustedRouterZDR$0.0449—$0.0449—$0.0449per 1M tokens$0.3165$0.0317$1.266n/an/an/an/an/an/a · 1d n/a
77★TensorXOpperZDREUfp8$0.1413—$0.1413—$0.1413per 1M tokens$0.5$0.125$1.5n/an/an/an/an/an/a · 1d n/a
78TensorXRequestyZDREU$0.1461—$0.1461—$0.1461per 1M tokens$0.5$0.13$1.5n/an/an/an/an/an/a · 1d n/a
79★Featherless AITrustedRouterZDRfp8cache ≈ input$0.2409—$0.2409—$0.2409per 1M tokens$0.2374$0.2374$0.9495n/an/an/an/an/an/a · 1d n/a
80NebiusTrustedRouterZDRcache ≈ input$0.3212—$0.3212—$0.3212per 1M tokens$0.3165$0.3165$1.266n/an/an/an/an/an/a · 1d n/a
81NebiusTrustedRouterZDRcache ≈ input$0.3212—$0.3212—$0.3212per 1M tokens$0.3165$0.3165$1.266n/an/an/an/an/an/a · 1d n/a
List, quoted, and effective prices are all shown in USD per 1M. Original values are stored as USD per token.TPS n/a is shown as n/a. Latency windows: OpenRouter 30m, Vercel 1h, gateway-only sources n/a.
Data quality notes (4)
Method24 hours · 5m

How the numbers are computed

Every displayed figure comes from a stored observation and a deterministic rule. The index keeps the quote, discount, peak window, effective price, retention class, and raw payload so that any value can be recalculated rather than merely trusted.

Collection

A systemd timer triggers an independent collector every five minutes. It fetches four models from five gateways: OpenRouter endpoints, Vercel AI Gateway endpoints, the Requesty public model catalog, Opper public model routes, and TrustedRouter endpoint lists. Payloads are validated, normalized, archived as gzip, written to SQLite, and projected into per-model read caches.

A single gateway or model failure does not stop the others. Failed combinations keep their last successful offers and are labeled partial or error. If every combination fails, the previous cache is left untouched and health turns stale; no synthetic point is inserted.

Offer identity

An offer is a model × gateway × provider × tier × region × quantization × route configuration. Tier, region, quantization, and gateway route are never merged into one price. OpenRouter tags such as /us and /fp8 become region and quantization attributes; /flex, /priority, and /spot become tiers. Vercel inference regions become separate offers. Opper service routes and TrustedRouter endpoint IDs become the route dimension when they distinguish otherwise identical offers.

Price formula

Blended price = input × input_weight + cache_read × cache_weight + output × output_weight. Weights are normalized when their total is not 100%. The default mix is 2.5% / 97% / 0.5%.

List = quoted / (1 − discount). Effective price applies the UTC peak rule or time override at the observation time. Prices are stored in USD per token, so currency and token-unit changes are reversible display transforms. The gateway-fee toggle applies a second, clearly labeled PAYG multiplier.

  • Discount changes are real signals and are not smoothed.
  • Peak windows wrap across midnight and honor ISO weekdays.
  • Historical points use the current FX rate; historical FX is not replayed.
  • The chart draws one real offer history per provider, not a per-bucket minimum across gateways.

Retention

Provider retention is classified as strict, safety, no-training, retained, or unknown. Strict means no routine content storage, logging, moderation retention, or training as reported by the source. Safety means the source allows retention for abuse, safety, or legal review. No-training means content may be retained but is not used for training. Retained means content may be stored and used for training. Unknown means the source did not publish enough detail.

Gateway retention is a separate static policy. OpenRouter does not store prompts by default and enforces provider ZDR per request. Vercel deletes prompts and outputs after the request. Requesty logs content by default unless disabled. Opper and TrustedRouter report no default prompt storage. The ZDR filter applies to provider retention; the tooltip explains the gateway layer.

TPS, latency, and uptime

TPS is output tokens/sec p50. Vercel reports p50 throughput in its endpoint API. OpenRouter endpoint TPS is often empty, so the collector parses the public model page per model every 30 minutes. Requesty, Opper, and TrustedRouter do not publish TPS for these routes, so they show n/a. Missing TPS is never estimated.

Latency is time-to-first-token; uptime is the source’s trailing window. These fields are evidence only and are kept in the price table for audit.

Storage, coverage, and preferences

SQLite runs in WAL mode with the collector and web process separate. Raw 5-minute snapshots are kept for 30 days, 15-minute aggregates for 180 days, 30-minute aggregates for 2 years, and gzipped source payloads for 90 days. Each bucket uses its last observation. A gap is carried forward only when the last real observation is at most 10 minutes older than the bucket.

The three ranges use fixed granularity: 24 hours at 5 minutes, 3 days at 15 minutes, and 7 days at 30 minutes. Coverage is the share of buckets with at least one observation. Display preferences, filters, and provider selections are stored in the browser; only the last language/model landing target uses a small cookie so the root redirect works before React loads.

Public source audit

The collector accesses only public endpoints and public model pages. No bearer tokens are used. Source sites’ terms and robots policies are respected; requests run at a five-minute cadence.

FAQmethod, gaps, TPS, and pricing

Questions the data should answer

01What price is actually being compared?

The chart and table use the effective blended price: input × input weight + cache-read × cache weight + output × output weight. Each offer stores input, cache-read, and output prices in USD per token. The default usage mix is 2.5% input, 97% cache read, and 0.5% output. List price is used only for the struck-through reference and discount badge.

02What is the difference between a gateway and a provider?

A gateway is the routing and billing layer (OpenRouter, Vercel AI Gateway, Requesty, Opper, TrustedRouter). A provider is the organization that actually runs inference (DeepInfra, Morph, Wafer, Moonshot AI, Z.AI, and others). One provider can appear through several gateways at different prices. The chart draws the provider’s current best offer; the full snapshot lists every gateway offer so the choice is auditable.

03How is Zero Data Retention determined?

Retention is two layers: gateway retention and provider retention. Provider retention is normalized to strict, safety, no-training, retained, or unknown using the source’s published flags: OpenRouter’s ZDR endpoint list, Vercel’s has_zdr and has_no_training, Requesty’s data_retention fields, Opper’s compliance metadata, and TrustedRouter’s endpoint flags. A strict provider does not guarantee that the gateway itself does not log content; check both layers. The ZDR filter defaults to strict only and can include safety retention.

04Are gateway fees included in the ranking?

By default the index compares published token rates, matching the existing OpenRouter and Vercel data. The “Include gateway fees” toggle applies each gateway’s public PAYG estimate: OpenRouter 5.5%, Requesty 5%, Opper 3%, TrustedRouter 5.5%, and Vercel 0%. BYOK, enterprise contracts, and payment methods can change the real all-in cost, so the toggle is an estimate rather than a quote.

05Why does history start at a recent timestamp?

No gateway exposes historical provider quotes for these models. History begins at the first successful collection and is never back-filled or synthesized. The collector runs every five minutes; new models and new gateways start with an empty series and grow over time. Gaps longer than the ten-minute forward-fill allowance are rendered as hatched bands rather than connected lines.

06Why can the same provider have different prices on different gateways?

Each offer is a specific route: model × gateway × provider × tier × region × quantization × route. A provider may have a discounted endpoint on one gateway, a regional endpoint on another, or a different quantization. The index never merges those into one price. The chart picks the provider’s current best offer for the selected tier, retention filter, gateway filter, and usage mix; the full snapshot keeps every route.

07Does changing currency or token unit change the ranking?

No. Prices are stored in USD per token. Currency and token-unit conversion are display-only multipliers using the latest daily ECB reference rates. Changing the usage mix, tier, ZDR mode, gateway filter, or gateway-fee toggle does recompute the ranking.

08Is this an official DeepSeek, Moonshot, Z.ai, OpenRouter, or Vercel product?

No. This is an independent, self-hosted, read-only index built from public endpoints and public model pages. It does not use bearer tokens or private APIs, is not affiliated with any model provider or gateway, and is not a purchasing commitment or a commercial data license.