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.
Effective blend = input × 2.5% + cache × 97.0% + output × 0.5%. Fees are PAYG estimates; BYOK and enterprise contracts may differ.
offers 81Providers by price
Best current price
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
Full snapshot · server-rendered
Every offer, with its evidence
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.
| # | Plot | Provider | Gateway | Attributes | List | Discount | Quoted | Peak | Effective blend | Input | Cache | Output | TPS p50 | Latency p50 | Uptime |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 01★ | Pearl Research | OpenRouter | $0.00566 | — | $0.00566 | — | $0.00566per 1M tokens | $0.05 | $0.003 | $0.3 | 140 | n/a | 100.00% | ||
| 02★ | Morph | Vercel AI Gateway | $0.00643 | — | $0.00643 | — | $0.00643per 1M tokens | $0.022 | $0.004 | $0.4 | 133 | 634 ms | 100.00% | ||
| 03★ | DeepInfra | OpenRouter | $0.0138 | -51% | $0.006772 | — | $0.006772per 1M tokens | $0.098 | $0.00294 | $0.294 | 117 | n/a | 100.00% | ||
| 04 | DeepInfra | Requesty | $0.006772 | — | $0.006772 | — | $0.006772per 1M tokens | $0.098 | $0.00294 | $0.294 | n/a | n/a | n/a | ||
| 05★ | OpenInference | OpenRouter | $0.00694 | — | $0.00694 | — | $0.00694per 1M tokens | $0.05 | $0.002 | $0.75 | 169 | n/a | 100.00% | ||
| 06★ | Cohere | OpenRouter | $0.0073 | — | $0.0073 | — | $0.0073per 1M tokens | $0.115 | $0.0025 | $0.4 | 133 | n/a | 100.00% | ||
| 07★ | Ant Digital | OpenRouter | $0.0193 | -60% | $0.007728 | — | $0.007728per 1M tokens | $0.12 | $0.0024 | $0.48 | 97 | n/a | 100.00% | ||
| 08★ | River | OpenRouter | $0.007728 | — | $0.007728 | — | $0.007728per 1M tokens | $0.12 | $0.0024 | $0.48 | 75 | n/a | 100.00% | ||
| 09★ | Prime Intellect | OpenRouter | $0.007946 | — | $0.007946 | — | $0.007946per 1M tokens | $0.0568 | $0.00312 | $0.7 | 126 | n/a | 100.00% | ||
| 10★ | Sail Research | OpenRouter | $0.00829 | — | $0.00829 | — | $0.00829per 1M tokens | $0.04 | $0.007 | $0.1 | 119 | n/a | 100.00% | ||
| 11★ | Cloudflare Workers AI | OpenRouter | $0.00841 | — | $0.00841 | — | $0.00841per 1M tokens | $0.1 | $0.003 | $0.6 | 94 | n/a | 100.00% | ||
| 12★ | DekaLLM | OpenRouter | $0.00841 | — | $0.00841 | — | $0.00841per 1M tokens | $0.1 | $0.003 | $0.6 | 132 | n/a | 100.00% | ||
| 13★ | Relace | OpenRouter | $0.00841 | — | $0.00841 | — | $0.00841per 1M tokens | $0.12 | $0.003 | $0.5 | 141 | n/a | 100.00% | ||
| 14 | Relace | Vercel AI Gateway | $0.00841 | — | $0.00841 | — | $0.00841per 1M tokens | $0.12 | $0.003 | $0.5 | 248 | 1,215 ms | 100.00% | ||
| 15 | Morph | OpenRouter | $0.008925 | — | $0.008925 | — | $0.008925per 1M tokens | $0.059 | $0.005 | $0.52 | 112 | n/a | 100.00% | ||
| 16★ | Alibaba Cloud | Vercel AI Gateway | $0.00966 | — | $0.00966 | off-peak | $0.00966per 1M tokens | $0.15 | $0.003 | $0.6 | 253 | 5,637 ms | 100.00% | ||
| 17★ | DigitalOcean | OpenRouter | $0.00966 | — | $0.00966 | — | $0.00966per 1M tokens | $0.15 | $0.003 | $0.6 | 175 | n/a | 100.00% | ||
| 18★ | Wafer | OpenRouter | $0.0105 | — | $0.0105 | — | $0.0105per 1M tokens | $0.066 | $0.0065 | $0.5 | 167 | n/a | 100.00% | ||
| 19 | Wafer | Vercel AI Gateway | $0.0105 | — | $0.0105 | — | $0.0105per 1M tokens | $0.066 | $0.0065 | $0.5 | 186 | 359 ms | 100.00% | ||
| 20★ | Inceptron | OpenRouter | $0.0113 | — | $0.0113 | — | $0.0113per 1M tokens | $0.1 | $0.006 | $0.6 | 125 | n/a | 100.00% | ||
| 21★ | Modal | Opper | $0.0116 | — | $0.0116 | — | $0.0116per 1M tokens | $0.18 | $0.0036 | $0.72 | n/a | n/a | n/a | ||
| 22★ | Nebius | OpenRouter | $0.0193 | -40% | $0.0116 | — | $0.0116per 1M tokens | $0.18 | $0.0036 | $0.72 | 230 | n/a | 100.00% | ||
| 23 | Relace | Requesty | $0.012 | — | $0.012 | — | $0.012per 1M tokens | $0.07 | $0.008 | $0.5 | n/a | n/a | n/a | ||
| 24★ | Entrim | Opper | $0.0128 | — | $0.0128 | — | $0.0128per 1M tokens | $0.2 | $0.005 | $0.6 | n/a | n/a | n/a | ||
| 25★ | InferenceNet | OpenRouter | $0.0131 | — | $0.0131 | — | $0.0131per 1M tokens | $0.08 | $0.008 | $0.666 | 146 | n/a | 100.00% | ||
| 26 | Wafer | OpenRouter | $0.0131 | — | $0.0131 | — | $0.0131per 1M tokens | $0.036 | $0.01 | $0.5 | 157 | n/a | 100.00% | ||
| 27★ | ModelRun | OpenRouter | $0.0134 | — | $0.0134 | — | $0.0134per 1M tokens | $0.17 | $0.006 | $0.67 | 177 | n/a | 100.00% | ||
| 28★ | Makora | OpenRouter | $0.0136 | — | $0.0136 | — | $0.0136per 1M tokens | $0.15 | $0.006 | $0.8 | 125 | n/a | 100.00% | ||
| 29 | Sail Research | TrustedRouter | $0.0137 | — | $0.0137 | — | $0.0137per 1M tokens | $0.095 | $0.01 | $0.3165 | n/a | n/a | n/a | ||
| 30★ | Prima Labs | OpenRouter | $0.0155 | — | $0.0155 | — | $0.0155per 1M tokens | $0.24 | $0.0048 | $0.96 | 139 | n/a | 100.00% | ||
| 31 | Inceptron | TrustedRouter | $0.0155 | — | $0.0155 | — | $0.0155per 1M tokens | $0.1055 | $0.01 | $0.633 | n/a | n/a | n/a | ||
| 32 | Wafer | TrustedRouter | $0.0158 | — | $0.0158 | — | $0.0158per 1M tokens | $0.1372 | $0.01 | $0.5275 | n/a | n/a | n/a | ||
| 33 | Wafer | TrustedRouter | $0.0158 | — | $0.0158 | — | $0.0158per 1M tokens | $0.1372 | $0.01 | $0.5275 | n/a | n/a | n/a | ||
| 34 | Modal | OpenRouter | $0.0161 | — | $0.0161 | — | $0.0161per 1M tokens | $0.25 | $0.005 | $1 | 109 | n/a | 100.00% | ||
| 35★ | Runware | Requesty | $0.0165 | — | $0.0165 | — | $0.0165per 1M tokens | $0.15 | $0.01 | $0.6 | n/a | n/a | n/a | ||
| 36★ | Ionstream | OpenRouter | $0.0185 | — | $0.0185 | — | $0.0185per 1M tokens | $0.21 | $0.0105 | $0.62 | 195 | n/a | 100.00% | ||
| 37★ | CoreWeave | OpenRouter | $0.0193 | — | $0.0193 | — | $0.0193per 1M tokens | $0.3 | $0.006 | $1.2 | 241 | n/a | 100.00% | ||
| 38 | DigitalOcean | Vercel AI Gateway | $0.0193 | — | $0.0193 | — | $0.0193per 1M tokens | $0.3 | $0.006 | $1.2 | 264 | 608 ms | 100.00% | ||
| 39★ | Fireworks AI | OpenRouter | $0.0193 | — | $0.0193 | — | $0.0193per 1M tokens | $0.3 | $0.006 | $1.2 | 187 | n/a | 100.00% | ||
| 40 | Fireworks AI | Requesty | $0.0193 | — | $0.0193 | — | $0.0193per 1M tokens | $0.3 | $0.006 | $1.2 | n/a | n/a | n/a | ||
| 41 | Fireworks AI | Vercel AI Gateway | $0.0193 | — | $0.0193 | — | $0.0193per 1M tokens | $0.3 | $0.006 | $1.2 | 289 | 1,159 ms | 100.00% | ||
| 42★ | NEAR AI | OpenRouter | $0.0193 | — | $0.0193 | — | $0.0193per 1M tokens | $0.3 | $0.006 | $1.2 | 46 | n/a | n/a | ||
| 43 | Nebius | Requesty | $0.0193 | — | $0.0193 | — | $0.0193per 1M tokens | $0.3 | $0.006 | $1.2 | n/a | n/a | n/a | ||
| 44 | Nebius | Vercel AI Gateway | $0.0193 | — | $0.0193 | — | $0.0193per 1M tokens | $0.3 | $0.006 | $1.2 | n/a | 452 ms | 100.00% | ||
| 45★ | Novita AI | Requesty | $0.0193 | — | $0.0193 | — | $0.0193per 1M tokens | $0.3 | $0.006 | $1.2 | n/a | n/a | n/a | ||
| 46★ | Parasail | OpenRouter | $0.0193 | — | $0.0193 | — | $0.0193per 1M tokens | $0.3 | $0.006 | $1.2 | 207 | n/a | 100.00% | ||
| 47 | Parasail | Vercel AI Gateway | $0.0193 | — | $0.0193 | — | $0.0193per 1M tokens | $0.3 | $0.006 | $1.2 | n/a | 367 ms | 100.00% | ||
| 48★ | Reka | OpenRouter | $0.0193 | — | $0.0193 | — | $0.0193per 1M tokens | $0.3 | $0.006 | $1.2 | 159 | n/a | 100.00% | ||
| 49★ | Together AI | OpenRouter | $0.0193 | — | $0.0193 | — | $0.0193per 1M tokens | $0.3 | $0.006 | $1.2 | 169 | n/a | 100.00% | ||
| 50 | Together AI | Requesty | $0.0193 | — | $0.0193 | — | $0.0193per 1M tokens | $0.3 | $0.006 | $1.2 | n/a | n/a | n/a | ||
| 51 | Together AI | Vercel AI Gateway | $0.0193 | — | $0.0193 | — | $0.0193per 1M tokens | $0.3 | $0.006 | $1.2 | 265 | 975 ms | 100.00% | ||
| 52★ | Crusoe | OpenRouter | $0.02 | — | $0.02 | — | $0.02per 1M tokens | $0.29 | $0.007 | $1.2 | 198 | n/a | 100.00% | ||
| 53★ | Baseten | OpenRouter | $0.0203 | — | $0.0203 | — | $0.0203per 1M tokens | $0.3 | $0.007 | $1.2 | 157 | n/a | 100.00% | ||
| 54 | Baseten | Vercel AI Gateway | $0.0203 | — | $0.0203 | — | $0.0203per 1M tokens | $0.3 | $0.007 | $1.2 | 202 | 713 ms | 100.00% | ||
| 55★ | Mistral | OpenRouter | $0.0203 | — | $0.0203 | — | $0.0203per 1M tokens | $0.3 | $0.007 | $1.2 | 169 | n/a | 100.00% | ||
| 56 | Mistral | Opper | $0.0203 | — | $0.0203 | — | $0.0203per 1M tokens | $0.3 | $0.007 | $1.2 | n/a | n/a | n/a | ||
| 57 | Mistral | Vercel AI Gateway | $0.0203 | — | $0.0203 | — | $0.0203per 1M tokens | $0.3 | $0.007 | $1.2 | 312 | 2,137 ms | 100.00% | ||
| 58★ | Venice | OpenRouter | $0.0208 | — | $0.0208 | — | $0.0208per 1M tokens | $0.3 | $0.0075 | $1.2 | 111 | n/a | n/a | ||
| 59 | Mistral | Opper | $0.0223 | — | $0.0223 | — | $0.0223per 1M tokens | $0.33 | $0.0077 | $1.32 | n/a | n/a | n/a | ||
| 60 | Mistral | Vercel AI Gateway | $0.0223 | — | $0.0223 | — | $0.0223per 1M tokens | $0.33 | $0.0077 | $1.32 | 312 | 2,137 ms | 100.00% | ||
| 61 | Baseten | TrustedRouter | $0.0239 | — | $0.0239 | — | $0.0239per 1M tokens | $0.3165 | $0.01 | $1.266 | n/a | n/a | n/a | ||
| 62 | Baseten | TrustedRouter | $0.0239 | — | $0.0239 | — | $0.0239per 1M tokens | $0.3165 | $0.01 | $1.266 | n/a | n/a | n/a | ||
| 63 | Cloudflare Workers AI | TrustedRouter | $0.0239 | — | $0.0239 | — | $0.0239per 1M tokens | $0.3165 | $0.01 | $1.266 | n/a | n/a | n/a | ||
| 64★ | Telnyx | TrustedRouter | $0.0239 | — | $0.0239 | — | $0.0239per 1M tokens | $0.3165 | $0.01 | $1.266 | n/a | n/a | n/a | ||
| 65 | Telnyx | TrustedRouter | $0.0239 | — | $0.0239 | — | $0.0239per 1M tokens | $0.3165 | $0.01 | $1.266 | n/a | n/a | n/a | ||
| 66 | Runware | Vercel AI Gateway | $0.0248 | — | $0.0248 | — | $0.0248per 1M tokens | $0.23 | $0.015 | $0.91 | n/a | 331 ms | 100.00% | ||
| 67 | Fireworks AI | OpenRouter | $0.029 | — | $0.029 | — | $0.029per 1M tokens | $0.45 | $0.009 | $1.8 | 187 | n/a | 100.00% | ||
| 68 | Fireworks AI | Vercel AI Gateway | $0.029 | — | $0.029 | — | $0.029per 1M tokens | $0.45 | $0.009 | $1.8 | 289 | 1,159 ms | 100.00% | ||
| 69★ | Melious | Requesty | $0.0308 | — | $0.0308 | — | $0.0308per 1M tokens | $0.23 | $0.02 | $1.14 | n/a | n/a | n/a | ||
| 70★ | Particle AI | OpenRouter | $0.0334 | — | $0.0334 | — | $0.0334per 1M tokens | $0.06 | $0.03 | $0.55 | 108 | n/a | 100.00% | ||
| 71★ | Tinfoil | TrustedRouter | $0.0337 | — | $0.0337 | — | $0.0337per 1M tokens | $0.633 | $0.0106 | $1.53 | n/a | n/a | n/a | ||
| 72 | Tinfoil | TrustedRouter | $0.0337 | — | $0.0337 | — | $0.0337per 1M tokens | $0.633 | $0.0106 | $1.53 | n/a | n/a | n/a | ||
| 73 | Particle AI | Vercel AI Gateway | $0.0179 | — | $0.0179 | 2× | $0.0358per 1M tokens | $0.07 | $0.03 | $1 | n/a | 401 ms | 100.00% | ||
| 74★ | Sference | Opper | $0.0444 | — | $0.0444 | — | $0.0444per 1M tokens | $0.35 | $0.03 | $1.32 | n/a | n/a | n/a | ||
| 75 | Sference | Requesty | $0.0444 | — | $0.0444 | — | $0.0444per 1M tokens | $0.35 | $0.03 | $1.32 | n/a | n/a | n/a | ||
| 76★ | Confidential AI | TrustedRouter | $0.0449 | — | $0.0449 | — | $0.0449per 1M tokens | $0.3165 | $0.0317 | $1.266 | n/a | n/a | n/a | ||
| 77★ | TensorX | Opper | $0.1413 | — | $0.1413 | — | $0.1413per 1M tokens | $0.5 | $0.125 | $1.5 | n/a | n/a | n/a | ||
| 78 | TensorX | Requesty | $0.1461 | — | $0.1461 | — | $0.1461per 1M tokens | $0.5 | $0.13 | $1.5 | n/a | n/a | n/a | ||
| 79★ | Featherless AI | TrustedRouter | $0.2409 | — | $0.2409 | — | $0.2409per 1M tokens | $0.2374 | $0.2374 | $0.9495 | n/a | n/a | n/a | ||
| 80 | Nebius | TrustedRouter | $0.3212 | — | $0.3212 | — | $0.3212per 1M tokens | $0.3165 | $0.3165 | $1.266 | n/a | n/a | n/a | ||
| 81 | Nebius | TrustedRouter | $0.3212 | — | $0.3212 | — | $0.3212per 1M tokens | $0.3165 | $0.3165 | $1.266 | n/a | n/a | n/a |
Data quality notes (4)
- Duplicate offer deepseek-v4.1-flash-1017:opper:byteplus:standard:global:default:bytedance-ap; kept the better observation.
- Duplicate offer kimi-k3.1-pro:opper:moonshotai:standard:global:default:moonshot-api-global; kept the better observation.
- Duplicate offer kimi-k3.1-pro:opper:novita:standard:us:default:novita-api-us; kept the better observation.
- Duplicate offer kimi-k3.1-pro:openrouter:bedrock:standard:global:default:base; kept the better observation.
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.
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.