Gateway · OpenRouter
OpenRouter
A gateway that routes one API to many inference providers. Its per-token price is compared with first-party list prices; its fee is charged when credits are bought.
Prices reported by OpenRouter’s public API, snapshot · third-party-reported, not measured by Agent
Markup over first-party prices
0%per-token markup on 10 of 10 models
5.5% with the card credit feeCalculation
- Claude Haiku 4.5
- Claude Sonnet 5
- Claude Sonnet 5.5
- Claude Opus 4.8
- Claude Opus 5
- Claude Opus 5.5
- Claude Fable 5.1
- GPT-6 Luna
- Gemini 3.8 Flash
- Gemini 3.5 Flash
- per-token markup over the first-party list price (input and output)
- With the 5.5% card credit fee (input) (calculation, hollow)
| Item | Per-token markup (input) | Per-token markup (output) | With the 5.5% card credit fee (input) |
|---|---|---|---|
| Claude Haiku 4.5 | 0% | 0% | 5.5% |
| Claude Sonnet 5 | 0% | 0% | 5.5% |
| Claude Sonnet 5.5 | 0% | 0% | 5.5% |
| Claude Opus 4.8 | 0% | 0% | 5.5% |
| Claude Opus 5 | 0% | 0% | 5.5% |
| Claude Opus 5.5 | 0% | 0% | 5.5% |
| Claude Fable 5.1 | 0% | 0% | 5.5% |
| GPT-6 Luna | 0% | 0% | 5.5% |
| Gemini 3.8 Flash | 0% | 0% | 5.5% |
| Gemini 3.5 Flash | 0% | 0% | 5.5% |
List-price calculation, not a run. 10 rows, 3 series: Per-token markup (input), Per-token markup (output), With the 5.5% card credit fee (input). Per-token markup (input): all at 0%. Per-token markup (output): all at 0%.
Notes
Per-token markup, and the markup after the Standard credit-purchase fee (calculation)
A calculation: OpenRouter list price ÷ first-party list price − 1, then × (1 + 5.5%) for credits bought by card on the Standard plan (purchases large enough that the minimum fee does not apply). Fees as published on 2026-10-06; first-party prices from the vendors’ list prices.
Sources: OpenRouter public API: models and provider endpoints (snapshot), OpenRouter pricing and fees, Anthropic list prices (Claude models), OpenAI list prices, Google Gemini list prices
At a glance
Not reported
latency and throughput
The keyless API returned latency for 0 of 265 endpoints. Gateway delay is not measured: no key in the environment.
What is measured and what is not
- Per-token price through OpenRouter vs first-party
- ReportedReported list prices, snapshot 2026-10-06
- Credit-purchase fee
- Reported5.5% on Standard (third-party-reported, 2026-10-06)
- Provider latency and throughput (last 30 min)
- Not measuredunknown: the keyless API returned none for 265 endpoints
- Time to first token and total time through the gateway vs direct
- Not measurednot measured: no key in the environment. The live harness sends nothing without an OpenRouter key.
- Billed cost per call through the gateway
- Not measurednot measured: no key in the environment. The live harness sends nothing without an OpenRouter key.
Every value from the study
Each row is one of its prices on its own track, with the other providers of the same chart as muted dots (20 values). Reported prices, not measured. Use Table for the plain values; each row links to the chart it copies.
Reported by OpenRouter’s public API, not measured by AgentMuted dots: the other providers on the same chartUSD per million tokens
OpenRouter in Inference provider index: 27 models, 52 providers: 20 values, first Claude Haiku 4.5: OpenRouter vs Anthropic list price (Input) $1.00.
Compare OpenRouter
Price rows state the gap and name no winner: a reported price has no interval.
vs Anthropic
OpenRouter vs Anthropic
14 ties
OpenRouter vs Google AI Studio
4 ties
vs OpenAI
OpenRouter vs OpenAI
2 ties
Next
Write-ups that use this data
AI coding agent best practices: 12 rules, each backed by a measurement
12 rules for running AI coding agents, each with one measured number: validation, model choice, effort, caching, memory, routing, CLIs and sample size.
Claude Fable 5.1 vs Opus 5.5 vs Sonnet 5.5: speed, tokens and price tested
24 of 24: Claude Fable 5.1, Opus 5.5 and Sonnet 5.5 each passed every hard task. Fable cost 3.3x Opus and 6.5x Sonnet per pass (list-price calculation).
LLM API pricing comparison, October 2026: Claude vs GPT vs Gemini per million tokens
21 LLM API prices per million tokens, October 2026: Claude, GPT, Gemini and more. Blended prices span 100x. Price per token is not price per task.