---
title: "Open-Weight Model Pricing Ranked: The 2026 Discount Table"
canonical: "https://router.xark.io/resources/open-weight-model-pricing-ranked-2026"
description: "Every open-weight model we serve, ranked by how far its price sits below its publisher's own rate — on the plain rate card and on a real agent workload."
section: "resources"
updated: "2026-09-08"
source: "https://router.xark.io/resources/open-weight-model-pricing-ranked-2026.md"
---

# Open-Weight Model Pricing Ranked: The 2026 Discount Table

*Published 2026-09-08. Topics: Rankings, Pricing, Open-weight.*

Every open-weight model we serve, ranked by how far its price sits below its publisher's own rate — on the plain rate card and on a real agent workload.

Ranked by discount depth against each model's own publisher, the callable open-weight catalogue here runs 36-42% below official pricing on a plain rate card, and 65-68% once a repeated prompt prefix is served from cache on a real agent workload — the two figures differ because caching changes what counts as 'the bill,' not what the model costs per token.

## Two rankings, because one number hides the workload

A discount percentage means nothing without the shape of the bill it was computed on. The rate-card ranking below prices every token fresh, which is the right comparison for a one-shot request — a single classification call, a one-off summarisation job. It is the wrong comparison for anything that runs in a loop.

An agent or a chat session resends the same system prompt, the same tool schema, and a growing transcript on every turn. That repeated prefix is billed at a cached rate rather than the standard one, and industry reporting on prompt caching puts the structural saving from caching alone at 41-80% on repeated-prefix workloads, independent of which model is used [1]. The agent ranking below applies that same mechanism to our own rate table, on a stated workload rather than a vague 'up to' figure.

## The agent-workload ranking

This is the same seven models, the same publisher's own rate as the baseline, on one stated shape of work: 400 million input tokens a month with 60% of that input a repeated prefix, and 8 million output tokens. That volume and cache share are conservative — a coding agent with a fixed system prompt and a stable tool schema typically repeats considerably more than 60% of its input.

## Why the market moved this direction

This is not an isolated pattern. Independent pricing surveys published in 2026 put open-weight hosted APIs at $0.07-$0.90 per million tokens against list prices as high as $15 per million input and $60 per million output at the top of the closed-frontier tier — a spread of up to 625x for comparable-class tasks [2]. The same reporting notes list pricing across the market fell roughly 80% between early 2025 and early 2026 [2], which is the general trend this table sits inside rather than an exception to it.

None of that is a claim that open-weight models are categorically better. Closed frontier models measurably lead on reasoning-heavy benchmarks as of September 2026, by a margin independent reporting puts at several percentage points [3]. The claim this table supports is narrower and checkable: for the models in it, the discount against that model's own publisher is real, it widens under caching, and both numbers are computed from the same rate table the API bills from rather than asserted.

## The full table

Models marked not callable are catalogued at their intended price but not yet served by any configured upstream — a request for one returns a clear error rather than a fabricated result. Seven of twenty-four are callable today.

| Model | Publisher | Rate-card discount | Agent-workload discount | Callable |
| --- | --- | --- | --- | --- |
| Kimi K2.6 | Moonshot AI | 42% | 68% | Yes |
| GLM-5.2 | Z.ai | 42% | 68% | Yes |
| Kimi K3 | Moonshot AI | 40% | 65% | Yes |
| Qwen-Image | Alibaba | 40% | — | Yes |
| Qwen3 Embedding 8B | Alibaba | 40% | — | Yes |
| DeepSeek V4 Pro | DeepSeek | 37% | 66% | Yes |
| DeepSeek V4 Flash | DeepSeek | 36% | 65% | Yes |

## Sources

| # | Title | Publisher | URL | Cited for |
| --- | --- | --- | --- | --- |
| 1 | Prompt Caching in 2026: Cut Your LLM API Costs by Up to 90% | DevToolLab | https://devtoollab.com/blog/prompt-caching-guide | General industry figure for caching's structural cost reduction, cited for the mechanism, not for any specific model's rate. |
| 2 | LLM Inference Cost 2026: Cost per Million Tokens | packet.ai | https://packet.ai/blog/llm-inference-cost | Market-wide pricing spread and the 2025-2026 price decline, cited as market context. |
| 3 | Open Source vs Closed LLMs: Technical Comparison 2026 | Hakia | https://hakia.com/compare/open-vs-closed-llms/ | Cited for the honest counterpoint: closed frontier models retain a measured benchmark lead. |