Data

Proprietary models converge. Open-weights models don't.

Short answer. 6 of the 9 models that two or more hosts price here cost the same on every host, within 1.15×. DeepSeek V4 Flash 0731 does not: $0.06 per million input tokens on DeepInfra against $0.44 on Novita AI, a 7.3× gap.

In plain words. Some AI models are offered by several companies, and each sets its own price. For most of them the price is about the same everywhere. For 3, it is not: one company charges 7.3× what another does.

When a model's maker sets a list price, the hosts that resell it follow that price and the market converges: 6 of the 9 models served by two or more hosts in this dataset cost the same wherever you run them (within 1.15×). When there is no list price to follow, because the weights are open and the maker does not sell them itself, each host charges what it likes and there is no pattern: 3 models show a real spread, the widest being DeepSeek V4 Flash 0731 at 7.3×, and 2 have no reference price at all. The list prices were verified on November 18, 2026 against the official pages of DeepSeek, Moonshot AI, Z.ai, Alibaba and Minimax. The comparison below covers 36 verified offerings of 14 models across 7 hosts.

Offerings verified between November 16, 2026 and November 18, 2026 against each host's official pricing page. Prices are USD per million tokens. How this is checked

Where the price is the same

6 models where every host charges within 1.15× of the cheapest. On these models, the per-token price is not what separates the hosts.

Where the hosts' prices differ

3 models where the most expensive host charges more than 1.15× the cheapest for identical weights. Sorted by input price, cheapest first.

DeepSeek V4 Flash 0731 7.3× spread

DeepInfra charges $0.06 per million input tokens; Novita AI charges $0.44.

Host Input Output Context Source
DeepInfra $0.06 $0.18 1.0M deepinfra.com
Baseten $0.13 $0.26 — baseten.co
Novita AI $0.44 $1.32 1.0M novita.ai

gpt-oss-120b 3.0× spread

Novita AI charges $0.05 per million input tokens; Fireworks AI, Groq and Together AI charge $0.15.

Host Input Output Context Source
Novita AI $0.05 $0.25 131K novita.ai
Baseten $0.10 $0.50 — baseten.co
Together AI $0.15 $0.60 131K docs.together.ai
Fireworks AI $0.15 $0.60 131K docs.fireworks.ai
Groq $0.15 $0.60 131K console.groq.com

Llama 3.3 70B Instruct 1.4× spread

DeepInfra charges $0.10 per million input tokens; Novita AI charges $0.135.

Novita AI serves it with a 12K-token context; DeepInfra with 131K.

Host Input Output Context Source
DeepInfra $0.10 $0.32 131K deepinfra.com
Novita AI $0.135 $0.40 12K novita.ai

Models with a single host

7 models below have a single host; for 2 of them (DeepSeek V4 Flash 0731 and Qwen3.8 27B) there is no list price to show. There is nothing to compare here: each of these models is available from one host only.

Model Host Input Output Context Source
gpt-oss-20b Groq $0.075 $0.30 131K console.groq.com
Llama 3.1 8B Instruct DeepInfra $0.02 $0.04 131K deepinfra.com
Qwen3 32B DeepInfra $0.08 $0.28 41K deepinfra.com
Qwen3.8 Flash OpenRouter $0.15 $0.47 1M openrouter.ai
Qwen3.8 Max Fireworks AI $2.00 $6.00 — docs.fireworks.ai
DeepSeek V4 Flash 0731 OpenRouter (resellers only) no list price no list price 1.3M openrouter.ai
Qwen3.8 27B OpenRouter (resellers only) no list price no list price 1M openrouter.ai

DeepSeek V4 Flash 0731 is open-weights and has no model maker's list price on OpenRouter: 27 resellers served it on September 15, 2026, at prices that neither converge nor carry a struck-through list price, so there is no reference figure to publish. OpenRouter's :floor suffix routes a request to the cheapest of them at that moment. Qwen3.8 27B is open-weights and has no model maker's list price on OpenRouter: 16 resellers served it on September 15, 2026, at prices that neither converge nor carry a struck-through list price, so there is no reference figure to publish. OpenRouter's :floor suffix routes a request to the cheapest of them at that moment.

Recently retired

14 offerings that were in this table and no longer can be: delisted, moved behind an enterprise contract, or no longer on the host's official price list. Hosts remove these quietly; we keep the record.

Verification

Every offering above was read on its host's official pricing page; dates range from November 16, 2026 to November 18, 2026. Every price on this page is a link to the page it was read from. For OpenRouter, the price shown is the model maker's own list price on OpenRouter's providers page for that model, without promotional discounts (OpenRouter shows a discounted price with the list price struck through). It is neither what a default request pays (by default OpenRouter load-balances each request across several hosts, weighted towards the cheaper ones, so the effective price varies per request) nor the lowest price available through OpenRouter: resellers often undercut the maker, and the :floor suffix or sort: "price" gets you the cheapest of them at that moment, a figure that moves on its own as promotions end and hosts come and go (why the catalog number is not what you pay). Open-weights models whose maker does not serve them on OpenRouter have no list price; they are listed with "no list price" instead of a number. Offerings that could not be verified on an official page are not shown as prices: they are either excluded or listed under "Recently retired" (last review November 6, 2026). Grouping threshold: hosts within 1.15× of the cheapest input price count as "the same price".