InferIndex · https://inferindex.dev/en/compare/qwen/qwen3-vl-235b-a22b-thinking/vs/sakana/sakana-namazu
Qwen3 VL 235B A22B Thinking costs from $1.72 per million tokens and Sakana Namazu from $1.71 (at a 3:1 input:output mix): the cheapest price for each; prices checked on .
Verdict
At these prices, the two models cost about the same per million tokens (at a 3:1 input:output mix).
Each model's lowest blended price, per 1M tokens, across every provider we track.
| Model | Lowest blended price, $ per 1M tokens. Green background: the most favourable value of each column. | Input price of the cheapest offer, per 1M tokens | Output price of the cheapest offer, per 1M tokens | The provider's published policy says the text you send is not used to train models. We only show what is published; we can't check it ourselves. | For 2,000 input tokens and 500 output tokens per request, 1,000 requests a day, at the cheapest offer for that workload. Change the workload above. | Offers | Providers | The maximum amount of text, counted in tokens, the model can take in and write in a single request. Past this limit, the request is refused or cut. | Observation |
|---|---|---|---|---|---|---|---|---|---|
| $1.71, most favourable value of the column | $0.95, most favourable value of the column | $4.00 | – | $117.00, most favourable value of the columnat Sakana AI via OpenRouter | 3 | 2 | 262k | Cheapest. Lowest blended price, $ per 1M tokens | |
| Most expensive offer · $1.88. The highest blended price among comparable offers: one price per provider (its cheapest route), standard tier, current prices only. Priority tiers and prices converted from points are not counted. | $0.98 | $3.95, most favourable value of the column | at NanoGPT | $118.05at Featherless | 4 | 4, most favourable value of the column | 33k |
Green background: the most favourable value of each column.
Prices as of Oct 30, 2026, 9:04 PM UTCSame rules as the API's /cheapest route. The monthly estimate uses the cheapest offer for that workload.