> This is a page from the Tuna docs (https://tuna.ai/docs/models). The docs index is at https://tuna.ai/llms.txt, and all pages in one file are at https://tuna.ai/llms-full.txt. Add `.md` to any docs URL to get its Markdown.
>
> Tuna's serverless API is OpenAI compatible. Use an OpenAI SDK with the base URL `https://api-us.tuna.ai/v1` and a Tuna API key.

# Models & Pricing

| | Model | Input types | Input /M | Cache read /M | Output /M | SLA speed | Parameter size | Intelligence |
| --- | --- | --- | ---: | ---: | ---: | ---: | ---: | ---: |
| <ModelLogo provider="moonshot" /> | [Kimi K3 Ultrafast](#kimi-k3-ultrafast) | <Modalities image video /> | $18.00 | $1.80 | $90.00 | >250 tok/s | 2.8 trillion | <Intelligence out-of-4="4" /> |
| <ModelLogo provider="deepseek" /> | [DeepSeek V4.1 Flash Ultrafast](#deepseek-v4.1-flash-ultrafast) | <Modalities image /> | $1.80 | $0.18 | $7.20 | >350 tok/s | 552 billion | <Intelligence out-of-4="2" /> |
| <ModelLogo provider="zai" /> | [GLM-5.3 Flash Ultrafast](#glm-5.3-flash-ultrafast) | <Modalities image video /> | $0.90 | $0.18 | $3.00 | >450 tok/s | 320 billion | <Intelligence out-of-4="2" /> |
| Automatically receive up to 50% off if the output speed does not meet SLA. |||||||||



Tuna currently only serves open-weight models, with [US regional routing](https://tuna.ai/docs/us-regional-routing.md) and [Zero Data Retention](https://tuna.ai/docs/privacy-and-zdr.md).

Prices shown are denominated in US dollars, per 1 million tokens. [Precision of billing](https://tuna.ai/docs/account/billing.md) is per 1 single token.

Use the specific model ID to pin your requests to that exact model. If that model is deprecated, requests to its ID will fail. The auto-updating model ID routes to the latest model in the same family, so you can use the newest model without changing your code. Prices can change between model generations in a family. When using an auto-updating model ID, billing is based on whichever model you are routed to.

Cache read is the price for [cached input tokens](https://tuna.ai/docs/api/input-caching.md). Input is implicitly a cache write, and Tuna bills input and cache writes at the same rate. See [Billing](https://tuna.ai/docs/account/billing.md) for how token usage is charged.

<ModelCard title="Kimi K3 Ultrafast" description="Our strongest open-weight model, from Moonshot AI." model-maker="moonshot" specific-model-id="tuna-us/moonshotai/kimi-k3-ultrafast" auto-updating-model-id="tuna-us/moonshotai/kimi-latest-ultrafast" regional-routing="US only" total-context="1M" max-output-tokens="131072" vision="yes" video image-token-size-pixels="28x28" precision="Original weights" parameters="2.8 trillion" active-parameters="104 billion" released="2026-07-16" announcement-url="https://www.kimi.ai/blog/kimi-k3" intelligence-out-of-4="4" input-USD-per-1M-tokens="18.00" cache-read-USD-per-1M-tokens="1.80" output-USD-per-1M-tokens="90.00" output-speed-sla-tok-per-sec="250" reasoning-effort-levels="low, high, max" />


<ModelCard title="DeepSeek V4.1 Flash Ultrafast" description="A fast and economical workhorse from DeepSeek. According to DeepSeek, V4.1 Flash is more powerful than the much-larger V4 Pro." model-maker="deepseek" specific-model-id="tuna-us/deepseek/deepseek-v4.1-flash-ultrafast" auto-updating-model-id="tuna-us/deepseek/deepseek-flash-latest-ultrafast" regional-routing="US only" total-context="1M" max-output-tokens="131072" vision="yes" image-token-size-pixels="42x42" precision="Original weights" parameters="552 billion" active-parameters="8 billion for input, 16 billion for output" released="2026-09-10" announcement-url="https://www.deepseek.com/en/news/deepseek-v4-1-flash/" intelligence-out-of-4="2" input-USD-per-1M-tokens="1.80" cache-read-USD-per-1M-tokens="0.18" output-USD-per-1M-tokens="7.20" output-speed-sla-tok-per-sec="350" reasoning-effort-levels="none, low, high, max" />

<ModelCard title="GLM-5.3 Flash Ultrafast" description="A fast, low-cost model from Z.ai with moderate intelligence." model-maker="zai" specific-model-id="tuna-us/z-ai/glm-5.3-flash-ultrafast" auto-updating-model-id="tuna-us/z-ai/glm-flash-latest-ultrafast" regional-routing="US only" total-context="1M" max-output-tokens="131072" vision="yes" video image-token-size-pixels="28x28" precision="Original weights" parameters="320 billion" active-parameters="18 billion" released="2026-08-26" announcement-url="https://z.ai/blog/glm-5.3-flash" intelligence-out-of-4="2" input-USD-per-1M-tokens="0.90" cache-read-USD-per-1M-tokens="0.18" output-USD-per-1M-tokens="3.00" output-speed-sla-tok-per-sec="450" reasoning-effort-levels="low, high, max" />

---

- This page: [Models & Pricing](https://tuna.ai/docs/models.md)
- Index of all pages: [llms.txt](https://tuna.ai/llms.txt)
- All pages in one file: [llms-full.txt](https://tuna.ai/llms-full.txt)