> ## Documentation Index
> Fetch the complete documentation index at: https://docs.kymaapi.com/llms.txt
> Use this file to discover all available pages before exploring further.

# All Models

> Browse Kyma's active models by capability, cost, latency, and use case.

Kyma currently serves **75 models** across language, image, video, and audio. All models are verified working and accessible through the same `/v1` API. Language models are pay-per-token; image and video are flat per-call or pay-per-second depending on SKU; audio is per-character (TTS), per-minute (transcription / understand), or flat per call (music, voice clone, voice design). Live catalog: `GET /v1/models` (model metadata) and `GET /v1/pricing` (full pricing — text + image + video + audio in one round-trip).

```bash theme={null}
curl https://kymaapi.com/v1/models
```

## How to choose quickly

* **Start with `qwen-3.6-plus`** if you want the best default for general work, coding, and reasoning.
* **Step up to `qwen-3.7-max`** when you want the highest-quality Qwen for hard reasoning and multilingual work and cost is secondary.
* **Use `grok-4.3`** for frontier-quality general work and agentic coding at a balanced price.
* **Use `gemini-3.5-flash`** when you need 1M context with multimodal input (image, audio, video) and fast responses.
* **Use `kimi-k2.6`** for tool-heavy agents, long coding sessions, and image-aware workflows.
* **Use `deepseek-v4-pro`** for top reasoning and complex coding with 1M context.
* **Use `deepseek-v4-flash`** when you want V4-family quality at the cheapest price.
* **Use `gemini-2.5-flash`** when you need 1M context or cheap long-context throughput.
* **Use `qwen-3-32b`** when latency matters and you still want strong coding quality.
* **Use `glm-5.1`** when you need a long-running coding agent for repo-scale engineering work.
* **Use `sonar`** when the answer needs live web data with citations — current events, prices, releases (`sonar-pro` for deeper research).

## Filter the catalog

The live `GET /v1/models` endpoint now supports capability filters so agents can select models programmatically instead of hardcoding a shortlist.

```bash theme={null}
# Tool-capable models for coding agents
curl "https://kymaapi.com/v1/models?recommended_for=coding&tools=true&supported_parameters=tools,structured_outputs"

# Fast, cheap models with at least 128K context
curl "https://kymaapi.com/v1/models?latency_tier=fast&cost_tier=cheap&min_context_window=128000"

# Vision-capable models
curl "https://kymaapi.com/v1/models?vision=true&input_modalities=text,image"
```

## Recommended Models

<CardGroup cols={2}>
  <Card title="Qwen 3.6 Plus" icon="star" href="/models/qwen-3.6-plus">
    **#1 most popular.** Closed-weight, highest quality overall. 131K context.

    ```
    model="qwen-3.6-plus"
    ```
  </Card>

  <Card title="DeepSeek V4 Flash" icon="star" href="/models/deepseek-v4-flash">
    **Best value V4.** 1M context, MIT, native reasoning. \$0.19/M input.

    ```
    model="deepseek-v4-flash"
    ```
  </Card>

  <Card title="DeepSeek V4 Pro" icon="star" href="/models/deepseek-v4-pro">
    **Top reasoning.** 1.6T MoE flagship, 1M context, complex coding.

    ```
    model="deepseek-v4-pro"
    ```
  </Card>

  <Card title="Kimi K2.5" icon="star" href="/models/kimi-k2.6">
    **Best for agents.** Multimodal agentic model. 262K context.

    ```
    model="kimi-k2.6"
    ```
  </Card>
</CardGroup>

## Capability Guide

| Need                             | Best first pick                                     | Why                                                                                              |
| -------------------------------- | --------------------------------------------------- | ------------------------------------------------------------------------------------------------ |
| General default                  | [`qwen-3.6-plus`](/models/qwen-3.6-plus)            | Best overall quality, strong multilingual reasoning                                              |
| Max Qwen quality                 | [`qwen-3.7-max`](/models/qwen-3.7-max)              | Highest-quality Qwen, 1M context — premium step-up from 3.6 Plus                                 |
| Frontier agentic (balanced cost) | [`grok-4.3`](/models/grok-4.3)                      | Frontier reasoning + tool use at a balanced price, 1M context                                    |
| Multimodal 1M context            | [`gemini-3.5-flash`](/models/gemini-3.5-flash)      | Image/audio/video input, fast, 1M context                                                        |
| Tool-heavy agents                | [`kimi-k2.6`](/models/kimi-k2.6)                    | Strong tool use, long context, multimodal                                                        |
| Top reasoning                    | [`deepseek-v4-pro`](/models/deepseek-v4-pro)        | 1.6T MoE flagship, 1M context, native reasoning                                                  |
| Best value                       | [`deepseek-v4-flash`](/models/deepseek-v4-flash)    | V4-tier quality at the lowest price, 1M context                                                  |
| Long-running coding agents       | [`glm-5.1`](/models/glm-5.1)                        | Better fit for repo-scale engineering and multi-step execution                                   |
| Fast coding                      | `qwen-3-32b`                                        | Lower latency while staying strong on code and math                                              |
| 1M context                       | `gemini-2.5-flash`                                  | Cheapest long-context option on Kyma                                                             |
| Vision                           | `gemma-4-31b`                                       | Reliable image + text workflows                                                                  |
| Live web search                  | [`sonar`](/models/sonar)                            | Real-time web search with citations; [`sonar-pro`](/models/sonar-pro) for deeper research        |
| Image generation                 | [`gpt-image-2`](/models/gpt-image-2)                | OpenAI flagship — best text-in-image, multilingual typography. Quality dropdown low/medium/high. |
| Design-quality images            | [`recraft-v4`](/models/image-generation#recraft-v4) | #1 HF Arena. Brand and illustration default at \$0.054.                                          |
| Video generation                 | [`kling-3-pro`](/models/kling-3-pro)                | Premium cinematic clips, hero brand video                                                        |

## Tier 1 — Highest Quality

| Model ID                                         | Name              | Context | Speed  | Best For                                           |
| ------------------------------------------------ | ----------------- | ------- | ------ | -------------------------------------------------- |
| [`qwen-3.6-plus`](/models/qwen-3.6-plus)         | Qwen 3.6 Plus     | 131K    | Medium | General, #1 traffic                                |
| [`qwen-3.7-max`](/models/qwen-3.7-max)           | Qwen 3.7 Max      | 1M      | Medium | Max Qwen quality, reasoning, multilingual          |
| [`grok-4.3`](/models/grok-4.3)                   | Grok 4.3          | 1M      | Medium | Frontier general, agentic coding                   |
| [`gemini-3.5-flash`](/models/gemini-3.5-flash)   | Gemini 3.5 Flash  | 1M      | Fast   | Multimodal input, fast long-context                |
| [`deepseek-v4-pro`](/models/deepseek-v4-pro)     | DeepSeek V4 Pro   | 1M      | Medium | Top reasoning, complex coding                      |
| [`deepseek-v4-flash`](/models/deepseek-v4-flash) | DeepSeek V4 Flash | 1M      | Fast   | Best value, long context                           |
| `deepseek-v3`                                    | DeepSeek V3       | 160K    | Medium | Previous-gen flagship, stable                      |
| [`deepseek-r1`](/models/deepseek-r1)             | DeepSeek R1       | 64K     | Slow   | Reasoning, analysis                                |
| [`kimi-k2.6`](/models/kimi-k2.6)                 | Kimi K2.6         | 262K    | Medium | Agentic coding, multimodal                         |
| `gemma-4-31b`                                    | Gemma 4 31B       | 128K    | Medium | Multimodal, vision                                 |
| `qwen-3-32b`                                     | Qwen 3 32B        | 32K     | Fast   | Code, math, multilingual                           |
| `llama-3.3-70b`                                  | Llama 3.3 70B     | 128K    | Fast   | General, most popular open model                   |
| `minimax-m2.5`                                   | MiniMax M2.5      | 196K    | Medium | Agentic coding (SWE-bench 80.2%)                   |
| [`glm-5.1`](/models/glm-5.1)                     | GLM 5.1           | 203K    | Medium | Long-running coding agents, repo-scale engineering |

## Tier 2 — High Quality

| Model ID                                 | Name             | Context | Speed  | Best For                                |
| ---------------------------------------- | ---------------- | ------- | ------ | --------------------------------------- |
| `minimax-m2.7`                           | MiniMax M2.7     | 205K    | Medium | Agentic coding, productivity, debugging |
| `gpt-oss-120b`                           | GPT-OSS 120B     | 128K    | Medium | Writing, general intelligence           |
| `qwen-3-coder`                           | Qwen 3 Coder     | 131K    | Medium | Code generation                         |
| `gemini-2.5-flash`                       | Gemini 2.5 Flash | 1M      | Fast   | Long context                            |
| `gemini-3-flash`                         | Gemini 3 Flash   | 1M      | Fast   | Ultra-long context                      |
| [`glm-4.5-air`](/models/glm-4.5-air)     | GLM 4.5 Air      | 131K    | Fast   | Cheap agentic bulk tasks                |
| [`glm-4.7-flash`](/models/glm-4.7-flash) | GLM 4.7 Flash    | 203K    | Fast   | Cheap long-context throughput           |

## Web Search

Live, web-grounded models that search the web on every request and return cited answers. They bill a small flat web-search fee **on top of** token cost — see [Pricing → Web search](/pricing#web-search). No tool-calling support: the search runs internally, you just ask a question. Alias `search` → `sonar`.

| Model ID                         | Name      | Context | Speed  | Best For                                          |
| -------------------------------- | --------- | ------- | ------ | ------------------------------------------------- |
| [`sonar`](/models/sonar)         | Sonar     | 127K    | Medium | Quick cited answers, current events, live lookups |
| [`sonar-pro`](/models/sonar-pro) | Sonar Pro | 200K    | Medium | Deep multi-step research, longer cited reports    |

## Image Generation

Async endpoint at [`POST /v1/images/generations`](/api-reference/images-generations) — pay per image, no token billing. See the [Image Generation guide](/models/image-generation) for prompting tips and full examples.

| Model                                                                     | Best For                                                    |                 Cost / image                | Input           |
| ------------------------------------------------------------------------- | ----------------------------------------------------------- | :-----------------------------------------: | --------------- |
| [`gpt-image-2`](/models/gpt-image-2)                                      | **Text-in-image** — multilingual typography, logos, posters | $0.014 / $0.081 / \$0.297 (low/medium/high) | text + image    |
| [`flux-2-pro`](/models/image-generation#flux-2-pro)                       | Photoreal, multi-reference blend (up to 10 sources)         |                $0.041–$0.101                | text + image(s) |
| [`recraft-v4-pro`](/models/image-generation#recraft-v4-pro)               | 4MP print-ready design                                      |                   \$0.338                   | text            |
| [`ideogram-v3`](/models/image-generation#ideogram-v3)                     | Typography, logos, packaging                                |                   \$0.108                   | text            |
| [`recraft-v4`](/models/image-generation#recraft-v4)                       | Design-quality, brand assets                                |                   \$0.054                   | text            |
| [`flux-kontext-pro`](/models/image-generation#flux-kontext-pro)           | Image edit, inpaint, refine                                 |                   \$0.054                   | text + image    |
| [`recraft-v4-vector`](/models/image-generation#recraft-v4-vector)         | **Native SVG** — logos, icons                               |                   \$0.108                   | text            |
| [`recraft-v4-vector-pro`](/models/image-generation#recraft-v4-vector-pro) | 4MP SVG, print-ready                                        |                   \$0.405                   | text            |
| [`minimax-image-01`](/models/minimax-image-01)                            | Sub-cent budget tier, bulk                                  |                   \$0.005                   | text            |

## Video Generation

Async endpoint at [`POST /v1/videos/generations`](/api-reference/videos-generations) — pay per second of generated footage. See the [Video Generation guide](/models/video-generation) for prompting tips and the full per-SKU breakdown.

| Model                                            | Best For                       | Cost / sec |  5s clip  |  Audio  | Input        |
| ------------------------------------------------ | ------------------------------ | :--------: | :-------: | :-----: | ------------ |
| [`kling-2.5-pro`](/models/kling-2.5-pro)         | Budget cinematic, b-roll       |  \$0.0945  |  \$0.4725 |    —    | text + image |
| [`kling-3-pro`](/models/kling-3-pro)             | Premium cinematic, hero video  |  \$0.1512  |  \$0.7560 |    —    | text + image |
| [`kling-3-pro-audio`](/models/kling-3-pro-audio) | Cinematic w/ diegetic sound    |  \$0.2268  |  \$1.1340 |  native | text + image |
| [`seedance-2-pro`](/models/seedance-2-pro)       | Action, multi-shot, social     |  \$0.40959 | \$2.04795 | bundled | text + image |
| [`seedance-2-fast`](/models/seedance-2-fast)     | Social shorts, rapid iteration | \$0.326565 | \$1.63283 | bundled | text + image |

<Info>
  For the live canonical list, use `GET /v1/models`. Disabled models are intentionally omitted from this page.
</Info>

<Info>
  Models are updated regularly. Use `GET /v1/models` for the latest list.
</Info>