> ## 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. # Pricing > Pay-per-token pricing, credits, and rate limits. Start with $0.50 free. ## How pricing works Kyma charges per token. Every request has: * **input tokens** for your prompt and context * **output tokens** for the model's response No monthly fee, no seat fee, no contract. Prices below are per **1 million tokens**. For the live canonical table, use `GET /v1/models` or `GET /v1/credits/pricing`. ## Pricing per model ### Cheapest useful models Use these for bulk automation, extraction, and simple workloads. | Model | Input / 1M | Output / 1M | Best for | | ------------------- | :-------------------: | :---------: | ---------------------------------------------------------- | | `glm-4.7-flash` | \$0.08 | \$0.54 | Cheap long-context throughput | | `gemma-4-31b` | \$0.19 | \$0.54 | Cheap multimodal / vision | | `deepseek-v4-flash` | $0.19 · $0.019 cached | \$0.38 | Best value V4 — 1M context, native reasoning | | `gpt-oss-120b` | \$0.20 | \$0.81 | Cheap writing + general tasks | | `glm-4.5-air` | \$0.18 | \$1.15 | Cheap agentic bulk work | | `step-3.7-flash` | \$0.27 | \$1.55 | Cheap multimodal flash — text+image+video in, tool calling | ### Balanced value Use these when you want strong quality without flagship pricing. | Model | Input / 1M | Output / 1M | Best for | | --------------- | :--------: | :---------: | ------------------------------------------------------- | | `qwen-3-32b` | \$0.39 | \$0.81 | Fast coding loops | | `minimax-m2.5` | \$0.41 | \$1.62 | Agentic coding | | `minimax-m2.7` | \$0.41 | \$1.62 | Productivity + debugging | | `minimax-m3` | \$0.41 | \$1.62 | Newest MiniMax — agentic coding, 1M context, multimodal | | `deepseek-v3` | \$0.81 | \$2.30 | Best value frontier-class model | | `llama-3.3-70b` | \$1.19 | \$1.19 | Balanced open model | ### Flagship / premium Use these when quality or capability matters more than cost. Rows showing `· cached` print the cached input price inline (10% of normal input — applies to repeated system prompts and tool definitions on caching-enabled models; see [prompt caching](#prompt-caching)). | Model | Input / 1M | Output / 1M | Best for | | ----------------------- | :-------------------: | :---------: | -------------------------------------------------------- | | `qwen-3-coder` | \$0.68 | \$2.16 | Code-specialized output | | `deepseek-r1` | \$0.74 | \$2.90 | Deep reasoning | | `kimi-k2.6` | \$1.28 | \$5.40 | Agentic flagship (newest) | | `kimi-k2.7-code` | \$1.28 | \$5.40 | Coding specialist — fewer reasoning tokens, 262K context | | `kimi-k2.5` | \$0.68 | \$3.78 | Agentic flagship (previous-gen) | | `qwen-3.6-plus` | \$0.68 | \$4.05 | Best default overall | | `qwen-3.7-plus` | \$0.54 | \$2.16 | Newest Qwen flagship — vision + 1M context | | `deepseek-v4-pro` | $2.35 · $0.235 cached | \$4.70 | Top reasoning, complex coding (1M context) | | `claude-opus-4-7` | $6.75 · $0.675 cached | \$33.75 | Anthropic flagship — top engineering quality | | `claude-sonnet-4-6` | $4.05 · $0.405 cached | \$20.25 | Anthropic balanced — long-running agentic | | `claude-haiku-4-5` | $1.35 · $0.135 cached | \$6.75 | Anthropic fast tier — 200K context | | `glm-5.2` | \$1.89 | \$5.94 | Newest flagship — 1M context, #1 open-weight coding | | `glm-5.1` | \$1.89 | \$5.94 | Long-running coding agents (previous-gen) | | `nemotron-3-ultra-550b` | \$0.68 | \$3.38 | Largest US open-weight — 1M context, fast reasoning | ### Long-context & multimodal Use these when context length or image input is the bottleneck. | Model | Input / 1M | Output / 1M | Best for | | ------------------ | :--------: | :---------: | -------------------------- | | `gemini-2.5-flash` | \$0.41 | \$3.38 | 1M context | | `gemini-3-flash` | \$0.68 | \$4.05 | Newer long-context preview | | `gemma-4-31b` | \$0.19 | \$0.54 | Vision + text workflows | ### Web search Perplexity's Sonar models run a live web search on every request and return cited answers. They bill **two components on the same request**: normal token pricing **plus** a flat web-search fee for the live search. | Model | Input / 1M | Output / 1M | Web-search fee | Best for | | -------------------------------- | :--------: | :---------: | :-----------------: | ----------------------------------- | | [`sonar`](/models/sonar) | \$1.35 | \$1.35 | \$0.00675 / request | Quick cited answers, current events | | [`sonar-pro`](/models/sonar-pro) | \$4.05 | \$20.25 | \$0.00675 / request | Deep research, longer cited reports | The web-search fee is flat per request — it does not scale with tokens — so a short `sonar` question is dominated by the search fee, not the tokens. Every response's `usage.cost` already includes it. (The `GET /v1/pricing` catalog lists the per-token prices above; the flat search fee is applied per request at billing time, not as a catalog field.) Standard models have no per-request fee; use Sonar only when you actually need fresh web data. ### Image generation Image models bill per image, not per token. Cost shown is what you pay; the underlying provider price is marked up 1.35×. See the [Image Generation guide](/models/image-generation) and the [API reference](/api-reference/images-generations). | Model | Cost / image | Best for | | ------------------------------------------------------------------------- | :---------------------------------------: | ------------------------------------------------------------------------------ | | [`gpt-image-2`](/models/gpt-image-2) | $0.014 low · $0.081 medium · \$0.297 high | OpenAI flagship — text-in-image, multilingual typography | | [`imagen-4-ultra`](/models/imagen-4-ultra) | \$0.081 | Google Imagen 4 premium — print-ready hero, 4K-scale assets | | [`imagen-4`](/models/imagen-4) | \$0.054 | Google Imagen 4 standard — photoreal portraits + scenes | | [`imagen-4-fast`](/models/imagen-4-fast) | \$0.027 | Google Imagen 4 fast tier — drafts, social previews | | [`nano-banana`](/models/nano-banana) | \$0.046 | Google Gemini image-gen — **native edit mode** (image-in + prompt → image-out) | | [`nano-banana-3-flash`](/models/nano-banana-3-flash) | \$0.046 | Same as above, Gemini 3.1 preview tier | | [`flux-2-pro`](/models/image-generation#flux-2-pro) | $0.041 (1MP) · $0.101 (4MP) | Photoreal, multi-reference blend (up to 10 sources) | | [`recraft-v4-pro`](/models/image-generation#recraft-v4-pro) | \$0.338 | 4MP print-ready design | | [`recraft-v4-vector-pro`](/models/image-generation#recraft-v4-vector-pro) | \$0.405 | 4MP native SVG, print-ready signage | | [`recraft-v4-vector`](/models/image-generation#recraft-v4-vector) | \$0.108 | Native SVG output — editable paths and layers | | `ideogram-v3` | \$0.108 | Typography, logos, packaging | | `flux-1.1-ultra` | \$0.081 | Cinematic photo, hero shots, editorial (legacy — prefer flux-2-pro) | | `recraft-v4` | \$0.054 | Design-quality default — #1 HF Arena | | `recraft-v3` | \$0.054 | Legacy — prefer recraft-v4 | | `flux-kontext-pro` | \$0.054 | Image edit, inpaint (requires `image_url`) | | [`minimax-image-01`](/models/minimax-image-01) | \$0.005 | Sub-cent budget tier, bulk | A request with `n: 4` is billed as 4 images. `gpt-image-2` requests can opt into `quality: low`/`medium`/`high` per call; the hold books the right tier amount up front so high-quality requests reserve \$0.297 (no refund-and-rebill drift). Holds refund in full if generation fails. Use [Which model should I use?](/models/recommended) to pick by task rather than by price. ## What does a typical request cost? | Use case | Model | Tokens (in+out) | Cost | | ------------------------ | ------------------ | :-------------: | :--------: | | Quick extraction | `glm-4.7-flash` | \~500 | \~\$0.0001 | | Screenshot understanding | `gemma-4-31b` | \~1,000 | \~\$0.0003 | | Code review | `qwen-3-32b` | \~3,000 | \~\$0.001 | | Long document summary | `gemini-2.5-flash` | \~10,000 | \~\$0.005 | | Deep reasoning task | `deepseek-r1` | \~5,000 | \~\$0.005 | | Repo-scale agent step | `glm-5.1` | \~8,000 | \~\$0.013 | With the **\$0.50 signup credit**, you can make hundreds or thousands of requests depending on model choice. ## How billing works 1. Before each request, Kyma holds an estimate from your balance 2. After the response completes, Kyma calculates the real token cost 3. If the real cost is lower, the difference is refunded automatically You pay for actual usage, not the initial estimate. ## Credits | Action | Amount | | ----------------- | :--------------------: | | Signup bonus | +\$0.50 | | Referral reward | +\$0.50 | | Purchase packages | $5 / $20 / $100 / $500 | Credits never expire. Auto top-up is supported in the dashboard. ```bash theme={null} # Check your balance curl https://kymaapi.com/v1/credits/balance \ -H "Authorization: Bearer ky-your-api-key" # Full pricing catalog (text + image + video + audio) curl https://kymaapi.com/v1/pricing ``` ## Video generation Per-second models scale with the `duration` parameter (default 5s, max 10–15s by model). Hailuo bills flat per call. | Model | Cost | Audio | Notes | | ------------------------------------------------ | :----------: | :-----: | ---------------------------- | | [`kling-2.5-pro`](/models/kling-2.5-pro) | \$0.0945/s | — | Budget cinematic | | [`veo-3-fast`](/models/veo-3-fast) | \$0.135/s | — | Google Veo budget (720p) | | [`hailuo-02-512p`](/models/hailuo-02-512p) | \$0.140 flat | — | Cheapest video (I2V only) | | [`kling-3-pro`](/models/kling-3-pro) | \$0.1512/s | — | Premium cinematic | | [`kling-3-pro-audio`](/models/kling-3-pro-audio) | \$0.2268/s | native | Cinematic + audio | | [`seedance-2-fast`](/models/seedance-2-fast) | \$0.326565/s | bundled | Social shorts | | [`seedance-2-pro`](/models/seedance-2-pro) | \$0.40959/s | bundled | Multi-shot action | | [`hailuo-02-768p`](/models/hailuo-02-768p) | \$0.420 flat | — | Mid-tier Hailuo | | [`veo-3`](/models/veo-3) | \$0.540/s | native | Veo flagship (1080p + audio) | | [`hailuo-02-1080p`](/models/hailuo-02-1080p) | \$0.780 flat | — | Hailuo top tier | See [Video Generation](/models/video-generation). Live source: `GET /v1/pricing` (video rows). ## Audio Audio splits by capability — transcription, understanding, realtime, TTS, music, voice, SFX. **Speech-to-text (per minute, 1-min minimum billable)** | Model | Cost | Notes | | -------------------------------------------------------------------------------- | :-----------: | ------------------------------------------------------------------------------- | | [`whisper-v3-turbo`](/models/whisper-v3-turbo) | \$0.0009/min | Whisper v3 Turbo — 228× realtime. Alias `transcribe` | | [`gpt-4o-mini-transcribe-2025-12-15`](/models/gpt-4o-mini-transcribe-2025-12-15) | \$0.00405/min | OpenAI premium STT — code-switching, conversational. Alias `transcribe-quality` | **Audio understanding (per minute)** | Model | Cost | Notes | | ------------------------------------------------------ | :----------: | -------------------------------- | | [`gemini-3-flash-audio`](/models/gemini-3-flash-audio) | \$0.0006/min | Tone, music, scene understanding | **Realtime translation (per minute)** | Model | Cost | Notes | | ----------------------------------------------- | :----------: | ------------------------------------------------------- | | `gpt-realtime-translate` | \$0.034/min | OpenAI | | `gemini-2.5-flash-native-audio-preview-12-2025` | varies | Live API session | | `gemini-3.5-live-translate-preview` | \$0.0634/min | Google — speech-to-speech translation, Live API session | **TTS (per 1k characters)** | Model | Cost | Notes | | ------------------------ | :------: | ------------------------------------------------------ | | `minimax-speech-turbo` | \$0.090 | Lowest-latency voice | | `minimax-speech-hd` | \$0.140 | Production multilingual | | `eleven-flash-v2-5` | \$0.2025 | ElevenLabs fast | | `eleven-turbo-v2-5` | \$0.2025 | ElevenLabs turbo | | `eleven-multilingual-v2` | \$0.405 | ElevenLabs quality | | `eleven-v3` | \$0.405 | ElevenLabs most expressive — audio tags, 70+ languages | **Music** | Model | Cost | Notes | | ------------------------------------------------ | :----------: | --------------------- | | [`minimax-music`](/models/minimax-music) | \$0.045/song | MiniMax flat per song | | [`minimax-music-pro`](/models/minimax-music-pro) | \$0.210/song | Music-2.6 family | | `elevenlabs-music` | \$0.135/s | Pay per second | **Voice services & SFX (flat per call)** | Model | Cost | Notes | | ------------------------------------------------------ | :-----------: | ------------------------------------ | | [`minimax-voice-clone`](/models/minimax-voice-clone) | \$2.10/voice | Clone from 10s–5min reference | | [`minimax-voice-design`](/models/minimax-voice-design) | \$4.20/voice | Generate voice from text description | | `elevenlabs-sfx` | \~\$0.027/gen | Sound effect (auto duration) | Live source: `GET /v1/pricing` (audio rows). ## Prompt caching Cached input tokens are charged at **10% of the normal input price**. That means: * repeated system prompts get much cheaper * tool definitions become cheaper over repeated runs * long agent sessions benefit the most [Learn more about prompt caching →](/guides/prompt-caching) ## Rate limits Kyma uses a tier-based system similar to xAI and Anthropic-style paid access: your tier increases based on **total credits purchased**, not lifetime usage. | Tier | Min Purchase | RPM | Per-model RPM | TPM | | -------------- | :----------: | :-: | :-----------: | :--: | | 0 (Free) | \$0 | 30 | 25 | 200K | | 1 (Starter) | \$10 | 60 | 40 | 500K | | 2 (Builder) | \$50 | 120 | 80 | 2M | | 3 (Pro) | \$250 | 200 | 150 | 5M | | 4 (Enterprise) | \$1,000 | 300 | 200 | 10M | **RPM** = requests per minute **Per-model RPM** = how many requests per minute a single model can take **TPM** = tokens per minute across your account There are no daily or monthly caps. Your balance and tier are the real limits. ```bash theme={null} # Check your current limits curl https://kymaapi.com/v1/auth/limits \ -H "Authorization: Bearer ky-your-api-key" ``` ## What happens when you hit a limit? **Out of credits** ```json theme={null} { "error": { "message": "Insufficient credits. Add credits at https://kymaapi.com/dashboard.", "type": "insufficient_credits" } } ``` **Too many requests** ```json theme={null} { "error": { "message": "Rate limit exceeded (30 RPM for Tier 0). Try again in a few seconds.", "type": "rate_limit" } } ``` The `Retry-After` header tells you when to retry. ## How to spend less * Use cheaper models for extraction, routing, and repetitive automation * Use `qwen-3-32b` instead of a flagship if you mainly need fast coding help * Use `gemini-2.5-flash` only when long context is the real need * Use `deepseek-r1` only when the task truly needs deeper reasoning * Purchase credits if you need higher rate limits, not just more balance ## Next steps * [Get your API key](https://kymaapi.com) * [Quickstart guide](/quickstart) * [Which model should I use?](/models/recommended)