# Kyma API

> Kyma API is an LLM API gateway that routes one key to 106 models and publishes measured uptime per model. One endpoint, 106 models, 70 language/reasoning, 12 retrieval, 10 image, 3 video, 10 audio. OpenAI- and Anthropic-SDK compatible, multi-route redundancy with automatic failover. Pay per token for language models, per image for image generation, per second or per clip for video, and per character / minute / track / generation for audio. Cached prompt input is billed at each model's own cached-input rate, published beside its input rate. $0.50 free credit on signup, no card required — it spends on the free tier (44 of 106 models: everything billed per token (language, embedding, reranking) at or under $3/M output and $0.50/M input, plus everything billed per unit at or under $0.01 per billing unit), not on the whole catalogue.

Base URL: `https://kymaapi.com/v1`

## Docs

- [Introduction](https://docs.kymaapi.com/introduction): What Kyma API is and why it exists
- [Quickstart](https://docs.kymaapi.com/quickstart): Get an API key and make your first request in 30 seconds
- [Pricing](https://kymaapi.com/pricing): Per-model pricing, in the unit each model is sold by
- [Model Recommendations](https://docs.kymaapi.com/models/recommended): Which model to use for which task
- [Model Aliases](https://docs.kymaapi.com/guides/model-aliases): Use "best", "fast", "code", "cheap" instead of exact model IDs
- [FAQ](https://docs.kymaapi.com/faq): Common questions and answers

## SDK and Integration Guides

- [Any OpenAI Client](https://docs.kymaapi.com/guides/any-openai-client): Drop-in replacement for any OpenAI-compatible SDK or tool
- [Python](https://docs.kymaapi.com/guides/python): Full Python guide with streaming, async, error handling
- [JavaScript](https://docs.kymaapi.com/guides/javascript): Node.js and browser integration
- [Anthropic SDK](https://docs.kymaapi.com/guides/anthropic): Use Kyma with the Anthropic Messages API
- [cURL](https://docs.kymaapi.com/guides/curl): Raw HTTP examples
- [LangChain](https://docs.kymaapi.com/guides/langchain): LangChain ChatOpenAI integration
- [Vercel AI SDK](https://docs.kymaapi.com/guides/vercel-ai-sdk): Next.js and Vercel AI SDK provider

## AI Coding Agent Setup

- [Universal Agent Setup](https://docs.kymaapi.com/guides/agent-setup): One guide for all agents. Auto-config via /v1/config endpoint
- [Cline](https://kymaapi.com/for/cline): Cline (VS Code) setup with Kyma
- [Roo Code](https://kymaapi.com/for/roo-code): Roo Code setup with Kyma
- [Cursor](https://kymaapi.com/for/cursor): Cursor IDE setup with Kyma
- [Claude Code](https://kymaapi.com/for/claude-code): Claude Code setup with Kyma
- [OpenClaw](https://kymaapi.com/for/openclaw): OpenClaw setup with Kyma
- [Windsurf](https://docs.kymaapi.com/guides/windsurf): Windsurf setup with Kyma
- [Aider](https://docs.kymaapi.com/guides/aider): Aider CLI setup with Kyma
- [LangChain](https://kymaapi.com/for/langchain): LangChain ChatOpenAI setup with Kyma
- [n8n](https://kymaapi.com/for/n8n): n8n no-code automation setup with Kyma
- [Open WebUI](https://kymaapi.com/for/openwebui): Open WebUI connection setup with Kyma

## Features

- [Streaming](https://docs.kymaapi.com/guides/streaming): SSE streaming for all models
- [Prompt Caching](https://docs.kymaapi.com/guides/prompt-caching): cached input billed at each model's own cached rate
- [Tool Calling](https://docs.kymaapi.com/guides/tool-calling): Function calling across all supported models
- [Structured Outputs](https://docs.kymaapi.com/guides/structured-outputs): JSON mode and response_format
- [Authentication](https://docs.kymaapi.com/guides/authentication): API keys (ky-) and session tokens (ks-)
- [Error Handling](https://docs.kymaapi.com/guides/error-handling): Error codes, retry logic, rate limit headers

## Site Pages

- [Pricing](https://kymaapi.com/pricing): Full pricing for every model
- [Models](https://kymaapi.com/models): Browse all models with live performance data
- [Image Generation API](https://kymaapi.com/image-generation): FLUX, Ideogram, Recraft, GPT Image
- [Video Generation API](https://kymaapi.com/video-generation): Kling 3 Pro, Kling AI Avatar v2 Pro, Veo 3.1 Fast
- [Text-to-Speech API](https://kymaapi.com/text-to-speech): ElevenLabs and MiniMax voices
- [Speech-to-Text API](https://kymaapi.com/transcription): Whisper transcription
- [Compare](https://kymaapi.com/compare): Model-vs-model comparison pages, plus how Kyma compares to other gateways and direct APIs
- [Rankings](https://kymaapi.com/rankings): Top models by tokens, speed, and uptime (live)
- [Status](https://kymaapi.com/status): Live per-model availability
- [Blog](https://kymaapi.com/blog): Guides on LLM gateways, coding agents and media models
- [Glossary](https://kymaapi.com/glossary): LLM gateway, router, prompt caching, failover, tool calling defined

## Model Comparisons

Every page below carries three things and nothing else: what each model costs on Kyma today, what Kyma measured while serving it (availability, throughput, latency), and the specification its creator publishes. No borrowed benchmark scores. Any two to four model ids from the catalogue also work as a URL, sorted and joined with `-vs-`, so a combination that is not listed here is still a page.

- [grok-4.6 vs claude-fable-5](https://kymaapi.com/compare/claude-fable-5-vs-grok-4.6): frontier, side by side on price, measured uptime and published spec
- [grok-4.6 vs gpt-5.6-sol](https://kymaapi.com/compare/gpt-5.6-sol-vs-grok-4.6): frontier, side by side on price, measured uptime and published spec
- [claude-fable-5 vs gpt-5.6-sol-pro](https://kymaapi.com/compare/claude-fable-5-vs-gpt-5.6-sol-pro): frontier, side by side on price, measured uptime and published spec
- [claude-opus-5 vs gpt-5.6-sol](https://kymaapi.com/compare/claude-opus-5-vs-gpt-5.6-sol): frontier, side by side on price, measured uptime and published spec
- [grok-4.6 vs grok-4.5](https://kymaapi.com/compare/grok-4.5-vs-grok-4.6): frontier, side by side on price, measured uptime and published spec
- [claude-sonnet-5 vs gemini-3.1-pro](https://kymaapi.com/compare/claude-sonnet-5-vs-gemini-3.1-pro): mid tier, side by side on price, measured uptime and published spec
- [gpt-5.6-terra vs claude-sonnet-5](https://kymaapi.com/compare/claude-sonnet-5-vs-gpt-5.6-terra): mid tier, side by side on price, measured uptime and published spec
- [qwen-3.8-max vs qwen-3.7-max](https://kymaapi.com/compare/qwen-3.7-max-vs-qwen-3.8-max): mid tier, side by side on price, measured uptime and published spec
- [qwen-3.8-max vs deepseek-v4.1-flash](https://kymaapi.com/compare/deepseek-v4.1-flash-vs-qwen-3.8-max): mid tier, side by side on price, measured uptime and published spec
- [kimi-k3 vs deepseek-v4.1-flash](https://kymaapi.com/compare/deepseek-v4.1-flash-vs-kimi-k3): mid tier, side by side on price, measured uptime and published spec
- [deepseek-v4.1-flash vs qwen-3.6-plus](https://kymaapi.com/compare/deepseek-v4.1-flash-vs-qwen-3.6-plus): open-weight workhorses, side by side on price, measured uptime and published spec
- [kimi-k2.6 vs minimax-m2.5](https://kymaapi.com/compare/kimi-k2.6-vs-minimax-m2.5): open-weight workhorses, side by side on price, measured uptime and published spec
- [llama-3.3-70b vs gpt-oss-120b](https://kymaapi.com/compare/gpt-oss-120b-vs-llama-3.3-70b): open-weight workhorses, side by side on price, measured uptime and published spec
- [qwen-3-coder vs minimax-m2.5](https://kymaapi.com/compare/minimax-m2.5-vs-qwen-3-coder): open-weight workhorses, side by side on price, measured uptime and published spec
- [deepseek-r1 vs deepseek-v4.1-flash](https://kymaapi.com/compare/deepseek-r1-vs-deepseek-v4.1-flash): open-weight workhorses, side by side on price, measured uptime and published spec
- [qwen-3.6-plus vs kimi-k2.6](https://kymaapi.com/compare/kimi-k2.6-vs-qwen-3.6-plus): open-weight workhorses, side by side on price, measured uptime and published spec
- [glm-5.1 vs deepseek-v4.1-flash](https://kymaapi.com/compare/deepseek-v4.1-flash-vs-glm-5.1): open-weight workhorses, side by side on price, measured uptime and published spec
- [qwen-3-32b vs gpt-oss-120b](https://kymaapi.com/compare/gpt-oss-120b-vs-qwen-3-32b): open-weight workhorses, side by side on price, measured uptime and published spec
- [minimax-m2.5 vs glm-5.1](https://kymaapi.com/compare/glm-5.1-vs-minimax-m2.5): open-weight workhorses, side by side on price, measured uptime and published spec
- [kimi-k2.6 vs deepseek-v4.1-flash](https://kymaapi.com/compare/deepseek-v4.1-flash-vs-kimi-k2.6): open-weight workhorses, side by side on price, measured uptime and published spec
- [llama-3.3-70b vs qwen-3-32b](https://kymaapi.com/compare/llama-3.3-70b-vs-qwen-3-32b): open-weight workhorses, side by side on price, measured uptime and published spec
- [deepseek-v4-flash vs gemini-3-flash](https://kymaapi.com/compare/deepseek-v4-flash-vs-gemini-3-flash): cheap and fast, side by side on price, measured uptime and published spec
- [deepseek-v3 vs deepseek-v4-flash](https://kymaapi.com/compare/deepseek-v3-vs-deepseek-v4-flash): cheap and fast, side by side on price, measured uptime and published spec
- [gemini-3-flash vs qwen-3.7-plus](https://kymaapi.com/compare/gemini-3-flash-vs-qwen-3.7-plus): cheap and fast, side by side on price, measured uptime and published spec
- [qwen-3.6-plus vs deepseek-v4-flash](https://kymaapi.com/compare/deepseek-v4-flash-vs-qwen-3.6-plus): cheap and fast, side by side on price, measured uptime and published spec
- [gemini-3.7-flash vs gpt-5.6-luna](https://kymaapi.com/compare/gemini-3.7-flash-vs-gpt-5.6-luna): cheap and fast, side by side on price, measured uptime and published spec
- [gemini-3.7-flash vs deepseek-v4-flash](https://kymaapi.com/compare/deepseek-v4-flash-vs-gemini-3.7-flash): cheap and fast, side by side on price, measured uptime and published spec
- `GET /v1/compare/popular?sort=views&window=30d`: the combinations readers open most, live, ranked by total times opened. The list above is the curated set; this endpoint is the current one.

## API Reference

- [POST /v1/chat/completions](https://docs.kymaapi.com/api-reference/chat-completions): OpenAI-compatible chat completions
- [GET /v1/models](https://docs.kymaapi.com/api-reference/models-list): List all models with pricing and capabilities
- [POST /v1/images/generations](https://docs.kymaapi.com/api-reference/images-generations): Image generation (async)
- [POST /v1/videos/generations](https://docs.kymaapi.com/api-reference/videos-generations): Video generation (async)
- [POST /v1/audio/transcriptions](https://docs.kymaapi.com/api-reference/audio-transcriptions): Speech-to-text
- [POST /v1/audio/speech](https://docs.kymaapi.com/api-reference/audio-speech): Text-to-speech
- [POST /v1/auth/register](https://docs.kymaapi.com/api-reference/auth-register): Create account and get API key

## Discovery Endpoints (no auth required)

- `GET /v1/models`: Full model list with pricing, context windows, capabilities
- `GET /v1/models/recommend?usecase=coding`: Model recommendation by use case
- `GET /v1/models/recommend?agent=cline`: Agent-specific recommendation with config example
- `GET /v1/config`: Auto-configuration for agents (base_url, models, endpoints)
- `GET /v1/capabilities`: Gateway capabilities summary
- `GET /v1/credits/pricing`: Per-model pricing table
- `GET /v1/status`: Service status
- `GET /v1/models/uptime`: 7-day per-model uptime percentages

## Models

All language models use the OpenAI chat completions format. Counts and prices below are generated from the live catalog.

### Language and reasoning models (per 1M tokens)

- `claude-fable-5.1`: Claude Fable 5.1 (Anthropic), 1M context (tools, vision, reasoning). $13.50 in / $67.50 out per 1M. Anthropic's newest Mythos-class flagship — improves on Fable 5 across the board, biggest gains in agentic coding and long-running agentic workflows. 1M context, 128K output, vision, file input, adaptive thinking.
- `claude-fable-5`: Claude Fable 5 (Anthropic), 1M context (tools, vision, reasoning). $13.50 in / $67.50 out per 1M. Anthropic's Mythos-class flagship tier — above Opus in capability. 1M context, vision, file input, extended reasoning.
- `gpt-6-astra`: GPT-6 Astra (OpenAI), 1M context (tools, vision, reasoning). $13.50 in / $67.50 out per 1M, cached input $1.35 per 1M. OpenAI's GPT-6 flagship. 1.05M context, image input, reasoning; the rate doubles above 272K prompt tokens.
- `claude-opus-5`: Claude Opus 5 (Anthropic), 1M context (tools, vision, reasoning). $6.75 in / $33.75 out per 1M, cached input $0.675 per 1M. Anthropic's flagship tier. 1M context, vision, file input, prompt caching, extended reasoning.
- `claude-opus-4-7`: Claude Opus 4.7 (Anthropic), 1M context (tools, vision, reasoning). $6.75 in / $33.75 out per 1M, cached input $0.675 per 1M. Anthropic's flagship reasoning + agentic tier. 1M context, vision, prompt caching, code execution. Best for hardest tasks.
- `claude-sonnet-4-6`: Claude Sonnet 4.6 (Anthropic), 1M context (tools, vision, reasoning). $4.05 in / $20.25 out per 1M, cached input $0.405 per 1M. Anthropic's balanced tier. 1M context, vision, agentic tool use, prompt caching. The default workhorse.
- `sonar-pro`: Sonar Pro (Perplexity), 200K context (vision). $4.05 in / $20.25 out per 1M, prompt caching supported (cached rate not published). Perplexity's pro web-search model. Deeper multi-step search, 200K context, longer cited answers. Per-request search fee on top of tokens.
- `kimi-k3`: Kimi K3 (Moonshot AI), 1M context (tools, vision, reasoning). $3.768 in / $18.837 out per 1M, cached input $0.405 per 1M. Moonshot's 2.8T open-weight multimodal reasoning model. Successor to K2.7 — 1M context, vision input, built for long-horizon agentic work.
- `gpt-5.6-sol`: GPT-5.6 Sol (OpenAI), 1M context (tools, vision, reasoning). $3.151 in / $15.753 out per 1M, cached input $0.393875 per 1M. OpenAI's top 5.6 tier. 1.05M context, vision, file input; the rate doubles above 272K prompt tokens.
- `grok-4.6`: Grok 4.6 (xAI), 500K context (tools, vision, reasoning). $2.758 in / $8.274 out per 1M. xAI's flagship from August 2026, succeeded by Grok 4.7. 500K context, vision, file input, reasoning; the rate doubles above 200K prompt tokens.
- `grok-4.5`: Grok 4.5 (xAI), 500K context (tools, vision, reasoning). $2.73 in / $8.189 out per 1M. xAI's flagship from July 2026. 500K context, vision, file input, reasoning; the rate doubles above 200K prompt tokens.
- `gpt-5.6-sol-pro`: GPT-5.6 Sol Pro (OpenAI), 1M context (tools, vision, reasoning). $2.70 in / $13.50 out per 1M, cached input $0.3375 per 1M. Sol at the same list price with the Pro serving profile. 1.05M context, vision, file input; the rate doubles above 272K prompt tokens.
- `gpt-5.6-terra-pro`: GPT-5.6 Terra Pro (OpenAI), 1M context (tools, vision, reasoning). $2.70 in / $16.20 out per 1M, cached input $0.27 per 1M. Terra's Pro tier, twice Terra's list price. 1.05M context, vision, file input; the rate doubles above 272K prompt tokens.
- `claude-sonnet-5`: Claude Sonnet 5 (Anthropic), 1M context (tools, vision, reasoning). $2.70 in / $13.50 out per 1M, cached input $0.27 per 1M. Anthropic's balanced tier. 1M context, vision, file input, prompt caching, extended reasoning.
- `gpt-5.6-terra`: GPT-5.6 Terra (OpenAI), 1M context (tools, vision, reasoning). $2.70 in / $16.20 out per 1M, cached input $0.27 per 1M. OpenAI's balanced GPT-5.6 tier, between the Sol flagship and the Luna cost tier. 1M context, accepts text, images and files.
- `gemini-3.1-pro`: Gemini 3.1 Pro (Google), 1M context (tools, vision, reasoning). $2.70 in / $16.20 out per 1M, cached input $0.27 per 1M. Google's Pro reasoning tier — the step above Flash. 1M context, 64K max output, accepts text, image, audio, video and file; the rate steps up above 200K prompt tokens.
- `qwen-3.8-max`: Qwen 3.8 Max (Alibaba), 1M context (tools, vision, reasoning). $2.228 in / $6.684 out per 1M, cached input $0.2781 per 1M. Alibaba's newest flagship, GA successor to the 3.7 Max line — and the first Max with vision. 1M context, multimodal reasoning over text and images, cheaper per token than the 3.7 it replaces.
- `grok-4.7`: Grok 4.7 (xAI), 500K context (tools, vision, reasoning). $2.16 in / $6.48 out per 1M, cached input $0.54 per 1M. xAI's newest flagship for coding, agentic tasks and knowledge work, built on a larger base model than Grok 4.6. 500K context, image and file input, reasoning at low to xhigh effort; the rate doubles above 200K prompt tokens.
- `gemini-3.5-flash`: Gemini 3.5 Flash (Google), 1M context (tools, vision, reasoning). $1.928 in / $11.563 out per 1M, cached input $0.2025 per 1M. Newest Gemini Flash. 1M context, multimodal input.
- `grok-4.3`: Grok 4.3 (xAI), 1M context (tools, vision, reasoning). $1.92 in / $3.838 out per 1M, cached input $0.27 per 1M. xAI's frontier model. 1M context, strong reasoning + tool use.
- `glm-5.1`: GLM 5.1 (Zhipu AI), 203K context (tools, reasoning). $1.89 in / $5.94 out per 1M, cached input $0.27675 per 1M. #1 SWE-Bench Pro open-weight. 8-hour agentic runs.
- `qwen-3.7-max`: Qwen 3.7 Max (Alibaba), 1M context (tools, reasoning). $1.863 in / $5.586 out per 1M, cached input $0.16875 per 1M. Alibaba's newest closed-weight flagship. 1M context, top reasoning + multilingual.
- `muse-spark-1.2`: Muse Spark 1.2 (Meta), 1M context (tools, vision, reasoning). $1.773 in / $6.025 out per 1M. Meta's Muse Spark 1.2 — the model behind Muse Code, with bigger gains in coding and agentic work over 1.1. 1M context, multimodal input (text, image, video, file, audio), reasoning.
- `grok-4.20-multi-agent`: Grok 4.20 Multi-Agent (xAI), 2M context (vision, reasoning). $1.767 in / $3.534 out per 1M. Grok 4.20 run as a multi-agent ensemble, at the same list price. 2M context, vision, file input, reasoning.
- `grok-4.20`: Grok 4.20 (xAI), 2M context (tools, vision, reasoning). $1.763 in / $3.528 out per 1M. xAI's 4.20 generation. 2M context, vision, file input, reasoning; the rate doubles above 200K prompt tokens.
- `muse-spark-1.3`: Muse Spark 1.3 (Meta), 1M context (tools, vision, reasoning). $1.688 in / $5.738 out per 1M. Meta's Muse Spark 1.3, the release after 1.2 on the same line. 1M context, multimodal input (text, image, video, file, audio), reasoning, tool calling and structured outputs.
- `muse-spark-1.1`: Muse Spark 1.1 (Meta), 1M context (tools, vision, reasoning). $1.542 in / $5.243 out per 1M. Meta's Muse Spark tier. 1M context, vision, file input, reasoning — it spends ~160 tokens thinking before a one-word answer.
- `grok-build`: Grok Build (xAI), 256K context (tools, vision, reasoning). $1.389 in / $2.777 out per 1M, cached input $0.27 per 1M. xAI's coding-specialized model. Fast, tool-native, built for agentic dev.
- `claude-haiku-4-5`: Claude Haiku 4.5 (Anthropic), 200K context (tools, vision, reasoning). $1.35 in / $6.75 out per 1M, cached input $0.135 per 1M. Anthropic's fast tier. Sub-second TTFT, vision, tool use, prompt caching. 200K context.
- `sonar`: Sonar (Perplexity), 127K context (vision). $1.35 in / $1.35 out per 1M, prompt caching supported (cached rate not published). Perplexity's live web-search model. Returns current, cited answers — grounded in a real-time search of the web. Bills a small per-request search fee on top of tokens.
- `hermes-3-405b`: Hermes 3 405B (Nousresearch), 131K context (tools). $1.35 in / $1.35 out per 1M. Nous Research's fine-tune of Llama 3.1 405B, tuned for steerability rather than refusal: it follows a system prompt further than the Instruct model it is built on, which is why roleplay, persona and agent-scaffold work keep reaching for it. Reliable function calling and structured output are part of the tune, not bolted on.
- `glm-5.3`: GLM 5.3 (Zhipu AI), 1M context (tools, reasoning). $1.178 in / $3.702 out per 1M, prompt caching supported (cached rate not published). Zhipu's newest flagship — coding/agentic upgrade over GLM 5.2. ~1.3M context, open weights.
- `glm-5.2`: GLM 5.2 (Zhipu AI), 1M context (tools, reasoning). $1.101 in / $3.76 out per 1M, cached input $0.29835 per 1M. Frontier open-weight. #1 Intelligence Index among open models. 1M context, long-horizon agentic coding.
- `gemini-3.8-flash`: Gemini 3.8 Flash (Google), 1M context (tools, vision, reasoning). $1.013 in / $5.063 out per 1M, prompt caching supported (cached rate not published). Google's newest Flash tier, GA 2026-09-02 — significant gains over 3.7 Flash on software engineering and agentic tasks. 1M context, 64K output, text, image, audio, video and file input, reasoning, tool calling, structured outputs.
- `gemini-3.6-flash`: Gemini 3.6 Flash (Google), 1M context (tools, vision, reasoning). $1.013 in / $5.063 out per 1M, cached input $0.10125 per 1M. Google's July 2026 Flash tier. 1M context, accepts text, image, audio and video, and costs less per output token than 3.5 Flash.
- `gemini-3.7-flash`: Gemini 3.7 Flash (Google), 1M context (tools, vision, reasoning). $1.013 in / $5.063 out per 1M, cached input $0.050625 per 1M. Google's newest Flash tier. 1M context and 64K max output, the widest input set in the family — text, image, audio, video and file — with reasoning, tool calling and structured outputs.
- `kimi-k2.7-code`: Kimi K2.7 Code (Moonshot AI), 262K context (tools, vision, reasoning). $1.009 in / $4.774 out per 1M. Coding specialist. +21.8% Kimi Code Bench vs K2.6, ~30% fewer reasoning tokens. Always-thinking. 262K context.
- `hermes-3-70b`: Hermes 3 70B (Nousresearch), 131K context (tools). $0.945 in / $0.945 out per 1M. The 70B of the same tune, at 30% less per million. Keeps the steerability the 405B is chosen for and gives up depth on the hardest reasoning, which is the trade most persona and agent workloads are happy to make.
- `kimi-k2.6`: Kimi K2.6 (Moonshot AI), 262K context (tools, vision, reasoning). $0.7856 in / $3.667 out per 1M. Moonshot's newest. Agentic + vision + reasoning. 262K context.
- `deepseek-r1`: DeepSeek R1 (DeepSeek), 64K context (tools, reasoning). $0.7425 in / $2.957 out per 1M. Top reasoning model. 96% cheaper than o1.
- `gemini-3-flash`: Gemini 3 Flash (Google), 1M context (tools, vision, reasoning). $0.675 in / $4.05 out per 1M, cached input $0.0675 per 1M. Newest Gemini. 1M context.
- `nemotron-3-ultra-550b`: Nemotron 3 Ultra 550B (NVIDIA), 1M context (tools, reasoning). $0.675 in / $3.375 out per 1M, cached input $0.135 per 1M. NVIDIA's strongest US open-weight. 550B MoE (55B active), hybrid Mamba-Transformer. 1M context, 300+ tok/s.
- `deepseek-v3`: DeepSeek V3 (DeepSeek), 160K context (tools, reasoning). $0.518 in / $0.7571 out per 1M. Previous-gen flagship. Stable, proven.
- `qwen-3.6-plus`: Qwen 3.6 Plus (Alibaba), 1M context (tools, vision, reasoning). $0.454 in / $2.724 out per 1M, prompt caching supported (cached rate not published). Alibaba's newest flagship. #1 on Kyma.
- `qwen-3.7-plus`: Qwen 3.7 Plus (Alibaba), 1M context (tools, vision, reasoning). $0.4431 in / $1.773 out per 1M, cached input $0.0864 per 1M. Alibaba's newest Plus flagship. 1M context, vision input, top agentic + reasoning.
- `muse-glimmer-30b`: Muse Glimmer 30B (Meta), 131K context (tools, vision, reasoning). $0.405 in / $1.62 out per 1M. Meta's open-weight (Apache 2.0) 30B dense multimodal model, distilled from Muse Spark and tuned for local agentic work. Vision + reasoning, single-GPU friendly.
- `gemini-3.5-flash-lite`: Gemini 3.5 Flash Lite (Google), 1M context (tools, vision, reasoning). $0.405 in / $3.375 out per 1M, cached input $0.0405 per 1M. Google's cheapest 1M-context tier. Takes text, image, audio and video; output price includes thinking tokens.
- `minimax-m2.5`: MiniMax M2.5 (MiniMax), 197K context (tools, reasoning). $0.405 in / $1.62 out per 1M, prompt caching supported (cached rate not published). SWE-bench 80.2%. Top agentic coding.
- `minimax-m3`: MiniMax M3 (MiniMax), 1M context (tools, vision, reasoning). $0.405 in / $1.62 out per 1M, cached input $0.0756 per 1M. MSA sparse attention. SWE-Bench Pro 59%, Terminal-Bench 66%. Agentic coding, 1M context, multimodal input.
- `minimax-m2.7`: MiniMax M2.7 (MiniMax), 205K context (tools, reasoning). $0.405 in / $1.62 out per 1M. Next-gen agentic productivity.
- `qwen-3-coder`: Qwen 3 Coder (Alibaba), 131K context (tools). $0.3586 in / $1.629 out per 1M, cached input $0.135 per 1M. Purpose-built for code generation.
- `qwen3.8-27b`: Qwen 3.8 27B (Alibaba), 1M context (tools, vision, reasoning). $0.3576 in / $2.554 out per 1M. Alibaba's open-weight (Apache-2.0) dense 27B vision-language model from the Qwen 3.8 line. 1M context, text, image and video input, reasoning, tool calling and structured outputs — the open checkpoint next to the closed Qwen 3.8 Max and Flash.
- `gpt-5.6-luna`: GPT-5.6 Luna (OpenAI), 1M context (tools, vision, reasoning). $0.3127 in / $1.877 out per 1M, cached input $0.027 per 1M. OpenAI's cheapest 5.6 tier. 1.05M context, vision, file input; the rate doubles above 272K prompt tokens.
- `llama-4-maverick`: Llama 4 Maverick (Meta), 1M context (tools, vision). $0.27 in / $1.08 out per 1M. Meta's larger Llama 4 tier, above Scout. 1M context, vision, served from two independent providers.
- `step-3.7-flash`: Step 3.7 Flash (StepFun), 256K context (tools, vision, reasoning). $0.27 in / $1.552 out per 1M, cached input $0.054 per 1M. StepFun's fast flash tier. 256K context, multimodal input, tool calling. Cheap throughput.
- `deepseek-v4-flash-vision-exp`: DeepSeek V4 Flash Vision (DeepSeek), 1M context (tools, vision, reasoning). $0.2514 in / $0.7542 out per 1M. Experimental vision-enabled release of DeepSeek V4 Flash (open weights, MIT, 305B MoE) — the same efficiency tier with image input. DeepSeek labels it experimental; expect the id to move when a stable release lands.
- `qwen3.8-flash`: Qwen 3.8 Flash (Alibaba), 1M context (tools, vision, reasoning). $0.2045 in / $0.641 out per 1M, prompt caching supported (cached rate not published). Alibaba's newest Flash tier — ultra cost-efficient multimodal MoE. 1M context, vision, cheaper per token than the Max line.
- `glm-4.5-air`: GLM 4.5 Air (Zhipu AI), 131K context (tools, reasoning). $0.1945 in / $1.272 out per 1M, cached input $0.03375 per 1M. Cheap agentic MoE (106B/12B active).
- `mimo-v2.5`: MiMo V2.5 (Xiaomi), 1M context (tools, vision, reasoning). $0.1859 in / $0.3718 out per 1M. Xiaomi's open-weight (MIT) flagship — multimodal, 1M context, reasoning. Strong agentic and coding work at low cost.
- `glm-5.3-flash`: GLM 5.3 Flash (Zhipu AI), 1M context (tools, vision, reasoning). $0.1791 in / $0.5972 out per 1M, prompt caching supported (cached rate not published). Zhipu's newest Flash — MIT-licensed, multimodal, latency/cost-optimized successor to GLM 4.7 Flash. ~1.3M context, vision.
- `gpt-5.6-luna-pro`: GPT-5.6 Luna Pro (OpenAI), 1M context (tools, vision, reasoning). $0.1548 in / $0.9288 out per 1M, cached input $0.027 per 1M. Luna at the same list price with the Pro serving profile. 1.05M context, vision, file input; the rate doubles above 272K prompt tokens.
- `llama-3.3-70b`: Llama 3.3 70B (Meta), 128K context (tools). $0.135 in / $0.432 out per 1M, prompt caching supported (cached rate not published). Most popular open model. Great all-rounder.
- `deepseek-v4-flash`: DeepSeek V4 Flash (DeepSeek), 1M context (tools, reasoning). $0.1264 in / $0.2526 out per 1M, cached input $0.0243 per 1M. 284B MoE. 1M context. Fast + cheap V4 tier.
- `hy3`: Hunyuan 3 (Tencent), 262K context (tools, reasoning). $0.108 in / $0.4455 out per 1M. Tencent's Hunyuan 3 flagship. 256K context, reasoning, tool use.
- `qwen-3-32b`: Qwen 3 32B (Alibaba), 33K context (tools, reasoning). $0.108 in / $0.378 out per 1M, prompt caching supported (cached rate not published). Coding-focused 32B. Strong on code, math and multilingual.
- `deepseek-v4.1-flash`: DeepSeek V4.1 Flash (DeepSeek), 1M context (tools, vision, reasoning). $0.1048 in / $0.3141 out per 1M. DeepSeek's successor to both V4 Flash and V4 Pro: 1M context, native image input, thinking and non-thinking modes. The lab routes V4 Pro onto it from 2026-09-14.
- `glm-4.7-flash`: GLM 4.7 Flash (Zhipu AI), 203K context (tools, reasoning). $0.081 in / $0.54 out per 1M, cached input $0.0135 per 1M. Ultra cheap. 200K context. Fast.
- `gemma-4-31b`: Gemma 4 31B (Google), 128K context (tools, vision, reasoning). $0.0763 in / $0.218 out per 1M, cached input $0.135 per 1M. Google's newest open model. Multimodal.
- `qwen3.7-flash`: Qwen 3.7 Flash (Alibaba), 1M context (tools, vision, reasoning). $0.0504 in / $0.2187 out per 1M, cached input $0.0081 per 1M. Alibaba's vision-language reasoning model. 1M context, takes text, image and video, and is the cheapest model in the catalogue by a wide margin.
- `gpt-oss-120b`: GPT-OSS 120B (OpenAI), 128K context (tools, reasoning). $0.0494 in / $0.2406 out per 1M, prompt caching supported (cached rate not published). OpenAI's open source. 120B parameters.

### Retrieval models (per 1M tokens)

Embeddings and reranking. These do NOT use chat completions — see the endpoint
on each model's page.

- `embeddinggemma-300m`: EmbeddingGemma 300M (Google), 2K context. $0.0027 in / $0.00 out per 1M. 768-dimension embeddings from a 300M-parameter model. Built for on-device and high-volume indexing — the cheapest way to embed a large corpus, at a fraction of the usual per-million rate.
- `bge-base-en`: BGE Base EN v1.5 (Baai), 1K context. $0.00675 in / $0.00 out per 1M. 768-dimension English embeddings — half the vector of bge-large-en at the same per-million rate, so an index built on it is half the storage and half the comparison cost. Retrieval quality gives up little on short chunks, which is what the 512-token window enforces anyway.
- `all-minilm-l12`: all-MiniLM-L12-v2 (Sentence-transformers), 1K context. $0.00675 in / $0.00 out per 1M. 384-dimension embeddings — the smallest vector on the shelf, and the default of the sentence-transformers library, so an enormous amount of existing code expects exactly this shape. Twelve layers where the L6 has six: better recall, still tiny.
- `all-minilm-l6`: all-MiniLM-L6-v2 (Sentence-transformers), 1K context. $0.00675 in / $0.00 out per 1M. 384 dimensions from six layers — the most downloaded embedding model there is, and the one most tutorials and starter repos hard-code. Reach for it to match an existing index or to keep a local prototype and a hosted one on the same vectors.
- `gte-base`: GTE Base (Alibaba), 1K context. $0.00675 in / $0.00 out per 1M. 768-dimension general text embeddings from Alibaba's Tongyi lab, trained on a broader mixture than BGE and often a point or two ahead of it on out-of-domain retrieval. Same size and same price as bge-base-en, so the choice is which one your corpus likes.
- `qwen3-embedding-8b`: Qwen3 Embedding 8B (Alibaba), 33K context. $0.0135 in / $0.00 out per 1M. 4096-dimension embeddings with a 32K input window and strong multilingual retrieval. Use when recall quality matters more than the per-million rate, or when documents are long enough that a 2K window would have to chunk them.
- `bge-m3`: BGE-M3 (Baai), 8K context. $0.0135 in / $0.00 out per 1M. 1024-dimension embeddings across 100+ languages, built for retrieval that has to work in more than English. The 8K window takes a whole page without chunking. Reach for it when the corpus is multilingual and the per-million rate matters.
- `qwen3-embedding-0.6b`: Qwen3 Embedding 0.6B (Alibaba), 33K context. $0.0135 in / $0.00 out per 1M. 1024-dimension embeddings from the smallest of the Qwen3 retrieval line, at the same rate as its larger siblings. The 32K window is the reason to reach for it: long documents embed whole while the vector stays small enough to index cheaply.
- `bge-large-en`: BGE Large EN v1.5 (Baai), 1K context. $0.0135 in / $0.00 out per 1M. 1024-dimension English embeddings, and still one of the most widely benchmarked retrieval models in production. The 512-token window forces chunking, which is why the newer entries above exist — but an index already built on it stays comparable.
- `multilingual-e5-large`: Multilingual E5 Large (Microsoft), 1K context. $0.0135 in / $0.00 out per 1M. 1024-dimension embeddings trained on 94 languages, and the most-cited multilingual retrieval baseline outside BGE. Pick it against bge-m3 when the corpus is short-chunk and the comparison is cross-language recall rather than window size.
- `qwen3-embedding-4b`: Qwen3 Embedding 4B (Alibaba), 33K context. $0.027 in / $0.00 out per 1M. 2560-dimension embeddings — the middle of the Qwen3 retrieval line by recall, not by price. The 8B is both better and cheaper; this SKU costs twice as much per million tokens. Reach for the 4B only when the index is already fixed at 2560 dimensions.
- `qwen3-reranker-8b`: Qwen3 Reranker 8B (Alibaba), 41K context. $0.135 in / $0.00 out per 1M. Scores how well each document answers a query, so a retriever's top 50 can be cut to the 5 worth sending to a model. Sits between search and synthesis: embeddings decide what to fetch, this decides what survives. A 40K window means whole documents can be judged without chunking.

### Decision models (per 1M input tokens, output free)

Send a state and your choice questions to `POST /v1/decisions`; each question
comes back with one of your options and a confidence. These do NOT use chat
completions.

- `jev`: Jev 1.13 (TypeSafe), 32K context. $0.0567 in / $0.00 out per 1M. Answers choice questions about a state with one option and a confidence. No prose, no images — a classifier you can put in front of a model, a tool call or a risky command. Billed per input token, rounded up to the nearest $0.0001.

### Image generation

- `minimax-image-01`: MiniMax Image 01 (MiniMax). $0.005 / image. Sub-cent image generation. Cheapest tier on Kyma — $0.005 per image flat regardless of resolution. 5 aspect ratios (1:1, 16:9, 9:16, 4:3, 3:4). Best for high-volume / budget workflows.
- `gpt-image-2.5-flare`: GPT Image 2.5 Flare (OpenAI). $0.019 / image. OpenAI's GPT Image 2.5 (Sep 2026), Flare variant for fast everyday generation. Strong identity hold across reference images, exact text-in-image, photoreal portraits. Quality tiers low/medium/high — default medium; each reference image adds a small per-request charge. 1024×1024 / 1024×1536 / 1536×1024.
- `flux-2-pro`: FLUX.2 Pro (Black Forest Labs). $0.0405 / image. BFL's 32B flagship (3× larger than Flux 1.1). Photoreal, multi-reference (up to 10 sources), unified gen+edit, ~60% accurate text-in-image. $0.03/MP base + $0.015 per extra MP.
- `flux-kontext-pro`: FLUX.1 Kontext Pro (Black Forest Labs). $0.054 / image. Image-to-image edit and refinement. Mask + inpaint.
- `recraft-v4`: Recraft V4 (Recraft). $0.054 / image. Top of HF Arena (#1, beats Midjourney V8 / DALL-E 3 / FLUX). Design-aware composition, lighting, textures.
- `nano-banana-3-flash`: Nano Banana 3 Flash (Google). $0.061 / image. Google's Gemini 3.1 image-gen. Native edit-mode (image-in + prompt → image-out) in 3 size tiers (512/1K/2K), with sharper output than the Gemini 2.5 image generation it replaces.
- `gpt-image-2`: GPT Image 2 (OpenAI). $0.072 / image. OpenAI's flagship image model (Apr 2026). Near-perfect text-in-image (multilingual), reasoning-augmented composition, photorealism, logo-grade lettering. Quality tiers low/medium/high — picker default medium. 1024×1024 / 1024×1536 / 1536×1024 / 2048×2048.
- `ideogram-v3`: Ideogram V3 (Ideogram). $0.081 / image. Text-in-image specialist. Best for typography, packaging, logos.
- `recraft-v4-vector`: Recraft V4 Vector (Recraft). $0.108 / image. Native SVG output — actual paths + structured layers, edit in Figma/Illustrator. Only model on the market that ships true vector files.
- `recraft-v4-pro`: Recraft V4 Pro (Recraft). $0.3375 / image. Recraft V4 at 4MP for print-ready / large-scale assets. Same design taste as V4, higher resolution.

### Video generation

- `kling-3-pro`: Kling 3 Pro (Kuaishou). $0.1512 / second. Flagship Kling. Photoreal humans, smooth motion, sharper than 2.5. 3-15s, no audio. Text-to-video, or image-to-video with image_url as the first frame.
- `kling-avatar-v2-pro`: Kling AI Avatar v2 Pro (Kuaishou). $0.15525 / second. Talking or singing avatar video from one portrait and one audio track. The face lip-syncs to your speech or song, your audio plays through unchanged, and the clip runs as long as the audio (5 to 60 s). Send image_url, audio_url (PCM WAV only for now) and duration_s (your audio's length); billed per second of the finished clip.
- `veo-3.1-fast`: Veo 3.1 Fast (Google). $0.135 / second. Google Veo 3.1 Fast — 720p video with native audio (dialogue, ambient, lip-sync), including spoken Vietnamese. 4, 6 or 8s. T2V or I2V via image_url.

### Audio: speech, transcription, music, sound

- `whisper-v3-turbo`: Whisper Large v3 Turbo (OpenAI). $0.0009 / minute. Speech-to-text. 228x realtime inference. Transcripts with timestamps + language detect.
- `gpt-4o-mini-transcribe-2025-12-15`: GPT-4o mini Transcribe (OpenAI). $0.00405 / minute. Speech-to-text. OpenAI's premium quality STT — best real-world accuracy on conversational audio, noisy backgrounds, and code-switching (Vi/En etc). RETIRING 2027-02-26 — OpenAI shuts down the gpt-4o-transcribe family; migrate to gpt-transcribe. Returns a plain transcript: no per-segment timestamps, so use json or text (not verbose_json/srt/vtt).
- `gpt-transcribe`: GPT Transcribe (OpenAI). $0.006075 / minute. Speech-to-text. OpenAI's current premium STT and the replacement for the gpt-4o-transcribe family — high real-world accuracy on conversational audio, noisy backgrounds, and code-switching (Vi/En etc). Returns a plain transcript: no per-segment timestamps, so use json or text (not verbose_json/srt/vtt).
- `gemini-3.5-transcribe`: Gemini 3.5 Transcribe (Google). $0.00675 / minute. Speech-to-text. Google's dedicated file transcription model — 85+ languages, up to 1 hour per request. OpenAI-compatible /v1/audio/transcriptions. Returns a plain transcript: no per-segment timestamps, so use json or text (not verbose_json/srt/vtt).
- `eleven-multilingual-v2`: ElevenLabs Multilingual v2 (ElevenLabs). $0.405 / 1K characters. Hero-quality multilingual TTS. 29 languages, expressive voices, brand-safe consistent delivery.
- `eleven-flash-v2-5`: ElevenLabs Flash v2.5 (ElevenLabs). $0.2025 / 1K characters. Ultra-low-latency TTS, ~75ms time-to-first-byte. Half the per-char cost of Multilingual v2. 32 languages.
- `eleven-turbo-v2-5`: ElevenLabs Turbo v2.5 (ElevenLabs). $0.2025 / 1K characters. Balanced TTS — quicker than Multilingual, better quality than Flash. Half cost vs Multilingual. 32 languages.
- `minimax-speech-hd`: MiniMax Speech HD (MiniMax). $0.07 / 1K characters. MiniMax HD voice. Multilingual, expressive, ~2.9× cheaper than ElevenLabs Multilingual v2 at the same production quality tier.
- `minimax-speech-turbo`: MiniMax Speech Turbo (MiniMax). $0.04 / 1K characters. MiniMax low-latency voice. Multilingual, ~2.2× cheaper than ElevenLabs Flash v2.5. Best for bulk TTS, real-time voice agents, conversational AI.
- `lyria-3.5`: Lyria 3.5 (Google). $0.108 / track. Google's music model: a full song with vocals from a text prompt, optional lyrics in any language (sings Vietnamese). MP3, up to a couple of minutes; length and structure are steered by the prompt. Flat price per song. Output carries Google's SynthID watermark.

## Model Aliases

Send these as the model name and Kyma resolves to the best current model:

- `best` → `qwen-3.6-plus`
- `fast` → `gemini-3.5-flash-lite`
- `code` → `qwen-3-coder`
- `cheap` → `deepseek-v4-flash`
- `long-context` → `gemini-3-flash`
- `vision` → `gemma-4-31b`
- `reasoning` → `deepseek-r1`
- `agent` → `kimi-k2.6`
- `best-agent` → `kimi-k2.6`
- `balanced` → `llama-3.3-70b`
- `glm-flagship` → `glm-5.2`
- `search` → `sonar`
- `transcribe` → `whisper-v3-turbo`
- `transcribe-quality` → `gpt-4o-mini-transcribe-2025-12-15`
- `kimi-k2.5` → `kimi-k2.6`
- `deepseek-v4-pro` → `deepseek-v4.1-flash`

## Full Model Catalog

Every active model with full specs. Format: id | name | creator | category | context | pricing | capabilities.

- `deepseek-v4-flash-vision-exp` | DeepSeek V4 Flash Vision | DeepSeek | out:text | 1M ctx | $0.2514 in / $0.7542 out per 1M | tools/vision/reasoning
- `qwen3.8-27b` | Qwen 3.8 27B | Alibaba | out:text | 1M ctx | $0.3576 in / $2.554 out per 1M | tools/vision/reasoning
- `gemini-3.8-flash` | Gemini 3.8 Flash | Google | out:text | 1M ctx | $1.013 in / $5.063 out per 1M, prompt caching supported (cached rate not published) | tools/vision/reasoning/prompt-caching
- `claude-fable-5.1` | Claude Fable 5.1 | Anthropic | out:text | 1M ctx | $13.50 in / $67.50 out per 1M | tools/vision/reasoning
- `claude-fable-5` | Claude Fable 5 | Anthropic | out:text | 1M ctx | $13.50 in / $67.50 out per 1M | tools/vision/reasoning
- `grok-4.7` | Grok 4.7 | xAI | out:text | 500K ctx | $2.16 in / $6.48 out per 1M, cached input $0.54 per 1M | tools/vision/reasoning/prompt-caching
- `grok-4.6` | Grok 4.6 | xAI | out:text | 500K ctx | $2.758 in / $8.274 out per 1M | tools/vision/reasoning
- `llama-4-maverick` | Llama 4 Maverick | Meta | out:text | 1M ctx | $0.27 in / $1.08 out per 1M | tools/vision
- `muse-spark-1.1` | Muse Spark 1.1 | Meta | out:text | 1M ctx | $1.542 in / $5.243 out per 1M | tools/vision/reasoning
- `muse-spark-1.2` | Muse Spark 1.2 | Meta | out:text | 1M ctx | $1.773 in / $6.025 out per 1M | tools/vision/reasoning
- `muse-spark-1.3` | Muse Spark 1.3 | Meta | out:text | 1M ctx | $1.688 in / $5.738 out per 1M | tools/vision/reasoning
- `muse-glimmer-30b` | Muse Glimmer 30B | Meta | out:text | 131K ctx | $0.405 in / $1.62 out per 1M | tools/vision/reasoning
- `mimo-v2.5` | MiMo V2.5 | Xiaomi | out:text | 1M ctx | $0.1859 in / $0.3718 out per 1M | tools/vision/reasoning
- `hy3` | Hunyuan 3 | Tencent | out:text | 262K ctx | $0.108 in / $0.4455 out per 1M | tools/reasoning
- `grok-4.20-multi-agent` | Grok 4.20 Multi-Agent | xAI | out:text | 2M ctx | $1.767 in / $3.534 out per 1M | vision/reasoning
- `grok-4.20` | Grok 4.20 | xAI | out:text | 2M ctx | $1.763 in / $3.528 out per 1M | tools/vision/reasoning
- `grok-4.5` | Grok 4.5 | xAI | out:text | 500K ctx | $2.73 in / $8.189 out per 1M | tools/vision/reasoning
- `gpt-5.6-sol-pro` | GPT-5.6 Sol Pro | OpenAI | out:text | 1M ctx | $2.70 in / $13.50 out per 1M, cached input $0.3375 per 1M | tools/vision/reasoning/prompt-caching
- `gpt-5.6-sol` | GPT-5.6 Sol | OpenAI | out:text | 1M ctx | $3.151 in / $15.753 out per 1M, cached input $0.393875 per 1M | tools/vision/reasoning/prompt-caching
- `gpt-6-astra` | GPT-6 Astra | OpenAI | out:text | 1M ctx | $13.50 in / $67.50 out per 1M, cached input $1.35 per 1M | tools/vision/reasoning/prompt-caching
- `gpt-5.6-terra-pro` | GPT-5.6 Terra Pro | OpenAI | out:text | 1M ctx | $2.70 in / $16.20 out per 1M, cached input $0.27 per 1M | tools/vision/reasoning/prompt-caching
- `gpt-5.6-luna-pro` | GPT-5.6 Luna Pro | OpenAI | out:text | 1M ctx | $0.1548 in / $0.9288 out per 1M, cached input $0.027 per 1M | tools/vision/reasoning/prompt-caching
- `gpt-5.6-luna` | GPT-5.6 Luna | OpenAI | out:text | 1M ctx | $0.3127 in / $1.877 out per 1M, cached input $0.027 per 1M | tools/vision/reasoning/prompt-caching
- `claude-sonnet-5` | Claude Sonnet 5 | Anthropic | out:text | 1M ctx | $2.70 in / $13.50 out per 1M, cached input $0.27 per 1M | tools/vision/reasoning/prompt-caching
- `claude-opus-5` | Claude Opus 5 | Anthropic | out:text | 1M ctx | $6.75 in / $33.75 out per 1M, cached input $0.675 per 1M | tools/vision/reasoning/prompt-caching
- `gpt-5.6-terra` | GPT-5.6 Terra | OpenAI | out:text | 1M ctx | $2.70 in / $16.20 out per 1M, cached input $0.27 per 1M | tools/vision/reasoning/prompt-caching
- `qwen3.7-flash` | Qwen 3.7 Flash | Alibaba | out:text | 1M ctx | $0.0504 in / $0.2187 out per 1M, cached input $0.0081 per 1M | tools/vision/reasoning/prompt-caching
- `gemini-3.5-flash-lite` | Gemini 3.5 Flash Lite | Google | out:text | 1M ctx | $0.405 in / $3.375 out per 1M, cached input $0.0405 per 1M | tools/vision/reasoning/prompt-caching
- `gemini-3.1-pro` | Gemini 3.1 Pro | Google | out:text | 1M ctx | $2.70 in / $16.20 out per 1M, cached input $0.27 per 1M | tools/vision/reasoning/prompt-caching
- `gemini-3.6-flash` | Gemini 3.6 Flash | Google | out:text | 1M ctx | $1.013 in / $5.063 out per 1M, cached input $0.10125 per 1M | tools/vision/reasoning/prompt-caching
- `gemini-3.7-flash` | Gemini 3.7 Flash | Google | out:text | 1M ctx | $1.013 in / $5.063 out per 1M, cached input $0.050625 per 1M | tools/vision/reasoning/prompt-caching
- `kimi-k3` | Kimi K3 | Moonshot AI | out:text | 1M ctx | $3.768 in / $18.837 out per 1M, cached input $0.405 per 1M | tools/vision/reasoning/prompt-caching
- `qwen-3.8-max` | Qwen 3.8 Max | Alibaba | out:text | 1M ctx | $2.228 in / $6.684 out per 1M, cached input $0.2781 per 1M | tools/vision/reasoning/prompt-caching
- `qwen3.8-flash` | Qwen 3.8 Flash | Alibaba | out:text | 1M ctx | $0.2045 in / $0.641 out per 1M, prompt caching supported (cached rate not published) | tools/vision/reasoning/prompt-caching
- `qwen-3.7-max` | Qwen 3.7 Max | Alibaba | out:text | 1M ctx | $1.863 in / $5.586 out per 1M, cached input $0.16875 per 1M | tools/reasoning/prompt-caching
- `qwen-3.6-plus` | Qwen 3.6 Plus | Alibaba | out:text | 1M ctx | $0.454 in / $2.724 out per 1M, prompt caching supported (cached rate not published) | tools/vision/reasoning/prompt-caching
- `qwen-3.7-plus` | Qwen 3.7 Plus | Alibaba | out:text | 1M ctx | $0.4431 in / $1.773 out per 1M, cached input $0.0864 per 1M | tools/vision/reasoning/prompt-caching
- `qwen-3-coder` | Qwen 3 Coder | Alibaba | out:text | 131K ctx | $0.3586 in / $1.629 out per 1M, cached input $0.135 per 1M | tools/prompt-caching
- `qwen-3-32b` | Qwen 3 32B | Alibaba | out:text | 33K ctx | $0.108 in / $0.378 out per 1M, prompt caching supported (cached rate not published) | tools/reasoning/prompt-caching
- `gemma-4-31b` | Gemma 4 31B | Google | out:text | 128K ctx | $0.0763 in / $0.218 out per 1M, cached input $0.135 per 1M | tools/vision/reasoning/prompt-caching
- `minimax-m2.5` | MiniMax M2.5 | MiniMax | out:text | 197K ctx | $0.405 in / $1.62 out per 1M, prompt caching supported (cached rate not published) | tools/reasoning/prompt-caching
- `minimax-m3` | MiniMax M3 | MiniMax | out:text | 1M ctx | $0.405 in / $1.62 out per 1M, cached input $0.0756 per 1M | tools/vision/reasoning/prompt-caching
- `deepseek-v4-flash` | DeepSeek V4 Flash | DeepSeek | out:text | 1M ctx | $0.1264 in / $0.2526 out per 1M, cached input $0.0243 per 1M | tools/reasoning/prompt-caching
- `deepseek-v4.1-flash` | DeepSeek V4.1 Flash | DeepSeek | out:text | 1M ctx | $0.1048 in / $0.3141 out per 1M | tools/vision/reasoning
- `deepseek-v3` | DeepSeek V3 | DeepSeek | out:text | 160K ctx | $0.518 in / $0.7571 out per 1M | tools/reasoning
- `deepseek-r1` | DeepSeek R1 | DeepSeek | out:text | 64K ctx | $0.7425 in / $2.957 out per 1M | tools/reasoning
- `gemini-3.5-flash` | Gemini 3.5 Flash | Google | out:text | 1M ctx | $1.928 in / $11.563 out per 1M, cached input $0.2025 per 1M | tools/vision/reasoning/prompt-caching
- `gemini-3-flash` | Gemini 3 Flash | Google | out:text | 1M ctx | $0.675 in / $4.05 out per 1M, cached input $0.0675 per 1M | tools/vision/reasoning/prompt-caching
- `llama-3.3-70b` | Llama 3.3 70B | Meta | out:text | 128K ctx | $0.135 in / $0.432 out per 1M, prompt caching supported (cached rate not published) | tools/prompt-caching
- `gpt-oss-120b` | GPT-OSS 120B | OpenAI | out:text | 128K ctx | $0.0494 in / $0.2406 out per 1M, prompt caching supported (cached rate not published) | tools/reasoning/prompt-caching
- `nemotron-3-ultra-550b` | Nemotron 3 Ultra 550B | NVIDIA | out:text | 1M ctx | $0.675 in / $3.375 out per 1M, cached input $0.135 per 1M | tools/reasoning/prompt-caching
- `step-3.7-flash` | Step 3.7 Flash | StepFun | out:text | 256K ctx | $0.27 in / $1.552 out per 1M, cached input $0.054 per 1M | tools/vision/reasoning/prompt-caching
- `kimi-k2.7-code` | Kimi K2.7 Code | Moonshot AI | out:text | 262K ctx | $1.009 in / $4.774 out per 1M | tools/vision/reasoning
- `kimi-k2.6` | Kimi K2.6 | Moonshot AI | out:text | 262K ctx | $0.7856 in / $3.667 out per 1M | tools/vision/reasoning
- `claude-opus-4-7` | Claude Opus 4.7 | Anthropic | out:text | 1M ctx | $6.75 in / $33.75 out per 1M, cached input $0.675 per 1M | tools/vision/reasoning/prompt-caching
- `claude-sonnet-4-6` | Claude Sonnet 4.6 | Anthropic | out:text | 1M ctx | $4.05 in / $20.25 out per 1M, cached input $0.405 per 1M | tools/vision/reasoning/prompt-caching
- `claude-haiku-4-5` | Claude Haiku 4.5 | Anthropic | out:text | 200K ctx | $1.35 in / $6.75 out per 1M, cached input $0.135 per 1M | tools/vision/reasoning/prompt-caching
- `minimax-m2.7` | MiniMax M2.7 | MiniMax | out:text | 205K ctx | $0.405 in / $1.62 out per 1M | tools/reasoning
- `glm-5.2` | GLM 5.2 | Zhipu AI | out:text | 1M ctx | $1.101 in / $3.76 out per 1M, cached input $0.29835 per 1M | tools/reasoning/prompt-caching
- `glm-5.3` | GLM 5.3 | Zhipu AI | out:text | 1M ctx | $1.178 in / $3.702 out per 1M, prompt caching supported (cached rate not published) | tools/reasoning/prompt-caching
- `glm-5.1` | GLM 5.1 | Zhipu AI | out:text | 203K ctx | $1.89 in / $5.94 out per 1M, cached input $0.27675 per 1M | tools/reasoning/prompt-caching
- `glm-4.5-air` | GLM 4.5 Air | Zhipu AI | out:text | 131K ctx | $0.1945 in / $1.272 out per 1M, cached input $0.03375 per 1M | tools/reasoning/prompt-caching
- `glm-4.7-flash` | GLM 4.7 Flash | Zhipu AI | out:text | 203K ctx | $0.081 in / $0.54 out per 1M, cached input $0.0135 per 1M | tools/reasoning/prompt-caching
- `glm-5.3-flash` | GLM 5.3 Flash | Zhipu AI | out:text | 1M ctx | $0.1791 in / $0.5972 out per 1M, prompt caching supported (cached rate not published) | tools/vision/reasoning/prompt-caching
- `grok-4.3` | Grok 4.3 | xAI | out:text | 1M ctx | $1.92 in / $3.838 out per 1M, cached input $0.27 per 1M | tools/vision/reasoning/prompt-caching
- `grok-build` | Grok Build | xAI | out:text | 256K ctx | $1.389 in / $2.777 out per 1M, cached input $0.27 per 1M | tools/vision/reasoning/prompt-caching
- `sonar` | Sonar | Perplexity | out:text | 127K ctx | $1.35 in / $1.35 out per 1M, prompt caching supported (cached rate not published) | vision/prompt-caching
- `sonar-pro` | Sonar Pro | Perplexity | out:text | 200K ctx | $4.05 in / $20.25 out per 1M, prompt caching supported (cached rate not published) | vision/prompt-caching
- `flux-2-pro` | FLUX.2 Pro | Black Forest Labs | out:image | - ctx | $0.0405 / image | vision
- `flux-kontext-pro` | FLUX.1 Kontext Pro | Black Forest Labs | out:image | - ctx | $0.054 / image | vision
- `ideogram-v3` | Ideogram V3 | Ideogram | out:image | - ctx | $0.081 / image | -
- `recraft-v4` | Recraft V4 | Recraft | out:image | - ctx | $0.054 / image | -
- `recraft-v4-pro` | Recraft V4 Pro | Recraft | out:image | - ctx | $0.3375 / image | -
- `recraft-v4-vector` | Recraft V4 Vector | Recraft | out:image | - ctx | $0.108 / image | -
- `kling-3-pro` | Kling 3 Pro | Kuaishou | out:video | - ctx | $0.1512 / second | -
- `kling-avatar-v2-pro` | Kling AI Avatar v2 Pro | Kuaishou | out:video+audio | - ctx | $0.15525 / second | -
- `nano-banana-3-flash` | Nano Banana 3 Flash | Google | out:image | - ctx | $0.061 / image | vision
- `veo-3.1-fast` | Veo 3.1 Fast | Google | out:video+audio | - ctx | $0.135 / second | -
- `jev` | Jev 1.13 | TypeSafe | out:text | 32K ctx | $0.0567 in / $0.00 out per 1M | -
- `embeddinggemma-300m` | EmbeddingGemma 300M | Google | out:text | 2K ctx | $0.0027 in / $0.00 out per 1M | -
- `qwen3-embedding-8b` | Qwen3 Embedding 8B | Alibaba | out:text | 33K ctx | $0.0135 in / $0.00 out per 1M | -
- `bge-m3` | BGE-M3 | Baai | out:text | 8K ctx | $0.0135 in / $0.00 out per 1M | -
- `qwen3-embedding-0.6b` | Qwen3 Embedding 0.6B | Alibaba | out:text | 33K ctx | $0.0135 in / $0.00 out per 1M | -
- `qwen3-embedding-4b` | Qwen3 Embedding 4B | Alibaba | out:text | 33K ctx | $0.027 in / $0.00 out per 1M | -
- `bge-large-en` | BGE Large EN v1.5 | Baai | out:text | 1K ctx | $0.0135 in / $0.00 out per 1M | -
- `bge-base-en` | BGE Base EN v1.5 | Baai | out:text | 1K ctx | $0.00675 in / $0.00 out per 1M | -
- `multilingual-e5-large` | Multilingual E5 Large | Microsoft | out:text | 1K ctx | $0.0135 in / $0.00 out per 1M | -
- `all-minilm-l12` | all-MiniLM-L12-v2 | Sentence-transformers | out:text | 1K ctx | $0.00675 in / $0.00 out per 1M | -
- `all-minilm-l6` | all-MiniLM-L6-v2 | Sentence-transformers | out:text | 1K ctx | $0.00675 in / $0.00 out per 1M | -
- `gte-base` | GTE Base | Alibaba | out:text | 1K ctx | $0.00675 in / $0.00 out per 1M | -
- `hermes-3-405b` | Hermes 3 405B | Nousresearch | out:text | 131K ctx | $1.35 in / $1.35 out per 1M | tools
- `hermes-3-70b` | Hermes 3 70B | Nousresearch | out:text | 131K ctx | $0.945 in / $0.945 out per 1M | tools
- `qwen3-reranker-8b` | Qwen3 Reranker 8B | Alibaba | out:text | 41K ctx | $0.135 in / $0.00 out per 1M | -
- `whisper-v3-turbo` | Whisper Large v3 Turbo | OpenAI | out:text | 4K ctx | $0.0009 / minute | -
- `gpt-4o-mini-transcribe-2025-12-15` | GPT-4o mini Transcribe | OpenAI | out:text | 2K ctx | $0.00405 / minute | -
- `gpt-transcribe` | GPT Transcribe | OpenAI | out:text | 2K ctx | $0.006075 / minute | -
- `gemini-3.5-transcribe` | Gemini 3.5 Transcribe | Google | out:text | 4K ctx | $0.00675 / minute | -
- `eleven-multilingual-v2` | ElevenLabs Multilingual v2 | ElevenLabs | out:audio | 5K ctx | $0.405 / 1K characters | -
- `eleven-flash-v2-5` | ElevenLabs Flash v2.5 | ElevenLabs | out:audio | 5K ctx | $0.2025 / 1K characters | -
- `eleven-turbo-v2-5` | ElevenLabs Turbo v2.5 | ElevenLabs | out:audio | 5K ctx | $0.2025 / 1K characters | -
- `minimax-speech-hd` | MiniMax Speech HD | MiniMax | out:audio | 5K ctx | $0.07 / 1K characters | -
- `minimax-speech-turbo` | MiniMax Speech Turbo | MiniMax | out:audio | 5K ctx | $0.04 / 1K characters | -
- `lyria-3.5` | Lyria 3.5 | Google | out:audio | 5K ctx | $0.108 / track | -
- `gpt-image-2` | GPT Image 2 | OpenAI | out:image | - ctx | $0.072 / image | vision
- `gpt-image-2.5-flare` | GPT Image 2.5 Flare | OpenAI | out:image | - ctx | $0.019 / image | vision
- `minimax-image-01` | MiniMax Image 01 | MiniMax | out:image | - ctx | $0.005 / image | -

## Key Facts

- OpenAI SDK compatible: set base_url to `https://kymaapi.com/v1` and use a ky- API key
- Anthropic Messages API compatible: POST /v1/messages
- Image generation: POST /v1/images/generations (async, poll GET /v1/jobs/{id})
- Video generation: POST /v1/videos/generations (async, poll GET /v1/jobs/{id})
- Audio: transcription (POST /v1/audio/transcriptions), text-to-speech (POST /v1/audio/speech)
- Multi-route redundancy: automatic failover keeps user-facing errors near zero
- Prompt caching: cached input billed at each model's own cached rate, automatic where supported
- Tool calling and JSON structured outputs: supported on language models
- Rate limits: tier-based, scaling with credits purchased
- Free tier: the $0.50 signup credit spends on 44 of 106 models: everything billed per token (language, embedding, reranking) at or under $3/M output and $0.50/M input, plus everything billed per unit at or under $0.01 per billing unit. Everything else that generates media needs a top-up; free-tier media today: `gemini-3.5-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `gpt-transcribe`, `minimax-image-01`, `whisper-v3-turbo`
- Signup: https://kymaapi.com or POST /v1/auth/register

## Optional

- [Changelog](https://kymaapi.com/changelog.md): Dated list of what changed, newest first (also at https://kymaapi.com/changelog)
- [Use Cases](https://docs.kymaapi.com/guides/use-cases/chatbot): Chatbot, coding agent, RAG, data extraction, automation
- [MCP Server](https://docs.kymaapi.com/guides/mcp-server): Streamable HTTP at https://mcp.kymaapi.com/mcp (OAuth) plus local/dev stdio