# llm.buzz

> llm.buzz serves many models through one API that OpenAI, Anthropic and OpenRouter clients can call. Each model is served by one or more providers: cloud providers Surogate connects, and independent providers that list their own endpoints at their own prices.

Everything below in one file, with SDK snippets, examples, the full model table and every docs page: [llms-full.txt](https://llm.buzz/llms-full.txt).

## API

- OpenAI and OpenRouter compatible base URL: https://api.llm.buzz/api/v1 (Chat Completions `/chat/completions`, Responses `/responses`, Embeddings `/embeddings`, Images `/images` and `/images/generations`, Models `/models`)
- Anthropic compatible base URL: https://api.llm.buzz/api (the Anthropic SDK adds `/v1/messages`; the full route is https://api.llm.buzz/api/v1/messages)
- Authentication: `Authorization: Bearer <key>` on every request; the Messages API also takes `x-api-key: <key>`
- Keys: created in the console, https://app.llm.buzz/console/keys
- Model names: as listed below, most of them `author/slug`; a suffix picks the routing for one call (`:floor` cheapest first, `:nitro` fastest first); `:online` is accepted, but llm.buzz runs no web search today, so the call is served without one
- App attribution: send `X-Title` and `HTTP-Referer` with your app's name and site so usage is credited to a recognised app

## Keyless JSON endpoints

- `GET https://api.llm.buzz/api/v1/models`: every model in the OpenRouter shape, with prices, context and supported parameters. `?region=eu` lists only models with an EU provider; `?output_modalities=image` filters by output.
- `GET https://api.llm.buzz/api/v1/models/{author}/{slug}`: one model.
- `GET https://api.llm.buzz/api/v1/models/{author}/{slug}/endpoints`: the model's providers with their prices, limits and 24-hour uptime.
- `GET https://api.llm.buzz/api/v1/model/{author}/{slug}`: one model in a `{"data": ...}` envelope.

## Docs

- [Quickstart](https://llm.buzz/docs/raw/quickstart.md): Call any model on llm.buzz with the OpenAI or Anthropic SDK you already use.
- [Choosing an API](https://llm.buzz/docs/raw/choosing-an-api.md): llm.buzz serves each kind of model on the API made for it. A chat model answers Chat Completions, Responses and Messages alike; embeddings, image, audio and decision models have their own routes.
- [Coming from OpenRouter](https://llm.buzz/docs/raw/from-openrouter.md): llm.buzz speaks OpenRouter's API, so most OpenRouter code works after you change the base URL and the key. This page lists what else differs, with links to the pages that explain more.
- [Chat Completions](https://llm.buzz/docs/raw/chat-completions.md): Chat Completions is OpenAI's conversation API, the one most SDKs and coding agents speak. llm.buzz serves it at POST /chat/completions under https://api.llm.buzz/api/v1 for every text model, with OpenRouter's extensions, so the OpenAI and OpenRouter SDKs call it with the base URL changed.
- [Responses](https://llm.buzz/docs/raw/responses.md): Responses is OpenAI's API of items in and items out, with the conversation's state kept by llm.buzz, so a follow-up sends only its own input. llm.buzz serves it at POST https://api.llm.buzz/api/v1/responses for every text model, and the OpenAI SDK and Codex call it with the base URL changed.
- [Messages](https://llm.buzz/docs/raw/messages.md): Messages is Anthropic's API. llm.buzz serves it at POST https://api.llm.buzz/api/v1/messages for every text model, Claude or not, so the Anthropic SDK and the tools built on it work with the base URL alone.
- [Embeddings](https://llm.buzz/docs/raw/embeddings.md): llm.buzz serves embeddings models on the OpenAI Embeddings API, so the OpenAI and OpenRouter SDKs reach them with the base URL alone. Chat Completions, Responses and Messages refuse an embeddings model with a 400 on model that names POST /api/v1/embeddings.
- [Images](https://llm.buzz/docs/raw/images.md): llm.buzz serves image generation models on OpenRouter's Image API, POST /api/v1/images, and on the OpenAI Images API, POST /api/v1/images/generations, so the OpenRouter and OpenAI SDKs reach them with the base URL alone. An answer is never streamed, and every image comes back as base64 in b64_json.
- [Audio](https://llm.buzz/docs/raw/audio.md): llm.buzz serves speech to text and text to speech with OpenRouter's request and answer shapes, so the OpenAI and OpenRouter SDKs reach them with the base URL alone. Each audio model serves one of the two. Chat Completions, Responses and Messages refuse an audio model with a 400 that names its route.
- [Decisions](https://llm.buzz/docs/raw/decisions.md): The decisions routes take a state and up to 32 typed questions about it, and answer each one in a fixed shape: a probability for noul, the chosen category and a probability per category for choice, and a position on your scale for score. No public model on llm.buzz answers them.
- [Tools and structured output](https://llm.buzz/docs/raw/tools-and-structured-output.md): Tools let a model ask your code to run a function; structured output makes it answer in JSON that matches your schema. Both work on Chat Completions, Responses and Messages, each in its own shape.
- [Streaming](https://llm.buzz/docs/raw/streaming.md): With stream: true the answer arrives as server-sent events while the model writes it. Chat Completions, Responses and Messages all stream, each with its own events.
- [Reasoning](https://llm.buzz/docs/raw/reasoning.md): Reasoning models think before they answer. You set how much in the field your API uses, and llm.buzz sends it to each provider in that provider's terms, by OpenRouter's rules.
- [Images in requests](https://llm.buzz/docs/raw/images-in-requests.md): Models that read images take them inside a message. This page covers images on Chat Completions and Messages, and a message can mix text and several images.
- [Prompt caching](https://llm.buzz/docs/raw/prompt-caching.md): A provider that caches a prompt bills the repeated start of your next request at its cached-input price, a fraction of its input price. Most providers cache on their own. Claude caches only where your request marks it, and llm.buzz never adds a mark for you.
- [Authentication](https://llm.buzz/docs/raw/authentication.md): Every request carries one of your keys. You create keys in the console, send them in the Authorization header, and can give each one a spending limit.
- [Models and routing](https://llm.buzz/docs/raw/models-and-routing.md): Each model on llm.buzz is served by one or more providers. You name the model; llm.buzz picks a provider, moves to the next one when a provider fails, and follows your preferences when you give them.
- [Pricing and discounts](https://llm.buzz/docs/raw/pricing.md): You pay per token, or per second of audio, per character or per image on a model priced that way, at the price of the provider that answered your request, from prepaid credit. Every price is public: on each model's page, in the model list, and in the market log.
- [Usage and limits](https://llm.buzz/docs/raw/usage-and-limits.md): Every answer says what the request used and what it cost, and a few limits decide when a request is refused. This page lists both, and where to read them again afterwards.
- [Retries and idempotency](https://llm.buzz/docs/raw/retries-and-idempotency.md): llm.buzz retries across a model's providers inside one request, and an Idempotency-Key makes your own retries safe. This page says what each does, and what a retry costs.
- [Errors](https://llm.buzz/docs/raw/errors.md): Every error on the model API comes in one envelope: the HTTP status, a message that says what to do, and a code your program can branch on.
- [All docs in one file](https://llm.buzz/docs/llms-full.txt): every docs page as Markdown
- [Release notes](https://llm.buzz/docs/release-notes): what changed for callers, newest first ([RSS](https://llm.buzz/docs/release-notes/rss.xml))

## Guides

- [Cheapest models for coding agents](https://llm.buzz/docs/guides/cheapest-models-for-coding-agents): A coding agent needs a model that calls tools, and it sends a lot of tokens. These are the cheapest models with tool calling on llm.buzz right now, and how to point Claude Code, Codex, Cline, OpenCode and Aider at them.
- [EU-only inference](https://llm.buzz/docs/guides/eu-only-inference): Keeping a request on providers in the EU is one field on llm.buzz, and it holds when a provider fails. Here are the EU providers and models live right now, the request to send, and what happens when no EU provider can answer.
- [Routing and failover for agents](https://llm.buzz/docs/guides/routing-and-failover-for-agents): An agent that runs for hours meets every kind of provider failure. How llm.buzz orders a model's providers, moves to the next one when a provider fails, and how your agent steers both and retries safely.
- [Vision and image pipelines](https://llm.buzz/docs/guides/vision-and-image-pipelines): Some models read images and some make them. Here are the models live on llm.buzz for each, with the request shapes for sending an image in and for getting one back.
- [Batch jobs](https://llm.buzz/docs/guides/batch-jobs): llm.buzz does not run batch jobs today, so a large job is many single requests. How to send them so a failure never runs one twice, a busy provider slows you down instead of failing you, and the cheapest provider answers.
- [Listing your model as a provider](https://llm.buzz/docs/guides/listing-your-model-as-a-provider): An inference company can sell its endpoint on llm.buzz at its own price. The steps from sign-up to the first paid request: the application, the listing, the automated check and the monthly statement.

## Providers

- [Become a provider](https://llm.buzz/providers/join): list an inference endpoint on llm.buzz at your own price
- [All providers](https://llm.buzz/providers): compare providers by location, data policy and the models they serve
- [Alibaba](https://llm.buzz/providers/alibaba): cloud provider, Non-EU, 6 models. Hasn't declared whether it trains on prompts or how long it keeps them.
- [Anthropic](https://llm.buzz/providers/anthropic): cloud provider, Non-EU, 9 models. Hasn't declared whether it trains on prompts or how long it keeps them.
- [DeepInfra](https://llm.buzz/providers/deepinfra): cloud provider, Non-EU, 38 models. Hasn't declared whether it trains on prompts or how long it keeps them.
- [llm.buzz](https://llm.buzz/providers/llm-buzz): cloud provider, Non-EU, 36 models. Hasn't declared whether it trains on prompts or how long it keeps them.
- [Moonshot AI](https://llm.buzz/providers/moonshot-ai): cloud provider, Non-EU, 2 models. Hasn't declared whether it trains on prompts or how long it keeps them.
- [Novita](https://llm.buzz/providers/novita): cloud provider, Non-EU, 7 models. Hasn't declared whether it trains on prompts or how long it keeps them.
- [OpenAI](https://llm.buzz/providers/openai): cloud provider, Non-EU, 22 models. Hasn't declared whether it trains on prompts or how long it keeps them.
- [Prime Intellect](https://llm.buzz/providers/prime-intellect): cloud provider, Non-EU, 11 models. Hasn't declared whether it trains on prompts or how long it keeps them.
- [Scaleway](https://llm.buzz/providers/scaleway): cloud provider, EU, 10 models. Hasn't declared whether it trains on prompts or how long it keeps them.
- [Simpleminds EU](https://llm.buzz/providers/simpleminds-eu): independent provider, EU, 1 model. Doesn't train on prompts and keeps nothing.
- [Surogate Spark](https://llm.buzz/providers/surogate-spark): cloud provider, EU, 1 model. Doesn't train on prompts and keeps nothing.

## Models

Prices are the first-ranked provider's, in USD per million tokens unless a line names another unit. [All models](https://llm.buzz/models); the full table is in [llms-full.txt](https://llm.buzz/llms-full.txt).

- [Anthropic: Claude Fable 5](https://llm.buzz/models/anthropic/claude-fable-5/llms.txt): `anthropic/claude-fable-5`, $7.50 input and $37.50 output (25% off until 2026-11-06 00:00 UTC); $0.75 cache read; 1,000,000 context; tools, structured_output, caching; 2 live providers
- [Anthropic: Claude Fable 5.1](https://llm.buzz/models/anthropic/claude-fable-5.1/llms.txt): `anthropic/claude-fable-5.1`, $7.50 input and $37.50 output (25% off until 2026-11-06 00:00 UTC); $0.1875 cache read; 1,000,000 context; tools, structured_output, caching; 2 live providers
- [Anthropic: Claude Haiku 5.5](https://llm.buzz/models/anthropic/claude-haiku-5.5/llms.txt): `anthropic/claude-haiku-5.5`, $0.10 input and $0.50 output; $0.01 cache read; 1,000,000 context; tools, structured_output, caching; 2 live providers
- [Anthropic: Claude Opus 4.7](https://llm.buzz/models/anthropic/claude-opus-4.7/llms.txt): `anthropic/claude-opus-4.7`, $3.75 input and $18.75 output (25% off until 2026-11-06 00:00 UTC); $0.375 cache read; 1,000,000 context; tools, structured_output, caching; 2 live providers
- [Anthropic: Claude Opus 4.8](https://llm.buzz/models/anthropic/claude-opus-4.8/llms.txt): `anthropic/claude-opus-4.8`, $3.75 input and $18.75 output (25% off until 2026-11-06 00:00 UTC); $0.375 cache read; 1,000,000 context; tools, structured_output, caching; 2 live providers
- [Anthropic: Claude Opus 5](https://llm.buzz/models/anthropic/claude-opus-5/llms.txt): `anthropic/claude-opus-5`, $3.75 input and $18.75 output (25% off until 2026-11-06 00:00 UTC); $0.375 cache read; 1,000,000 context; tools, structured_output, caching; 2 live providers
- [Anthropic: Claude Opus 5.5](https://llm.buzz/models/anthropic/claude-opus-5.5/llms.txt): `anthropic/claude-opus-5.5`, $3.00 input and $15.00 output (25% off until 2026-11-06 00:00 UTC); $0.15 cache read; 1,000,000 context; tools, structured_output, caching; 2 live providers
- [Anthropic: Claude Sonnet 5](https://llm.buzz/models/anthropic/claude-sonnet-5/llms.txt): `anthropic/claude-sonnet-5`, $1.50 input and $7.50 output (25% off until 2026-11-06 00:00 UTC); $0.15 cache read; 1,000,000 context; tools, structured_output, caching; 2 live providers
- [Anthropic: Claude Sonnet 5.5](https://llm.buzz/models/anthropic/claude-sonnet-5.5/llms.txt): `anthropic/claude-sonnet-5.5`, $2.00 input and $10.00 output; $0.10 cache read; 1,000,000 context; tools, structured_output, caching; 2 live providers
- [BAAI: bge-base-en-v1.5](https://llm.buzz/models/baai/bge-base-en-v1.5/llms.txt): `baai/bge-base-en-v1.5`, $0.005 input; 512 context; 768 dimensions; 1 live provider
- [BAAI: bge-large-en-v1.5](https://llm.buzz/models/baai/bge-large-en-v1.5/llms.txt): `baai/bge-large-en-v1.5`, $0.01 input; 512 context; 1,024 dimensions; 1 live provider
- [BAAI: bge-m3](https://llm.buzz/models/baai/bge-m3/llms.txt): `baai/bge-m3`, $0.01 input; 8,192 context; 1,024 dimensions; 1 live provider
- [Black Forest Labs: FLUX.2 Klein 4B](https://llm.buzz/models/black-forest-labs/flux.2-klein-4b/llms.txt): `black-forest-labs/flux.2-klein-4b`, $0.014 per image; 1 live provider
- [Black Forest Labs: FLUX.2 Max](https://llm.buzz/models/black-forest-labs/flux.2-max/llms.txt): `black-forest-labs/flux.2-max`, $0.07 per image; 1 live provider
- [Black Forest Labs: FLUX.2 Pro](https://llm.buzz/models/black-forest-labs/flux.2-pro/llms.txt): `black-forest-labs/flux.2-pro`, $0.03 per image; 1 live provider
- [DeepSeek: DeepSeek V4 Flash 0731](https://llm.buzz/models/deepseek/deepseek-v4-flash-0731/llms.txt): `deepseek/deepseek-v4-flash-0731`, $0.461 input and $0.9219 output; $0.0922 cache read; 1,048,576 context; tools, structured_output, caching; 3 live providers; EU available
- [DeepSeek: DeepSeek V4 Flash Vision Exp](https://llm.buzz/models/deepseek/deepseek-v4-flash-vision-exp/llms.txt): `deepseek/deepseek-v4-flash-vision-exp`, $0.33 input and $0.99 output (25% off until 2026-11-06 00:00 UTC); $0.0105 cache read; 1,048,576 context; tools, structured_output, caching; 2 live providers
- [DeepSeek: DeepSeek V4 Pro 0813](https://llm.buzz/models/deepseek/deepseek-v4-pro-0813/llms.txt): `deepseek/deepseek-v4-pro-0813`, $1.30 input and $2.60 output; $0.10 cache read; 1,048,576 context; tools, structured_output, caching; 2 live providers
- [DeepSeek: DeepSeek V4.1 Flash](https://llm.buzz/models/deepseek/deepseek-v4.1-flash/llms.txt): `deepseek/deepseek-v4.1-flash`, $0.30 input and $1.20 output; $0.006 cache read; 1,048,576 context; tools, structured_output, caching; 3 live providers; EU available
- [DeepSeek: DeepSeek V4.1 Flash 1017](https://llm.buzz/models/deepseek/deepseek-v4.1-flash-1017/llms.txt): `deepseek/deepseek-v4.1-flash-1017`, $0.15 input and $0.45 output (25% off until 2026-11-06 00:00 UTC); $0.0045 cache read; 1,048,576 context; tools, structured_output, caching; 3 live providers
- [Google: Nano Banana Pro \(Gemini 3 Pro Image\)](https://llm.buzz/models/google/gemini-3-pro-image/llms.txt): `google/gemini-3-pro-image`, $0.1344 per image; 1 live provider
- [Google: Nano Banana 2 \(Gemini 3.1 Flash Image\)](https://llm.buzz/models/google/gemini-3.1-flash-image/llms.txt): `google/gemini-3.1-flash-image`, $0.0672 per image; 1 live provider
- [Google: Nano Banana 2 Lite \(Gemini 3.1 Flash Lite Image\)](https://llm.buzz/models/google/gemini-3.1-flash-lite-image/llms.txt): `google/gemini-3.1-flash-lite-image`, $0.0336 per image; 1 live provider
- [Google: Gemma 4 26B A4B](https://llm.buzz/models/google/gemma-4-26b-a4b-it/llms.txt): `google/gemma-4-26b-a4b-it`, $0.07 input and $0.34 output; 262,144 context; tools, structured_output; 3 live providers; EU available
- [Google: Gemma 4 31B](https://llm.buzz/models/google/gemma-4-31b-it/llms.txt): `google/gemma-4-31b-it`, $0.15 input and $0.30 output (25% off until 2026-11-06 00:00 UTC); 262,144 context; tools, structured_output; 2 live providers
- [hexgrad: Kokoro 82M](https://llm.buzz/models/hexgrad/kokoro-82m/llms.txt): `hexgrad/kokoro-82m`, $0.99 per million characters; 1 live provider
- [Intfloat: E5-Base-v2](https://llm.buzz/models/intfloat/e5-base-v2/llms.txt): `intfloat/e5-base-v2`, $0.005 input; 512 context; 768 dimensions; 1 live provider
- [Intfloat: E5-Large-v2](https://llm.buzz/models/intfloat/e5-large-v2/llms.txt): `intfloat/e5-large-v2`, $0.01 input; 512 context; 1,024 dimensions; 1 live provider
- [Intfloat: Multilingual-E5-Large](https://llm.buzz/models/intfloat/multilingual-e5-large/llms.txt): `intfloat/multilingual-e5-large`, $0.01 input; 512 context; 1,024 dimensions; 1 live provider
- [Mistral: Mistral Medium 3.5](https://llm.buzz/models/mistralai/mistral-medium-3-5/llms.txt): `mistralai/mistral-medium-3-5`, $1.7286 input and $8.6428 output; 180,000 context; tools, structured_output; 1 live provider; EU available
- [Mistral: Mistral Small 3.2 24B](https://llm.buzz/models/mistralai/mistral-small-3.2-24b-instruct/llms.txt): `mistralai/mistral-small-3.2-24b-instruct`, $0.129675 input and $0.30255 output (25% off until 2026-11-06 00:00 UTC); 128,000 context; tools, structured_output; 2 live providers; EU available
- [Moondream: Moondream 3 Preview](https://llm.buzz/models/moondream/moondream3-preview/llms.txt): `moondream/moondream3-preview`, $0.30 input and $2.50 output; 32,000 context; 1 live provider
- [Moondream: Moondream 3.1](https://llm.buzz/models/moondream/moondream3.1-9b-a2b/llms.txt): `moondream/moondream3.1-9b-a2b`, $0.30 input and $2.50 output; 32,000 context; 1 live provider
- [MoonshotAI: Kimi K3](https://llm.buzz/models/moonshotai/kimi-k3/llms.txt): `moonshotai/kimi-k3`, $2.565 input and $12.825 output (10% off until 2026-11-06 00:00 UTC); $0.2565 cache read; 1,048,576 context; tools, structured_output, caching; 6 live providers
- [MoonshotAI: Kimi K3.1 Pro](https://llm.buzz/models/moonshotai/kimi-k3.1-pro/llms.txt): `moonshotai/kimi-k3.1-pro`, $2.00 input and $10.00 output; $0.20 cache read; 1,048,576 context; tools, structured_output, caching; 1 live provider
- [NVIDIA: Nemotron 3 Super](https://llm.buzz/models/nvidia/nemotron-3-super-120b-a12b/llms.txt): `nvidia/nemotron-3-super-120b-a12b`, $0.085 input and $0.40 output; 262,144 context; tools, structured_output; 1 live provider
- [OpenAI: GPT-4.1](https://llm.buzz/models/openai/gpt-4.1/llms.txt): `openai/gpt-4.1`, $2.00 input and $8.00 output; $0.50 cache read; 1,047,576 context; tools, structured_output, caching; 2 live providers
- [OpenAI: GPT-4.1 Mini](https://llm.buzz/models/openai/gpt-4.1-mini/llms.txt): `openai/gpt-4.1-mini`, $0.36 input and $1.44 output (10% off until 2026-11-06 00:00 UTC); $0.09 cache read; 1,047,576 context; tools, structured_output, caching; 2 live providers
- [OpenAI: GPT-4o-mini](https://llm.buzz/models/openai/gpt-4o-mini/llms.txt): `openai/gpt-4o-mini`, $0.15 input and $0.60 output; $0.075 cache read; 128,000 context; tools, structured_output, caching; 2 live providers
- [OpenAI: GPT-5 Mini](https://llm.buzz/models/openai/gpt-5-mini/llms.txt): `openai/gpt-5-mini`, $0.25 input and $2.00 output; $0.025 cache read; 400,000 context; tools, structured_output, caching; 2 live providers
- [OpenAI: GPT-5 Nano](https://llm.buzz/models/openai/gpt-5-nano/llms.txt): `openai/gpt-5-nano`, $0.045 input and $0.36 output (10% off until 2026-11-06 00:00 UTC); $0.0045 cache read; 400,000 context; tools, structured_output, caching; 2 live providers
- [OpenAI: GPT-5.4](https://llm.buzz/models/openai/gpt-5.4/llms.txt): `openai/gpt-5.4`, $2.50 input and $15.00 output; $0.25 cache read; 1,050,000 context; tools, structured_output, caching; 2 live providers
- [OpenAI: GPT-5.4 Mini](https://llm.buzz/models/openai/gpt-5.4-mini/llms.txt): `openai/gpt-5.4-mini`, $0.75 input and $4.50 output; $0.075 cache read; 400,000 context; tools, structured_output, caching; 2 live providers
- [OpenAI: GPT-5.4 Nano](https://llm.buzz/models/openai/gpt-5.4-nano/llms.txt): `openai/gpt-5.4-nano`, $0.20 input and $1.25 output; $0.02 cache read; 400,000 context; tools, structured_output, caching; 2 live providers
- [OpenAI: GPT-5.5](https://llm.buzz/models/openai/gpt-5.5/llms.txt): `openai/gpt-5.5`, $5.00 input and $30.00 output; $0.50 cache read; 1,050,000 context; tools, structured_output, caching; 2 live providers
- [OpenAI: GPT-5.6 Luna](https://llm.buzz/models/openai/gpt-5.6-luna/llms.txt): `openai/gpt-5.6-luna`, $0.20 input and $1.20 output; $0.02 cache read; 1,050,000 context; tools, structured_output, caching; 2 live providers
- [OpenAI: GPT-5.6 Sol](https://llm.buzz/models/openai/gpt-5.6-sol/llms.txt): `openai/gpt-5.6-sol`, $4.00 input and $20.00 output; $0.40 cache read; 1,050,000 context; tools, structured_output, caching; 2 live providers
- [OpenAI: GPT-5.6 Terra](https://llm.buzz/models/openai/gpt-5.6-terra/llms.txt): `openai/gpt-5.6-terra`, $1.80 input and $10.80 output (10% off until 2026-11-06 00:00 UTC); $0.18 cache read; 1,050,000 context; tools, structured_output, caching; 2 live providers
- [OpenAI: GPT-6 Astra](https://llm.buzz/models/openai/gpt-6-astra/llms.txt): `openai/gpt-6-astra`, $10.00 input and $50.00 output; $1.00 cache read; 1,050,000 context; tools, structured_output, caching; 2 live providers
- [OpenAI: GPT-6 Luna](https://llm.buzz/models/openai/gpt-6-luna/llms.txt): `openai/gpt-6-luna`, $0.10 input and $0.50 output; $0.01 cache read; 1,050,000 context; tools, structured_output, caching; 2 live providers
- [OpenAI: GPT-6 Sol](https://llm.buzz/models/openai/gpt-6-sol/llms.txt): `openai/gpt-6-sol`, $2.00 input and $10.00 output; $0.20 cache read; 1,050,000 context; tools, structured_output, caching; 2 live providers
- [OpenAI: GPT-6.1 Sol](https://llm.buzz/models/openai/gpt-6.1-sol/llms.txt): `openai/gpt-6.1-sol`, $2.00 input and $10.00 output; $0.10 cache read; 1,050,000 context; tools, structured_output, caching; 2 live providers
- [OpenAI: GPT Image 2](https://llm.buzz/models/openai/gpt-image-2/llms.txt): `openai/gpt-image-2`, $5.00 input and $30.00 output; 1 live provider
- [OpenAI: GPT Image 2.5 Flare](https://llm.buzz/models/openai/gpt-image-2.5-flare/llms.txt): `openai/gpt-image-2.5-flare`, $5.00 input and $30.00 output; 1 live provider
- [OpenAI: GPT Image 2.5 Sunburst](https://llm.buzz/models/openai/gpt-image-2.5-sunburst/llms.txt): `openai/gpt-image-2.5-sunburst`, $5.00 input and $30.00 output; 1 live provider
- [OpenAI: gpt-oss-120b](https://llm.buzz/models/openai/gpt-oss-120b/llms.txt): `openai/gpt-oss-120b`, $0.05 input and $0.25 output; 131,072 context; tools, structured_output; 3 live providers; EU available
- [OpenAI: Text Embedding 3 Large](https://llm.buzz/models/openai/text-embedding-3-large/llms.txt): `openai/text-embedding-3-large`, $0.13 input; 8,192 context; 3,072 dimensions; 1 live provider
- [OpenAI: Text Embedding 3 Small](https://llm.buzz/models/openai/text-embedding-3-small/llms.txt): `openai/text-embedding-3-small`, $0.02 input; 8,192 context; 1,536 dimensions; 1 live provider
- [OpenAI: Text Embedding Ada 002](https://llm.buzz/models/openai/text-embedding-ada-002/llms.txt): `openai/text-embedding-ada-002`, $0.10 input; 8,192 context; 1,536 dimensions; 1 live provider
- [OpenAI: Whisper Large V3](https://llm.buzz/models/openai/whisper-large-v3/llms.txt): `openai/whisper-large-v3`, $7.50 per million seconds of audio; 2 live providers; EU available
- [OpenAI: Whisper Large V3 Turbo](https://llm.buzz/models/openai/whisper-large-v3-turbo/llms.txt): `openai/whisper-large-v3-turbo`, $3.33 per million seconds of audio; 1 live provider
- [Qwen: Qwen Image 3](https://llm.buzz/models/qwen/qwen-image-3/llms.txt): `qwen/qwen-image-3`, $0.03 per image; 1 live provider
- [Qwen: Qwen3 Embedding 4B](https://llm.buzz/models/qwen/qwen3-embedding-4b/llms.txt): `qwen/qwen3-embedding-4b`, $0.02 input; 32,768 context; 2,560 dimensions; 1 live provider
- [Qwen: Qwen3 Embedding 8B](https://llm.buzz/models/qwen/qwen3-embedding-8b/llms.txt): `qwen/qwen3-embedding-8b`, $0.01 input; 32,768 context; 4,096 dimensions; 1 live provider
- [Qwen: Qwen3.5-0.8B](https://llm.buzz/models/qwen/qwen3.5-0.8b/llms.txt): `qwen/qwen3.5-0.8b`, $0.04 input and $0.08 output; 65,536 context; tools, structured_output; 0 live providers; temporarily unavailable
- [Qwen: Qwen3.5-2B](https://llm.buzz/models/qwen/qwen3.5-2b/llms.txt): `qwen/qwen3.5-2b`, $0.06 input and $0.18 output; 65,536 context; tools, structured_output; 0 live providers; temporarily unavailable
- [Qwen: Qwen3.5-4B](https://llm.buzz/models/qwen/qwen3.5-4b/llms.txt): `qwen/qwen3.5-4b`, $0.10 input and $0.30 output; 65,536 context; tools, structured_output; 0 live providers; temporarily unavailable
- [Qwen: Qwen3.5-9B](https://llm.buzz/models/qwen/qwen3.5-9b/llms.txt): `qwen/qwen3.5-9b`, $0.18 input and $0.54 output; 65,536 context; tools, structured_output; 0 live providers; temporarily unavailable
- [Qwen: Qwen3.6 35B A3B](https://llm.buzz/models/qwen/qwen3.6-35b-a3b/llms.txt): `qwen/qwen3.6-35b-a3b`, $0.25 input and $1.25 output; 262,144 context; tools, structured_output; 3 live providers; EU available
- [Qwen: Qwen3.8 27B](https://llm.buzz/models/qwen/qwen3.8-27b/llms.txt): `qwen/qwen3.8-27b`, $0.20 input and $2.50 output; $0.05 cache read; 262,144 context; tools, structured_output, caching; 4 live providers; EU available
- [Qwen: Qwen3.8 Flash](https://llm.buzz/models/qwen/qwen3.8-flash/llms.txt): `qwen/qwen3.8-flash`, $0.1125 input and $0.3525 output (25% off until 2026-11-06 00:00 UTC); $0.012 cache read; 1,000,000 context; tools, structured_output, caching; 4 live providers
- [Qwen: Qwen3.8 Max \(0902\)](https://llm.buzz/models/qwen/qwen3.8-max-0902/llms.txt): `qwen/qwen3.8-max-0902`, $2.00 input and $6.00 output; $0.25 cache read; 1,000,000 context; tools, structured_output, caching; 1 live provider
- [Qwen: Qwen3.8 Omni Flash](https://llm.buzz/models/qwen/qwen3.8-omni-flash/llms.txt): `qwen/qwen3.8-omni-flash`, $0.15 input and $0.47 output; $0.016 cache read; 1,000,000 context; tools, structured_output, caching; 1 live provider
- [Sentence Transformers: all-MiniLM-L12-v2](https://llm.buzz/models/sentence-transformers/all-minilm-l12-v2/llms.txt): `sentence-transformers/all-minilm-l12-v2`, $0.005 input; 512 context; 384 dimensions; 1 live provider
- [Sentence Transformers: all-MiniLM-L6-v2](https://llm.buzz/models/sentence-transformers/all-minilm-l6-v2/llms.txt): `sentence-transformers/all-minilm-l6-v2`, $0.005 input; 512 context; 384 dimensions; 1 live provider
- [Sentence Transformers: all-mpnet-base-v2](https://llm.buzz/models/sentence-transformers/all-mpnet-base-v2/llms.txt): `sentence-transformers/all-mpnet-base-v2`, $0.005 input; 512 context; 768 dimensions; 1 live provider
- [Sentence Transformers: multi-qa-mpnet-base-dot-v1](https://llm.buzz/models/sentence-transformers/multi-qa-mpnet-base-dot-v1/llms.txt): `sentence-transformers/multi-qa-mpnet-base-dot-v1`, $0.005 input; 512 context; 768 dimensions; 1 live provider
- [Sentence Transformers: paraphrase-MiniLM-L6-v2](https://llm.buzz/models/sentence-transformers/paraphrase-minilm-l6-v2/llms.txt): `sentence-transformers/paraphrase-minilm-l6-v2`, $0.005 input; 512 context; 384 dimensions; 1 live provider
- [Surogate: Surogate 3.7 Flash](https://llm.buzz/models/surogate/surogate3.7-flash/llms.txt): `surogate/surogate3.7-flash`, $0.10 input and $0.75 output; $0.05 cache read; 1,048,576 context; tools, structured_output, caching; 2 live providers; EU available; zero retention available
- [Thenlper: GTE-Base](https://llm.buzz/models/thenlper/gte-base/llms.txt): `thenlper/gte-base`, $0.005 input; 512 context; 768 dimensions; 1 live provider
- [Thenlper: GTE-Large](https://llm.buzz/models/thenlper/gte-large/llms.txt): `thenlper/gte-large`, $0.01 input; 512 context; 1,024 dimensions; 1 live provider
- [Xiaomi: MiMo-V2.6-Flash](https://llm.buzz/models/xiaomi/mimo-v2.6-flash/llms.txt): `xiaomi/mimo-v2.6-flash`, $0.14 input and $0.28 output; $0.0028 cache read; 1,048,576 context; tools, structured_output, caching; 1 live provider
- [Xiaomi: MiMo-V2.6-Pro](https://llm.buzz/models/xiaomi/mimo-v2.6-pro/llms.txt): `xiaomi/mimo-v2.6-pro`, $0.43 input and $0.87 output; $0.0036 cache read; 1,048,576 context; tools, structured_output, caching; 2 live providers
- [Z.ai: GLM 5.3](https://llm.buzz/models/z-ai/glm-5.3/llms.txt): `z-ai/glm-5.3`, $0.98 input and $3.08 output; $0.182 cache read; 1,000,000 context; tools, structured_output, caching; 5 live providers; EU available
- [Z.ai: GLM 5.3 Flash](https://llm.buzz/models/z-ai/glm-5.3-flash/llms.txt): `z-ai/glm-5.3-flash`, $0.15 input and $0.50 output; $0.03 cache read; 1,048,576 context; tools, structured_output, caching; 4 live providers

## The market

- [Pricing](https://llm.buzz/pricing): providers set their prices; how credits and the service fee work
- [Benchmarks](https://llm.buzz/benchmarks): each model's providers by measured speed and price
- [Market log](https://llm.buzz/market): new models, new provider listings and price changes, dated ([RSS](https://llm.buzz/market/rss.xml))
- [Status](https://llm.buzz/status): every model's availability over the last 72 hours
- [EU routing](https://llm.buzz/eu): keeping a request on EU providers
- [Tools](https://llm.buzz/tools): the request options a call can switch on
- [Rankings](https://llm.buzz/rankings): every live model by measured speed, latency, uptime, price and providers
- [Everything on llm.buzz](https://llm.buzz/inventory): every provider, model, app and agent in one list

## For agents

- [Machine-readable surfaces](https://llm.buzz/for-ai): this file, the docs as Markdown and the sitemaps
- [Everything in one file](https://llm.buzz/llms-full.txt): the API, SDK snippets, examples, the full model table and every docs page
- [Collections](https://llm.buzz/collections): models grouped by what they can do
- [Sitemap](https://llm.buzz/sitemap.xml): every page
- [Apps and agents](https://llm.buzz/apps): how to point each coding agent, editor, chat app and SDK at llm.buzz