Models
The platform publishes its own model catalog: what is available right now, how to name it in a request, what every capability means, and how to choose a model for your task.
What the catalog is
The catalog is the list of models the platform can route right now. It is not written into this documentation and not maintained by hand: the page below reads it from the gateway, exactly as your code would.
curl https://api.kumorouter.com/v1/modelsThe answer is an OpenAI-shaped list: object: "list" and a data array whose every element is an object: "model". Reading it needs no key.
Not everything the platform holds gets in — only what can actually be called: the model is active and has at least one enabled capability in the published supplier configuration. A model's protocols and modalities are the exact intersection of what the catalog declares and what real supplier access has proven. So the list moves on its own when a supplier channel is withdrawn or added.
canonical_nameThe model's canonical name — what a request names it by.aliasesThe aliases that lead to this same model.vendorWho made the model — code, display names, brand color.context_window_tokensHow many tokens the model accepts in one request. Absent when the catalog publishes no figure.max_output_tokensHow many tokens it may answer with. Declared separately and never derived from the context window.released_onThe day the model's maker released it, as `yyyy-mm-dd`. Not the day it was added here.supplier_countDeprecated compatibility placeholder, always `1`. **Not** the number of suppliers behind a model — that is not published. Kept only so a client generated against an earlier release keeps parsing this listing; it will be removed.protocol_codesThe protocols the model is reachable by.modality_codesThe kind of work: text generation, embeddings, image generation.capabilitiesWhat the model can do on each pair of protocol and modality — see below.catalog_revisionA member of the list itself rather than of a model — the catalog revision, which grows on every change.{
"object": "model",
"canonical_name": "<model>",
"aliases": ["<alias>"],
"vendor": { "code": "<vendor>" },
"protocol_codes": ["chat_completions"],
"modality_codes": ["text_generation"],
"capabilities": [
{
"protocol_code": "chat_completions",
"modality_code": "text_generation",
"streaming_status": "proven",
"tools_status": "unproven",
"structured_output_mode": "json_schema"
}
]
}The catalog
Every model on the platform in one table, one row per model. The whole row opens that model's page; the single exception is the chip beside the identifier, which copies the name to the clipboard and leads nowhere.
ModelThe name, and under it the canonical name — exactly the string you will put in the `model` member. The maker stands beside it.TypeWhat the model does: text, embeddings, images.ProtocolsWhich protocols it can be called on.ContextHow many tokens fit into one request together with its answer.Max outputThe ceiling on the answer, in tokens.InputThe price of a million input tokens.OutputThe price of a million output tokens.ReleasedThe day the platform dated the model's release.The filters sit above the table. The search box looks at the name, the canonical name and the maker. Four rails follow, each narrowing on the thing it names: the maker, the type, the protocol, and a context window of "at least this much". The rails add up — choose a type and a protocol and you are asking for a model that does both. Pressing the chosen chip again clears it, and "Reset the filters" puts every rail back at once. The counter under them says how many rows are left, out of how many.
A column head sorts the table: the first press ascending, the second descending. A model the platform has published nothing for in that column sinks to the bottom in both directions — a dash means "not published", not "zero".
None of the figures in the table are written into this article. The platform serves the models and everything about them except money as a live catalog, and the rates as a published price list; the page reads both documents every time it is opened. So a model an operator adds or withdraws appears and disappears here on its own. If the price list cannot be read at this moment, the model list stays where it is and the rates stand as dashes.
A live list: the models come from the platform catalog and the rates from the published price list. A row opens the model’s own page; a column head sorts the table.
| Type | Protocols | ||||||
|---|---|---|---|---|---|---|---|
Claude Sonnet 5 claude-sonnet-5Anthropic | Text | Messages Chat Responses | 1M | 128K | $1.2 | $6 | Jun 30, 2026 |
Gemini 3.6 Flash gemini-3.6-flashGoogle | Text | Chat | 1M | 65.5K | $0.4 | $1.8 | Jul 21, 2026 |
Gemini 3.8 Flash gemini-3.8-flashGoogle | Text | Chat Responses | 1M | 65.5K | $0.4 | $2.1 | Sep 2, 2026 |
GLM 5.3 Flash glm-5.3-flashZhipu | Text | Chat Responses | 1M | 131.1K | $0.2 | $0.6 | Aug 26, 2026 |
Kimi K2.8 kimi-k2-8Moonshot AI | Text | Chat | 1M | — | $0.8 | $4 | Sep 11, 2026 |
Kimi K3 kimi-k3Moonshot AI | Text | Chat Responses | 1M | 1M | $1.7 | $8.3 | Jul 16, 2026 |
Kimi K3.1 Pro kimi-k3-1-proMoonshot AI | Text | Chat | 1M | 943.7K | $1.6 | $8 | Oct 23, 2026 |
Claude Opus 4.8 anthropic/claude-opus-4-8Anthropic | Text | Messages Chat Responses | 1M | 128K | $2.6 | $12.8 | May 28, 2026 |
GPT Image 2 openai/gpt-image-2OpenAI | Images | Images | — | — | — | — | Apr 21, 2026 |
Claude Fable 5 anthropic/claude-fable-5Anthropic | Text | Messages Chat Responses | 1M | 128K | $5.1 | $25.5 | Jun 7, 2026 |
Claude Fable 5.1 anthropic/claude-fable-5-1Anthropic | Text | Messages Chat Responses | 1M | 128K | $6 | $30 | Sep 1, 2026 |
Claude Fable 5.2 anthropic/claude-fable-5-2Anthropic | Text | Messages Chat Responses | 1M | 128K | $5.1 | $25.7 | Nov 9, 2026 |
Claude Haiku 4.5 anthropic/claude-haiku-4-5Anthropic | Text | Messages Chat Responses | 200K | 64K | $0.6 | $3 | Oct 15, 2025 |
Claude Opus 4.5 anthropic/claude-opus-4-5-20251101Anthropic | Text | Messages Chat | 200K | 64K | $2.6 | $12.8 | Nov 24, 2025 |
Claude Opus 4.6 anthropic/claude-opus-4-6Anthropic | Text | Messages Chat Responses | 1M | 128K | $2.6 | $12.8 | Feb 4, 2026 |
Claude Opus 4.7 anthropic/claude-opus-4-7Anthropic | Text | Messages Chat Responses | 1M | 128K | $2.6 | $12.8 | Apr 14, 2026 |
Claude Opus 5.5 anthropic/claude-opus-5-5Anthropic | Text | Messages Chat Responses | 1M | 128K | $2.2 | $11 | Sep 22, 2026 |
Claude Opus 5 anthropic/claude-opus-5Anthropic | Text | Messages Chat Responses | 1M | 128K | $2.6 | $12.8 | Jul 24, 2026 |
Claude Sonnet 5.5 anthropic/claude-sonnet-5-5Anthropic | Text | Messages Chat Responses | 1M | 128K | $1.1 | $5.5 | Sep 28, 2026 |
Claude Sonnet 4.5 anthropic/claude-sonnet-4-5-20250929Anthropic | Text | Messages Chat | 200K | 64K | $1.5 | $7.7 | Sep 29, 2025 |
Claude Sonnet 4.6 anthropic/claude-sonnet-4-6Anthropic | Text | Messages Chat Responses | 1M | 128K | $1.5 | $7.7 | Feb 17, 2026 |
Gemini 3 Flash Preview google/gemini-3-flash-previewGoogle | Text | Chat Responses | 1M | 65.5K | $0.3 | $1.5 | Dec 17, 2025 |
Gemini 3.1 Flash Lite google/gemini-3.1-flash-liteGoogle | Text | Chat | 1M | 65.5K | $0.2 | $0.9 | May 7, 2026 |
Gemini 4 Carbon google/gemini-4-carbonGoogle | Text | Chat Responses | 1M | 32.8K | $1.1 | $5.5 | Nov 10, 2026 |
Gemini 3.1 Pro Low google/gemini-3.1-pro-lowGoogle | Text | Chat | 1M | 65.5K | $1.1 | $6.6 | Feb 19, 2026 |
Gemini 4 Argon google/gemini-4-argonGoogle | Text | Chat Responses | 1M | 32.8K | $1.1 | $5.5 | Oct 13, 2026 |
Gemini 3.6 Flash High google/gemini-3.6-flash-highGoogle | Text | Chat | 1M | 65.5K | $0.4 | $1.9 | Jul 21, 2026 |
Gemini 3.7 Flash High google/gemini-3.7-flash-highGoogle | Text | Chat | 1M | 65.5K | $0.4 | $1.9 | Aug 13, 2026 |
Gemini 3.8 Flash High google/gemini-3.8-flash-highGoogle | Text | Chat | 1M | 65.5K | $0.5 | $2.3 | Sep 2, 2026 |
Codex Auto Review openai/codex-auto-reviewOpenAI | Text | Chat Responses | 1.1M | 128K | $3 | $18 | — |
GPT-5.3 Codex Spark openai/gpt-5.3-codex-sparkOpenAI | Text | Chat | 128K | 32K | $0.9 | $7.1 | Feb 5, 2026 |
GPT-5.5 openai/gpt-5.5OpenAI | Text | Chat Responses | 1.1M | 128K | $2.6 | $15.3 | Apr 23, 2026 |
GPT-5.6 Luna openai/gpt-5.6-lunaOpenAI | Text | Chat Responses | 1.1M | 128K | $0.1 | $0.6 | Jul 9, 2026 |
GPT-5.6 Sol openai/gpt-5.6-solOpenAI | Text | Chat Responses | 1.1M | 128K | $2 | $10.2 | Jul 9, 2026 |
GPT-6.1 Sol openai/gpt-6.1-solOpenAI | Text | Chat Responses | 1.1M | 128K | $1.1 | $5.5 | Sep 29, 2026 |
GPT-6.1 Terra openai/gpt-6.1-terraOpenAI | Text | Chat Responses | 1.1M | 128K | $0.9 | $4.3 | Oct 26, 2026 |
GPT-6.2 Astra openai/gpt-6.2-astraOpenAI | Text | Chat Responses | 1.1M | 128K | $4.8 | $24 | Nov 17, 2026 |
GPT-6.2 Sol openai/gpt-6.2-solOpenAI | Text | Chat Responses | 1.1M | 128K | $1.1 | $5.5 | Nov 17, 2026 |
GPT-6 Astra openai/gpt-6-astraOpenAI | Text | Chat Responses | 1.1M | 128K | $6 | $30 | Sep 4, 2026 |
GPT-5.6 Terra openai/gpt-5.6-terraOpenAI | Text | Chat Responses | 1.1M | 128K | $1 | $6.1 | Jul 9, 2026 |
GPT-6 Sol openai/gpt-6-solOpenAI | Text | Chat Responses | 1.1M | 128K | $1.1 | $5.5 | Sep 22, 2026 |
GPT-6 Luna openai/gpt-6-lunaOpenAI | Text | Chat Responses | 1.1M | 128K | $0.06 | $0.3 | Sep 22, 2026 |
Grok 4.5 xai/grok-4.5xAI | Text | Chat Responses | 500K | 500K | $1 | $3.1 | Jul 8, 2026 |
Grok 4.6 xai/grok-4.6xAI | Text | Chat Responses | 500K | 500K | $1 | $3.1 | Aug 12, 2026 |
Grok 4.7 xai/grok-4.7xAI | Text | Chat Responses | 500K | 500K | $1.1 | $3.3 | Sep 21, 2026 |
GLM-5.2 zai/glm-5.2Zhipu | Text | Chat Responses | 1M | 131.1K | $0.7 | $2.2 | Jun 13, 2026 |
GLM-5.3 zai/glm-5.3Zhipu | Text | Chat Responses | 1M | 131.1K | $0.8 | $2.6 | Aug 14, 2026 |
GLM-5.3 Raw zai/glm-5.3-rawZhipu | Text | Chat | 1M | 131.1K | $3 | $8.4 | Sep 14, 2026 |
Claude Haiku 5.5 anthropic/claude-haiku-5-5Anthropic | Text | Messages Chat | 1M | 128K | $0.06 | $0.3 | Oct 7, 2026 |
Mistral Large 4 mistral-large-4Mistral AI | Text | Chat | 1M | 262.1K | $0.8 | $2.4 | Oct 6, 2026 |
Mistral Medium 3.5 mistral-medium-3-5Mistral AI | Text | Chat | 262.1K | 209.7K | $1.7 | $8.7 | Apr 30, 2026 |
Mistral Small 4 mistral-small-4Mistral AI | Text | Chat | 262.1K | 209.7K | $0.2 | $0.8 | Mar 16, 2026 |
Devstral 2 devstral-2Mistral AI | Text | Chat | 262.1K | 209.7K | $0.5 | $2.3 | Dec 9, 2025 |
DeepSeek V4.1 Flash deepseek-v4-1-flashDeepSeek | Text | Chat | 1M | 393.2K | $0.1 | $0.5 | Sep 10, 2026 |
DeepSeek V4 Pro 0813 deepseek-v4-pro-0813DeepSeek | Text | Chat | 1M | 393.2K | $0.5 | $1.6 | Aug 12, 2026 |
DeepSeek V4 Flash deepseek-v4-flashDeepSeek | Text | Chat | 1M | 943.7K | $0.07 | $0.1 | Apr 24, 2026 |
Qwen3.8 Max 0902 qwen3-8-max-0902Qwen | Text | Chat | 1M | 131.1K | $2.3 | $7 | Sep 3, 2026 |
Qwen3.8 Max Preview qwen3-8-max-previewQwen | Text | Chat | 1M | 131.1K | $2.3 | $7 | Jul 19, 2026 |
Qwen3.7 Max qwen3-7-maxQwen | Text | Chat | 1M | 131.1K | $1.7 | $5.1 | May 21, 2026 |
Qwen3.8 Flash qwen3-8-flashQwen | Text | Chat | 1M | 131.1K | $0.2 | $0.5 | Aug 26, 2026 |
Qwen3.8 Omni Flash qwen3-8-omni-flashQwen | Text | Chat | 1M | 131.1K | $0.2 | $0.5 | Sep 21, 2026 |
Qwen Image 2.1 Pro qwen-image-2-1-proQwen | Images | Images | — | — | — | — | Oct 17, 2026 |
Qwen Image 2.1 Turbo qwen-image-2-1-turboQwen | Images | Images | — | — | — | — | Oct 17, 2026 |
Qwen Image 3 qwen-image-3Qwen | Images | Images | — | — | — | — | Aug 5, 2026 |
Qwen Image 3 Pro qwen-image-3-proQwen | Images | Images | — | — | — | — | Aug 5, 2026 |
Qwen3.8 27B qwen3-8-27bQwen | Text | Chat | 1M | 235.9K | $0.05 | $2.9 | Aug 14, 2026 |
Qwen3.8 27B Antislop qwen3-8-27b-antislopQwen | Text | Chat | 262.1K | 16.4K | $0.7 | $6 | Oct 3, 2026 |
Qwen3.7 Plus qwen3-7-plusQwen | Text | Chat | 1M | 131.1K | $0.4 | $1.5 | Jun 3, 2026 |
Qwen3 Coder Next qwen3-coder-nextQwen | Text | Chat | 262.1K | 235.9K | $0.1 | $0.9 | Feb 4, 2026 |
MiniMax M3 minimax-m3MiniMax | Text | Chat | 1M | 512K | $0.3 | $1.4 | May 31, 2026 |
MiniMax M2.7 minimax-m2-7MiniMax | Text | Chat | 204.8K | 176.9K | $0.3 | $1.4 | Mar 18, 2026 |
Kimi K2.7 Code kimi-k2-7-codeMoonshot AI | Text | Chat | 262.1K | 235.9K | $0.8 | $3.9 | Jun 12, 2026 |
Kimi K2.6 kimi-k2-6Moonshot AI | Text | Chat | 262.1K | 235.9K | $0.8 | $4 | Apr 20, 2026 |
GLM-5.3 FlashX glm-5-3-flashxZhipu | Text | Chat | 1M | 131.1K | $0.4 | $1.5 | Sep 18, 2026 |
MiMo V2.6 Pro mimo-v2-6-proXiaomi | Text | Chat | 1.1M | 131.1K | $0.5 | $1 | Sep 21, 2026 |
MiMo V2.6 Flash mimo-v2-6-flashXiaomi | Text | Chat | 1.1M | 131.1K | $0.2 | $0.3 | Sep 21, 2026 |
Step 5 Preview step-5-previewStepFun | Text | Chat | 1M | 64K | $1.2 | $3.1 | Oct 8, 2026 |
Step 3.7 Flash step-3-7-flashStepFun | Text | Chat | 262.1K | 230.4K | $0.2 | $1.3 | May 28, 2026 |
Muse Glimmer 30B muse-glimmer-30bMeta | Text | Chat | 131.1K | 16.4K | $0.3 | $1.4 | Aug 9, 2026 |
Nemotron 3 Ultra nemotron-3-ultraNVIDIA | Text | Chat | 262.1K | 182.5K | $0.7 | $2.8 | Jun 4, 2026 |
Nemotron 3 Super nemotron-3-superNVIDIA | Text | Chat | 262.1K | 235.9K | $0.09 | $0.5 | Mar 11, 2026 |
Seed 2.1 Turbo seed-2-1-turboByteDance Seed | Text | Chat | 262.1K | 235.9K | $0.6 | $2.9 | Aug 12, 2026 |
Seed 2.0 Code seed-2-0-codeByteDance Seed | Text | Chat | 262.1K | 131.1K | $0.6 | $3.5 | Aug 12, 2026 |
Hy4 Preview hy4-previewTencent | Text | Chat | 1M | 64K | $1 | $2.9 | Aug 28, 2026 |
Command A+ command-a-plusCohere | Text | Chat | 192K | 64K | $0.3 | $1.7 | Sep 22, 2026 |
Inkling inklingThinking Machines | Text | Chat | 524.3K | 471.9K | $1.2 | $4.7 | Jul 17, 2026 |
LongCat 2.0 longcat-2-0Meituan | Text | Chat | 1M | 262.1K | $0.3 | $1.4 | Jul 20, 2026 |
Nova 2 Lite nova-2-liteAmazon | Text | Chat | 1M | 65.5K | $0.3 | $2.9 | Dec 2, 2025 |
Solar Pro 4 solar-pro-4Upstage | Text | Chat | 524.3K | 131.1K | $0.1 | $0.4 | Aug 10, 2026 |
Aion 3.5 aion-3-5AionLabs | Text | Chat | 262.1K | 32.8K | $3.5 | $7 | Sep 23, 2026 |
Mercury 2.5 mercury-2-5Inception | Text | Chat | 260K | 65.5K | $0.05 | $0.2 | Sep 8, 2026 |
Llama 4 Maverick llama-4-maverickMeta | Text | Chat | 1M | 16.4K | $0.2 | $0.8 | Apr 5, 2025 |
Granite 4.2 8B granite-4-2-8bIBM | Text | Chat | 131.1K | 118K | $0.07 | $0.3 | Aug 31, 2026 |
GPT Image 2.5 openai/gpt-image-2.5OpenAI | Images | Images | — | — | — | — | — |
Clef clefCloudflare | Decisions | System One | 65.5K | — | $0.05 | — | Oct 1, 2026 |
Clef Flash clef-flashCloudflare | Decisions | System One | 24.6K | — | $0.05 | — | Oct 1, 2026 |
Clef Omni clef-omniCloudflare | Decisions | System One | 65.5K | — | $0.2 | — | Oct 9, 2026 |
D1 liquid-d1Liquid AI | Decisions | System One | 65.5K | — | $0.02 | — | Oct 1, 2026 |
D1 Ultra liquid-d1-ultraLiquid AI | Decisions | System One | 32.8K | — | $0.05 | — | Oct 15, 2026 |
Jev 1.13 jev-1-13TypeSafe | Decisions | System One | 262.1K | — | $0.05 | — | Sep 18, 2026 |
Jev 1.14 jev-1-14TypeSafe | Decisions | System One | 262.1K | — | $0.05 | — | Oct 14, 2026 |
Microsoft-Decision-1 microsoft-decision-1Microsoft | Decisions | System One | 32.8K | — | $0.05 | — | Oct 9, 2026 |
Solar Decide solar-decideUpstage | Decisions | System One | 524.3K | — | $0.06 | — | Sep 28, 2026 |
Solar Decide Flash solar-decide-flashUpstage | Decisions | System One | 524.3K | — | $0.06 | — | Oct 8, 2026 |
Span-01 span-01Respan | Decisions | System One | — | — | $0.02 | — | Sep 26, 2026 |
Span-02 span-02Respan | Decisions | System One | 131.1K | — | $0.01 | — | Oct 16, 2026 |
Decider V1.2 pplx-decider-v1-2Perplexity | Decisions | System One | 262.1K | — | $0.02 | — | Oct 16, 2026 |
Decider Flash V1.2 pplx-decider-flash-v1-2Perplexity | Decisions | System One | 262.1K | — | $0.01 | — | Oct 16, 2026 |
Drex v1.5 drex-v1-5Nace.AI | Decisions | System One | 131.1K | — | $0.05 | — | Oct 9, 2026 |
Drex v2.0 drex-v2-0Nace.AI | Decisions | System One | 131.1K | — | $0.07 | — | Oct 12, 2026 |
Classify-1 classify-1ScaleDown | Decisions | System One | 1M | — | $0.05 | — | Oct 13, 2026 |
Mercury Decide mercury-decideInception | Decisions | System One | 65.5K | — | $0.02 | — | Sep 30, 2026 |
Tev1 4B Experimental tev1-4b-experimentalTogether AI | Decisions | System One | 32.8K | — | $0.05 | — | Sep 30, 2026 |
Kev 4B kev-4bJared Palmer | Decisions | System One | 8.2K | — | $0.05 | — | Sep 25, 2026 |
GPT Image 1.5 openai/gpt-image-1.5OpenAI | Images | Images | — | — | — | — | Nov 25, 2025 |
GPT Image 1 openai/gpt-image-1OpenAI | Images | Images | — | — | — | — | Apr 24, 2025 |
GPT Image 2.5 Flare openai/gpt-image-2.5-flareOpenAI | Images | Images | — | — | — | — | — |
GPT Image 2.5 Sunburst openai/gpt-image-2.5-sunburstOpenAI | Images | Images | — | — | — | — | — |
Grok Imagine Lite xai/grok-imagine-image-litexAI | Images | Images | — | — | — | — | — |
OpenJev openjevRawModels | Decisions | System One | 32.8K | — | $0.05 | — | — |
OpenJev Small openjev-smallRawModels | Decisions | System One | 32.8K | — | $0.03 | — | — |
GPT Image 2.6 Sunburst openai/gpt-image-2.6-sunburstOpenAI | Images | Images | — | — | — | — | — |
How to name a model
A request names the model as a string in the model member. Either the canonical name or any alias that leads to the same model will do.
- A canonical name belongs to one model and to no other.
- An alias is a second name for the same model. At any moment an alias leads to exactly one model; over time it can be pointed elsewhere, and that is the whole point of it — code that names an alias moves with it.
- Canonical names and aliases live in one namespace: the same string cannot be both, and cannot belong to two models.
A name no live model answers to is refused straight away — the platform says plainly that it has no such model instead of guessing at one.
A key may carry a scope. If that scope lists models, the key may name only those: a scope is a whitelist, not a preference. A call that names something outside the list is refused rather than routed.
What the platform records about a key →
How to read the capabilities
Capabilities are not declared for a model in general. They are declared for each pair of a protocol and a modality, so one model can do more on one protocol than on another.
Protocols
chat_completionsThe OpenAI-shaped conversational operation: messages in, `choices` out.responsesThe second operation of that ecosystem, with a request and answer shape of its own.anthropic_messagesThe Anthropic-native shape, understood by clients and SDKs written against that API.embeddingsVectors for text.imagesImage generation.Modalities
A modality is the kind of work rather than the shape of the request: text_generation, embeddings, image_generation. The protocol says how you ask; the modality says what you get. A key's scope restricts modalities, which is why the pair of them decides whether a call is allowed at all.
The three states
Every capability — streaming, tools, structured output, strict semantics, streaming of structured output — stands in one of three states.
| State | What it means | What the gateway does |
|---|---|---|
| Proven | The platform checked it on a real supplier channel. | The call goes upstream. |
| Not proven | The platform has not checked it. Not "it fails", but "we have not proven it". | A request that needs the capability is refused before the supplier is contacted. |
| Unsupported | The capability is not there. | Such a request is refused in the same way. |
The difference between "not proven" and "unsupported" is in where it comes from, not in what you see: both are refused alike and refused early. The refusal happens without reaching the supplier and does not change if you repeat the same request — if you need a capability, pick a model that has it proven.
Structured output carries a mode as well: json_object (the answer must be a JSON object) or json_schema (the answer must match your schema); none means there is no mode at all.
How a response schema is stated → Tools →
The model page
Every model in the catalog has a page of its own at /models/<canonical name>. It collects what you would otherwise assemble from several sources:
- the figures: context window, output ceiling and release date;
- a quickstart with this model's identifier already substituted — copy the code as it stands;
- a capability matrix per protocol: what is proven and what is not;
- the wallet's prices per dimension;
- links onward to the integration pages with that model chosen.
The catalogue table above leads to these pages, and the documentation search indexes them.
How to choose a model
The catalog answers "what is available"; the choosing is yours. An order that saves time:
- Filter by protocolKeep the models that speak the protocol your client speaks. Changing the client costs more than changing the model.
- Check the capabilitiesIf you need tools, streaming or a strict response schema, the capability has to be proven rather than merely mentioned.
- Compare the volumesThe context window decides how much you can send, the output ceiling how much you can get back. They are two independent figures.
- Work out the priceRates are published per million tokens, separately for input and for output, so no single number compares two models.
- Check measured performanceThe model card shows request latency, generation speed and availability over the last 24 hours. Missing measurements are not a zero delay or perfect availability.
- Note the release dateIt is the day the maker released the model, so it tells you the model's generation, not when it was added here.
Do not choose based on a single request. Take a dozen of your real tasks, run two or three candidates over them, and compare the answers and the spend — the catalog gives you a shortlist, your own run decides.




