agentleFS
0xatd0xatd/cheaptokens-skills/skills/venice-chat/SKILL.md

venice-chat

Skill2 starsChanged 5 months agoMITView on GitHub

Call POST /chat/completions on Venice. Covers the OpenAI-compatible request shape, Venice-only venice_parameters (web search, E2EE, characters, thinking control, X search), multimodal inputs (images/audio/video), tool calls, reasoning controls, streaming, prompt caching, structured output, and model feature suffixes.

  • Reads credentials

1 other project uses a version of this, 1 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 1 is distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    All optional. Combined with model feature suffixes, these are how you enable Venice features.

    line 61
  2. Very specific:

    Use venice_parameters.disable_thinking: true to skip thinking entirely on supported models.

    line 219
  3. Very specific:

    Prefer json_schema over the legacy json_object.

    line 236
  4. Very specific:

    Leave venice_parameters.enable_e2ee at default true, or set false to fall back to TEE-only.

    line 244
  5. Very specific:

    When enable_web_search is "auto" or "on", the response includes venice_parameters.web_search_citations[] where each entry has url, title, …

    line 260

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Venice Chat Completions

POST /api/v1/chat/completions is Venice's main text endpoint. It's OpenAI-compatible, plus a venice_parameters object for Venice-only features.

Use when

  • You need LLM text generation, with or without tools, with or without streaming.
  • You want multimodal inputs (images, audio, video) to a vision/audio-capable model.
  • You want Venice-specific features: web search, E2EE, characters, xAI X/Twitter search, strip-thinking, web scraping.
  • You need prompt caching for large system prompts or long documents.
  • You need structured (json_schema) output.

For the newer Alpha Responses API, see venice-responses.

Minimal request

curl https://api.venice.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $VENICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "zai-org-glm-5-1",
    "messages": [{"role": "user", "content": "Why is the sky blue?"}]
  }'

Response shape is the standard OpenAI chat.completion object (id, object: "chat.completion", choices[].message, usage). With stream: true, responses come as SSE data: lines in chat.completion.chunk format.

The request body

Core fields (OpenAI-compatible)

FieldNotes
modelstring — model ID, trait name, or compatibility mapping. Suffixes allowed (see below). Required.
messagesarray of system / developer / user / assistant / tool messages. Required, min 1.
temperature, top_p, top_k, min_p, min_temp, max_tempsampling controls
repetition_penalty, frequency_penalty, presence_penaltyrepetition controls
max_tokens (deprecated) / max_completion_tokensupper bound on output tokens
nnumber of choices (keep 1 to minimize cost)
seedinteger for reproducibility
stop / stop_token_idsup to 4 strings, or raw token IDs
stream, stream_options.include_usageSSE streaming + include usage in the final chunk
response_format{type:"json_schema", json_schema:{...}} (preferred), {type:"json_object"}, or {type:"text"}
tools, tool_choice, parallel_tool_callsfunction calling / built-in tools
logprobs, top_logprobsreturn token log-probabilities
reasoning.effort / reasoning_effortnone | minimal | low | medium | high | xhigh | max
reasoning.summaryauto | concise | detailed
prompt_cache_key, prompt_cache_retention (default/extended/24h)prompt caching hints
text.verbositylow/medium/high/auto
metadatakey/value strings for tracking
user, storeaccepted but ignored (OpenAI compat)

venice_parameters (Venice-only)

All optional. Combined with model feature suffixes, these are how you enable Venice features.

FieldTypeDefaultEffect
character_slugstring—Apply a published Venice character. Slug is the "Public ID" on the character page. See venice-characters.
strip_thinking_responseboolfalseStrip <think>...</think> from the assistant output on reasoning models.
disable_thinkingboolfalseDisable thinking entirely on supported reasoning models and strip tags.
enable_e2eebooltrueEnd-to-end encryption on E2EE-capable models when E2EE headers are present. Set to false to force TEE-only.
enable_web_search"off"/"auto"/"on""off"Venice server-side web search. Citations arrive in the first streamed chunk or the response.
enable_web_scrapingboolfalseScrape any URLs found in the last user message (Firecrawl).
enable_web_citationsboolfalseAsk the LLM to cite sources with ^1^ / ^1,3^ superscripts.
include_search_results_in_streamboolfalseExperimental — emit search results as the first stream chunk.
return_search_results_as_documentsbool—Also surface search results as a synthetic tool call venice_web_search_documents (LangChain-friendly).
include_venice_system_promptbooltruePrepend Venice's curated system prompt. Turn off for full control.
enable_x_searchboolfalsexAI native web + X/Twitter search (Grok models with supportsXSearch). Adds ~$0.01/search.

Model feature suffixes

Some venice_parameters can also be expressed as model feature suffixes on the model string — useful when the caller/library (OpenAI SDK, LangChain) can't set venice_parameters. Syntax:

<model-id>:<key>=<value>[&<key>=<value>…]

Values are URL-decoded. Supported keys (exact match):

KeyTypeMaps to
enable_web_searchon / off / autovenice_parameters.enable_web_search
enable_web_citations"true" / "false"venice_parameters.enable_web_citations
enable_web_scraping"true" / "false"venice_parameters.enable_web_scraping
include_venice_system_prompt"true" / "false"venice_parameters.include_venice_system_prompt
include_search_results_in_stream"true" / "false"venice_parameters.include_search_results_in_stream
return_search_results_as_documents"true" / "false"venice_parameters.return_search_results_as_documents
character_slugstringvenice_parameters.character_slug
strip_thinking_response"true" / "false"venice_parameters.strip_thinking_response
disable_thinking"true" / "false"venice_parameters.disable_thinking

Unknown keys are silently ignored. Examples:

zai-org-glm-5-1:enable_web_search=on
kimi-k2-6:strip_thinking_response=true&enable_web_search=auto
zai-org-glm-5-1:character_slug=alan-watts

Note: enable_e2ee and enable_x_search can only be set via venice_parameters, not as suffixes.

Messages and modalities

messages[].content is either a string or an array of typed parts. Roles: user, assistant, tool, system, developer (reasoning models like o-series / codex).

Text + image (image_url)

{
  "model": "zai-org-glm-5-1",
  "messages": [{
    "role": "user",
    "content": [
      {"type": "text", "text": "What's in this image?"},
      {"type": "image_url", "image_url": {"url": "https://example.com/cat.jpg"}}
    ]
  }]
}
  • url accepts a public URL or data:image/png;base64,....
  • Models with model_spec.capabilities.supportsMultipleImages: true preserve images across the whole conversation; single-image vision models only keep images from the last user message. Check model_spec.capabilities.maxImages for the per-request cap.

Audio input (input_audio)

{
  "role": "user",
  "content": [
    {"type": "text", "text": "Transcribe this clip."},
    {"type": "input_audio", "input_audio": {"data": "<base64>", "format": "wav"}}
  ]
}

Formats: wav, mp3, aiff, aac, ogg, flac, m4a, pcm16, pcm24. Audio URLs are not supported — always inline base64.

Video input (video_url)

{
  "role": "user",
  "content": [
    {"type": "text", "text": "Summarize this."},
    {"type": "video_url", "video_url": {"url": "https://www.youtube.com/watch?v=..."}}
  ]
}

Accepts public URLs (including YouTube for some providers) or data:video/mp4;base64,.... Supported formats: mp4, mpeg, mov, webm.

Prompt caching (cache_control)

Any text / image_url / input_audio / video_url part can carry:

{"cache_control": {"type": "ephemeral", "ttl": "1h"}}

Combine with prompt_cache_key and prompt_cache_retention: "24h" on the root request for predictable cache routing. Cache read / write pricing is model-specific — check model_spec.pricing on /models.

Tools & function calling

Function tools

{
  "tools": [{
    "type": "function",
    "function": {
      "name": "get_weather",
      "description": "Get current weather for a city",
      "parameters": {
        "type": "object",
        "properties": {"city": {"type": "string"}},
        "required": ["city"]
      },
      "strict": true
    }
  }],
  "tool_choice": "auto"
}
  • tool_choice can also be "required", "none", or {"type":"function","function":{"name":"get_weather"}}.
  • parallel_tool_calls: true (default) lets the model emit multiple calls at once.
  • Respond by appending {"role":"tool","tool_call_id":"...","content":"..."} before the next call.

Built-in tools

"tools": [{"type": "web_search"}, {"type": "x_search"}]

Equivalent to toggling venice_parameters.enable_web_search / enable_x_search. x_search requires a model with supportsXSearch.

Reasoning models

On thinking models (GLM 5.1, Kimi K2.6, Claude Opus 4.7, GPT-5.4 Pro, …):

{
  "model": "zai-org-glm-5-1",
  "reasoning": {"effort": "medium", "summary": "auto"},
  "venice_parameters": {"strip_thinking_response": false},
  "messages": [...]
}
  • reasoning_effort is the OpenAI-compatible flat variant (takes precedence over reasoning.effort).
  • Reasoning models may return reasoning_content or structured reasoning_details[] on the assistant message. Pass reasoning_details back verbatim in the next turn — it encodes thought signatures for providers like Claude Opus 4.7 and GPT-5.4 Pro.
  • Use venice_parameters.disable_thinking: true to skip thinking entirely on supported models.

Structured output (response_format)

{
  "response_format": {
    "type": "json_schema",
    "json_schema": {
      "type": "object",
      "properties": {"name": {"type": "string"}, "age": {"type": "number"}},
      "required": ["name", "age"]
    }
  }
}

Prefer json_schema over the legacy json_object. Plain text is the default ({"type": "text"}).

E2EE (end-to-end encryption)

For models advertising supportsE2EE:

  1. Perform an HPKE / Noise handshake with Venice (see docs.venice.ai/e2ee).
  2. Send encrypted payload with the required E2EE request headers.
  3. Leave venice_parameters.enable_e2ee at default true, or set false to fall back to TEE-only.

E2EE is not supported on /responses — use /chat/completions for encrypted inference.

Streaming

{"stream": true, "stream_options": {"include_usage": true}}
  • Response is text/event-stream. Each event is data: {...chunk...}\n\n, terminated by data: [DONE].
  • include_usage: true adds a final chunk with token counts.
  • With venice_parameters.include_search_results_in_stream: true, the first chunk carries venice_search_results.

Web-search answers

When enable_web_search is "auto" or "on", the response includes venice_parameters.web_search_citations[] where each entry has url, title, content (snippet), and date. Turn on enable_web_citations to have the model insert ^1^ superscripts inline.

Error handling specifics

  • 402 — insufficient balance. Bearer: INSUFFICIENT_BALANCE. x402: PAYMENT_REQUIRED with structured topUpInstructions and siwxChallenge.
  • 422 — prompt violates Venice or provider content policy. May include suggested_prompt.
  • 413 — payload too large (mostly vision/audio).
  • 429 — rate limit. See /api_keys/rate_limits and venice-errors.

Common gotchas

  • max_tokens is deprecated — prefer max_completion_tokens.
  • Image URLs must be publicly reachable from Venice's network. Localhost / signed S3 URLs without public access fail.
  • Audio inputs cannot be URLs — always base64.
  • Single-image vision models drop older images on each turn; chain them into the last user message.
  • For multi-turn with tools on Claude Opus 4.7, GPT-5.4 Pro, and similar, always round-trip reasoning_details unchanged.
  • parallel_tool_calls: true means you MUST be prepared to execute several tools in parallel before sending a single tool-role reply chain.
  • character_slug replaces the default Venice system prompt. Combine with include_venice_system_prompt: false for total control.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.