available the model ID is deprecated

Not specified by the original author.

TL;DR

'Invalid parameter: model mixtral-8x7b-32768 is not available' means the model was deprecated. Known swaps: mixtral-8x7b-32768 to llama-3.1-8b-instant or llama-3.3-70b-versatile, gemma2-9b-it to llama-3.1-8b-instant, llama-3.1-70b-versatile to llama-3.3-70b-versatile.

Fix

1. 'Invalid parameter: model mixtral-8x7b-32768 is not available' means the model was deprecated. Expected: You get the expected result; the problem is gone.

When to use

• You are setting up or using this Groq 400 'model is not available' feature.
• The symptom matches: the model ID is deprecated.

When NOT to use

• Unrelated Groq 400 'model is not available' issues (different feature, different failure).
• You need general documentation for the tool; check the official docs instead.

Compatibility

Reported against Groq 400 'model is not available' (mentions 3.1, 3.3).

Variant phrasings

the model ID is deprecated

Why it happens

Groq retires model IDs aggressively. A 400 naming the model means the ID is dead, not your code.

Edge cases

• If your error message differs even slightly, this is probably a different issue; search the exact text.
• Behavior can change between releases; the linked source reflects the versions above.
• If the fix does not help, capture the full error output and check the source link for updates.

Source: Groq retires model IDs aggressively. A 400 naming the model means the ID is dead, not your code.

Verified resolution: [groq-common-errors skill]: 'Invalid parameter: model mixtral-8x7b-32768 is not available' means the model was deprecated. Known swaps: mixtral-8x7b-32768 to llama-3.1-8b-instant or llama-3.3-70b-versatile, gemma2-9b-it to llama-3.1-8b-instant, llama-3.1-70b-versatile to llama-3.3-70b-versatile. Check the live list at console.groq.com/docs/models or call GET /openai/v1/models before pinning an ID in config.

Source URL: https://github.com/funxgao/claude-code-plugins-plus-skills/blob/HEAD/plugins/saas-packs/groq-pack/skills/groq-common-errors/SKILL.md

Not specified by the original author.

TL;DR: A retired model is not available for use. Requests to it fail. Migrate deprecated models before the retirement date. Test the replacement on your tasks well before the deadline; newer generations can behave differently enough to need prompt or eval updates.

Retirement is a hard failure, not a warning

Lifecycle states: active, deprecated (functional, not recommended, has a retirement date and a recommended replacement), retired (requests fail).

What to do

1. Watch the model deprecations page for every model ID you call. Anthropic gives at least 60 days notice before retiring publicly released models, and notifies customers with active deployments.
2. Migrate deprecated models before the retirement date. Test the replacement on your tasks well before the deadline; newer generations can behave differently enough to need prompt or eval updates.
3. Audit usage: the Console offers an API usage audit to find where deprecated models are still being called. Run it after every deprecation announcement.
4. Remember partner platforms set their own schedules. A model can be alive on the Claude API and retired on Bedrock or Google Cloud, or vice versa. Check the lifecycle on the platform you actually call.
5. Deprecated models are documented as likely less reliable than active ones. Move workloads to active models for the highest level of support.

The trap

Hardcoding a model ID and forgetting it. The 60-day notice only helps if someone is watching; otherwise the first symptom is a wave of failures on retirement day. The other trap: assuming one retirement schedule everywhere. Your Bedrock deployment has its own dates.

Checklist

• Keep a registry of every model ID in every config, with its retirement date. Review it monthly.
• When a deprecation is announced, the migration is the task. "Still works today" is not a plan.

When to use this

• You are seeing this exact error message; match the block above, not just part of it.
• The failing call matches the scenario in the title: Anthropic model retirement.
• You want the fastest verified fix before digging through logs.

When not to use this

• Your error text differs from the block above; close cousins often have different causes.
• The stack trace points at a different component than the one in the title.
• You already applied this fix and the error persists; look for a second cause instead of reapplying.

Compatibility

• Not pinned to a specific version; follows current Anthropic behavior.

Anthropic's deprecations page documents the active/deprecated/retired states, that requests to retired models fail, 60-day minimum notice, the usage audit, and that Bedrock/Google Cloud set their own retirement schedules. Verified live at https://platform.claude.com/docs/en/about-claude/model-deprecations.

Not specified by the original author.

Parallel /v1/search: searchqueries is required (max 5), sessionid groups search plus extract

TL;DR

Context: Parallel Search quickstart docs plus Parallel's official agent-skill reference: /v1/search requires both objective and searchqueries. searchqueries is an array of keyword probes: max 5 queries, 200 characters per query, docs recommend 2-3 diverse queries of 3-6 words. objective has a 5,000-character maximum.

Use this when you run into the situation in the title.

When not to use this skill: unrelated tasks. It covers only the procedure above.

Compatibility

The steps above apply to the commands named in them. This skill does not pin a version, so if a flag looks different on your machine, check your installed version's docs first.

Parallel /v1/search request contract: the required fields agents forget New integrations use /v1/search (v1beta is legacy). The request contract has sharp edges: - search_queries is required, not optional. Max 5 queries, 200 characters each. The docs recommend 2-3 diverse queries of 3-6 words each: one vague mega-query returns mush. - objective is the natural-language research goal, up to 5,000 characters. Put context, soft source preference, and freshness preference here. - session_id (up to 1,000 chars) is the cross-API grouping key - reuse the same id across Search and Extract calls for one logical task, and the server treats them as one unit. If you omit it, the server returns one; pass it back on follow-ups. - client_model names the model consuming the results so the API can tune excerpt sizing and format for it. - Auth is the x-api-key header. Not Authorization: Bearer. Every first-integration 401 is this. Send flat top-level fields the API actually wants: objective, searchqueries, mode, then advancedsettings for maxresults, sourcepolicy, fetch_policy. Read the warnings array on every response; the API tells you when it reduced or ignored something.

Context: Parallel Search quickstart docs plus Parallel's official agent-skill reference: /v1/search requires both objective and searchqueries. searchqueries is an array of keyword probes: max 5 queries, 200 characters per query, docs recommend 2-3 diverse queries of 3-6 words. objective has a 5,000-character maximum. sessionid (up to 1,000 chars) can be reused across Search API and Extract API calls for one logical task; the server returns one if omitted. clientmodel identifies the consuming model to tune defaults. Auth uses x-api-key header, not Authorization Bearer.

Source: Parallel Search quickstart docs plus Parallel's official agent-skill reference: /v1/search requires both objective and searchqueries. searchqueries is an array of keyword probes: max 5 queries, 200 characters per query, docs recommend 2-3 diverse queries of 3-6 words. objective has a 5,000-character maximum. sessionid (up to 1,000 chars) can be reused across Search API and Extract API calls for one logical task; the server returns one if omitted. clientmodel identifies the consuming model to tune defaults. Auth uses x-api-key header, not Authorization Bearer.

Verified resolution: # Parallel /v1/search request contract: the required fields agents forget New integrations use /v1/search (v1beta is legacy). The request contract has sharp edges: - search_queries is required, not optional. Max 5 queries, 200 characters each. The docs recommend 2-3 diverse queries of 3-6 words each: one vague mega-query returns mush. - objective is the natural-language research goal, up to 5,000 characters. Put context, soft source preference, and freshness preference here. - session_id (up to 1,000 chars) is the cross-API grouping key: reuse the same id across Search and Extract calls for one logical task, and the server treats them as one unit. If you omit it, the server returns one; pass it back on follow-ups. - client_model names the model consuming the results so the API can tune excerpt sizing and format for it. - Auth is the x-api-key header. Not Authorization: Bearer. Every first-integration 401 is this. Send flat top-level fields the API actually wants: objective, searchqueries, mode, then advancedsettings for maxresults, sourcepolicy, fetch_policy. Read the warnings array on every response; the API tells you when it reduced or ignored something.

Source URL: https://docs.parallel.ai/search/search-quickstart