Synthetic Claude Code wrapper (defaults to K3 as the model)

A developer created a shell wrapper called 'synclaude' that routes Claude Code's interface through Synthetic's API, allowing users to run open models like Kimi K3, GLM 5.2, and MiniMax M3 while keeping Claude Code's agent and tool features. The wrapper validates models against Synthetic's live catalogue and ensures all model slots use the chosen model.

A shell wrapper that points Claude Code https://claude.com/claude-code at Synthetic https://synthetic.new , so you keep the Claude Code interface — agents, tools, subagents, slash commands — while inference runs on open models like Kimi K3, GLM 5.2 and MiniMax M3. It is one function plus three helpers. Paste the block below into your shell rc and you are done. - Picks a model per run with a substring: --model k3 , --model glm-5.2 - Validates the model against Synthetic's live catalogue, so a typo fails immediately with the real options instead of silently doing the wrong thing - Points every model slot at your choice — main, opus, sonnet, haiku and subagents — so delegated work does not quietly fall back to something else - Leaks nothing into your shell: every variable is scoped to the child process | Tool | Why | |---|---| claude | the CLI itself — npm i -g @anthropic-ai/claude-code | curl | fetches the model catalogue | jq | parses it — brew install jq | awk , sed , find | matching and caching already on macOS/Linux | Shell: bash 3.2+ or zsh . It uses arrays, so it is not POSIX sh . A Synthetic API key: https://synthetic.new https://synthetic.new → Settings → API Keys . Add your key and the function to ~/.zshrc or ~/.bashrc : export SYNTHETIC API KEY="syn xxxxxxxxxxxxxxxx" Then paste this block: ── synclaude ──────────────────────────────────────────────────────────────── Run Claude Code against Synthetic https://synthetic.new . Works in bash 3.2+ and zsh. Requires: claude, curl, jq, awk. Fetches the model catalogue, cached for six hours under TMPDIR. Pass any argument to force a refetch. synclaude models { local cache="${TMPDIR:-/tmp}/synclaude-models-$ id -u .json" if -n "${1:-}" || -s "$cache" || -n "$ find "$cache" -mmin +360 2 /dev/null " ; then if curl -fsS -m 20 https://api.synthetic.new/v1/models \ -H "Authorization: Bearer ${SYNTHETIC API KEY:-}" -o "$cache.tmp" 2 /dev/null; then mv -f "$cache.tmp" "$cache" else rm -f "$cache.tmp" A stale cache still beats failing outright when the network is down. -s "$cache" || return 1 fi fi jq -r '.data ?.id' "$cache" 2 /dev/null | sort } Turns a shorthand into exactly one model id, e.g. k3 - hf:moonshotai/Kimi-K3. An exact id wins over a substring, without which a model whose name is a prefix of another could never be selected. Ambiguous or unknown input fails with the real options rather than guessing. awk, not grep: a GREP OPTIONS containing -n in the environment prefixes line numbers onto every match and corrupts the resolved id. synclaude resolve model { local query="$1" ids matches if command -v jq /dev/null 2 &1; then printf &2 "synclaude: --model needs 'jq' to read the catalogue brew install jq \n" return 1 fi if ids="$ synclaude models "; then printf &2 'synclaude: could not fetch the catalogue from api.synthetic.new\n' return 1 fi if "$query" = "--list" ; then printf '%s\n' "$ids" return 0 fi matches="$ printf '%s\n' "$ids" | awk -v q="$query" '$0 == q' " -z "$matches" && matches="$ printf '%s\n' "$ids" | awk -v q="$query" 'BEGIN{q=tolower q } index tolower $0 , q ' " A model published since the cache was written: refetch once before failing. if -z "$matches" ; then ids="$ synclaude models force " || : matches="$ printf '%s\n' "$ids" | awk -v q="$query" 'BEGIN{q=tolower q } index tolower $0 , q ' " fi if -z "$matches" ; then printf &2 "synclaude: no model matches '%s'. Available:\n" "$query" printf '%s\n' "$ids" | sed 's/^/ /' &2 return 1 fi if "$ printf '%s\n' "$matches" | awk 'END{print NR}' " -gt 1 ; then printf &2 "synclaude: '%s' is ambiguous, it matches:\n" "$query" printf '%s\n' "$matches" | sed 's/^/ /' &2 return 1 fi printf '%s\n' "$matches" } synclaude help { cat <<HELP synclaude - Claude Code against Synthetic Usage: synclaude --model <id|substring --thinking|--no-thinking claude args ... synclaude --help Options: --model <m Override every model for this run - main, opus, sonnet, haiku and subagent all become <m . Takes a full model id or any case-insensitive substring that matches exactly one. --no-thinking Turn extended thinking off the default here, see below . --thinking Turn extended thinking back on. -h, --help Show this message. Claude's own help is 'claude --help'. Everything else is passed to claude untouched. Current configuration: credential SYNTHETIC API KEY endpoint ${SYNTHETIC BASE URL:-https://api.synthetic.new/anthropic} model ${SYNTHETIC MODEL:-hf:moonshotai/Kimi-K3} thinking ${SYNTHETIC THINKING:-off} HELP printf '\nAvailable models:\n' synclaude resolve model --list 2 /dev/null | sed 's/^/ /' } synclaude { local model="${SYNTHETIC MODEL:-hf:moonshotai/Kimi-K3}" local base url="${SYNTHETIC BASE URL:-https://api.synthetic.new/anthropic}" Off by default because the default model requires it - see the notes below. local thinking="${SYNTHETIC THINKING:-off}" local requested model="" local -a args args= while $ -gt 0 ; do case "$1" in -h|--help synclaude help; return 0 ;; --no-thinking thinking=off; shift ;; --thinking thinking=on; shift ;; --model if -z "${2:-}" ; then printf &2 'synclaude: --model needs a value try: synclaude --help \n' return 2 fi requested model="$2"; shift 2 ;; --model= requested model="${1 --model=}"; shift ;; args+= "$1" ; shift ;; esac done if -z "${SYNTHETIC API KEY:-}" ; then printf &2 'synclaude: SYNTHETIC API KEY is not set\n' return 1 fi if command -v claude /dev/null 2 &1; then printf &2 "synclaude: 'claude' not found in PATH. Install: npm i -g @anthropic-ai/claude-code\n" return 127 fi if -n "$requested model" ; then model="$ synclaude resolve model "$requested model" " || return 1 fi Claude Code reads any non-empty value as "on", so "off" means empty. local disable thinking=1 "$thinking" = "on" && disable thinking= printf &2 'synclaude: endpoint=%s | model=%s | thinking=%s\n' "$base url" "$model" "$thinking" env 1 keeps all of this scoped to the child process, and reaches the real binary rather than this function. env \ ANTHROPIC BASE URL="$base url" \ ANTHROPIC AUTH TOKEN="$SYNTHETIC API KEY" \ ANTHROPIC API KEY= \ ANTHROPIC MODEL="$model" \ ANTHROPIC DEFAULT OPUS MODEL="$model" \ ANTHROPIC DEFAULT SONNET MODEL="$model" \ ANTHROPIC DEFAULT HAIKU MODEL="$model" \ CLAUDE CODE SUBAGENT MODEL="$model" \ CLAUDE CODE DISABLE THINKING="$disable thinking" \ CLAUDE CODE DISABLE NONESSENTIAL TRAFFIC=1 \ CLAUDE CODE ATTRIBUTION HEADER=0 \ CLAUDE CODE MAX OUTPUT TOKENS="${CLAUDE CODE MAX OUTPUT TOKENS:-32000}" \ MAX THINKING TOKENS="${MAX THINKING TOKENS:-100000}" \ IS DEMO="${IS DEMO-true}" \ claude ${args @ +"${args @ }"} } Reload with exec $SHELL -l , then run synclaude --help . synclaude interactive, default model synclaude -p "explain this repo" one-shot synclaude --model glm-5.2 --thinking switch model, thinking on synclaude --model k2.7 substring is enough synclaude --help options + live model list --model accepts any case-insensitive substring that matches exactly one catalogue entry. Everything the wrapper does not recognise is forwarded to claude untouched, so --resume , --output-format json , --verbose and the rest all work as usual. bash $ synclaude --model glm synclaude: 'glm' is ambiguous, it matches: hf:zai-org/GLM-4.7-Flash hf:zai-org/GLM-5.2 Thinking is off by default , and that is not an arbitrary choice. Claude Code sends a reasoning effort of medium to third-party models. Some models do not accept that value. Kimi K3 advertises only 'high','low','max' , so with thinking on every request fails : API Error: 500 {"error":"Error from inference backend: 500 Unsupported thinking effort='medium'; supported values are 'high','low','max' ."} There is currently no way to change the value Claude Code sends. --effort its own CLI flag , CLAUDE CODE EFFORT LEVEL , CLAUDE CODE ALWAYS ENABLE EFFORT and CLAUDE CODE DISABLE ADAPTIVE THINKING were each tested against this endpoint and the error came back identical, still naming medium . Synthetic's catalogue does not publish per-model effort levels either, so the wrapper cannot map them for you. Turning thinking off avoids the rejected parameter entirely, which is why it is the default here. The trade-off is real: you lose extended reasoning. On a model that accepts medium , turn it back on: synclaude --model glm-5.2 --thinking If you would rather default to a model that thinks, set SYNTHETIC MODEL=hf:zai-org/GLM-5.2 and SYNTHETIC THINKING=on . All optional except the key. | Variable | Default | Purpose | |---|---|---| SYNTHETIC API KEY | — | Required. Your Synthetic key | SYNTHETIC MODEL | hf:moonshotai/Kimi-K3 | Default model | SYNTHETIC THINKING | off | on to default extended thinking on | SYNTHETIC BASE URL | https://api.synthetic.new/anthropic | Endpoint | CLAUDE CODE MAX OUTPUT TOKENS | 32000 | Max output tokens | MAX THINKING TOKENS | 100000 | Thinking budget when thinking is on | IS DEMO | true | Trims the startup banner. IS DEMO= synclaude restores it | Two details worth knowing: hides the "Tips for getting started" and "What's new" panels and your account/org line. Claude Code treats IS DEMO any non-empty value as on — including 0 and false — so the only way back to the full banner is an empty one: IS DEMO= synclaude .on every run so a real Anthropic key sitting in your environment cannot outrank the Synthetic token. ANTHROPIC API KEY is blanked SYNTHETIC API KEY is not set — export it, then reload your shell. no model matches '...' — the error lists every available id. The catalogue is cached for six hours; to force a refresh: rm -f "${TMPDIR:-/tmp}/synclaude-models-$ id -u .json" Unsupported thinking effort='medium' — that model rejects the effort level Claude Code sends. Drop --thinking , or pick another model. Model ids change. Synthetic rotates them without notice — Kimi-K2.5 was a working default until it began returning 404. That is exactly why this wrapper reads the catalogue from the API rather than hardcoding a list. Run synclaude --help to see what is live right now. Tested on macOS with Claude Code 2.1.220 in both bash and zsh — including pristine shells with no rc files — covering the default model, --model overrides, ambiguous and unknown input, missing key and missing binary, and live end-to-end runs against the real API on Kimi K3 and GLM 5.2. Public domain / CC0. Use it however you like.