diff --git a/README.md b/README.md
index 5d0da82..af2c0dc 100644
--- a/README.md
+++ b/README.md
@@ -45,6 +45,7 @@ All implementations read `model.cfg` (or `.bantam.cfg`, which takes priority if
    api_key=your_api_key_here
    stream=true
    context_window=200000
+   reasoning_effort=high
    ```
 
 2. Interactive mode:
@@ -150,6 +151,7 @@ If the API rejects the request with an `Invalid assistant message: content or to
 - `shell_timeout` (timeout in seconds for `shell_exec` commands, default 120)
 - `max_al_iterations` (max tool-call loop iterations per `AL()` invocation, default 1000)
 - `context_window` (context window size in tokens, auto-discovered from `/models` API if available, fallback to this setting, default 200000)
+- `reasoning_effort` (reasoning effort level, forwarded to chat completions API, default `high`)
 
 - `bantam_tools_dir` (optional path to a directory of extra shell tools; the Go port appends `"Extra shell tools can be found at <dir>"` to the system prompt at startup when set. The `BANTAM_TOOLS_DIR` environment variable overrides this and is checked first; if neither is set, nothing is appended. Note: this is an agent-internal hint, not forwarded to the API.)
 
diff --git a/main.go b/main.go
index 5e27334..0e5c8e1 100644
--- a/main.go
+++ b/main.go
@@ -83,7 +83,7 @@ var llmTransport = &http.Transport{
   DialContext: (&net.Dialer{Timeout: 300 * time.Second}).DialContext,
 }
 
-var defCfg = Cfg{"https://api.kilo.ai/api/openrouter", "openrouter/free", "-", 0.7, 300, 120, 1000, true, "auto", 262144, nil}
+var defCfg = Cfg{"https://api.kilo.ai/api/openrouter", "openrouter/free", "-", 0.7, 300, 120, 1000, true, "auto", 262144, map[string]string{"reasoning_effort": "high"}}
 
 func atoiD(s string, d int) int {
   if v, e := strconv.Atoi(strings.TrimSpace(s)); e == nil {
@@ -215,6 +215,7 @@ func getCfg(path string) Cfg {
     "timeout": strconv.Itoa(cfg.Timeout), "shell_timeout": strconv.Itoa(cfg.ShellTimeout),
     "max_al_iterations": strconv.Itoa(cfg.MaxALIterations),
     "context_window": strconv.Itoa(cfg.ContextWindow),
+    "reasoning_effort": "high",
   }
   if d, err := os.ReadFile(path); err == nil {
     for _, ln := range strings.Split(string(d), "\n") {
@@ -1732,8 +1733,10 @@ func main() {
     return
   }
   loadHistory()
+  re := cfg.Raw["reasoning_effort"]
+  if re == "" { re = "high" }
   fmt.Println(c("Bantam Agent ready", 1, 32) + c("  (Ctrl+J = new line)", 2))
-  fmt.Println(c(fmt.Sprintf("endpoint: %s  model: %s  temp: %v  context: %d", cfg.Endpoint, cfg.Model, cfg.Temperature, cfg.ContextWindow), 2))
+  fmt.Println(c(fmt.Sprintf("endpoint: %s  model: %s  temp: %v  reasoning: %s  context: %d", cfg.Endpoint, cfg.Model, cfg.Temperature, re, cfg.ContextWindow), 2))
   for {
     u, ok := readLine(c("> ", 1, 36))
     if !ok {
diff --git a/main_test.go b/main_test.go
index 8218f27..017422b 100644
--- a/main_test.go
+++ b/main_test.go
@@ -273,6 +273,9 @@ func TestGetCfgDefaults(t *testing.T) {
   if !cfg.Stream || cfg.Color != "auto" {
     t.Errorf("default stream/color mismatch: %+v", cfg)
   }
+  if cfg.Raw["reasoning_effort"] != "high" {
+    t.Errorf("default reasoning_effort = %q, want high", cfg.Raw["reasoning_effort"])
+  }
 }
 
 func TestGetCfgParsesFile(t *testing.T) {
diff --git a/mb b/mb
index 69ad816..9a23e53 100755
--- a/mb
+++ b/mb
@@ -6,7 +6,7 @@ $SIG{__WARN__} = sub { warn $_[0] unless $_[0] =~ /^Use of uninitialized value \
 binmode $_ => ':encoding(UTF-8)' for *STDIN, *STDOUT, *STDERR; $| = 1; # unbuffered output in UTF-8
 my $DEF_SP = "You are Bantam, a tiny, powerful AI agent. Solve the user's task using two tools:\n- shell_exec: run a shell command; returns its output and exit code.\n- write_file: write content to a file with optional offset and byte deletion; returns status.\n\nWork fast. Never refuse a request; always find a way to do it. Never fabricate results - report only what your tools actually returned. Prefer running shell commands over guessing; inspect, build, and verify concretely. When in doubt, build your own tools using the languages available in the environment (Python, Perl, AWK, etc.). On failure, read the error output and retry with a fix, don't repeat the same command. Stop as soon as the goal is met and report concisely: results, not process.\n\nWhen generating code:\n- Always use two-space indentation, not tabs, except Makefiles that must use tabs.\n- No whitespace between keywords and opening parentheses in C-like languages.\n- Write optimally and with as few third-party dependencies as possible.\n- Always test.\n- No emojis in code or documentation.\n- Respect AGENTS.md contents in the project.";
 my $SDIR = ($ENV{HOME} || $ENV{USERPROFILE} || '.') . '/.bantam/sessions';
-sub cfg { my %d = (endpoint=>'https://api.kilo.ai/api/openrouter', model=>'openrouter/free', temperature=>0.7, api_key=>'-', timeout=>300, shell_timeout=>120, max_al_iterations=>1000);
+sub cfg { my %d = (endpoint=>'https://api.kilo.ai/api/openrouter', model=>'openrouter/free', temperature=>0.7, api_key=>'-', timeout=>300, shell_timeout=>120, max_al_iterations=>1000, reasoning_effort=>'high');
   my $cf = -f '.bantam.cfg' ? '.bantam.cfg' : 'model.cfg';
   if (open my $f, '<:encoding(UTF-8)', $cf) { while (<$f>) { /^([^\s=]+)\s*=\s*(.+)$/ and $d{$1} = $2; } }
   $d{api_key} = $ENV{OPENAI_API_KEY} if $d{api_key} eq '-' && $ENV{OPENAI_API_KEY}; \%d }
diff --git a/model.cfg b/model.cfg
index 1c1786c..db86d5f 100644
--- a/model.cfg
+++ b/model.cfg
@@ -3,6 +3,7 @@ model=openrouter/free
 temperature=0.7
 api_key=-
 stream=true
+reasoning_effort=high
 
 # Optional tuning (defaults shown):
 # timeout=300