Skip to content

Self-improving AI Employees for everyone

config: add Claude Opus 5 and new Gemini Flash models

trohitg952d43ef5aae
diff --git a/server/config/llm_defaults.json b/server/config/llm_defaults.json
index d1e06fe9..bc0524a6 100644
--- a/server/config/llm_defaults.json
+++ b/server/config/llm_defaults.json
@@ -1,6 +1,6 @@
{
- "version": "2026.07.23",
- "last_updated": "2026-07-23",
+ "version": "2026.07.25",
+ "last_updated": "2026-07-25",
"_description": "LLM provider defaults. popular_models drives the ordered global selector and offline fallback independently of token constraints. POLICY (2026-07-23): popular_models lists only models with >= 1M-token context windows — providers whose models are all below 1M carry an empty list and contribute nothing to the global selector (their models stay reachable via the live per-provider fetch_models dropdown). base_url directly configures the eight OpenAI-compatible native providers; dedicated OpenAI, Anthropic, and Gemini providers use SDK defaults, while OpenRouter has its own gateway default. Runtime proxy credentials can override supported endpoints. Model specs are enriched by model_registry.json (OpenRouter cache).",
"agent": {
@@ -52,14 +52,16 @@
"temperature_range": [0.0, 2.0]
},
"anthropic": {
- "default_model": "claude-opus-4-8",
- "popular_models": ["claude-fable-5", "claude-sonnet-5", "claude-opus-4-8", "claude-opus-4-7", "claude-sonnet-4-6"],
+ "default_model": "claude-opus-5",
+ "popular_models": ["claude-opus-5", "claude-fable-5", "claude-sonnet-5", "claude-opus-4-8", "claude-opus-4-7", "claude-sonnet-4-6"],
+ "_models_note": "claude-opus-5 (released 2026-07-24) is the new Opus flagship and default: near-Fable-5 intelligence at Opus pricing ($5/$25 — half of Fable 5), 1M context, 128K max output. The claude-opus-5-fast variant (2x pricing) is deliberately not curated here; select it via the live dropdown if needed.",
"detection_patterns": ["claude", "anthropic"],
"base_url": "https://api.anthropic.com/v1",
"models_endpoint": "https://api.anthropic.com/v1/models",
"api_key_param": "anthropic_api_key",
"max_tokens_param": "max_tokens",
"max_output_tokens": {
+ "claude-opus-5": 128000,
"claude-fable-5": 128000,
"claude-opus-4-8": 128000,
"claude-opus-4-7": 128000,
@@ -69,6 +71,7 @@
"_default": 8192
},
"context_length": {
+ "claude-opus-5": 1048576,
"claude-fable-5": 1048576,
"claude-opus-4-8": 1048576,
"claude-opus-4-7": 1048576,
@@ -81,8 +84,8 @@
"temperature_range": [0.0, 1.0]
},
"gemini": {
- "default_model": "gemini-3.5-flash",
- "popular_models": ["gemini-3.5-flash", "gemini-3.1-pro-preview", "gemini-3.1-flash-lite", "gemini-3-flash-preview", "gemini-2.5-pro", "gemini-2.5-flash", "gemini-2.5-flash-lite"],
+ "default_model": "gemini-3.6-flash",
+ "popular_models": ["gemini-3.6-flash", "gemini-3.5-flash", "gemini-3.5-flash-lite", "gemini-3.1-pro-preview", "gemini-3.1-flash-lite", "gemini-3-flash-preview", "gemini-2.5-pro", "gemini-2.5-flash", "gemini-2.5-flash-lite"],
"detection_patterns": ["gemini", "google", "gemma"],
"_detection_patterns_note": "'gemma' makes is_model_valid_for_provider accept the API-served Gemma models (gemma-4-*-it) on gemini nodes — without it the four agent-path call sites silently swap gemma to default_model. Cerebras keeps its own 'gemma-4' pattern for its gemma-4-31b (no -it suffix); is_model_valid_for_provider is per-provider so both coexist. Only the runtime-unused detect_provider_from_model classifier prefers gemini for gemma-* names (dict order).",
"base_url": "https://generativelanguage.googleapis.com/v1beta",
@@ -91,7 +94,9 @@
"max_tokens_param": "max_output_tokens",
"_models_note": "Real (concrete) model names only — no -latest rolling aliases. The curated list (max_output_tokens keys) serves BOTH the Gemini Developer API (AIza keys) and Vertex / Agent Platform (AQ. keys); gemini-* entries live-verified on both endpoints (2026-06-12). Vertex 404s on -latest aliases and its models.list rejects API keys, which is why the dropdown is curated instead of live-fetched. Gemma exception: gemma-4-31b-it + gemma-4-26b-a4b-it are served ONLY on the Developer API (free tier, ai.google.dev/gemma/docs/core/gemma_on_gemini_api, verified 2026-07-11) — Vertex keys must not see them, hence vertex_incompatible_models below. Gemma 4 supports systemInstruction and function calling natively (unlike the gemma-3 era); max output is undocumented, so the curated 8192 is a conservative fallback (registry cache wins when present).",
"max_output_tokens": {
+ "gemini-3.6-flash": 65536,
"gemini-3.5-flash": 65536,
+ "gemini-3.5-flash-lite": 65536,
"gemini-3.1-pro-preview": 65536,
"gemini-3.1-flash-lite": 65536,
"gemini-3-flash-preview": 65536,
@@ -103,7 +108,9 @@
"_default": 8192
},
"context_length": {
+ "gemini-3.6-flash": 1048576,
"gemini-3.5-flash": 1048576,
+ "gemini-3.5-flash-lite": 1048576,
"gemini-3.1-pro-preview": 1048576,
"gemini-3.1-flash-lite": 1048576,
"gemini-3-flash-preview": 1048576,
@@ -117,6 +124,7 @@
"_vertex_incompatible_models_note": "Curated models that only exist on the Gemini Developer API, filtered out of fetch_models when the key is a Vertex / Agent Platform key (GeminiProvider._vertex). Gemma is Model Garden self-deploy on Vertex (the 26B MaaS variant needs a different '-maas' id on a different surface), so the plain ids 404 there.",
"vertex_incompatible_models": ["gemma-4-31b-it", "gemma-4-26b-a4b-it"],
"thinking_models": ["gemini-2.5", "gemini-3"],
+ "_new_models_note": "gemini-3.6-flash (new default) and gemini-3.5-flash-lite both launched 2026-07-21 with 1M context / 65536 max output; 3.6 Flash is $1.50/$7.50, Flash-Lite $0.30/$2.50. gemini-3.5-pro is still not GA on the public API (enterprise Vertex preview only) so it stays out of the curated list.",
"thinking_type": "budget",
"temperature_range": [0.0, 2.0],
"_incompatible_models_note": "Models that the dropdown should hide because they need a different API endpoint than `generate_content`. antigravity-preview-05-2026 requires the Interactions API; selecting it currently surfaces a `google.genai.errors.APIError`. ChatUnifier reads this list in fetch_models and filters before returning. Drop entries here when the unifier gains routing support for the alternate endpoint.",
diff --git a/server/config/pricing.json b/server/config/pricing.json
index b939a639..3c016fd5 100644
--- a/server/config/pricing.json
+++ b/server/config/pricing.json
@@ -1,6 +1,6 @@
{
"version": "2026.07",
- "last_updated": "2026-07-23",
+ "last_updated": "2026-07-25",
"llm": {
"openai": {
@@ -16,6 +16,8 @@
"_default": {"input": 2.50, "output": 15.00}
},
"anthropic": {
+ "claude-opus-5": {"input": 5.00, "output": 25.00, "cache_read": 0.50},
+ "claude-opus-5-fast": {"input": 10.00, "output": 50.00, "cache_read": 1.00},
"claude-fable-5": {"input": 10.00, "output": 50.00, "cache_read": 1.00},
"claude-opus-4-8": {"input": 5.00, "output": 25.00, "cache_read": 0.50},
"claude-opus-4-7": {"input": 5.00, "output": 25.00, "cache_read": 0.50},
@@ -28,6 +30,8 @@
"_default": {"input": 3.00, "output": 15.00, "cache_read": 0.30}
},
"gemini": {
+ "gemini-3.6-flash": {"input": 1.50, "output": 7.50},
+ "gemini-3.5-flash-lite": {"input": 0.30, "output": 2.50},
"gemini-3.1-pro-preview": {"input": 2.00, "output": 12.00},
"gemini-3-flash-preview": {"input": 0.50, "output": 3.00},
"gemini-3-pro-preview": {"input": 2.00, "output": 12.00},