Skip to content

Self-improving AI Employees for everyone

chore(release): bump version to 0.0.93 + refresh LLM model lists

trohitg7d270744abd7
diff --git a/client/package.json b/client/package.json
index 9f04adf9..cd617d50 100644
--- a/client/package.json
+++ b/client/package.json
@@ -1,7 +1,7 @@
{
"name": "react-flow-client",
"private": true,
- "version": "0.0.92",
+ "version": "0.0.93",
"type": "module",
"scripts": {
"start": "vite --host 0.0.0.0",
diff --git a/package.json b/package.json
index b5aceec6..f1b7b310 100644
--- a/package.json
+++ b/package.json
@@ -1,6 +1,6 @@
{
"name": "machinaos",
- "version": "0.0.92",
+ "version": "0.0.93",
"description": "Open source workflow automation platform with AI agents, React Flow, and n8n-inspired architecture",
"type": "module",
"keywords": [
diff --git a/server/config/llm_defaults.json b/server/config/llm_defaults.json
index ce07c0d1..955eddec 100644
--- a/server/config/llm_defaults.json
+++ b/server/config/llm_defaults.json
@@ -1,6 +1,6 @@
{
- "version": "2026.06",
- "last_updated": "2026-06-16",
+ "version": "2026.07",
+ "last_updated": "2026-07-11",
"_description": "LLM provider defaults. Connection config (base_url, models_endpoint) drives both native SDK and LangChain paths. Model specs auto-enriched by model_registry.json (OpenRouter cache).",
"agent": {
@@ -14,27 +14,28 @@
"providers": {
"openai": {
- "default_model": "gpt-5.5",
+ "default_model": "gpt-5.6-sol",
"detection_patterns": ["gpt", "openai", "o1", "o3", "o4"],
"base_url": "https://api.openai.com/v1",
"models_endpoint": "https://api.openai.com/v1/models",
"api_key_param": "openai_api_key",
"max_tokens_param": "max_tokens",
+ "_models_note": "GPT-5.6 family (sol/terra/luna) GA 2026-07-09. gpt-5.5 / gpt-5.4 remain GA as legacy tiers. Dropped: gpt-5.2 (new requests blocked 2026-06-30), o3 (API shutdown 2026-12-11), o4-mini (API shutdown 2026-10-23) — they fall back to _default constraints if still selected before shutdown.",
"max_output_tokens": {
+ "gpt-5.6-sol": 128000,
+ "gpt-5.6-terra": 128000,
+ "gpt-5.6-luna": 128000,
"gpt-5.5": 128000,
"gpt-5.4": 128000,
- "gpt-5.2": 128000,
- "o4-mini": 100000,
- "o3": 100000,
"gpt-4.1": 32768,
"_default": 16384
},
"context_length": {
+ "gpt-5.6-sol": 1050000,
+ "gpt-5.6-terra": 1050000,
+ "gpt-5.6-luna": 1050000,
"gpt-5.5": 1050000,
"gpt-5.4": 1050000,
- "gpt-5.2": 400000,
- "o4-mini": 200000,
- "o3": 200000,
"gpt-4.1": 1047576,
"_default": 128000
},
@@ -54,7 +55,8 @@
"claude-fable-5": 128000,
"claude-opus-4-8": 128000,
"claude-opus-4-7": 128000,
- "claude-sonnet-4-6": 64000,
+ "claude-sonnet-5": 128000,
+ "claude-sonnet-4-6": 128000,
"claude-haiku-4-5": 64000,
"_default": 8192
},
@@ -62,6 +64,7 @@
"claude-fable-5": 1048576,
"claude-opus-4-8": 1048576,
"claude-opus-4-7": 1048576,
+ "claude-sonnet-5": 1048576,
"claude-sonnet-4-6": 1048576,
"claude-haiku-4-5": 200000,
"_default": 200000
@@ -148,24 +151,25 @@
},
"cerebras": {
"default_model": "gpt-oss-120b",
- "detection_patterns": ["cerebras", "gpt-oss", "qwen-3-235b", "zai-glm"],
+ "detection_patterns": ["cerebras", "gpt-oss", "zai-glm", "gemma-4"],
"base_url": "https://api.cerebras.ai/v1",
"models_endpoint": "https://api.cerebras.ai/v1/models",
"api_key_param": "api_key",
"max_tokens_param": "max_tokens",
+ "_models_note": "Per inference-docs.cerebras.ai 2026-07-11: gpt-oss-120b is the only production model (paid tier 131k context / 40k max completion); zai-glm-4.7 and gemma-4-31b are preview. qwen-3-235b* variants are shut down (migration target: gpt-oss-120b).",
"max_output_tokens": {
- "gpt-oss-120b": 65536,
- "qwen-3-235b": 40960,
+ "gpt-oss-120b": 40960,
"zai-glm-4.7": 40960,
+ "gemma-4-31b": 40960,
"_default": 8192
},
"context_length": {
"gpt-oss-120b": 131072,
- "qwen-3-235b": 131072,
"zai-glm-4.7": 131072,
+ "gemma-4-31b": 131072,
"_default": 131072
},
- "thinking_models": ["qwen-3-235b"],
+ "thinking_models": ["zai-glm-4.7"],
"thinking_type": "budget",
"temperature_range": [0.0, 1.5]
},
diff --git a/server/config/pricing.json b/server/config/pricing.json
index 47ede630..27a777e2 100644
--- a/server/config/pricing.json
+++ b/server/config/pricing.json
@@ -1,9 +1,13 @@
{
- "version": "2026.03",
- "last_updated": "2026-03-09",
+ "version": "2026.07",
+ "last_updated": "2026-07-11",
"llm": {
"openai": {
+ "gpt-5.6-sol": {"input": 5.00, "output": 30.00, "cache_read": 0.50},
+ "gpt-5.6-terra": {"input": 2.50, "output": 15.00, "cache_read": 0.25},
+ "gpt-5.6-luna": {"input": 1.00, "output": 6.00, "cache_read": 0.10},
+ "gpt-5.5": {"input": 5.00, "output": 30.00, "cache_read": 0.50},
"gpt-5.4": {"input": 2.50, "output": 15.00},
"gpt-5.3-chat": {"input": 1.75, "output": 14.00},
"gpt-5.2": {"input": 1.75, "output": 14.00},
@@ -12,7 +16,11 @@
"_default": {"input": 2.50, "output": 15.00}
},
"anthropic": {
+ "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},
"claude-opus-4-6": {"input": 5.00, "output": 25.00, "cache_read": 0.50},
+ "claude-sonnet-5": {"input": 3.00, "output": 15.00, "cache_read": 0.30},
"claude-sonnet-4-6": {"input": 3.00, "output": 15.00, "cache_read": 0.30},
"claude-haiku-4-5": {"input": 1.00, "output": 5.00, "cache_read": 0.10},
"claude-sonnet-4-0": {"input": 3.00, "output": 15.00, "cache_read": 0.30},
@@ -36,9 +44,10 @@
"_default": {"input": 0.15, "output": 0.60}
},
"cerebras": {
- "qwen-3-235b": {"input": 0.20, "output": 0.20},
- "llama3.1-8b": {"input": 0.10, "output": 0.10},
- "_default": {"input": 0.10, "output": 0.10}
+ "gpt-oss-120b": {"input": 0.35, "output": 0.75},
+ "zai-glm-4.7": {"input": 2.25, "output": 2.75},
+ "gemma-4-31b": {"input": 0.99, "output": 1.49},
+ "_default": {"input": 0.35, "output": 0.75}
},
"openrouter": {
"_default": {"input": 1.00, "output": 5.00}