@@ -142,8 +142,8 @@
"name": "Anthropic: Claude 3.5 Sonnet",
"cost_per_1m_in": 3,
"cost_per_1m_out": 15,
- "cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0,
+ "cost_per_1m_in_cached": 3.75,
+ "cost_per_1m_out_cached": 0.3,
"context_window": 200000,
"default_max_tokens": 4096,
"can_reason": false,
@@ -440,12 +440,12 @@
{
"id": "deepseek/deepseek-chat-v3-0324",
"name": "DeepSeek: DeepSeek V3 0324",
- "cost_per_1m_in": 0.9,
- "cost_per_1m_out": 0.9,
+ "cost_per_1m_in": 0.27,
+ "cost_per_1m_out": 1.12,
"cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0,
+ "cost_per_1m_out_cached": 0.135,
"context_window": 163840,
- "default_max_tokens": 10240,
+ "default_max_tokens": 81920,
"can_reason": false,
"supports_attachments": false,
"options": {}
@@ -524,11 +524,11 @@
"id": "deepseek/deepseek-v3.2-exp",
"name": "DeepSeek: DeepSeek V3.2 Exp",
"cost_per_1m_in": 0.27,
- "cost_per_1m_out": 0.41,
+ "cost_per_1m_out": 0.39999999999999997,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 163840,
- "default_max_tokens": 32768,
+ "default_max_tokens": 16384,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -719,7 +719,7 @@
"cost_per_1m_in_cached": 0.3833,
"cost_per_1m_out_cached": 0.075,
"context_window": 1048576,
- "default_max_tokens": 32768,
+ "default_max_tokens": 32767,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -787,19 +787,6 @@
"supports_attachments": true,
"options": {}
},
- {
- "id": "google/gemma-3-27b-it",
- "name": "Google: Gemma 3 27B",
- "cost_per_1m_in": 0.13,
- "cost_per_1m_out": 0.52,
- "cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0,
- "context_window": 96000,
- "default_max_tokens": 48000,
- "can_reason": false,
- "supports_attachments": true,
- "options": {}
- },
{
"id": "inception/mercury",
"name": "Inception: Mercury",
@@ -855,12 +842,12 @@
{
"id": "meta-llama/llama-3.1-70b-instruct",
"name": "Meta: Llama 3.1 70B Instruct",
- "cost_per_1m_in": 0.39999999999999997,
- "cost_per_1m_out": 0.39999999999999997,
+ "cost_per_1m_in": 0.88,
+ "cost_per_1m_out": 0.88,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 131072,
- "default_max_tokens": 8192,
+ "default_max_tokens": 13107,
"can_reason": false,
"supports_attachments": false,
"options": {}
@@ -1327,12 +1314,12 @@
{
"id": "mistralai/mistral-small-3.2-24b-instruct",
"name": "Mistral: Mistral Small 3.2 24B",
- "cost_per_1m_in": 0.09999999999999999,
- "cost_per_1m_out": 0.3,
+ "cost_per_1m_in": 0.06,
+ "cost_per_1m_out": 0.18,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 131072,
- "default_max_tokens": 13107,
+ "default_max_tokens": 65536,
"can_reason": false,
"supports_attachments": true,
"options": {}
@@ -1431,12 +1418,12 @@
{
"id": "moonshotai/kimi-k2-0905",
"name": "MoonshotAI: Kimi K2 0905",
- "cost_per_1m_in": 0.39,
- "cost_per_1m_out": 1.9,
+ "cost_per_1m_in": 1,
+ "cost_per_1m_out": 3,
"cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0,
+ "cost_per_1m_out_cached": 0.5,
"context_window": 262144,
- "default_max_tokens": 131072,
+ "default_max_tokens": 8192,
"can_reason": false,
"supports_attachments": false,
"options": {}
@@ -1575,6 +1562,25 @@
"supports_attachments": false,
"options": {}
},
+ {
+ "id": "nousresearch/hermes-4-405b",
+ "name": "Nous: Hermes 4 405B",
+ "cost_per_1m_in": 0.3,
+ "cost_per_1m_out": 1.2,
+ "cost_per_1m_in_cached": 0,
+ "cost_per_1m_out_cached": 0,
+ "context_window": 131072,
+ "default_max_tokens": 65536,
+ "can_reason": true,
+ "reasoning_levels": [
+ "low",
+ "medium",
+ "high"
+ ],
+ "default_reasoning_effort": "medium",
+ "supports_attachments": false,
+ "options": {}
+ },
{
"id": "openai/codex-mini",
"name": "OpenAI: Codex Mini",
@@ -1858,9 +1864,9 @@
"cost_per_1m_in": 0.25,
"cost_per_1m_out": 2,
"cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0.03,
+ "cost_per_1m_out_cached": 0.024999999999999998,
"context_window": 400000,
- "default_max_tokens": 40000,
+ "default_max_tokens": 64000,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -1877,9 +1883,9 @@
"cost_per_1m_in": 0.049999999999999996,
"cost_per_1m_out": 0.39999999999999997,
"cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0.005,
+ "cost_per_1m_out_cached": 0.01,
"context_window": 400000,
- "default_max_tokens": 64000,
+ "default_max_tokens": 40000,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -1932,11 +1938,11 @@
"id": "openai/gpt-oss-120b:exacto",
"name": "OpenAI: gpt-oss-120b (exacto)",
"cost_per_1m_in": 0.049999999999999996,
- "cost_per_1m_out": 0.24,
+ "cost_per_1m_out": 0.25,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 131072,
- "default_max_tokens": 13107,
+ "default_max_tokens": 16384,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -1950,8 +1956,8 @@
{
"id": "openai/gpt-oss-20b",
"name": "OpenAI: gpt-oss-20b",
- "cost_per_1m_in": 0.04,
- "cost_per_1m_out": 0.15,
+ "cost_per_1m_in": 0.03,
+ "cost_per_1m_out": 0.14,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 131072,
@@ -2160,12 +2166,12 @@
{
"id": "qwen/qwen-2.5-72b-instruct",
"name": "Qwen2.5 72B Instruct",
- "cost_per_1m_in": 0.12,
- "cost_per_1m_out": 0.39,
+ "cost_per_1m_in": 0.13,
+ "cost_per_1m_out": 0.39999999999999997,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
- "context_window": 32768,
- "default_max_tokens": 8192,
+ "context_window": 131072,
+ "default_max_tokens": 13107,
"can_reason": false,
"supports_attachments": false,
"options": {}
@@ -2289,12 +2295,12 @@
{
"id": "qwen/qwen3-14b",
"name": "Qwen: Qwen3 14B",
- "cost_per_1m_in": 0.06,
+ "cost_per_1m_in": 0.08,
"cost_per_1m_out": 0.24,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 40960,
- "default_max_tokens": 20480,
+ "default_max_tokens": 4096,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -2346,12 +2352,12 @@
{
"id": "qwen/qwen3-235b-a22b-2507",
"name": "Qwen: Qwen3 235B A22B Instruct 2507",
- "cost_per_1m_in": 0.25,
- "cost_per_1m_out": 1,
+ "cost_per_1m_in": 0.09999999999999999,
+ "cost_per_1m_out": 0.09999999999999999,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 262144,
- "default_max_tokens": 8192,
+ "default_max_tokens": 131072,
"can_reason": false,
"supports_attachments": false,
"options": {}
@@ -2378,8 +2384,8 @@
{
"id": "qwen/qwen3-30b-a3b",
"name": "Qwen: Qwen3 30B A3B",
- "cost_per_1m_in": 0.09,
- "cost_per_1m_out": 0.44999999999999996,
+ "cost_per_1m_in": 0.08,
+ "cost_per_1m_out": 0.28,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 131072,
@@ -2410,12 +2416,12 @@
{
"id": "qwen/qwen3-30b-a3b-thinking-2507",
"name": "Qwen: Qwen3 30B A3B Thinking 2507",
- "cost_per_1m_in": 0.09,
+ "cost_per_1m_in": 0.09999999999999999,
"cost_per_1m_out": 0.3,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 262144,
- "default_max_tokens": 65536,
+ "default_max_tokens": 26214,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -2464,25 +2470,6 @@
"supports_attachments": false,
"options": {}
},
- {
- "id": "qwen/qwen3-8b",
- "name": "Qwen: Qwen3 8B",
- "cost_per_1m_in": 0.2,
- "cost_per_1m_out": 0.2,
- "cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0,
- "context_window": 40960,
- "default_max_tokens": 2560,
- "can_reason": true,
- "reasoning_levels": [
- "low",
- "medium",
- "high"
- ],
- "default_reasoning_effort": "medium",
- "supports_attachments": false,
- "options": {}
- },
{
"id": "qwen/qwen3-coder-30b-a3b-instruct",
"name": "Qwen: Qwen3 Coder 30B A3B Instruct",
@@ -2499,12 +2486,12 @@
{
"id": "qwen/qwen3-coder",
"name": "Qwen: Qwen3 Coder 480B A35B",
- "cost_per_1m_in": 0.29,
- "cost_per_1m_out": 1.2,
+ "cost_per_1m_in": 1,
+ "cost_per_1m_out": 1.5,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 262144,
- "default_max_tokens": 32768,
+ "default_max_tokens": 131072,
"can_reason": false,
"supports_attachments": false,
"options": {}
@@ -2583,12 +2570,12 @@
{
"id": "qwen/qwen3-next-80b-a3b-instruct",
"name": "Qwen: Qwen3 Next 80B A3B Instruct",
- "cost_per_1m_in": 0.09999999999999999,
- "cost_per_1m_out": 0.7999999999999999,
+ "cost_per_1m_in": 0.14,
+ "cost_per_1m_out": 1.1,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 262144,
- "default_max_tokens": 131072,
+ "default_max_tokens": 26214,
"can_reason": false,
"supports_attachments": false,
"options": {}
@@ -2615,12 +2602,12 @@
{
"id": "qwen/qwen3-vl-235b-a22b-instruct",
"name": "Qwen: Qwen3 VL 235B A22B Instruct",
- "cost_per_1m_in": 0.5,
- "cost_per_1m_out": 2.5,
+ "cost_per_1m_in": 0.3,
+ "cost_per_1m_out": 1.49,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 131072,
- "default_max_tokens": 65536,
+ "default_max_tokens": 13107,
"can_reason": false,
"supports_attachments": true,
"options": {}
@@ -2644,6 +2631,19 @@
"supports_attachments": true,
"options": {}
},
+ {
+ "id": "qwen/qwen3-vl-30b-a3b-instruct",
+ "name": "Qwen: Qwen3 VL 30B A3B Instruct",
+ "cost_per_1m_in": 0.15,
+ "cost_per_1m_out": 0.6,
+ "cost_per_1m_in_cached": 0,
+ "cost_per_1m_out_cached": 0,
+ "context_window": 262144,
+ "default_max_tokens": 16384,
+ "can_reason": false,
+ "supports_attachments": true,
+ "options": {}
+ },
{
"id": "qwen/qwen3-vl-30b-a3b-thinking",
"name": "Qwen: Qwen3 VL 30B A3B Thinking",
@@ -2763,7 +2763,7 @@
"id": "alibaba/tongyi-deepresearch-30b-a3b",
"name": "Tongyi DeepResearch 30B A3B",
"cost_per_1m_in": 0.09,
- "cost_per_1m_out": 0.44999999999999996,
+ "cost_per_1m_out": 0.39999999999999997,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 131072,
@@ -2832,12 +2832,12 @@
{
"id": "z-ai/glm-4.5-air",
"name": "Z.AI: GLM 4.5 Air",
- "cost_per_1m_in": 0.19999999999999998,
- "cost_per_1m_out": 1.1,
+ "cost_per_1m_in": 0.13,
+ "cost_per_1m_out": 0.85,
"cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0.03,
+ "cost_per_1m_out_cached": 0,
"context_window": 131072,
- "default_max_tokens": 48000,
+ "default_max_tokens": 49152,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -2889,12 +2889,12 @@
{
"id": "z-ai/glm-4.6",
"name": "Z.AI: GLM 4.6",
- "cost_per_1m_in": 0.5,
- "cost_per_1m_out": 1.9,
+ "cost_per_1m_in": 0.6,
+ "cost_per_1m_out": 2,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 204800,
- "default_max_tokens": 102400,
+ "default_max_tokens": 20480,
"can_reason": true,
"reasoning_levels": [
"low",