@@ -54,7 +54,7 @@
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 1000000,
- "default_max_tokens": 100000,
+ "default_max_tokens": 32767,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -73,7 +73,7 @@
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 1000000,
- "default_max_tokens": 100000,
+ "default_max_tokens": 32767,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -535,19 +535,13 @@
{
"id": "deepseek/deepseek-chat-v3-0324",
"name": "DeepSeek: DeepSeek V3 0324",
- "cost_per_1m_in": 0.77,
- "cost_per_1m_out": 0.77,
+ "cost_per_1m_in": 0.9,
+ "cost_per_1m_out": 0.9,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 163840,
- "default_max_tokens": 65536,
- "can_reason": true,
- "reasoning_levels": [
- "low",
- "medium",
- "high"
- ],
- "default_reasoning_effort": "medium",
+ "default_max_tokens": 16384,
+ "can_reason": false,
"supports_attachments": false,
"options": {}
},
@@ -611,12 +605,12 @@
{
"id": "deepseek/deepseek-v3.2",
"name": "DeepSeek: DeepSeek V3.2",
- "cost_per_1m_in": 0.28,
+ "cost_per_1m_in": 0.27,
"cost_per_1m_out": 0.39999999999999997,
"cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0,
+ "cost_per_1m_out_cached": 0.216,
"context_window": 163840,
- "default_max_tokens": 32768,
+ "default_max_tokens": 16384,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -767,7 +761,7 @@
"cost_per_1m_in": 0.09999999999999999,
"cost_per_1m_out": 0.39999999999999997,
"cost_per_1m_in_cached": 0.18330000000000002,
- "cost_per_1m_out_cached": 0.01,
+ "cost_per_1m_out_cached": 0.024999999999999998,
"context_window": 1048576,
"default_max_tokens": 32767,
"can_reason": true,
@@ -807,7 +801,7 @@
"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",
@@ -928,7 +922,7 @@
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 256000,
- "default_max_tokens": 16384,
+ "default_max_tokens": 16000,
"can_reason": false,
"supports_attachments": false,
"options": {}
@@ -1001,8 +995,8 @@
{
"id": "meta-llama/llama-3.3-70b-instruct",
"name": "Meta: Llama 3.3 70B Instruct",
- "cost_per_1m_in": 0.25,
- "cost_per_1m_out": 0.75,
+ "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": 131072,
@@ -1092,12 +1086,12 @@
{
"id": "minimax/minimax-m2",
"name": "MiniMax: MiniMax M2",
- "cost_per_1m_in": 0.3,
- "cost_per_1m_out": 1.2,
+ "cost_per_1m_in": 0.27,
+ "cost_per_1m_out": 1.15,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
- "context_window": 204800,
- "default_max_tokens": 65536,
+ "context_window": 262144,
+ "default_max_tokens": 26214,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -1506,12 +1500,12 @@
{
"id": "moonshotai/kimi-k2",
"name": "MoonshotAI: Kimi K2 0711",
- "cost_per_1m_in": 0.456,
- "cost_per_1m_out": 1.8399999999999999,
+ "cost_per_1m_in": 0.5,
+ "cost_per_1m_out": 2.4,
"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": false,
"options": {}
@@ -1545,12 +1539,12 @@
{
"id": "moonshotai/kimi-k2-thinking",
"name": "MoonshotAI: Kimi K2 Thinking",
- "cost_per_1m_in": 0.5,
- "cost_per_1m_out": 2.5,
+ "cost_per_1m_in": 0.47,
+ "cost_per_1m_out": 2,
"cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0,
+ "cost_per_1m_out_cached": 0.14100000000000001,
"context_window": 262144,
- "default_max_tokens": 131072,
+ "default_max_tokens": 26214,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -1615,8 +1609,8 @@
{
"id": "nvidia/nemotron-nano-9b-v2",
"name": "NVIDIA: Nemotron Nano 9B V2",
- "cost_per_1m_in": 0.04,
- "cost_per_1m_out": 0.16,
+ "cost_per_1m_in": 0.06,
+ "cost_per_1m_out": 0.25,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 131072,
@@ -1688,6 +1682,25 @@
"supports_attachments": false,
"options": {}
},
+ {
+ "id": "nousresearch/hermes-4-70b",
+ "name": "Nous: Hermes 4 70B",
+ "cost_per_1m_in": 0.11,
+ "cost_per_1m_out": 0.38,
+ "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",
@@ -1990,9 +2003,9 @@
"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",
@@ -2095,8 +2108,8 @@
{
"id": "openai/gpt-oss-120b",
"name": "OpenAI: gpt-oss-120b",
- "cost_per_1m_in": 0.04,
- "cost_per_1m_out": 0.39999999999999997,
+ "cost_per_1m_in": 0.09,
+ "cost_per_1m_out": 0.36,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 131072,
@@ -2133,12 +2146,12 @@
{
"id": "openai/gpt-oss-20b",
"name": "OpenAI: gpt-oss-20b",
- "cost_per_1m_in": 0.045,
- "cost_per_1m_out": 0.18,
+ "cost_per_1m_in": 0.049999999999999996,
+ "cost_per_1m_out": 0.19999999999999998,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 131072,
- "default_max_tokens": 16384,
+ "default_max_tokens": 13107,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -2372,25 +2385,6 @@
"supports_attachments": false,
"options": {}
},
- {
- "id": "qwen/qwq-32b",
- "name": "Qwen: QwQ 32B",
- "cost_per_1m_in": 0.15,
- "cost_per_1m_out": 0.58,
- "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": "qwen/qwen-plus-2025-07-28",
"name": "Qwen: Qwen Plus 0728",
@@ -2535,12 +2529,12 @@
{
"id": "qwen/qwen3-235b-a22b-2507",
"name": "Qwen: Qwen3 235B A22B Instruct 2507",
- "cost_per_1m_in": 0.071,
- "cost_per_1m_out": 0.463,
+ "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": 26214,
+ "default_max_tokens": 131072,
"can_reason": false,
"supports_attachments": false,
"options": {}
@@ -2548,7 +2542,7 @@
{
"id": "qwen/qwen3-235b-a22b-thinking-2507",
"name": "Qwen: Qwen3 235B A22B Thinking 2507",
- "cost_per_1m_in": 0.13,
+ "cost_per_1m_in": 0.11,
"cost_per_1m_out": 0.6,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
@@ -2586,8 +2580,8 @@
{
"id": "qwen/qwen3-30b-a3b-instruct-2507",
"name": "Qwen: Qwen3 30B A3B Instruct 2507",
- "cost_per_1m_in": 0.08,
- "cost_per_1m_out": 0.33,
+ "cost_per_1m_in": 0.09,
+ "cost_per_1m_out": 0.3,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 262144,
@@ -2599,12 +2593,12 @@
{
"id": "qwen/qwen3-32b",
"name": "Qwen: Qwen3 32B",
- "cost_per_1m_in": 0.39999999999999997,
- "cost_per_1m_out": 0.7999999999999999,
+ "cost_per_1m_in": 0.15,
+ "cost_per_1m_out": 0.5,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 131072,
- "default_max_tokens": 16384,
+ "default_max_tokens": 4000,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -2634,34 +2628,15 @@
"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": 4096,
- "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",
- "cost_per_1m_in": 0.06,
- "cost_per_1m_out": 0.25,
+ "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": 131072,
+ "default_max_tokens": 26214,
"can_reason": false,
"supports_attachments": false,
"options": {}
@@ -2669,12 +2644,12 @@
{
"id": "qwen/qwen3-coder",
"name": "Qwen: Qwen3 Coder 480B A35B",
- "cost_per_1m_in": 0.22,
- "cost_per_1m_out": 0.95,
+ "cost_per_1m_in": 0.29,
+ "cost_per_1m_out": 1.2,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 262144,
- "default_max_tokens": 131072,
+ "default_max_tokens": 32768,
"can_reason": false,
"supports_attachments": false,
"options": {}
@@ -2753,12 +2728,12 @@
{
"id": "qwen/qwen3-next-80b-a3b-instruct",
"name": "Qwen: Qwen3 Next 80B A3B Instruct",
- "cost_per_1m_in": 0.15,
- "cost_per_1m_out": 1.5,
+ "cost_per_1m_in": 0.14,
+ "cost_per_1m_out": 1.4,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 262144,
- "default_max_tokens": 26214,
+ "default_max_tokens": 131072,
"can_reason": false,
"supports_attachments": false,
"options": {}
@@ -2785,12 +2760,12 @@
{
"id": "qwen/qwen3-vl-235b-a22b-instruct",
"name": "Qwen: Qwen3 VL 235B A22B Instruct",
- "cost_per_1m_in": 0.3,
- "cost_per_1m_out": 1.2,
+ "cost_per_1m_in": 0.22,
+ "cost_per_1m_out": 0.88,
"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": true,
"options": {}
@@ -2984,7 +2959,7 @@
"id": "alibaba/tongyi-deepresearch-30b-a3b",
"name": "Tongyi DeepResearch 30B A3B",
"cost_per_1m_in": 0.09,
- "cost_per_1m_out": 0.39999999999999997,
+ "cost_per_1m_out": 0.44999999999999996,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 131072,
@@ -3034,12 +3009,12 @@
{
"id": "z-ai/glm-4.5",
"name": "Z.AI: GLM 4.5",
- "cost_per_1m_in": 0.48,
- "cost_per_1m_out": 1.76,
+ "cost_per_1m_in": 0.6,
+ "cost_per_1m_out": 2.2,
"cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0.088,
+ "cost_per_1m_out_cached": 0.11,
"context_window": 131072,
- "default_max_tokens": 49152,
+ "default_max_tokens": 48000,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -3110,12 +3085,12 @@
{
"id": "z-ai/glm-4.6",
"name": "Z.AI: GLM 4.6",
- "cost_per_1m_in": 0.44,
- "cost_per_1m_out": 1.76,
+ "cost_per_1m_in": 0.5,
+ "cost_per_1m_out": 1.9,
"cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0.088,
+ "cost_per_1m_out_cached": 0,
"context_window": 204800,
- "default_max_tokens": 65536,
+ "default_max_tokens": 102400,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -3148,10 +3123,10 @@
{
"id": "x-ai/grok-3",
"name": "xAI: Grok 3",
- "cost_per_1m_in": 3,
- "cost_per_1m_out": 15,
+ "cost_per_1m_in": 5,
+ "cost_per_1m_out": 25,
"cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0.75,
+ "cost_per_1m_out_cached": 1.25,
"context_window": 131072,
"default_max_tokens": 13107,
"can_reason": false,
@@ -3161,10 +3136,10 @@
{
"id": "x-ai/grok-3-beta",
"name": "xAI: Grok 3 Beta",
- "cost_per_1m_in": 3,
- "cost_per_1m_out": 15,
+ "cost_per_1m_in": 5,
+ "cost_per_1m_out": 25,
"cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0.75,
+ "cost_per_1m_out_cached": 1.25,
"context_window": 131072,
"default_max_tokens": 13107,
"can_reason": false,
@@ -3248,12 +3223,12 @@
"options": {}
},
{
- "id": "x-ai/grok-4.1-fast:free",
- "name": "xAI: Grok 4.1 Fast (free)",
- "cost_per_1m_in": 0,
- "cost_per_1m_out": 0,
+ "id": "x-ai/grok-4.1-fast",
+ "name": "xAI: Grok 4.1 Fast",
+ "cost_per_1m_in": 0.19999999999999998,
+ "cost_per_1m_out": 0.5,
"cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0,
+ "cost_per_1m_out_cached": 0.049999999999999996,
"context_window": 2000000,
"default_max_tokens": 15000,
"can_reason": true,