@@ -171,7 +171,7 @@
"cost_per_1m_in_cached": 3.75,
"cost_per_1m_out_cached": 0.3,
"context_window": 200000,
- "default_max_tokens": 64000,
+ "default_max_tokens": 32000,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -485,12 +485,12 @@
{
"id": "deepseek/deepseek-v3.1-terminus",
"name": "DeepSeek: DeepSeek V3.1 Terminus",
- "cost_per_1m_in": 0.27,
- "cost_per_1m_out": 1,
+ "cost_per_1m_in": 0.22999999999999998,
+ "cost_per_1m_out": 0.8999999999999999,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 163840,
- "default_max_tokens": 16384,
+ "default_max_tokens": 81920,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -508,8 +508,8 @@
"cost_per_1m_out": 1,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
- "context_window": 131072,
- "default_max_tokens": 32768,
+ "context_window": 163840,
+ "default_max_tokens": 16384,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -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",
@@ -561,12 +561,12 @@
{
"id": "deepseek/deepseek-r1-0528",
"name": "DeepSeek: R1 0528",
- "cost_per_1m_in": 0.7,
- "cost_per_1m_out": 2.5,
+ "cost_per_1m_in": 0.39999999999999997,
+ "cost_per_1m_out": 1.75,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 163840,
- "default_max_tokens": 16384,
+ "default_max_tokens": 81920,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -700,7 +700,7 @@
"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",
@@ -852,19 +852,6 @@
"supports_attachments": false,
"options": {}
},
- {
- "id": "meta-llama/llama-3.1-405b-instruct",
- "name": "Meta: Llama 3.1 405B Instruct",
- "cost_per_1m_in": 3.5,
- "cost_per_1m_out": 3.5,
- "cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0,
- "context_window": 130815,
- "default_max_tokens": 13081,
- "can_reason": false,
- "supports_attachments": false,
- "options": {}
- },
{
"id": "meta-llama/llama-3.1-70b-instruct",
"name": "Meta: Llama 3.1 70B Instruct",
@@ -881,8 +868,8 @@
{
"id": "meta-llama/llama-3.1-8b-instruct",
"name": "Meta: Llama 3.1 8B Instruct",
- "cost_per_1m_in": 0.03,
- "cost_per_1m_out": 0.049999999999999996,
+ "cost_per_1m_in": 0.02,
+ "cost_per_1m_out": 0.03,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 131072,
@@ -998,8 +985,8 @@
{
"id": "minimax/minimax-m2",
"name": "MiniMax: MiniMax M2",
- "cost_per_1m_in": 0.255,
- "cost_per_1m_out": 1.02,
+ "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": 204800,
@@ -1412,12 +1399,12 @@
{
"id": "moonshotai/kimi-k2",
"name": "MoonshotAI: Kimi K2 0711",
- "cost_per_1m_in": 0.5,
- "cost_per_1m_out": 2.4,
+ "cost_per_1m_in": 1,
+ "cost_per_1m_out": 3,
"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": false,
"options": {}
@@ -1425,12 +1412,12 @@
{
"id": "moonshotai/kimi-k2-0905",
"name": "MoonshotAI: Kimi K2 0905",
- "cost_per_1m_in": 0.39999999999999997,
- "cost_per_1m_out": 2,
+ "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": {}
@@ -1438,12 +1425,12 @@
{
"id": "moonshotai/kimi-k2-0905:exacto",
"name": "MoonshotAI: Kimi K2 0905 (exacto)",
- "cost_per_1m_in": 0.6,
- "cost_per_1m_out": 2.5,
+ "cost_per_1m_in": 1,
+ "cost_per_1m_out": 3,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 262144,
- "default_max_tokens": 26214,
+ "default_max_tokens": 8192,
"can_reason": false,
"supports_attachments": false,
"options": {}
@@ -2001,12 +1988,12 @@
{
"id": "openai/gpt-oss-120b",
"name": "OpenAI: gpt-oss-120b",
- "cost_per_1m_in": 0.049999999999999996,
- "cost_per_1m_out": 0.25,
+ "cost_per_1m_in": 0.04,
+ "cost_per_1m_out": 0.39999999999999997,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 131072,
- "default_max_tokens": 16384,
+ "default_max_tokens": 65536,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -2021,11 +2008,11 @@
"id": "openai/gpt-oss-120b:exacto",
"name": "OpenAI: gpt-oss-120b (exacto)",
"cost_per_1m_in": 0.049999999999999996,
- "cost_per_1m_out": 0.25,
+ "cost_per_1m_out": 0.24,
"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",
@@ -2039,8 +2026,8 @@
{
"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,
@@ -2259,25 +2246,6 @@
"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",
@@ -2435,12 +2403,12 @@
{
"id": "qwen/qwen3-235b-a22b-thinking-2507",
"name": "Qwen: Qwen3 235B A22B Thinking 2507",
- "cost_per_1m_in": 0.11,
- "cost_per_1m_out": 0.6,
+ "cost_per_1m_in": 0.65,
+ "cost_per_1m_out": 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": true,
"reasoning_levels": [
"low",
@@ -2473,12 +2441,12 @@
{
"id": "qwen/qwen3-30b-a3b-instruct-2507",
"name": "Qwen: Qwen3 30B A3B Instruct 2507",
- "cost_per_1m_in": 0.09999999999999999,
- "cost_per_1m_out": 0.3,
+ "cost_per_1m_in": 0.08,
+ "cost_per_1m_out": 0.33,
"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": {}
@@ -2486,12 +2454,12 @@
{
"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",
@@ -2556,8 +2524,8 @@
{
"id": "qwen/qwen3-coder",
"name": "Qwen: Qwen3 Coder 480B A35B",
- "cost_per_1m_in": 0.39999999999999997,
- "cost_per_1m_out": 1.5999999999999999,
+ "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,
@@ -2685,8 +2653,8 @@
{
"id": "qwen/qwen3-vl-235b-a22b-thinking",
"name": "Qwen: Qwen3 VL 235B A22B Thinking",
- "cost_per_1m_in": 0.44999999999999996,
- "cost_per_1m_out": 3.5,
+ "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": 262144,
@@ -2902,12 +2870,12 @@
{
"id": "z-ai/glm-4.5-air",
"name": "Z.AI: GLM 4.5 Air",
- "cost_per_1m_in": 0.13,
- "cost_per_1m_out": 0.85,
+ "cost_per_1m_in": 0.19999999999999998,
+ "cost_per_1m_out": 1.1,
"cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0,
+ "cost_per_1m_out_cached": 0.03,
"context_window": 131072,
- "default_max_tokens": 49152,
+ "default_max_tokens": 48000,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -2959,12 +2927,12 @@
{
"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": 2.2,
"cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0,
+ "cost_per_1m_out_cached": 0.11,
"context_window": 204800,
- "default_max_tokens": 102400,
+ "default_max_tokens": 65536,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -2997,10 +2965,10 @@
{
"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,
@@ -3010,10 +2978,10 @@
{
"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,