@@ -193,8 +193,8 @@
"name": "Anthropic: Claude 3.5 Sonnet",
"cost_per_1m_in": 6,
"cost_per_1m_out": 30,
- "cost_per_1m_in_cached": 7.5,
- "cost_per_1m_out_cached": 0.6,
+ "cost_per_1m_in_cached": 0,
+ "cost_per_1m_out_cached": 0,
"context_window": 200000,
"default_max_tokens": 4096,
"can_reason": false,
@@ -592,10 +592,10 @@
{
"id": "deepseek/deepseek-v3.2",
"name": "DeepSeek: DeepSeek V3.2",
- "cost_per_1m_in": 0.26,
- "cost_per_1m_out": 0.39,
+ "cost_per_1m_in": 0.25,
+ "cost_per_1m_out": 0.38,
"cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0.19999999999999998,
+ "cost_per_1m_out_cached": 0.19,
"context_window": 163840,
"default_max_tokens": 32768,
"can_reason": true,
@@ -611,12 +611,12 @@
{
"id": "deepseek/deepseek-v3.2-exp",
"name": "DeepSeek: DeepSeek V3.2 Exp",
- "cost_per_1m_in": 0.21,
- "cost_per_1m_out": 0.32,
+ "cost_per_1m_in": 0.216,
+ "cost_per_1m_out": 0.328,
"cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0.16799999999999998,
+ "cost_per_1m_out_cached": 0,
"context_window": 163840,
- "default_max_tokens": 16384,
+ "default_max_tokens": 32768,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -649,12 +649,12 @@
{
"id": "deepseek/deepseek-r1-0528",
"name": "DeepSeek: R1 0528",
- "cost_per_1m_in": 0.56,
- "cost_per_1m_out": 2,
+ "cost_per_1m_in": 0.39999999999999997,
+ "cost_per_1m_out": 1.75,
"cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0.28,
+ "cost_per_1m_out_cached": 0,
"context_window": 163840,
- "default_max_tokens": 16384,
+ "default_max_tokens": 81920,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -748,7 +748,7 @@
"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,
@@ -769,7 +769,7 @@
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 1048576,
- "default_max_tokens": 32767,
+ "default_max_tokens": 32768,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -788,7 +788,7 @@
"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",
@@ -956,12 +956,12 @@
{
"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": {}
@@ -969,8 +969,8 @@
{
"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": 0.09,
+ "cost_per_1m_in": 0.02,
+ "cost_per_1m_out": 0.06,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 131072,
@@ -995,12 +995,12 @@
{
"id": "meta-llama/llama-3.3-70b-instruct",
"name": "Meta: Llama 3.3 70B Instruct",
- "cost_per_1m_in": 0.13,
- "cost_per_1m_out": 0.39999999999999997,
+ "cost_per_1m_in": 0.09999999999999999,
+ "cost_per_1m_out": 0.32,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 131072,
- "default_max_tokens": 13107,
+ "default_max_tokens": 8192,
"can_reason": false,
"supports_attachments": false,
"options": {}
@@ -1086,12 +1086,12 @@
{
"id": "minimax/minimax-m2",
"name": "MiniMax: MiniMax M2",
- "cost_per_1m_in": 0.254,
- "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": 0.127,
- "context_window": 262144,
- "default_max_tokens": 26214,
+ "cost_per_1m_out_cached": 0,
+ "context_window": 204800,
+ "default_max_tokens": 20480,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -1495,12 +1495,12 @@
{
"id": "moonshotai/kimi-k2-0905",
"name": "MoonshotAI: Kimi K2 0905",
- "cost_per_1m_in": 0.6,
- "cost_per_1m_out": 2.5,
+ "cost_per_1m_in": 0.59,
+ "cost_per_1m_out": 2.99,
"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": {}
@@ -1635,13 +1635,7 @@
"cost_per_1m_out_cached": 0,
"context_window": 131072,
"default_max_tokens": 81920,
- "can_reason": true,
- "reasoning_levels": [
- "low",
- "medium",
- "high"
- ],
- "default_reasoning_effort": "medium",
+ "can_reason": false,
"supports_attachments": false,
"options": {}
},
@@ -1664,25 +1658,6 @@
"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",
@@ -1985,9 +1960,9 @@
"cost_per_1m_in": 0.049999999999999996,
"cost_per_1m_out": 0.39999999999999997,
"cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0.01,
+ "cost_per_1m_out_cached": 0.005,
"context_window": 400000,
- "default_max_tokens": 40000,
+ "default_max_tokens": 64000,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -2106,6 +2081,57 @@
"supports_attachments": true,
"options": {}
},
+ {
+ "id": "openai/gpt-5.2",
+ "name": "OpenAI: GPT-5.2",
+ "cost_per_1m_in": 1.75,
+ "cost_per_1m_out": 14,
+ "cost_per_1m_in_cached": 0,
+ "cost_per_1m_out_cached": 0.175,
+ "context_window": 400000,
+ "default_max_tokens": 64000,
+ "can_reason": true,
+ "reasoning_levels": [
+ "low",
+ "medium",
+ "high"
+ ],
+ "default_reasoning_effort": "medium",
+ "supports_attachments": true,
+ "options": {}
+ },
+ {
+ "id": "openai/gpt-5.2-chat",
+ "name": "OpenAI: GPT-5.2 Chat",
+ "cost_per_1m_in": 1.75,
+ "cost_per_1m_out": 14,
+ "cost_per_1m_in_cached": 0,
+ "cost_per_1m_out_cached": 0.175,
+ "context_window": 128000,
+ "default_max_tokens": 8192,
+ "can_reason": false,
+ "supports_attachments": true,
+ "options": {}
+ },
+ {
+ "id": "openai/gpt-5.2-pro",
+ "name": "OpenAI: GPT-5.2 Pro",
+ "cost_per_1m_in": 21,
+ "cost_per_1m_out": 168,
+ "cost_per_1m_in_cached": 0,
+ "cost_per_1m_out_cached": 0,
+ "context_window": 400000,
+ "default_max_tokens": 64000,
+ "can_reason": true,
+ "reasoning_levels": [
+ "low",
+ "medium",
+ "high"
+ ],
+ "default_reasoning_effort": "medium",
+ "supports_attachments": true,
+ "options": {}
+ },
{
"id": "openai/gpt-oss-120b",
"name": "OpenAI: gpt-oss-120b",
@@ -2190,7 +2216,7 @@
"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": true,
"reasoning_levels": [
"low",
@@ -2395,16 +2421,35 @@
{
"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": 0.07,
+ "cost_per_1m_out": 0.26,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 32768,
- "default_max_tokens": 8192,
+ "default_max_tokens": 16384,
"can_reason": false,
"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",
@@ -2549,8 +2594,8 @@
{
"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": 0.22,
+ "cost_per_1m_out": 0.88,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 262144,
@@ -2581,12 +2626,12 @@
{
"id": "qwen/qwen3-30b-a3b",
"name": "Qwen: Qwen3 30B A3B",
- "cost_per_1m_in": 0.15,
- "cost_per_1m_out": 0.6,
+ "cost_per_1m_in": 0.09,
+ "cost_per_1m_out": 0.44999999999999996,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 131072,
- "default_max_tokens": 4000,
+ "default_max_tokens": 65536,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -2648,6 +2693,25 @@
"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",
@@ -2664,12 +2728,12 @@
{
"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": 0.28,
+ "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": 26214,
"can_reason": false,
"supports_attachments": false,
"options": {}
@@ -2677,19 +2741,13 @@
{
"id": "qwen/qwen3-coder:exacto",
"name": "Qwen: Qwen3 Coder 480B A35B (exacto)",
- "cost_per_1m_in": 0.38,
- "cost_per_1m_out": 1.53,
+ "cost_per_1m_in": 0.22,
+ "cost_per_1m_out": 1.7999999999999998,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 262144,
- "default_max_tokens": 131072,
- "can_reason": true,
- "reasoning_levels": [
- "low",
- "medium",
- "high"
- ],
- "default_reasoning_effort": "medium",
+ "default_max_tokens": 32768,
+ "can_reason": false,
"supports_attachments": false,
"options": {}
},
@@ -2762,11 +2820,11 @@
"id": "qwen/qwen3-next-80b-a3b-thinking",
"name": "Qwen: Qwen3 Next 80B A3B Thinking",
"cost_per_1m_in": 0.15,
- "cost_per_1m_out": 1.5,
+ "cost_per_1m_out": 1.2,
"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": true,
"reasoning_levels": [
"low",
@@ -2780,12 +2838,12 @@
{
"id": "qwen/qwen3-vl-235b-a22b-instruct",
"name": "Qwen: Qwen3 VL 235B A22B Instruct",
- "cost_per_1m_in": 0.22,
- "cost_per_1m_out": 0.88,
+ "cost_per_1m_in": 0.39999999999999997,
+ "cost_per_1m_out": 1.5999999999999999,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
- "context_window": 262144,
- "default_max_tokens": 26214,
+ "context_window": 131072,
+ "default_max_tokens": 16384,
"can_reason": false,
"supports_attachments": true,
"options": {}
@@ -3023,12 +3081,12 @@
{
"id": "z-ai/glm-4.5",
"name": "Z.AI: GLM 4.5",
- "cost_per_1m_in": 0.35,
- "cost_per_1m_out": 1.55,
+ "cost_per_1m_in": 0.48,
+ "cost_per_1m_out": 1.76,
"cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0,
+ "cost_per_1m_out_cached": 0.088,
"context_window": 131072,
- "default_max_tokens": 65536,
+ "default_max_tokens": 49152,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -3142,7 +3200,7 @@
"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": true,
"reasoning_levels": [
"low",