@@ -116,8 +116,8 @@
"name": "Anthropic: Claude 3.5 Haiku",
"cost_per_1m_in": 0.7999999999999999,
"cost_per_1m_out": 4,
- "cost_per_1m_in_cached": 1,
- "cost_per_1m_out_cached": 0.08,
+ "cost_per_1m_in_cached": 0,
+ "cost_per_1m_out_cached": 0,
"context_window": 200000,
"default_max_tokens": 4096,
"can_reason": false,
@@ -158,7 +158,7 @@
"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",
@@ -427,12 +427,12 @@
{
"id": "deepseek/deepseek-chat-v3-0324",
"name": "DeepSeek: DeepSeek V3 0324",
- "cost_per_1m_in": 0.27,
- "cost_per_1m_out": 1.12,
+ "cost_per_1m_in": 0.5,
+ "cost_per_1m_out": 1.5,
"cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0.135,
+ "cost_per_1m_out_cached": 0,
"context_window": 163840,
- "default_max_tokens": 81920,
+ "default_max_tokens": 16384,
"can_reason": false,
"supports_attachments": false,
"options": {}
@@ -453,8 +453,8 @@
{
"id": "deepseek/deepseek-chat-v3.1",
"name": "DeepSeek: DeepSeek V3.1",
- "cost_per_1m_in": 0.56,
- "cost_per_1m_out": 1.68,
+ "cost_per_1m_in": 0.27,
+ "cost_per_1m_out": 1,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 163840,
@@ -564,6 +564,25 @@
"supports_attachments": false,
"options": {}
},
+ {
+ "id": "deepseek/deepseek-r1-distill-llama-70b",
+ "name": "DeepSeek: R1 Distill Llama 70B",
+ "cost_per_1m_in": 0.03,
+ "cost_per_1m_out": 0.13,
+ "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": "google/gemini-2.0-flash-001",
"name": "Google: Gemini 2.0 Flash",
@@ -641,25 +660,6 @@
"supports_attachments": true,
"options": {}
},
- {
- "id": "google/gemini-2.5-flash-lite-preview-06-17",
- "name": "Google: Gemini 2.5 Flash Lite Preview 06-17",
- "cost_per_1m_in": 0.09999999999999999,
- "cost_per_1m_out": 0.39999999999999997,
- "cost_per_1m_in_cached": 0.18330000000000002,
- "cost_per_1m_out_cached": 0.024999999999999998,
- "context_window": 1048576,
- "default_max_tokens": 32767,
- "can_reason": true,
- "reasoning_levels": [
- "low",
- "medium",
- "high"
- ],
- "default_reasoning_effort": "medium",
- "supports_attachments": true,
- "options": {}
- },
{
"id": "google/gemini-2.5-flash-lite-preview-09-2025",
"name": "Google: Gemini 2.5 Flash Lite Preview 09-2025",
@@ -668,7 +668,7 @@
"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",
@@ -687,7 +687,7 @@
"cost_per_1m_in_cached": 0.3833,
"cost_per_1m_out_cached": 0.075,
"context_window": 1048576,
- "default_max_tokens": 32767,
+ "default_max_tokens": 32768,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -755,6 +755,25 @@
"supports_attachments": true,
"options": {}
},
+ {
+ "id": "google/gemini-3-pro-preview",
+ "name": "Google: Gemini 3 Pro Preview",
+ "cost_per_1m_in": 2,
+ "cost_per_1m_out": 12,
+ "cost_per_1m_in_cached": 2.375,
+ "cost_per_1m_out_cached": 0.19999999999999998,
+ "context_window": 1048576,
+ "default_max_tokens": 32768,
+ "can_reason": true,
+ "reasoning_levels": [
+ "low",
+ "medium",
+ "high"
+ ],
+ "default_reasoning_effort": "medium",
+ "supports_attachments": true,
+ "options": {}
+ },
{
"id": "inception/mercury",
"name": "Inception: Mercury",
@@ -836,12 +855,12 @@
{
"id": "meta-llama/llama-3.1-8b-instruct",
"name": "Meta: Llama 3.1 8B Instruct",
- "cost_per_1m_in": 0.049999999999999996,
- "cost_per_1m_out": 0.08,
+ "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,
- "default_max_tokens": 65536,
+ "default_max_tokens": 8192,
"can_reason": false,
"supports_attachments": false,
"options": {}
@@ -862,12 +881,12 @@
{
"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": 0.59,
+ "cost_per_1m_out": 0.7899999999999999,
"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": false,
"supports_attachments": false,
"options": {}
@@ -1367,12 +1386,12 @@
{
"id": "moonshotai/kimi-k2",
"name": "MoonshotAI: Kimi K2 0711",
- "cost_per_1m_in": 0.5700000000000001,
- "cost_per_1m_out": 2.3,
+ "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": {}
@@ -1380,12 +1399,12 @@
{
"id": "moonshotai/kimi-k2-0905",
"name": "MoonshotAI: Kimi K2 0905",
- "cost_per_1m_in": 0.5,
- "cost_per_1m_out": 2,
+ "cost_per_1m_in": 0.39,
+ "cost_per_1m_out": 1.9,
"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": {}
@@ -1476,8 +1495,8 @@
{
"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,
@@ -1530,6 +1549,19 @@
"supports_attachments": false,
"options": {}
},
+ {
+ "id": "nousresearch/hermes-3-llama-3.1-70b",
+ "name": "Nous: Hermes 3 70B Instruct",
+ "cost_per_1m_in": 0.39999999999999997,
+ "cost_per_1m_out": 0.39999999999999997,
+ "cost_per_1m_in_cached": 0,
+ "cost_per_1m_out_cached": 0,
+ "context_window": 12288,
+ "default_max_tokens": 1228,
+ "can_reason": false,
+ "supports_attachments": false,
+ "options": {}
+ },
{
"id": "nousresearch/hermes-4-405b",
"name": "Nous: Hermes 4 405B",
@@ -1956,12 +1988,12 @@
{
"id": "openai/gpt-oss-120b",
"name": "OpenAI: gpt-oss-120b",
- "cost_per_1m_in": 0.14,
- "cost_per_1m_out": 0.95,
+ "cost_per_1m_in": 0.049999999999999996,
+ "cost_per_1m_out": 0.25,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 131072,
- "default_max_tokens": 65536,
+ "default_max_tokens": 16384,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -2214,6 +2246,25 @@
"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",
@@ -2298,6 +2349,19 @@
"supports_attachments": false,
"options": {}
},
+ {
+ "id": "qwen/qwen-2.5-7b-instruct",
+ "name": "Qwen: Qwen2.5 7B Instruct",
+ "cost_per_1m_in": 0.07,
+ "cost_per_1m_out": 0.07,
+ "cost_per_1m_in_cached": 0,
+ "cost_per_1m_out_cached": 0,
+ "context_window": 32000,
+ "default_max_tokens": 16000,
+ "can_reason": false,
+ "supports_attachments": false,
+ "options": {}
+ },
{
"id": "qwen/qwen3-14b",
"name": "Qwen: Qwen3 14B",
@@ -2358,31 +2422,25 @@
{
"id": "qwen/qwen3-235b-a22b-2507",
"name": "Qwen: Qwen3 235B A22B Instruct 2507",
- "cost_per_1m_in": 0.22,
- "cost_per_1m_out": 0.7999999999999999,
+ "cost_per_1m_in": 0.25,
+ "cost_per_1m_out": 1,
"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": 8192,
+ "can_reason": false,
"supports_attachments": false,
"options": {}
},
{
"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": 0.3,
+ "cost_per_1m_out": 3,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
- "context_window": 262144,
- "default_max_tokens": 131072,
+ "context_window": 131072,
+ "default_max_tokens": 16384,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -2396,12 +2454,12 @@
{
"id": "qwen/qwen3-30b-a3b",
"name": "Qwen: Qwen3 30B A3B",
- "cost_per_1m_in": 0.08,
- "cost_per_1m_out": 0.28,
+ "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": 131072,
- "default_max_tokens": 65536,
+ "default_max_tokens": 4000,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -2415,25 +2473,25 @@
{
"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": {}
},
{
- "id": "qwen/qwen3-30b-a3b-thinking-2507",
- "name": "Qwen: Qwen3 30B A3B Thinking 2507",
- "cost_per_1m_in": 0.09999999999999999,
- "cost_per_1m_out": 0.3,
+ "id": "qwen/qwen3-32b",
+ "name": "Qwen: Qwen3 32B",
+ "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": 262144,
- "default_max_tokens": 26214,
+ "context_window": 131072,
+ "default_max_tokens": 4000,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -2445,14 +2503,14 @@
"options": {}
},
{
- "id": "qwen/qwen3-32b",
- "name": "Qwen: Qwen3 32B",
- "cost_per_1m_in": 0.15,
- "cost_per_1m_out": 0.5,
+ "id": "qwen/qwen3-4b:free",
+ "name": "Qwen: Qwen3 4B (free)",
+ "cost_per_1m_in": 0,
+ "cost_per_1m_out": 0,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
- "context_window": 131072,
- "default_max_tokens": 4000,
+ "context_window": 40960,
+ "default_max_tokens": 4096,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -2464,10 +2522,10 @@
"options": {}
},
{
- "id": "qwen/qwen3-4b:free",
- "name": "Qwen: Qwen3 4B (free)",
- "cost_per_1m_in": 0,
- "cost_per_1m_out": 0,
+ "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,
@@ -2576,8 +2634,8 @@
{
"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": 0.09999999999999999,
+ "cost_per_1m_out": 0.7999999999999999,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 262144,
@@ -2589,8 +2647,8 @@
{
"id": "qwen/qwen3-next-80b-a3b-thinking",
"name": "Qwen: Qwen3 Next 80B A3B Thinking",
- "cost_per_1m_in": 0.15,
- "cost_per_1m_out": 1.2,
+ "cost_per_1m_in": 0.3,
+ "cost_per_1m_out": 0.3,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 262144,
@@ -2640,12 +2698,12 @@
{
"id": "qwen/qwen3-vl-30b-a3b-instruct",
"name": "Qwen: Qwen3 VL 30B A3B Instruct",
- "cost_per_1m_in": 0.29,
- "cost_per_1m_out": 1,
+ "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": 131072,
+ "default_max_tokens": 26214,
"can_reason": false,
"supports_attachments": true,
"options": {}
@@ -2870,12 +2928,12 @@
{
"id": "z-ai/glm-4.5-air",
"name": "Z.AI: GLM 4.5 Air",
- "cost_per_1m_in": 0.14,
- "cost_per_1m_out": 0.86,
+ "cost_per_1m_in": 0.13,
+ "cost_per_1m_out": 0.85,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 131072,
- "default_max_tokens": 65536,
+ "default_max_tokens": 49152,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -2965,10 +3023,10 @@
{
"id": "x-ai/grok-3",
"name": "xAI: Grok 3",
- "cost_per_1m_in": 5,
- "cost_per_1m_out": 25,
+ "cost_per_1m_in": 3,
+ "cost_per_1m_out": 15,
"cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 1.25,
+ "cost_per_1m_out_cached": 0.75,
"context_window": 131072,
"default_max_tokens": 13107,
"can_reason": false,
@@ -2978,10 +3036,10 @@
{
"id": "x-ai/grok-3-beta",
"name": "xAI: Grok 3 Beta",
- "cost_per_1m_in": 5,
- "cost_per_1m_out": 25,
+ "cost_per_1m_in": 3,
+ "cost_per_1m_out": 15,
"cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 1.25,
+ "cost_per_1m_out_cached": 0.75,
"context_window": 131072,
"default_max_tokens": 13107,
"can_reason": false,