@@ -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,
@@ -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",
@@ -440,12 +440,12 @@
{
"id": "deepseek/deepseek-chat-v3-0324",
"name": "DeepSeek: DeepSeek V3 0324",
- "cost_per_1m_in": 0.25,
- "cost_per_1m_out": 1,
+ "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": 81920,
+ "default_max_tokens": 10240,
"can_reason": false,
"supports_attachments": false,
"options": {}
@@ -466,12 +466,12 @@
{
"id": "deepseek/deepseek-chat-v3.1",
"name": "DeepSeek: DeepSeek V3.1",
- "cost_per_1m_in": 0.27,
- "cost_per_1m_out": 1,
+ "cost_per_1m_in": 0.56,
+ "cost_per_1m_out": 1.68,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 163840,
- "default_max_tokens": 16384,
+ "default_max_tokens": 10240,
"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",
@@ -855,12 +855,12 @@
{
"id": "meta-llama/llama-3.1-70b-instruct",
"name": "Meta: Llama 3.1 70B Instruct",
- "cost_per_1m_in": 0.88,
- "cost_per_1m_out": 0.88,
+ "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": 131072,
- "default_max_tokens": 13107,
+ "default_max_tokens": 8192,
"can_reason": false,
"supports_attachments": false,
"options": {}
@@ -868,8 +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": 0.09,
+ "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,
@@ -878,15 +878,28 @@
"supports_attachments": false,
"options": {}
},
+ {
+ "id": "meta-llama/llama-3.2-3b-instruct",
+ "name": "Meta: Llama 3.2 3B Instruct",
+ "cost_per_1m_in": 0.03,
+ "cost_per_1m_out": 0.049999999999999996,
+ "cost_per_1m_in_cached": 0,
+ "cost_per_1m_out_cached": 0,
+ "context_window": 32768,
+ "default_max_tokens": 16000,
+ "can_reason": false,
+ "supports_attachments": false,
+ "options": {}
+ },
{
"id": "meta-llama/llama-3.3-70b-instruct",
"name": "Meta: Llama 3.3 70B Instruct",
- "cost_per_1m_in": 0.6,
- "cost_per_1m_out": 0.6,
+ "cost_per_1m_in": 0.13,
+ "cost_per_1m_out": 0.39,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 131072,
- "default_max_tokens": 65536,
+ "default_max_tokens": 60000,
"can_reason": false,
"supports_attachments": false,
"options": {}
@@ -1353,12 +1366,12 @@
{
"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": {}
@@ -1392,29 +1405,16 @@
{
"id": "mistralai/mixtral-8x7b-instruct",
"name": "Mistral: Mixtral 8x7B Instruct",
- "cost_per_1m_in": 0.6,
- "cost_per_1m_out": 0.6,
+ "cost_per_1m_in": 0.54,
+ "cost_per_1m_out": 0.54,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 32768,
- "default_max_tokens": 1024,
+ "default_max_tokens": 8192,
"can_reason": false,
"supports_attachments": false,
"options": {}
},
- {
- "id": "mistralai/pixtral-12b",
- "name": "Mistral: Pixtral 12B",
- "cost_per_1m_in": 0.15,
- "cost_per_1m_out": 0.15,
- "cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0,
- "context_window": 131072,
- "default_max_tokens": 13107,
- "can_reason": false,
- "supports_attachments": true,
- "options": {}
- },
{
"id": "mistralai/pixtral-large-2411",
"name": "Mistral: Pixtral Large 2411",
@@ -1457,12 +1457,12 @@
{
"id": "moonshotai/kimi-k2",
"name": "MoonshotAI: Kimi K2 0711",
- "cost_per_1m_in": 1,
- "cost_per_1m_out": 3,
+ "cost_per_1m_in": 0.6,
+ "cost_per_1m_out": 2.5,
"cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0,
+ "cost_per_1m_out_cached": 0.15,
"context_window": 131072,
- "default_max_tokens": 65536,
+ "default_max_tokens": 13107,
"can_reason": false,
"supports_attachments": false,
"options": {}
@@ -1566,8 +1566,8 @@
{
"id": "nvidia/nemotron-nano-9b-v2",
"name": "NVIDIA: Nemotron Nano 9B V2",
- "cost_per_1m_in": 0.06,
- "cost_per_1m_out": 0.25,
+ "cost_per_1m_in": 0.04,
+ "cost_per_1m_out": 0.16,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 131072,
@@ -1742,9 +1742,9 @@
"cost_per_1m_in": 0.09999999999999999,
"cost_per_1m_out": 0.39999999999999997,
"cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0.024999999999999998,
+ "cost_per_1m_out_cached": 0.03,
"context_window": 1047576,
- "default_max_tokens": 16384,
+ "default_max_tokens": 104757,
"can_reason": false,
"supports_attachments": true,
"options": {}
@@ -1935,9 +1935,9 @@
"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",
@@ -1954,9 +1954,9 @@
"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",
@@ -1989,12 +1989,12 @@
{
"id": "openai/gpt-oss-120b",
"name": "OpenAI: gpt-oss-120b",
- "cost_per_1m_in": 0.09999999999999999,
- "cost_per_1m_out": 0.49,
+ "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": 13107,
+ "default_max_tokens": 16384,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -2027,8 +2027,8 @@
{
"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,
@@ -2250,12 +2250,12 @@
{
"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": 0.07,
+ "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": {}
@@ -2366,8 +2366,8 @@
{
"id": "qwen/qwen3-14b",
"name": "Qwen: Qwen3 14B",
- "cost_per_1m_in": 0.049999999999999996,
- "cost_per_1m_out": 0.22,
+ "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,
@@ -2423,31 +2423,25 @@
{
"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": 0.09999999999999999,
+ "cost_per_1m_out": 0.09999999999999999,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 262144,
"default_max_tokens": 131072,
- "can_reason": true,
- "reasoning_levels": [
- "low",
- "medium",
- "high"
- ],
- "default_reasoning_effort": "medium",
+ "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": 0.65,
- "cost_per_1m_out": 3,
+ "cost_per_1m_in": 0.11,
+ "cost_per_1m_out": 0.6,
"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",
@@ -2480,12 +2474,12 @@
{
"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": {}
@@ -2493,12 +2487,12 @@
{
"id": "qwen/qwen3-30b-a3b-thinking-2507",
"name": "Qwen: Qwen3 30B A3B Thinking 2507",
- "cost_per_1m_in": 0.09999999999999999,
+ "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,
- "default_max_tokens": 26214,
+ "default_max_tokens": 65536,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -2547,25 +2541,6 @@
"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",
@@ -2666,8 +2641,8 @@
{
"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": 1.4,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 262144,
@@ -2699,11 +2674,11 @@
"id": "qwen/qwen3-vl-235b-a22b-instruct",
"name": "Qwen: Qwen3 VL 235B A22B Instruct",
"cost_per_1m_in": 0.3,
- "cost_per_1m_out": 1.49,
+ "cost_per_1m_out": 1.2,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
- "context_window": 131072,
- "default_max_tokens": 13107,
+ "context_window": 262144,
+ "default_max_tokens": 131072,
"can_reason": false,
"supports_attachments": true,
"options": {}
@@ -2762,11 +2737,11 @@
{
"id": "qwen/qwen3-vl-8b-instruct",
"name": "Qwen: Qwen3 VL 8B Instruct",
- "cost_per_1m_in": 0.18,
- "cost_per_1m_out": 0.7,
+ "cost_per_1m_in": 0.08,
+ "cost_per_1m_out": 0.5,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
- "context_window": 256000,
+ "context_window": 131072,
"default_max_tokens": 16384,
"can_reason": false,
"supports_attachments": true,
@@ -2928,12 +2903,12 @@
{
"id": "z-ai/glm-4.5-air",
"name": "Z.AI: GLM 4.5 Air",
- "cost_per_1m_in": 0.19999999999999998,
- "cost_per_1m_out": 1.2,
+ "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": 13107,
+ "default_max_tokens": 49152,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -2985,12 +2960,12 @@
{
"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",
@@ -3055,10 +3030,10 @@
{
"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,
@@ -3068,10 +3043,10 @@
{
"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,