@@ -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,
@@ -209,7 +209,7 @@
"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",
@@ -611,12 +611,12 @@
{
"id": "deepseek/deepseek-v3.2-exp",
"name": "DeepSeek: DeepSeek V3.2 Exp",
- "cost_per_1m_in": 0.28,
- "cost_per_1m_out": 0.39999999999999997,
+ "cost_per_1m_in": 0.21,
+ "cost_per_1m_out": 0.32,
"cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0,
+ "cost_per_1m_out_cached": 0.16799999999999998,
"context_window": 163840,
- "default_max_tokens": 32768,
+ "default_max_tokens": 16384,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -649,12 +649,12 @@
{
"id": "deepseek/deepseek-r1-0528",
"name": "DeepSeek: R1 0528",
- "cost_per_1m_in": 0.7999999999999999,
- "cost_per_1m_out": 2.4,
+ "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",
@@ -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",
@@ -956,12 +956,12 @@
{
"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": 0.049999999999999996,
+ "cost_per_1m_out": 0.08,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 131072,
- "default_max_tokens": 8192,
+ "default_max_tokens": 65536,
"can_reason": false,
"supports_attachments": false,
"options": {}
@@ -982,12 +982,12 @@
{
"id": "meta-llama/llama-3.3-70b-instruct",
"name": "Meta: Llama 3.3 70B Instruct",
- "cost_per_1m_in": 0.09999999999999999,
- "cost_per_1m_out": 0.32,
+ "cost_per_1m_in": 0.22999999999999998,
+ "cost_per_1m_out": 0.39999999999999997,
"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": {}
@@ -1469,12 +1469,12 @@
{
"id": "moonshotai/kimi-k2",
"name": "MoonshotAI: Kimi K2 0711",
- "cost_per_1m_in": 0.7,
- "cost_per_1m_out": 2.5,
+ "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": {}
@@ -1482,8 +1482,8 @@
{
"id": "moonshotai/kimi-k2-0905",
"name": "MoonshotAI: Kimi K2 0905",
- "cost_per_1m_in": 0.59,
- "cost_per_1m_out": 2.99,
+ "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,
@@ -1508,10 +1508,10 @@
{
"id": "moonshotai/kimi-k2-thinking",
"name": "MoonshotAI: Kimi K2 Thinking",
- "cost_per_1m_in": 0.6,
+ "cost_per_1m_in": 0.5,
"cost_per_1m_out": 2.5,
"cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0.15,
+ "cost_per_1m_out_cached": 0,
"context_window": 262144,
"default_max_tokens": 131072,
"can_reason": true,
@@ -1645,6 +1645,25 @@
"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",
@@ -1735,9 +1754,9 @@
"cost_per_1m_in": 0.09999999999999999,
"cost_per_1m_out": 0.39999999999999997,
"cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0.03,
+ "cost_per_1m_out_cached": 0.024999999999999998,
"context_window": 1047576,
- "default_max_tokens": 104757,
+ "default_max_tokens": 16384,
"can_reason": false,
"supports_attachments": true,
"options": {}
@@ -1928,9 +1947,9 @@
"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",
@@ -1947,9 +1966,9 @@
"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",
@@ -2141,12 +2160,12 @@
{
"id": "openai/gpt-oss-120b:exacto",
"name": "OpenAI: gpt-oss-120b (exacto)",
- "cost_per_1m_in": 0.039,
- "cost_per_1m_out": 0.19,
+ "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": 13107,
+ "default_max_tokens": 32768,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -2179,8 +2198,8 @@
{
"id": "openai/gpt-oss-20b",
"name": "OpenAI: gpt-oss-20b",
- "cost_per_1m_in": 0.049999999999999996,
- "cost_per_1m_out": 0.19999999999999998,
+ "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,
@@ -2661,25 +2680,6 @@
"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": 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",
@@ -2774,8 +2774,8 @@
{
"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": 0.09,
+ "cost_per_1m_out": 1.1,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 262144,
@@ -2787,8 +2787,8 @@
{
"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,
@@ -2806,35 +2806,16 @@
{
"id": "qwen/qwen3-vl-235b-a22b-instruct",
"name": "Qwen: Qwen3 VL 235B A22B Instruct",
- "cost_per_1m_in": 0.3,
- "cost_per_1m_out": 1.4,
+ "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": {}
},
- {
- "id": "qwen/qwen3-vl-235b-a22b-thinking",
- "name": "Qwen: Qwen3 VL 235B A22B Thinking",
- "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,
- "default_max_tokens": 131072,
- "can_reason": true,
- "reasoning_levels": [
- "low",
- "medium",
- "high"
- ],
- "default_reasoning_effort": "medium",
- "supports_attachments": true,
- "options": {}
- },
{
"id": "qwen/qwen3-vl-30b-a3b-instruct",
"name": "Qwen: Qwen3 VL 30B A3B Instruct",
@@ -3125,10 +3106,10 @@
{
"id": "z-ai/glm-4.5v",
"name": "Z.AI: GLM 4.5V",
- "cost_per_1m_in": 0.48,
- "cost_per_1m_out": 1.44,
+ "cost_per_1m_in": 0.6,
+ "cost_per_1m_out": 1.7999999999999998,
"cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0.088,
+ "cost_per_1m_out_cached": 0.11,
"context_window": 65536,
"default_max_tokens": 8192,
"can_reason": true,
@@ -3185,9 +3166,9 @@
"cost_per_1m_in": 0.3,
"cost_per_1m_out": 0.8999999999999999,
"cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0.049999999999999996,
+ "cost_per_1m_out_cached": 0,
"context_window": 131072,
- "default_max_tokens": 12000,
+ "default_max_tokens": 65536,
"can_reason": true,
"reasoning_levels": [
"low",
@@ -3227,10 +3208,10 @@
{
"id": "x-ai/grok-3-mini",
"name": "xAI: Grok 3 Mini",
- "cost_per_1m_in": 0.6,
- "cost_per_1m_out": 4,
+ "cost_per_1m_in": 0.3,
+ "cost_per_1m_out": 0.5,
"cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0.15,
+ "cost_per_1m_out_cached": 0.075,
"context_window": 131072,
"default_max_tokens": 13107,
"can_reason": true,
@@ -3246,10 +3227,10 @@
{
"id": "x-ai/grok-3-mini-beta",
"name": "xAI: Grok 3 Mini Beta",
- "cost_per_1m_in": 0.6,
- "cost_per_1m_out": 4,
+ "cost_per_1m_in": 0.3,
+ "cost_per_1m_out": 0.5,
"cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0.15,
+ "cost_per_1m_out_cached": 0.075,
"context_window": 131072,
"default_max_tokens": 13107,
"can_reason": true,