@@ -158,7 +158,7 @@
"cost_per_1m_in_cached": 3.75,
"cost_per_1m_out_cached": 0.3,
"context_window": 200000,
- "default_max_tokens": 32000,
+ "default_max_tokens": 64000,
"can_reason": true,
"has_reasoning_efforts": true,
"supports_attachments": true
@@ -296,12 +296,12 @@
{
"id": "deepseek/deepseek-chat-v3-0324",
"name": "DeepSeek: DeepSeek V3 0324",
- "cost_per_1m_in": 0.28,
- "cost_per_1m_out": 0.88,
+ "cost_per_1m_in": 0.24,
+ "cost_per_1m_out": 0.84,
"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": false,
"has_reasoning_efforts": false,
"supports_attachments": false
@@ -335,12 +335,12 @@
{
"id": "deepseek/deepseek-v3.1-terminus",
"name": "DeepSeek: DeepSeek V3.1 Terminus",
- "cost_per_1m_in": 0.44999999999999996,
- "cost_per_1m_out": 1.5,
+ "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": 131072,
- "default_max_tokens": 65536,
+ "context_window": 163840,
+ "default_max_tokens": 81920,
"can_reason": true,
"has_reasoning_efforts": true,
"supports_attachments": false
@@ -348,12 +348,12 @@
{
"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": 0.27,
+ "cost_per_1m_out": 0.41,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 163840,
- "default_max_tokens": 81920,
+ "default_max_tokens": 32768,
"can_reason": true,
"has_reasoning_efforts": true,
"supports_attachments": false
@@ -595,12 +595,12 @@
{
"id": "meta-llama/llama-3.1-405b-instruct",
"name": "Meta: Llama 3.1 405B Instruct",
- "cost_per_1m_in": 3,
- "cost_per_1m_out": 3,
+ "cost_per_1m_in": 0.7999999999999999,
+ "cost_per_1m_out": 0.7999999999999999,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
- "context_window": 131072,
- "default_max_tokens": 13107,
+ "context_window": 32768,
+ "default_max_tokens": 8192,
"can_reason": false,
"has_reasoning_efforts": false,
"supports_attachments": false
@@ -621,12 +621,12 @@
{
"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": 0.09999999999999999,
+ "cost_per_1m_out": 0.09999999999999999,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 131072,
- "default_max_tokens": 8192,
+ "default_max_tokens": 4000,
"can_reason": false,
"has_reasoning_efforts": false,
"supports_attachments": false
@@ -648,11 +648,11 @@
"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_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": 8192,
"can_reason": false,
"has_reasoning_efforts": false,
"supports_attachments": false
@@ -686,12 +686,12 @@
{
"id": "meta-llama/llama-4-maverick",
"name": "Meta: Llama 4 Maverick",
- "cost_per_1m_in": 0.15,
- "cost_per_1m_out": 0.85,
+ "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": 1048576,
- "default_max_tokens": 8192,
+ "default_max_tokens": 104857,
"can_reason": false,
"has_reasoning_efforts": false,
"supports_attachments": true
@@ -1076,12 +1076,12 @@
{
"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,
"has_reasoning_efforts": false,
"supports_attachments": true
@@ -1190,6 +1190,19 @@
"has_reasoning_efforts": false,
"supports_attachments": false
},
+ {
+ "id": "nvidia/llama-3.3-nemotron-super-49b-v1.5",
+ "name": "NVIDIA: Llama 3.3 Nemotron Super 49B V1.5",
+ "cost_per_1m_in": 0.09999999999999999,
+ "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,
+ "can_reason": true,
+ "has_reasoning_efforts": true,
+ "supports_attachments": false
+ },
{
"id": "nvidia/nemotron-nano-9b-v2",
"name": "NVIDIA: Nemotron Nano 9B V2",
@@ -1229,19 +1242,6 @@
"has_reasoning_efforts": false,
"supports_attachments": false
},
- {
- "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,
- "has_reasoning_efforts": true,
- "supports_attachments": false
- },
{
"id": "openai/codex-mini",
"name": "OpenAI: Codex Mini",
@@ -1534,9 +1534,9 @@
"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,
"has_reasoning_efforts": true,
"supports_attachments": true
@@ -1547,9 +1547,9 @@
"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,
"has_reasoning_efforts": true,
"supports_attachments": true
@@ -1583,12 +1583,12 @@
{
"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,
- "default_max_tokens": 65536,
+ "default_max_tokens": 13107,
"can_reason": true,
"has_reasoning_efforts": true,
"supports_attachments": false
@@ -1801,6 +1801,19 @@
"has_reasoning_efforts": true,
"supports_attachments": false
},
+ {
+ "id": "qwen/qwen3-235b-a22b:free",
+ "name": "Qwen: Qwen3 235B A22B (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": 13107,
+ "can_reason": false,
+ "has_reasoning_efforts": false,
+ "supports_attachments": false
+ },
{
"id": "qwen/qwen3-235b-a22b-2507",
"name": "Qwen: Qwen3 235B A22B Instruct 2507",
@@ -1856,12 +1869,12 @@
{
"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,
"has_reasoning_efforts": true,
"supports_attachments": false
@@ -1895,12 +1908,12 @@
{
"id": "qwen/qwen3-coder-30b-a3b-instruct",
"name": "Qwen: Qwen3 Coder 30B A3B Instruct",
- "cost_per_1m_in": 0.09999999999999999,
- "cost_per_1m_out": 0.3,
+ "cost_per_1m_in": 0.07,
+ "cost_per_1m_out": 0.28,
"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,
"has_reasoning_efforts": false,
"supports_attachments": false
@@ -1986,12 +1999,12 @@
{
"id": "qwen/qwen3-next-80b-a3b-thinking",
"name": "Qwen: Qwen3 Next 80B A3B Thinking",
- "cost_per_1m_in": 0.14,
- "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,
- "default_max_tokens": 26214,
+ "default_max_tokens": 131072,
"can_reason": true,
"has_reasoning_efforts": true,
"supports_attachments": false
@@ -2142,12 +2155,12 @@
{
"id": "z-ai/glm-4.5-air",
"name": "Z.AI: GLM 4.5 Air",
- "cost_per_1m_in": 0.19999999999999998,
- "cost_per_1m_out": 1.1,
+ "cost_per_1m_in": 0.14,
+ "cost_per_1m_out": 0.86,
"cost_per_1m_in_cached": 0,
- "cost_per_1m_out_cached": 0.03,
+ "cost_per_1m_out_cached": 0,
"context_window": 131072,
- "default_max_tokens": 48000,
+ "default_max_tokens": 65536,
"can_reason": true,
"has_reasoning_efforts": true,
"supports_attachments": false
@@ -2194,10 +2207,10 @@
{
"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,
@@ -2207,10 +2220,10 @@
{
"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,