npm - @fleetagent/pi-ai - Versions diffs - 0.0.6 → 0.0.8 - Mend

@fleetagent/pi-ai 0.0.6 → 0.0.8

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (42) hide show

package/README.md +1 -1
package/dist/image-models.generated.d.ts +15 -0
package/dist/image-models.generated.d.ts.map +1 -1
package/dist/image-models.generated.js +15 -0
package/dist/image-models.generated.js.map +1 -1
package/dist/models.generated.d.ts +863 -380
package/dist/models.generated.d.ts.map +1 -1
package/dist/models.generated.js +1064 -678
package/dist/models.generated.js.map +1 -1
package/dist/providers/anthropic.d.ts.map +1 -1
package/dist/providers/anthropic.js +21 -12
package/dist/providers/anthropic.js.map +1 -1
package/dist/providers/azure-openai-responses.d.ts.map +1 -1
package/dist/providers/azure-openai-responses.js +1 -1
package/dist/providers/azure-openai-responses.js.map +1 -1
package/dist/providers/images/openrouter.d.ts.map +1 -1
package/dist/providers/images/openrouter.js +1 -1
package/dist/providers/images/openrouter.js.map +1 -1
package/dist/providers/openai-codex-responses.d.ts.map +1 -1
package/dist/providers/openai-codex-responses.js +163 -81
package/dist/providers/openai-codex-responses.js.map +1 -1
package/dist/providers/openai-completions.d.ts.map +1 -1
package/dist/providers/openai-completions.js +14 -4
package/dist/providers/openai-completions.js.map +1 -1
package/dist/providers/openai-responses-shared.d.ts.map +1 -1
package/dist/providers/openai-responses-shared.js +4 -1
package/dist/providers/openai-responses-shared.js.map +1 -1
package/dist/providers/openai-responses.d.ts.map +1 -1
package/dist/providers/openai-responses.js +1 -1
package/dist/providers/openai-responses.js.map +1 -1
package/dist/types.d.ts +26 -2
package/dist/types.d.ts.map +1 -1
package/dist/types.js.map +1 -1
package/dist/utils/abort-signals.d.ts +6 -0
package/dist/utils/abort-signals.d.ts.map +1 -0
package/dist/utils/abort-signals.js +34 -0
package/dist/utils/abort-signals.js.map +1 -0
package/dist/utils/overflow.d.ts +2 -1
package/dist/utils/overflow.d.ts.map +1 -1
package/dist/utils/overflow.js +5 -2
package/dist/utils/overflow.js.map +1 -1
package/package.json +2 -1

package/dist/models.generated.js CHANGED Viewed

@@ -157,6 +157,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "anthropic.claude-opus-4-8": {
+            id: "anthropic.claude-opus-4-8",
+            name: "Claude Opus 4.8",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "anthropic.claude-sonnet-4-5-20250929-v1:0": {
             id: "anthropic.claude-sonnet-4-5-20250929-v1:0",
             name: "Claude Sonnet 4.5",
@@ -226,6 +243,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "au.anthropic.claude-opus-4-8": {
+            id: "au.anthropic.claude-opus-4-8",
+            name: "Claude Opus 4.8 (AU)",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "au.anthropic.claude-sonnet-4-5-20250929-v1:0": {
             id: "au.anthropic.claude-sonnet-4-5-20250929-v1:0",
             name: "Claude Sonnet 4.5 (AU)",
@@ -355,8 +389,8 @@ export const MODELS = {
             thinkingLevelMap: { "xhigh": "max" },
             input: ["text", "image"],
             cost: {
-                input: 5,
-                output: 25,
+                input: 5.5,
+                output: 27.5,
                 cacheRead: 0.5,
                 cacheWrite: 6.25,
             },
@@ -373,10 +407,27 @@ export const MODELS = {
             thinkingLevelMap: { "xhigh": "xhigh" },
             input: ["text", "image"],
             cost: {
-                input: 5,
-                output: 25,
-                cacheRead: 0.5,
-                cacheWrite: 6.25,
+                input: 5.5,
+                output: 27.5,
+                cacheRead: 0.55,
+                cacheWrite: 6.875,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
+        "eu.anthropic.claude-opus-4-8": {
+            id: "eu.anthropic.claude-opus-4-8",
+            name: "Claude Opus 4.8 (EU)",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.eu-central-1.amazonaws.com",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 5.5,
+                output: 27.5,
+                cacheRead: 0.55,
+                cacheWrite: 6.875,
             },
             contextWindow: 1000000,
             maxTokens: 128000,
@@ -390,10 +441,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 3,
-                output: 15,
-                cacheRead: 0.3,
-                cacheWrite: 3.75,
+                input: 3.3,
+                output: 16.5,
+                cacheRead: 0.33,
+                cacheWrite: 4.125,
             },
             contextWindow: 200000,
             maxTokens: 64000,
@@ -407,10 +458,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 3,
-                output: 15,
-                cacheRead: 0.3,
-                cacheWrite: 3.75,
+                input: 3.3,
+                output: 16.5,
+                cacheRead: 0.33,
+                cacheWrite: 4.125,
             },
             contextWindow: 1000000,
             maxTokens: 64000,
@@ -485,6 +536,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "global.anthropic.claude-opus-4-8": {
+            id: "global.anthropic.claude-opus-4-8",
+            name: "Claude Opus 4.8 (Global)",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "global.anthropic.claude-sonnet-4-5-20250929-v1:0": {
             id: "global.anthropic.claude-sonnet-4-5-20250929-v1:0",
             name: "Claude Sonnet 4.5 (Global)",
@@ -571,6 +639,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "jp.anthropic.claude-opus-4-8": {
+            id: "jp.anthropic.claude-opus-4-8",
+            name: "Claude Opus 4.8 (JP)",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "jp.anthropic.claude-sonnet-4-5-20250929-v1:0": {
             id: "jp.anthropic.claude-sonnet-4-5-20250929-v1:0",
             name: "Claude Sonnet 4.5 (JP)",
@@ -996,6 +1081,59 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 131072,
         },
+        "openai.gpt-5.4": {
+            id: "openai.gpt-5.4",
+            name: "GPT-5.4",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh" },
+            input: ["text", "image"],
+            cost: {
+                input: 2.75,
+                output: 16.5,
+                cacheRead: 0.275,
+                cacheWrite: 0,
+            },
+            contextWindow: 272000,
+            maxTokens: 128000,
+        },
+        "openai.gpt-5.5": {
+            id: "openai.gpt-5.5",
+            name: "GPT-5.5",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh" },
+            input: ["text", "image"],
+            cost: {
+                input: 5.5,
+                output: 33,
+                cacheRead: 0.55,
+                cacheWrite: 0,
+            },
+            contextWindow: 272000,
+            maxTokens: 128000,
+        },
+        "openai.gpt-oss-120b": {
+            id: "openai.gpt-oss-120b",
+            name: "gpt-oss-120b",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.15,
+                output: 0.6,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 16384,
+        },
         "openai.gpt-oss-120b-1:0": {
             id: "openai.gpt-oss-120b-1:0",
             name: "gpt-oss-120b",
@@ -1013,6 +1151,23 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 16384,
         },
+        "openai.gpt-oss-20b": {
+            id: "openai.gpt-oss-20b",
+            name: "gpt-oss-20b",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.07,
+                output: 0.3,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 16384,
+        },
         "openai.gpt-oss-20b-1:0": {
             id: "openai.gpt-oss-20b-1:0",
             name: "gpt-oss-20b",
@@ -1270,6 +1425,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "us.anthropic.claude-opus-4-8": {
+            id: "us.anthropic.claude-opus-4-8",
+            name: "Claude Opus 4.8 (US)",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "us.anthropic.claude-sonnet-4-5-20250929-v1:0": {
             id: "us.anthropic.claude-sonnet-4-5-20250929-v1:0",
             name: "Claude Sonnet 4.5 (US)",
@@ -1720,6 +1892,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "anthropic",
             baseUrl: "https://api.anthropic.com",
+            compat: { "forceAdaptiveThinking": true },
             reasoning: true,
             thinkingLevelMap: { "xhigh": "max" },
             input: ["text", "image"],
@@ -1738,6 +1911,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "anthropic",
             baseUrl: "https://api.anthropic.com",
+            compat: { "forceAdaptiveThinking": true, "supportsTemperature": false },
             reasoning: true,
             thinkingLevelMap: { "xhigh": "xhigh" },
             input: ["text", "image"],
@@ -1750,6 +1924,24 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "claude-opus-4-8": {
+            id: "claude-opus-4-8",
+            name: "Claude Opus 4.8",
+            api: "anthropic-messages",
+            provider: "anthropic",
+            baseUrl: "https://api.anthropic.com",
+            compat: { "forceAdaptiveThinking": true, "supportsTemperature": false },
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "claude-sonnet-4-0": {
             id: "claude-sonnet-4-0",
             name: "Claude Sonnet 4 (latest)",
@@ -1824,6 +2016,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "anthropic",
             baseUrl: "https://api.anthropic.com",
+            compat: { "forceAdaptiveThinking": true },
             reasoning: true,
             input: ["text", "image"],
             cost: {
@@ -1916,7 +2109,7 @@ export const MODELS = {
             cost: {
                 input: 0.1,
                 output: 0.4,
-                cacheRead: 0.03,
+                cacheRead: 0.025,
                 cacheWrite: 0,
             },
             contextWindow: 1047576,
@@ -2001,7 +2194,7 @@ export const MODELS = {
             cost: {
                 input: 0.15,
                 output: 0.6,
-                cacheRead: 0.08,
+                cacheRead: 0.075,
                 cacheWrite: 0,
             },
             contextWindow: 128000,
@@ -2127,7 +2320,7 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 10,
-                cacheRead: 0.13,
+                cacheRead: 0.125,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
@@ -2428,7 +2621,7 @@ export const MODELS = {
             provider: "azure-openai-responses",
             baseUrl: "",
             reasoning: true,
-            thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
+            thinkingLevelMap: { "off": null, "xhigh": "xhigh", "minimal": null, "low": null },
             input: ["text", "image"],
             cost: {
                 input: 30,
@@ -2552,7 +2745,7 @@ export const MODELS = {
             cost: {
                 input: 1.1,
                 output: 4.4,
-                cacheRead: 0.28,
+                cacheRead: 0.275,
                 cacheWrite: 0,
             },
             contextWindow: 200000,
@@ -2611,23 +2804,6 @@ export const MODELS = {
             contextWindow: 32000,
             maxTokens: 8000,
         },
-        "qwen-3-235b-a22b-instruct-2507": {
-            id: "qwen-3-235b-a22b-instruct-2507",
-            name: "Qwen 3 235B Instruct",
-            api: "openai-completions",
-            provider: "cerebras",
-            baseUrl: "https://api.cerebras.ai/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.6,
-                output: 1.2,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131000,
-            maxTokens: 32000,
-        },
         "zai-glm-4.7": {
             id: "zai-glm-4.7",
             name: "Z.AI GLM-4.7",
@@ -2823,6 +2999,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "cloudflare-ai-gateway",
             baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
+            compat: { "forceAdaptiveThinking": true },
             reasoning: true,
             thinkingLevelMap: { "xhigh": "max" },
             input: ["text", "image"],
@@ -2841,6 +3018,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "cloudflare-ai-gateway",
             baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
+            compat: { "forceAdaptiveThinking": true, "supportsTemperature": false },
             reasoning: true,
             thinkingLevelMap: { "xhigh": "xhigh" },
             input: ["text", "image"],
@@ -2853,6 +3031,24 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "claude-opus-4-8": {
+            id: "claude-opus-4-8",
+            name: "Claude Opus 4.8",
+            api: "anthropic-messages",
+            provider: "cloudflare-ai-gateway",
+            baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
+            compat: { "forceAdaptiveThinking": true, "supportsTemperature": false },
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "claude-sonnet-4": {
             id: "claude-sonnet-4",
             name: "Claude Sonnet 4 (latest)",
@@ -2893,6 +3089,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "cloudflare-ai-gateway",
             baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
+            compat: { "forceAdaptiveThinking": true },
             reasoning: true,
             input: ["text", "image"],
             cost: {
@@ -3347,24 +3544,6 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 128000,
         },
-        "@cf/moonshotai/kimi-k2.5": {
-            id: "@cf/moonshotai/kimi-k2.5",
-            name: "Kimi K2.5",
-            api: "openai-completions",
-            provider: "cloudflare-workers-ai",
-            baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
-            compat: { "sendSessionAffinityHeaders": true },
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.6,
-                output: 3,
-                cacheRead: 0.1,
-                cacheWrite: 0,
-            },
-            contextWindow: 256000,
-            maxTokens: 256000,
-        },
         "@cf/moonshotai/kimi-k2.6": {
             id: "@cf/moonshotai/kimi-k2.6",
             name: "Kimi K2.6",
@@ -3692,8 +3871,8 @@ export const MODELS = {
                 cacheRead: 0.1,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
-            maxTokens: 8192,
+            contextWindow: 262144,
+            maxTokens: 65536,
         },
         "accounts/fireworks/routers/glm-5p1-fast": {
             id: "accounts/fireworks/routers/glm-5p1-fast",
@@ -3735,7 +3914,7 @@ export const MODELS = {
     "github-copilot": {
         "claude-haiku-4.5": {
             id: "claude-haiku-4.5",
-            name: "Claude Haiku 4.5",
+            name: "Claude Haiku 4.5 (latest)",
             api: "anthropic-messages",
             provider: "github-copilot",
             baseUrl: "https://api.individual.githubcopilot.com",
@@ -3744,17 +3923,17 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
+                input: 1,
+                output: 5,
+                cacheRead: 0.1,
+                cacheWrite: 1.25,
             },
-            contextWindow: 144000,
-            maxTokens: 32000,
+            contextWindow: 200000,
+            maxTokens: 64000,
         },
         "claude-opus-4.5": {
             id: "claude-opus-4.5",
-            name: "Claude Opus 4.5",
+            name: "Claude Opus 4.5 (latest)",
             api: "anthropic-messages",
             provider: "github-copilot",
             baseUrl: "https://api.individual.githubcopilot.com",
@@ -3762,13 +3941,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 160000,
-            maxTokens: 32000,
+                input: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
+            },
+            contextWindow: 200000,
+            maxTokens: 32000,
         },
         "claude-opus-4.6": {
             id: "claude-opus-4.6",
@@ -3777,17 +3956,18 @@ export const MODELS = {
             provider: "github-copilot",
             baseUrl: "https://api.individual.githubcopilot.com",
             headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
+            compat: { "forceAdaptiveThinking": true },
             reasoning: true,
             thinkingLevelMap: { "xhigh": "max" },
             input: ["text", "image"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
+                input: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
             },
             contextWindow: 1000000,
-            maxTokens: 64000,
+            maxTokens: 32000,
         },
         "claude-opus-4.7": {
             id: "claude-opus-4.7",
@@ -3796,21 +3976,60 @@ export const MODELS = {
             provider: "github-copilot",
             baseUrl: "https://api.individual.githubcopilot.com",
             headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
+            compat: { "forceAdaptiveThinking": true, "supportsTemperature": false },
             reasoning: true,
             thinkingLevelMap: { "xhigh": "xhigh" },
             input: ["text", "image"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
+                input: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
+            },
+            contextWindow: 200000,
+            maxTokens: 32000,
+        },
+        "claude-opus-4.8": {
+            id: "claude-opus-4.8",
+            name: "Claude Opus 4.8",
+            api: "anthropic-messages",
+            provider: "github-copilot",
+            baseUrl: "https://api.individual.githubcopilot.com",
+            headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
+            compat: { "forceAdaptiveThinking": true, "supportsTemperature": false },
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
             },
-            contextWindow: 144000,
+            contextWindow: 200000,
             maxTokens: 64000,
         },
+        "claude-sonnet-4": {
+            id: "claude-sonnet-4",
+            name: "Claude Sonnet 4 (latest)",
+            api: "anthropic-messages",
+            provider: "github-copilot",
+            baseUrl: "https://api.individual.githubcopilot.com",
+            headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
+            compat: { "supportsEagerToolInputStreaming": false },
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 3,
+                output: 15,
+                cacheRead: 0.3,
+                cacheWrite: 3.75,
+            },
+            contextWindow: 216000,
+            maxTokens: 16000,
+        },
         "claude-sonnet-4.5": {
             id: "claude-sonnet-4.5",
-            name: "Claude Sonnet 4.5",
+            name: "Claude Sonnet 4.5 (latest)",
             api: "anthropic-messages",
             provider: "github-copilot",
             baseUrl: "https://api.individual.githubcopilot.com",
@@ -3819,12 +4038,12 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
+                input: 3,
+                output: 15,
+                cacheRead: 0.3,
+                cacheWrite: 3.75,
             },
-            contextWindow: 144000,
+            contextWindow: 200000,
             maxTokens: 32000,
         },
         "claude-sonnet-4.6": {
@@ -3834,13 +4053,14 @@ export const MODELS = {
             provider: "github-copilot",
             baseUrl: "https://api.individual.githubcopilot.com",
             headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
+            compat: { "forceAdaptiveThinking": true },
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
+                input: 3,
+                output: 15,
+                cacheRead: 0.3,
+                cacheWrite: 3.75,
             },
             contextWindow: 1000000,
             maxTokens: 32000,
@@ -3853,12 +4073,12 @@ export const MODELS = {
             baseUrl: "https://api.individual.githubcopilot.com",
             headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
             compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
-            reasoning: false,
+            reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
+                input: 1.25,
+                output: 10,
+                cacheRead: 0.125,
                 cacheWrite: 0,
             },
             contextWindow: 128000,
@@ -3866,7 +4086,7 @@ export const MODELS = {
         },
         "gemini-3-flash-preview": {
             id: "gemini-3-flash-preview",
-            name: "Gemini 3 Flash",
+            name: "Gemini 3 Flash Preview",
             api: "openai-completions",
             provider: "github-copilot",
             baseUrl: "https://api.individual.githubcopilot.com",
@@ -3875,9 +4095,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
+                input: 0.5,
+                output: 3,
+                cacheRead: 0.05,
                 cacheWrite: 0,
             },
             contextWindow: 128000,
@@ -3894,12 +4114,12 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
+                input: 2,
+                output: 12,
+                cacheRead: 0.2,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
+            contextWindow: 200000,
             maxTokens: 64000,
         },
         "gemini-3.5-flash": {
@@ -3913,12 +4133,12 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
+                input: 1.5,
+                output: 9,
+                cacheRead: 0.15,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
+            contextWindow: 200000,
             maxTokens: 64000,
         },
         "gpt-4.1": {
@@ -3932,36 +4152,17 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
+                input: 2,
+                output: 8,
+                cacheRead: 0.5,
                 cacheWrite: 0,
             },
             contextWindow: 128000,
             maxTokens: 16384,
         },
-        "gpt-4o": {
-            id: "gpt-4o",
-            name: "GPT-4o",
-            api: "openai-completions",
-            provider: "github-copilot",
-            baseUrl: "https://api.individual.githubcopilot.com",
-            headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 4096,
-        },
         "gpt-5-mini": {
             id: "gpt-5-mini",
-            name: "GPT-5-mini",
+            name: "GPT-5 Mini",
             api: "openai-responses",
             provider: "github-copilot",
             baseUrl: "https://api.individual.githubcopilot.com",
@@ -3970,9 +4171,9 @@ export const MODELS = {
             thinkingLevelMap: { "off": null, "minimal": "low" },
             input: ["text", "image"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
+                input: 0.25,
+                output: 2,
+                cacheRead: 0.025,
                 cacheWrite: 0,
             },
             contextWindow: 264000,
@@ -3989,17 +4190,17 @@ export const MODELS = {
             thinkingLevelMap: { "off": null, "minimal": "low", "xhigh": "xhigh" },
             input: ["text", "image"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
+                input: 1.75,
+                output: 14,
+                cacheRead: 0.175,
                 cacheWrite: 0,
             },
-            contextWindow: 264000,
-            maxTokens: 64000,
+            contextWindow: 400000,
+            maxTokens: 128000,
         },
         "gpt-5.2-codex": {
             id: "gpt-5.2-codex",
-            name: "GPT-5.2-Codex",
+            name: "GPT-5.2 Codex",
             api: "openai-responses",
             provider: "github-copilot",
             baseUrl: "https://api.individual.githubcopilot.com",
@@ -4008,9 +4209,9 @@ export const MODELS = {
             thinkingLevelMap: { "off": null, "minimal": "low", "xhigh": "xhigh" },
             input: ["text", "image"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
+                input: 1.75,
+                output: 14,
+                cacheRead: 0.175,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
@@ -4018,7 +4219,7 @@ export const MODELS = {
         },
         "gpt-5.3-codex": {
             id: "gpt-5.3-codex",
-            name: "GPT-5.3-Codex",
+            name: "GPT-5.3 Codex",
             api: "openai-responses",
             provider: "github-copilot",
             baseUrl: "https://api.individual.githubcopilot.com",
@@ -4027,9 +4228,9 @@ export const MODELS = {
             thinkingLevelMap: { "off": null, "minimal": "low", "xhigh": "xhigh" },
             input: ["text", "image"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
+                input: 1.75,
+                output: 14,
+                cacheRead: 0.175,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
@@ -4046,9 +4247,9 @@ export const MODELS = {
             thinkingLevelMap: { "off": null, "minimal": "low", "xhigh": "xhigh" },
             input: ["text", "image"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
+                input: 2.5,
+                output: 15,
+                cacheRead: 0.25,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
@@ -4056,7 +4257,7 @@ export const MODELS = {
         },
         "gpt-5.4-mini": {
             id: "gpt-5.4-mini",
-            name: "GPT-5.4 Mini",
+            name: "GPT-5.4 mini",
             api: "openai-responses",
             provider: "github-copilot",
             baseUrl: "https://api.individual.githubcopilot.com",
@@ -4065,9 +4266,28 @@ export const MODELS = {
             thinkingLevelMap: { "off": null, "minimal": "low", "xhigh": "xhigh" },
             input: ["text", "image"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
+                input: 0.75,
+                output: 4.5,
+                cacheRead: 0.075,
+                cacheWrite: 0,
+            },
+            contextWindow: 400000,
+            maxTokens: 128000,
+        },
+        "gpt-5.4-nano": {
+            id: "gpt-5.4-nano",
+            name: "GPT-5.4 nano",
+            api: "openai-responses",
+            provider: "github-copilot",
+            baseUrl: "https://api.individual.githubcopilot.com",
+            headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
+            reasoning: true,
+            thinkingLevelMap: { "off": null, "minimal": "low", "xhigh": "xhigh" },
+            input: ["text", "image"],
+            cost: {
+                input: 0.2,
+                output: 1.25,
+                cacheRead: 0.02,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
@@ -4084,32 +4304,32 @@ export const MODELS = {
             thinkingLevelMap: { "off": null, "minimal": "low", "xhigh": "xhigh" },
             input: ["text", "image"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
+                input: 5,
+                output: 30,
+                cacheRead: 0.5,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
             maxTokens: 128000,
         },
-        "grok-code-fast-1": {
-            id: "grok-code-fast-1",
-            name: "Grok Code Fast 1",
+        "raptor-mini": {
+            id: "raptor-mini",
+            name: "Raptor mini",
             api: "openai-completions",
             provider: "github-copilot",
             baseUrl: "https://api.individual.githubcopilot.com",
             headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
             compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
             reasoning: true,
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
+                input: 0.25,
+                output: 2,
+                cacheRead: 0.025,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
-            maxTokens: 64000,
+            contextWindow: 400000,
+            maxTokens: 128000,
         },
     },
     "google": {
@@ -4838,7 +5058,7 @@ export const MODELS = {
             cost: {
                 input: 1,
                 output: 3,
-                cacheRead: 0,
+                cacheRead: 0.5,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -4855,7 +5075,7 @@ export const MODELS = {
             cost: {
                 input: 0.15,
                 output: 0.6,
-                cacheRead: 0,
+                cacheRead: 0.075,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
@@ -4872,7 +5092,7 @@ export const MODELS = {
             cost: {
                 input: 0.075,
                 output: 0.3,
-                cacheRead: 0,
+                cacheRead: 0.0375,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
@@ -5158,9 +5378,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 1.74,
-                output: 3.48,
-                cacheRead: 0.145,
+                input: 0.435,
+                output: 0.87,
+                cacheRead: 0.003625,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -5474,6 +5694,23 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 262144,
         },
+        "devstral-latest": {
+            id: "devstral-latest",
+            name: "Devstral 2",
+            api: "mistral-conversations",
+            provider: "mistral",
+            baseUrl: "https://api.mistral.ai",
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.4,
+                output: 2,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 262144,
+        },
         "devstral-medium-2507": {
             id: "devstral-medium-2507",
             name: "Devstral Medium",
@@ -5752,11 +5989,11 @@ export const MODELS = {
             api: "mistral-conversations",
             provider: "mistral",
             baseUrl: "https://api.mistral.ai",
-            reasoning: true,
+            reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 1.5,
-                output: 7.5,
+                input: 0.4,
+                output: 2,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -5848,9 +6085,26 @@ export const MODELS = {
             contextWindow: 8000,
             maxTokens: 8000,
         },
-        "open-mixtral-8x22b": {
-            id: "open-mixtral-8x22b",
-            name: "Mixtral 8x22B",
+        "open-mistral-nemo": {
+            id: "open-mistral-nemo",
+            name: "Open Mistral Nemo",
+            api: "mistral-conversations",
+            provider: "mistral",
+            baseUrl: "https://api.mistral.ai",
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.15,
+                output: 0.15,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 128000,
+        },
+        "open-mixtral-8x22b": {
+            id: "open-mixtral-8x22b",
+            name: "Mixtral 8x22B",
             api: "mistral-conversations",
             provider: "mistral",
             baseUrl: "https://api.mistral.ai",
@@ -6253,7 +6507,7 @@ export const MODELS = {
             cost: {
                 input: 0.1,
                 output: 0.4,
-                cacheRead: 0.03,
+                cacheRead: 0.025,
                 cacheWrite: 0,
             },
             contextWindow: 1047576,
@@ -6338,7 +6592,7 @@ export const MODELS = {
             cost: {
                 input: 0.15,
                 output: 0.6,
-                cacheRead: 0.08,
+                cacheRead: 0.075,
                 cacheWrite: 0,
             },
             contextWindow: 128000,
@@ -6464,7 +6718,7 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 10,
-                cacheRead: 0.13,
+                cacheRead: 0.125,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
@@ -6747,7 +7001,7 @@ export const MODELS = {
             provider: "openai",
             baseUrl: "https://api.openai.com/v1",
             reasoning: true,
-            thinkingLevelMap: { "off": "none", "xhigh": "xhigh" },
+            thinkingLevelMap: { "off": "none", "xhigh": "xhigh", "minimal": null },
             input: ["text", "image"],
             cost: {
                 input: 5,
@@ -6765,7 +7019,7 @@ export const MODELS = {
             provider: "openai",
             baseUrl: "https://api.openai.com/v1",
             reasoning: true,
-            thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
+            thinkingLevelMap: { "off": null, "xhigh": "xhigh", "minimal": null, "low": null },
             input: ["text", "image"],
             cost: {
                 input: 30,
@@ -6889,7 +7143,7 @@ export const MODELS = {
             cost: {
                 input: 1.1,
                 output: 4.4,
-                cacheRead: 0.28,
+                cacheRead: 0.275,
                 cacheWrite: 0,
             },
             contextWindow: 200000,
@@ -6965,7 +7219,7 @@ export const MODELS = {
                 cacheRead: 0.175,
                 cacheWrite: 0,
             },
-            contextWindow: 272000,
+            contextWindow: 128000,
             maxTokens: 128000,
         },
         "gpt-5.4": {
@@ -7039,7 +7293,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 200000,
-            maxTokens: 128000,
+            maxTokens: 32000,
         },
         "claude-haiku-4-5": {
             id: "claude-haiku-4-5",
@@ -7098,6 +7352,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen",
+            compat: { "forceAdaptiveThinking": true },
             reasoning: true,
             thinkingLevelMap: { "xhigh": "max" },
             input: ["text", "image"],
@@ -7116,6 +7371,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen",
+            compat: { "forceAdaptiveThinking": true, "supportsTemperature": false },
             reasoning: true,
             thinkingLevelMap: { "xhigh": "xhigh" },
             input: ["text", "image"],
@@ -7128,6 +7384,24 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "claude-opus-4-8": {
+            id: "claude-opus-4-8",
+            name: "Claude Opus 4.8",
+            api: "anthropic-messages",
+            provider: "opencode",
+            baseUrl: "https://opencode.ai/zen",
+            compat: { "forceAdaptiveThinking": true, "supportsTemperature": false },
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "claude-sonnet-4": {
             id: "claude-sonnet-4",
             name: "Claude Sonnet 4",
@@ -7168,6 +7442,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen",
+            compat: { "forceAdaptiveThinking": true },
             reasoning: true,
             input: ["text", "image"],
             cost: {
@@ -7179,6 +7454,25 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 64000,
         },
+        "deepseek-v4-flash": {
+            id: "deepseek-v4-flash",
+            name: "DeepSeek V4 Flash",
+            api: "openai-completions",
+            provider: "opencode",
+            baseUrl: "https://opencode.ai/zen/v1",
+            compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
+            reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
+            input: ["text"],
+            cost: {
+                input: 0.14,
+                output: 0.28,
+                cacheRead: 0.03,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 384000,
+        },
         "deepseek-v4-flash-free": {
             id: "deepseek-v4-flash-free",
             name: "DeepSeek V4 Flash Free",
@@ -7563,7 +7857,7 @@ export const MODELS = {
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen/v1",
             reasoning: true,
-            thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
+            thinkingLevelMap: { "off": null, "xhigh": "xhigh", "minimal": null, "low": null },
             input: ["text", "image"],
             cost: {
                 input: 30,
@@ -7580,7 +7874,9 @@ export const MODELS = {
             api: "openai-completions",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen/v1",
+            compat: { "supportsReasoningEffort": false },
             reasoning: true,
+            thinkingLevelMap: { "off": null, "minimal": null, "low": null, "medium": null },
             input: ["text", "image"],
             cost: {
                 input: 1,
@@ -7614,6 +7910,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen/v1",
+            compat: { "thinkingFormat": "deepseek", "supportsReasoningEffort": false },
             reasoning: true,
             input: ["text", "image"],
             cost: {
@@ -7625,6 +7922,23 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 65536,
         },
+        "mimo-v2.5-free": {
+            id: "mimo-v2.5-free",
+            name: "MiMo V2.5 Free",
+            api: "openai-completions",
+            provider: "opencode",
+            baseUrl: "https://opencode.ai/zen/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 200000,
+            maxTokens: 32000,
+        },
         "minimax-m2.5": {
             id: "minimax-m2.5",
             name: "MiniMax M2.5",
@@ -7659,9 +7973,26 @@ export const MODELS = {
             contextWindow: 204800,
             maxTokens: 131072,
         },
-        "nemotron-3-super-free": {
-            id: "nemotron-3-super-free",
-            name: "Nemotron 3 Super Free",
+        "minimax-m3-free": {
+            id: "minimax-m3-free",
+            name: "MiniMax M3 Free",
+            api: "anthropic-messages",
+            provider: "opencode",
+            baseUrl: "https://opencode.ai/zen",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 200000,
+            maxTokens: 32000,
+        },
+        "nemotron-3-ultra-free": {
+            id: "nemotron-3-ultra-free",
+            name: "Nemotron 3 Ultra Free",
             api: "openai-completions",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen/v1",
@@ -7673,7 +8004,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 204800,
+            contextWindow: 1000000,
             maxTokens: 128000,
         },
         "qwen3.5-plus": {
@@ -7807,7 +8138,9 @@ export const MODELS = {
             api: "openai-completions",
             provider: "opencode-go",
             baseUrl: "https://opencode.ai/zen/go/v1",
+            compat: { "thinkingFormat": "deepseek", "supportsReasoningEffort": false },
             reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
             input: ["text", "image"],
             cost: {
                 input: 0.95,
@@ -7827,9 +8160,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.4,
-                output: 2,
-                cacheRead: 0.08,
+                input: 0.14,
+                output: 0.28,
+                cacheRead: 0.0028,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
@@ -7844,9 +8177,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 1,
-                output: 3,
-                cacheRead: 0.2,
+                input: 1.74,
+                output: 3.48,
+                cacheRead: 0.0145,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -7886,23 +8219,22 @@ export const MODELS = {
             contextWindow: 204800,
             maxTokens: 131072,
         },
-        "qwen3.5-plus": {
-            id: "qwen3.5-plus",
-            name: "Qwen3.5 Plus",
-            api: "openai-completions",
+        "minimax-m3": {
+            id: "minimax-m3",
+            name: "MiniMax M3",
+            api: "anthropic-messages",
             provider: "opencode-go",
-            baseUrl: "https://opencode.ai/zen/go/v1",
-            compat: { "thinkingFormat": "qwen" },
+            baseUrl: "https://opencode.ai/zen/go",
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.2,
-                output: 1.2,
-                cacheRead: 0.02,
-                cacheWrite: 0.25,
+                input: 0.6,
+                output: 2.4,
+                cacheRead: 0.12,
+                cacheWrite: 0,
             },
-            contextWindow: 262144,
-            maxTokens: 65536,
+            contextWindow: 512000,
+            maxTokens: 131072,
         },
         "qwen3.6-plus": {
             id: "qwen3.6-plus",
@@ -7919,7 +8251,41 @@ export const MODELS = {
                 cacheRead: 0.05,
                 cacheWrite: 0.625,
             },
-            contextWindow: 262144,
+            contextWindow: 1000000,
+            maxTokens: 65536,
+        },
+        "qwen3.7-max": {
+            id: "qwen3.7-max",
+            name: "Qwen3.7 Max",
+            api: "anthropic-messages",
+            provider: "opencode-go",
+            baseUrl: "https://opencode.ai/zen/go",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 2.5,
+                output: 7.5,
+                cacheRead: 0.5,
+                cacheWrite: 3.125,
+            },
+            contextWindow: 1000000,
+            maxTokens: 65536,
+        },
+        "qwen3.7-plus": {
+            id: "qwen3.7-plus",
+            name: "Qwen3.7 Plus",
+            api: "anthropic-messages",
+            provider: "opencode-go",
+            baseUrl: "https://opencode.ai/zen/go",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.4,
+                output: 1.6,
+                cacheRead: 0.04,
+                cacheWrite: 0.5,
+            },
+            contextWindow: 1000000,
             maxTokens: 65536,
         },
     },
@@ -7941,23 +8307,6 @@ export const MODELS = {
             contextWindow: 256000,
             maxTokens: 4096,
         },
-        "alibaba/tongyi-deepresearch-30b-a3b": {
-            id: "alibaba/tongyi-deepresearch-30b-a3b",
-            name: "Tongyi DeepResearch 30B A3B",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.09,
-                output: 0.44999999999999996,
-                cacheRead: 0.09,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 131072,
-        },
         "amazon/nova-2-lite-v1": {
             id: "amazon/nova-2-lite-v1",
             name: "Amazon: Nova 2 Lite",
@@ -8217,6 +8566,40 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "anthropic/claude-opus-4.8": {
+            id: "anthropic/claude-opus-4.8",
+            name: "Anthropic: Claude Opus 4.8",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
+        "anthropic/claude-opus-4.8-fast": {
+            id: "anthropic/claude-opus-4.8-fast",
+            name: "Anthropic: Claude Opus 4.8 (Fast)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 10,
+                output: 50,
+                cacheRead: 1,
+                cacheWrite: 12.5,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "anthropic/claude-sonnet-4": {
             id: "anthropic/claude-sonnet-4",
             name: "Anthropic: Claude Sonnet 4",
@@ -8285,23 +8668,6 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 262144,
         },
-        "arcee-ai/trinity-large-thinking:free": {
-            id: "arcee-ai/trinity-large-thinking:free",
-            name: "Arcee AI: Trinity Large Thinking (free)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 80000,
-        },
         "arcee-ai/trinity-mini": {
             id: "arcee-ai/trinity-mini",
             name: "Arcee AI: Trinity Mini",
@@ -8353,40 +8719,6 @@ export const MODELS = {
             contextWindow: 2000000,
             maxTokens: 30000,
         },
-        "baidu/cobuddy:free": {
-            id: "baidu/cobuddy:free",
-            name: "Baidu Qianfan: CoBuddy (free)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 65536,
-        },
-        "baidu/ernie-4.5-21b-a3b": {
-            id: "baidu/ernie-4.5-21b-a3b",
-            name: "Baidu: ERNIE 4.5 21B A3B",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.07,
-                output: 0.28,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 8000,
-        },
         "baidu/ernie-4.5-vl-28b-a3b": {
             id: "baidu/ernie-4.5-vl-28b-a3b",
             name: "Baidu: ERNIE 4.5 VL 28B A3B",
@@ -8515,13 +8847,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.32,
-                output: 0.8899999999999999,
+                input: 0.20020000000000002,
+                output: 0.8000999999999999,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 163840,
-            maxTokens: 16384,
+            contextWindow: 131072,
+            maxTokens: 16000,
         },
         "deepseek/deepseek-chat-v3-0324": {
             id: "deepseek/deepseek-chat-v3-0324",
@@ -8617,13 +8949,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.252,
-                output: 0.378,
-                cacheRead: 0.0252,
+                input: 0.2288,
+                output: 0.3432,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 65536,
+            maxTokens: 64000,
         },
         "deepseek/deepseek-v3.2-exp": {
             id: "deepseek/deepseek-v3.2-exp",
@@ -8648,37 +8980,18 @@ export const MODELS = {
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
-            compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
+            compat: { "requiresReasoningContentOnAssistantMessages": true },
             reasoning: true,
-            thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh" },
             input: ["text"],
             cost: {
-                input: 0.09999999999999999,
-                output: 0.19999999999999998,
-                cacheRead: 0.02,
+                input: 0.0983,
+                output: 0.1966,
+                cacheRead: 0.019700000000000002,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 16384,
-        },
-        "deepseek/deepseek-v4-flash:free": {
-            id: "deepseek/deepseek-v4-flash:free",
-            name: "DeepSeek: DeepSeek V4 Flash (free)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
-            reasoning: true,
-            thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 384000,
+            maxTokens: 131072,
         },
         "deepseek/deepseek-v4-pro": {
             id: "deepseek/deepseek-v4-pro",
@@ -8686,9 +8999,9 @@ export const MODELS = {
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
-            compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
+            compat: { "requiresReasoningContentOnAssistantMessages": true },
             reasoning: true,
-            thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh" },
             input: ["text"],
             cost: {
                 input: 0.435,
@@ -8716,40 +9029,6 @@ export const MODELS = {
             contextWindow: 32768,
             maxTokens: 4096,
         },
-        "google/gemini-2.0-flash-001": {
-            id: "google/gemini-2.0-flash-001",
-            name: "Google: Gemini 2.0 Flash",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0.09999999999999999,
-                output: 0.39999999999999997,
-                cacheRead: 0.024999999999999998,
-                cacheWrite: 0.08333333333333334,
-            },
-            contextWindow: 1000000,
-            maxTokens: 8192,
-        },
-        "google/gemini-2.0-flash-lite-001": {
-            id: "google/gemini-2.0-flash-lite-001",
-            name: "Google: Gemini 2.0 Flash Lite",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0.075,
-                output: 0.3,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 8192,
-        },
         "google/gemini-2.5-flash": {
             id: "google/gemini-2.5-flash",
             name: "Google: Gemini 2.5 Flash",
@@ -9186,7 +9465,7 @@ export const MODELS = {
             input: ["text"],
             cost: {
                 input: 0.02,
-                output: 0.049999999999999996,
+                output: 0.03,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -9227,6 +9506,23 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 4096,
         },
+        "meta-llama/llama-4-maverick": {
+            id: "meta-llama/llama-4-maverick",
+            name: "Meta: Llama 4 Maverick",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 0.15,
+                output: 0.6,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 16384,
+        },
         "meta-llama/llama-4-scout": {
             id: "meta-llama/llama-4-scout",
             name: "Meta: Llama 4 Scout",
@@ -9312,39 +9608,39 @@ export const MODELS = {
             contextWindow: 204800,
             maxTokens: 196608,
         },
-        "minimax/minimax-m2.5:free": {
-            id: "minimax/minimax-m2.5:free",
-            name: "MiniMax: MiniMax M2.5 (free)",
+        "minimax/minimax-m2.7": {
+            id: "minimax/minimax-m2.7",
+            name: "MiniMax: MiniMax M2.7",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0,
-                output: 0,
+                input: 0.27899999999999997,
+                output: 1.2,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 204800,
-            maxTokens: 8192,
+            maxTokens: 131072,
         },
-        "minimax/minimax-m2.7": {
-            id: "minimax/minimax-m2.7",
-            name: "MiniMax: MiniMax M2.7",
+        "minimax/minimax-m3": {
+            id: "minimax/minimax-m3",
+            name: "MiniMax: MiniMax M3",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
             reasoning: true,
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
-                input: 0.27899999999999997,
+                input: 0.3,
                 output: 1.2,
-                cacheRead: 0,
+                cacheRead: 0.06,
                 cacheWrite: 0,
             },
-            contextWindow: 204800,
-            maxTokens: 131072,
+            contextWindow: 1048576,
+            maxTokens: 512000,
         },
         "mistralai/codestral-2508": {
             id: "mistralai/codestral-2508",
@@ -9380,40 +9676,6 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 4096,
         },
-        "mistralai/devstral-medium": {
-            id: "mistralai/devstral-medium",
-            name: "Mistral: Devstral Medium",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.39999999999999997,
-                output: 2,
-                cacheRead: 0.04,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 4096,
-        },
-        "mistralai/devstral-small": {
-            id: "mistralai/devstral-small",
-            name: "Mistral: Devstral Small 1.1",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.09999999999999999,
-                output: 0.3,
-                cacheRead: 0.01,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 4096,
-        },
         "mistralai/ministral-14b-2512": {
             id: "mistralai/ministral-14b-2512",
             name: "Mistral: Ministral 3 14B 2512",
@@ -9499,23 +9761,6 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 4096,
         },
-        "mistralai/mistral-large-2411": {
-            id: "mistralai/mistral-large-2411",
-            name: "Mistral Large 2411",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 2,
-                output: 6,
-                cacheRead: 0.19999999999999998,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 4096,
-        },
         "mistralai/mistral-large-2512": {
             id: "mistralai/mistral-large-2512",
             name: "Mistral: Mistral Large 3 2512",
@@ -9669,23 +9914,6 @@ export const MODELS = {
             contextWindow: 65536,
             maxTokens: 4096,
         },
-        "mistralai/pixtral-large-2411": {
-            id: "mistralai/pixtral-large-2411",
-            name: "Mistral: Pixtral Large 2411",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 2,
-                output: 6,
-                cacheRead: 0.19999999999999998,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 4096,
-        },
         "mistralai/voxtral-small-24b-2507": {
             id: "mistralai/voxtral-small-24b-2507",
             name: "Mistral: Voxtral Small 24B 2507",
@@ -9777,16 +10005,35 @@ export const MODELS = {
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
+            compat: { "supportsDeveloperRole": false },
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.73,
-                output: 3.49,
-                cacheRead: 0.25,
+                input: 0.684,
+                output: 3.42,
+                cacheRead: 0.144,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 262144,
+        },
+        "moonshotai/kimi-k2.6:free": {
+            id: "moonshotai/kimi-k2.6:free",
+            name: "MoonshotAI: Kimi K2.6 (free)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            compat: { "supportsDeveloperRole": false },
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262142,
+            maxTokens: 4096,
         },
         "nex-agi/deepseek-v3.1-nex-n1": {
             id: "nex-agi/deepseek-v3.1-nex-n1",
@@ -9888,11 +10135,45 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
-            maxTokens: 4096,
+            maxTokens: 4096,
+        },
+        "nvidia/nemotron-3-super-120b-a12b:free": {
+            id: "nvidia/nemotron-3-super-120b-a12b:free",
+            name: "NVIDIA: Nemotron 3 Super (free)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 262144,
+        },
+        "nvidia/nemotron-3-ultra-550b-a55b": {
+            id: "nvidia/nemotron-3-ultra-550b-a55b",
+            name: "NVIDIA: Nemotron 3 Ultra",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.5,
+                output: 2.5,
+                cacheRead: 0.15,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 16384,
         },
-        "nvidia/nemotron-3-super-120b-a12b:free": {
-            id: "nvidia/nemotron-3-super-120b-a12b:free",
-            name: "NVIDIA: Nemotron 3 Super (free)",
+        "nvidia/nemotron-3-ultra-550b-a55b:free": {
+            id: "nvidia/nemotron-3-ultra-550b-a55b:free",
+            name: "NVIDIA: Nemotron 3 Ultra (free)",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
@@ -9905,7 +10186,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
-            maxTokens: 262144,
+            maxTokens: 65536,
         },
         "nvidia/nemotron-nano-12b-v2-vl:free": {
             id: "nvidia/nemotron-nano-12b-v2-vl:free",
@@ -10026,23 +10307,6 @@ export const MODELS = {
             contextWindow: 8191,
             maxTokens: 4096,
         },
-        "openai/gpt-4-0314": {
-            id: "openai/gpt-4-0314",
-            name: "OpenAI: GPT-4 (older v0314)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 30,
-                output: 60,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 8191,
-            maxTokens: 4096,
-        },
         "openai/gpt-4-1106-preview": {
             id: "openai/gpt-4-1106-preview",
             name: "OpenAI: GPT-4 Turbo (older v1106)",
@@ -10213,23 +10477,6 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 16384,
         },
-        "openai/gpt-4o-audio-preview": {
-            id: "openai/gpt-4o-audio-preview",
-            name: "OpenAI: GPT-4o Audio",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 2.5,
-                output: 10,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 16384,
-        },
         "openai/gpt-4o-mini": {
             id: "openai/gpt-4o-mini",
             name: "OpenAI: GPT-4o-mini",
@@ -10377,11 +10624,11 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 10,
-                cacheRead: 0.125,
+                cacheRead: 0.13,
                 cacheWrite: 0,
             },
             contextWindow: 128000,
-            maxTokens: 16384,
+            maxTokens: 32000,
         },
         "openai/gpt-5.1-codex": {
             id: "openai/gpt-5.1-codex",
@@ -10394,7 +10641,7 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 10,
-                cacheRead: 0.125,
+                cacheRead: 0.13,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
@@ -10428,11 +10675,11 @@ export const MODELS = {
             cost: {
                 input: 0.25,
                 output: 2,
-                cacheRead: 0.03,
+                cacheRead: 0.024999999999999998,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
-            maxTokens: 128000,
+            maxTokens: 100000,
         },
         "openai/gpt-5.2": {
             id: "openai/gpt-5.2",
@@ -10468,7 +10715,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 128000,
-            maxTokens: 32000,
+            maxTokens: 16384,
         },
         "openai/gpt-5.2-codex": {
             id: "openai/gpt-5.2-codex",
@@ -10639,7 +10886,7 @@ export const MODELS = {
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
             reasoning: true,
-            thinkingLevelMap: { "xhigh": "xhigh" },
+            thinkingLevelMap: { "xhigh": "xhigh", "off": null, "minimal": null, "low": null },
             input: ["text", "image"],
             cost: {
                 input: 30,
@@ -10744,13 +10991,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.03,
+                input: 0.029,
                 output: 0.14,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 131072,
+            maxTokens: 4096,
         },
         "openai/gpt-oss-20b:free": {
             id: "openai/gpt-oss-20b:free",
@@ -11004,8 +11251,8 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
-            maxTokens: 8192,
+            contextWindow: 262144,
+            maxTokens: 32768,
         },
         "poolside/laguna-xs.2:free": {
             id: "poolside/laguna-xs.2:free",
@@ -11021,8 +11268,8 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
-            maxTokens: 8192,
+            contextWindow: 262144,
+            maxTokens: 32768,
         },
         "prime-intellect/intellect-3": {
             id: "prime-intellect/intellect-3",
@@ -11058,23 +11305,6 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 16384,
         },
-        "qwen/qwen-2.5-7b-instruct": {
-            id: "qwen/qwen-2.5-7b-instruct",
-            name: "Qwen: Qwen2.5 7B Instruct",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.04,
-                output: 0.09999999999999999,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 32768,
-        },
         "qwen/qwen-plus": {
             id: "qwen/qwen-plus",
             name: "Qwen: Qwen-Plus",
@@ -11104,7 +11334,7 @@ export const MODELS = {
                 input: 0.26,
                 output: 0.78,
                 cacheRead: 0,
-                cacheWrite: 0.325,
+                cacheWrite: 0,
             },
             contextWindow: 1000000,
             maxTokens: 32768,
@@ -11186,13 +11416,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.14950000000000002,
-                output: 1.495,
-                cacheRead: 0,
+                input: 0.09999999999999999,
+                output: 0.09999999999999999,
+                cacheRead: 0.09999999999999999,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 4096,
+            maxTokens: 262144,
         },
         "qwen/qwen3-30b-a3b": {
             id: "qwen/qwen3-30b-a3b",
@@ -11209,7 +11439,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 20000,
+            maxTokens: 16384,
         },
         "qwen/qwen3-30b-a3b-instruct-2507": {
             id: "qwen/qwen3-30b-a3b-instruct-2507",
@@ -11220,13 +11450,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.09,
-                output: 0.3,
+                input: 0.04815,
+                output: 0.19305,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 262144,
-            maxTokens: 262144,
+            contextWindow: 131072,
+            maxTokens: 32000,
         },
         "qwen/qwen3-30b-a3b-thinking-2507": {
             id: "qwen/qwen3-30b-a3b-thinking-2507",
@@ -11628,13 +11858,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.13899999999999998,
+                input: 0.14,
                 output: 1,
-                cacheRead: 0,
+                cacheRead: 0.049999999999999996,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 4096,
+            maxTokens: 262144,
         },
         "qwen/qwen3.5-397b-a17b": {
             id: "qwen/qwen3.5-397b-a17b",
@@ -11682,7 +11912,7 @@ export const MODELS = {
                 input: 0.065,
                 output: 0.26,
                 cacheRead: 0,
-                cacheWrite: 0.08125,
+                cacheWrite: 0,
             },
             contextWindow: 1000000,
             maxTokens: 65536,
@@ -11699,7 +11929,7 @@ export const MODELS = {
                 input: 0.26,
                 output: 1.56,
                 cacheRead: 0,
-                cacheWrite: 0.325,
+                cacheWrite: 0,
             },
             contextWindow: 1000000,
             maxTokens: 65536,
@@ -11716,7 +11946,7 @@ export const MODELS = {
                 input: 0.3,
                 output: 1.7999999999999998,
                 cacheRead: 0,
-                cacheWrite: 0,
+                cacheWrite: 0.375,
             },
             contextWindow: 1000000,
             maxTokens: 65536,
@@ -11730,13 +11960,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.3,
+                input: 0.29,
                 output: 3.1999999999999997,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 262140,
         },
         "qwen/qwen3.6-35b-a3b": {
             id: "qwen/qwen3.6-35b-a3b",
@@ -11747,7 +11977,7 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.15,
+                input: 0.14,
                 output: 1,
                 cacheRead: 0,
                 cacheWrite: 0,
@@ -11815,10 +12045,27 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 2.5,
-                output: 7.5,
-                cacheRead: 0,
-                cacheWrite: 3.125,
+                input: 1.25,
+                output: 3.75,
+                cacheRead: 0.25,
+                cacheWrite: 1.5625,
+            },
+            contextWindow: 1000000,
+            maxTokens: 65536,
+        },
+        "qwen/qwen3.7-plus": {
+            id: "qwen/qwen3.7-plus",
+            name: "Qwen: Qwen3.7 Plus",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.39999999999999997,
+                output: 1.5999999999999999,
+                cacheRead: 0.08,
+                cacheWrite: 0.5,
             },
             contextWindow: 1000000,
             maxTokens: 65536,
@@ -11908,6 +12155,23 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 16384,
         },
+        "stepfun/step-3.7-flash": {
+            id: "stepfun/step-3.7-flash",
+            name: "StepFun: Step 3.7 Flash",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.19999999999999998,
+                output: 1.15,
+                cacheRead: 0.04,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 256000,
+        },
         "tencent/hy3-preview": {
             id: "tencent/hy3-preview",
             name: "Tencent: Hy3 preview",
@@ -11917,13 +12181,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.06599999999999999,
-                output: 0.26,
-                cacheRead: 0.029,
+                input: 0.063,
+                output: 0.21,
+                cacheRead: 0.020999999999999998,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 4096,
         },
         "thedrummer/rocinante-12b": {
             id: "thedrummer/rocinante-12b",
@@ -12044,40 +12308,6 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 65536,
         },
-        "xiaomi/mimo-v2-omni": {
-            id: "xiaomi/mimo-v2-omni",
-            name: "Xiaomi: MiMo-V2-Omni",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.39999999999999997,
-                output: 2,
-                cacheRead: 0.08,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 65536,
-        },
-        "xiaomi/mimo-v2-pro": {
-            id: "xiaomi/mimo-v2-pro",
-            name: "Xiaomi: MiMo-V2-Pro",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 1,
-                output: 3,
-                cacheRead: 0.19999999999999998,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 131072,
-        },
         "xiaomi/mimo-v2.5": {
             id: "xiaomi/mimo-v2.5",
             name: "Xiaomi: MiMo-V2.5",
@@ -12087,9 +12317,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.39999999999999997,
-                output: 2,
-                cacheRead: 0.08,
+                input: 0.14,
+                output: 0.28,
+                cacheRead: 0.0028,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -12104,13 +12334,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 1,
-                output: 3,
-                cacheRead: 0.19999999999999998,
+                input: 0.435,
+                output: 0.87,
+                cacheRead: 0.0036,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 16384,
+            maxTokens: 131072,
         },
         "z-ai/glm-4-32b": {
             id: "z-ai/glm-4-32b",
@@ -12155,13 +12385,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.13,
+                input: 0.125,
                 output: 0.85,
-                cacheRead: 0.024999999999999998,
+                cacheRead: 0.06,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 98304,
+            maxTokens: 131070,
         },
         "z-ai/glm-4.5-air:free": {
             id: "z-ai/glm-4.5-air:free",
@@ -12427,13 +12657,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.73,
-                output: 3.49,
-                cacheRead: 0.25,
+                input: 0.684,
+                output: 3.42,
+                cacheRead: 0.144,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262142,
+            maxTokens: 262144,
         },
         "~openai/gpt-latest": {
             id: "~openai/gpt-latest",
@@ -12624,7 +12854,7 @@ export const MODELS = {
         },
         "deepseek-ai/DeepSeek-V3": {
             id: "deepseek-ai/DeepSeek-V3",
-            name: "DeepSeek V3",
+            name: "DeepSeek-V3",
             api: "openai-completions",
             provider: "together",
             baseUrl: "https://api.together.ai/v1",
@@ -12772,6 +13002,25 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 131000,
         },
+        "nvidia/nemotron-3-ultra-550b-a55b": {
+            id: "nvidia/nemotron-3-ultra-550b-a55b",
+            name: "Nemotron 3 Ultra 550B A55B",
+            api: "openai-completions",
+            provider: "together",
+            baseUrl: "https://api.together.ai/v1",
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
+            reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
+            input: ["text"],
+            cost: {
+                input: 0.6,
+                output: 3.6,
+                cacheRead: 0.2,
+                cacheWrite: 0,
+            },
+            contextWindow: 512300,
+            maxTokens: 512300,
+        },
         "openai/gpt-oss-120b": {
             id: "openai/gpt-oss-120b",
             name: "GPT OSS 120B",
@@ -12831,20 +13080,20 @@ export const MODELS = {
         },
         "alibaba/qwen-3-235b": {
             id: "alibaba/qwen-3-235b",
-            name: "Qwen3 235B A22b Instruct 2507",
+            name: "Qwen3 235B A22B",
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: false,
+            reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.6,
-                output: 1.2,
-                cacheRead: 0.6,
+                input: 0.22,
+                output: 0.88,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131000,
-            maxTokens: 40000,
+            contextWindow: 262144,
+            maxTokens: 16384,
         },
         "alibaba/qwen-3-30b": {
             id: "alibaba/qwen-3-30b",
@@ -12887,7 +13136,7 @@ export const MODELS = {
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: true,
-            input: ["text", "image"],
+            input: ["text"],
             cost: {
                 input: 1.3,
                 output: 7.8,
@@ -12920,7 +13169,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: false,
+            reasoning: true,
             input: ["text"],
             cost: {
                 input: 1.5,
@@ -12954,7 +13203,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: false,
+            reasoning: true,
             input: ["text"],
             cost: {
                 input: 0.5,
@@ -13013,25 +13262,59 @@ export const MODELS = {
                 cacheRead: 0.24,
                 cacheWrite: 0,
             },
-            contextWindow: 262144,
+            contextWindow: 262144,
+            maxTokens: 32768,
+        },
+        "alibaba/qwen3-max-thinking": {
+            id: "alibaba/qwen3-max-thinking",
+            name: "Qwen 3 Max Thinking",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 1.2,
+                output: 6,
+                cacheRead: 0.24,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 65536,
+        },
+        "alibaba/qwen3-next-80b-a3b-instruct": {
+            id: "alibaba/qwen3-next-80b-a3b-instruct",
+            name: "Qwen3 Next 80B A3B Instruct",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.15,
+                output: 1.2,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
             maxTokens: 32768,
         },
-        "alibaba/qwen3-max-thinking": {
-            id: "alibaba/qwen3-max-thinking",
-            name: "Qwen 3 Max Thinking",
+        "alibaba/qwen3-next-80b-a3b-thinking": {
+            id: "alibaba/qwen3-next-80b-a3b-thinking",
+            name: "Qwen3 Next 80B A3B Thinking",
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 1.2,
-                output: 6,
-                cacheRead: 0.24,
+                input: 0.15,
+                output: 1.2,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
-            maxTokens: 65536,
+            contextWindow: 131072,
+            maxTokens: 32768,
         },
         "alibaba/qwen3-vl-thinking": {
             id: "alibaba/qwen3-vl-thinking",
@@ -13125,7 +13408,7 @@ export const MODELS = {
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: true,
-            input: ["text", "image"],
+            input: ["text"],
             cost: {
                 input: 1.25,
                 output: 3.75,
@@ -13135,6 +13418,23 @@ export const MODELS = {
             contextWindow: 991000,
             maxTokens: 64000,
         },
+        "alibaba/qwen3.7-plus": {
+            id: "alibaba/qwen3.7-plus",
+            name: "Qwen 3.7 Plus",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.39999999999999997,
+                output: 1.5999999999999999,
+                cacheRead: 0.08,
+                cacheWrite: 0.5,
+            },
+            contextWindow: 1000000,
+            maxTokens: 64000,
+        },
         "anthropic/claude-3-haiku": {
             id: "anthropic/claude-3-haiku",
             name: "Claude 3 Haiku",
@@ -13243,6 +13543,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
+            compat: { "forceAdaptiveThinking": true },
             reasoning: true,
             thinkingLevelMap: { "xhigh": "max" },
             input: ["text", "image"],
@@ -13261,6 +13562,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
+            compat: { "forceAdaptiveThinking": true, "supportsTemperature": false },
             reasoning: true,
             thinkingLevelMap: { "xhigh": "xhigh" },
             input: ["text", "image"],
@@ -13273,6 +13575,24 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "anthropic/claude-opus-4.8": {
+            id: "anthropic/claude-opus-4.8",
+            name: "Claude Opus 4.8",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            compat: { "forceAdaptiveThinking": true, "supportsTemperature": false },
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "anthropic/claude-sonnet-4": {
             id: "anthropic/claude-sonnet-4",
             name: "Claude Sonnet 4",
@@ -13313,6 +13633,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
+            compat: { "forceAdaptiveThinking": true },
             reasoning: true,
             input: ["text", "image"],
             cost: {
@@ -13418,17 +13739,17 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.77,
-                output: 0.77,
-                cacheRead: 0,
+                input: 0.27,
+                output: 1.12,
+                cacheRead: 0.135,
                 cacheWrite: 0,
             },
             contextWindow: 163840,
-            maxTokens: 16384,
+            maxTokens: 163840,
         },
         "deepseek/deepseek-v3.1": {
             id: "deepseek/deepseek-v3.1",
-            name: "DeepSeek-V3.1",
+            name: "DeepSeek V3.1",
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
@@ -13466,8 +13787,8 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: false,
-            input: ["text"],
+            reasoning: true,
+            input: ["text", "image"],
             cost: {
                 input: 0.28,
                 output: 0.42,
@@ -13483,8 +13804,8 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: false,
-            input: ["text"],
+            reasoning: true,
+            input: ["text", "image"],
             cost: {
                 input: 0.62,
                 output: 1.85,
@@ -13501,7 +13822,7 @@ export const MODELS = {
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: true,
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
                 input: 0.14,
                 output: 0.28,
@@ -13721,12 +14042,12 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: false,
+            reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.13,
-                output: 0.39999999999999997,
-                cacheRead: 0,
+                input: 0.15,
+                output: 0.6,
+                cacheRead: 0.015,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -14028,7 +14349,7 @@ export const MODELS = {
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: true,
-            input: ["text", "image"],
+            input: ["text"],
             cost: {
                 input: 0.3,
                 output: 1.2,
@@ -14045,7 +14366,7 @@ export const MODELS = {
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: true,
-            input: ["text", "image"],
+            input: ["text"],
             cost: {
                 input: 0.6,
                 output: 2.4,
@@ -14055,6 +14376,23 @@ export const MODELS = {
             contextWindow: 204800,
             maxTokens: 131100,
         },
+        "minimax/minimax-m3": {
+            id: "minimax/minimax-m3",
+            name: "MiniMax M3",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.3,
+                output: 1.2,
+                cacheRead: 0.06,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 1000000,
+        },
         "mistral/codestral": {
             id: "mistral/codestral",
             name: "Mistral Codestral",
@@ -14191,6 +14529,23 @@ export const MODELS = {
             contextWindow: 256000,
             maxTokens: 256000,
         },
+        "mistral/mistral-nemo": {
+            id: "mistral/mistral-nemo",
+            name: "Mistral Nemo 12B",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.02,
+                output: 0.04,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 131072,
+        },
         "mistral/mistral-small": {
             id: "mistral/mistral-small",
             name: "Mistral Small",
@@ -14344,6 +14699,40 @@ export const MODELS = {
             contextWindow: 262000,
             maxTokens: 262000,
         },
+        "nvidia/nemotron-3-super-120b-a12b": {
+            id: "nvidia/nemotron-3-super-120b-a12b",
+            name: "NVIDIA Nemotron 3 Super 120B A12B",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.15,
+                output: 0.65,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 32000,
+        },
+        "nvidia/nemotron-3-ultra-550b-a55b": {
+            id: "nvidia/nemotron-3-ultra-550b-a55b",
+            name: "Nemotron 3 Ultra",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.6,
+                output: 2.4,
+                cacheRead: 0.12,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 65000,
+        },
         "nvidia/nemotron-nano-12b-v2-vl": {
             id: "nvidia/nemotron-nano-12b-v2-vl",
             name: "Nvidia Nemotron Nano 12B V2 VL",
@@ -14521,7 +14910,7 @@ export const MODELS = {
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: true,
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
                 input: 1.25,
                 output: 10,
@@ -14872,7 +15261,7 @@ export const MODELS = {
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: true,
-            thinkingLevelMap: { "xhigh": "xhigh" },
+            thinkingLevelMap: { "xhigh": "xhigh", "off": null, "minimal": null, "low": null },
             input: ["text", "image"],
             cost: {
                 input: 30,
@@ -14883,6 +15272,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "openai/gpt-oss-120b": {
+            id: "openai/gpt-oss-120b",
+            name: "GPT OSS 120B",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.35,
+                output: 0.75,
+                cacheRead: 0.25,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 131000,
+        },
         "openai/gpt-oss-20b": {
             id: "openai/gpt-oss-20b",
             name: "GPT OSS 20B",
@@ -15053,6 +15459,40 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 8000,
         },
+        "stepfun/step-3.5-flash": {
+            id: "stepfun/step-3.5-flash",
+            name: "StepFun 3.5 Flash",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.09,
+                output: 0.3,
+                cacheRead: 0,
+                cacheWrite: 0.02,
+            },
+            contextWindow: 262114,
+            maxTokens: 262114,
+        },
+        "stepfun/step-3.7-flash": {
+            id: "stepfun/step-3.7-flash",
+            name: "Step 3.7 Flash",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.19999999999999998,
+                output: 1.15,
+                cacheRead: 0.04,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 256000,
+        },
         "xai/grok-4.1-fast-non-reasoning": {
             id: "xai/grok-4.1-fast-non-reasoning",
             name: "Grok 4.1 Fast Non-Reasoning",
@@ -15266,9 +15706,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.39999999999999997,
-                output: 2,
-                cacheRead: 0.08,
+                input: 0.14,
+                output: 0.28,
+                cacheRead: 0.0028,
                 cacheWrite: 0,
             },
             contextWindow: 1050000,
@@ -15283,9 +15723,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 1,
-                output: 3,
-                cacheRead: 0.19999999999999998,
+                input: 0.435,
+                output: 0.87,
+                cacheRead: 0.0036,
                 cacheWrite: 0,
             },
             contextWindow: 1050000,
@@ -15331,7 +15771,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: false,
+            reasoning: true,
             input: ["text", "image"],
             cost: {
                 input: 0.6,
@@ -15485,7 +15925,7 @@ export const MODELS = {
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: true,
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
                 input: 1.4,
                 output: 4.4,
@@ -15727,24 +16167,6 @@ export const MODELS = {
         },
     },
     "xiaomi-token-plan-ams": {
-        "mimo-v2-flash": {
-            id: "mimo-v2-flash",
-            name: "MiMo-V2-Flash",
-            api: "openai-completions",
-            provider: "xiaomi-token-plan-ams",
-            baseUrl: "https://token-plan-ams.xiaomimimo.com/v1",
-            compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.1,
-                output: 0.3,
-                cacheRead: 0.01,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 65536,
-        },
         "mimo-v2-omni": {
             id: "mimo-v2-omni",
             name: "MiMo-V2-Omni",
@@ -15819,24 +16241,6 @@ export const MODELS = {
         },
     },
     "xiaomi-token-plan-cn": {
-        "mimo-v2-flash": {
-            id: "mimo-v2-flash",
-            name: "MiMo-V2-Flash",
-            api: "openai-completions",
-            provider: "xiaomi-token-plan-cn",
-            baseUrl: "https://token-plan-cn.xiaomimimo.com/v1",
-            compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.1,
-                output: 0.3,
-                cacheRead: 0.01,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 65536,
-        },
         "mimo-v2-omni": {
             id: "mimo-v2-omni",
             name: "MiMo-V2-Omni",
@@ -15911,24 +16315,6 @@ export const MODELS = {
         },
     },
     "xiaomi-token-plan-sgp": {
-        "mimo-v2-flash": {
-            id: "mimo-v2-flash",
-            name: "MiMo-V2-Flash",
-            api: "openai-completions",
-            provider: "xiaomi-token-plan-sgp",
-            baseUrl: "https://token-plan-sgp.xiaomimimo.com/v1",
-            compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.1,
-                output: 0.3,
-                cacheRead: 0.01,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 65536,
-        },
         "mimo-v2-omni": {
             id: "mimo-v2-omni",
             name: "MiMo-V2-Omni",