@juspay/neurolink 12.37.4 → 12.37.5

package/dist/providers/googleVertex/client.js

@@ -46,7 +46,7 @@ import { SpanKind, SpanStatusCode, context as otelContext, trace as otelTrace, }
 import { calculateCost } from "../../utils/pricing.js";
 import { transformToolExecutions } from "../../utils/transformationUtils.js";
 import { resolveToolExecutionRecords } from "../../core/toolExecutionRecorder.js";
-import { resolveSamplingParams } from "../../models/modelRegistry.js";
+import { modelSupportsForcedToolChoice, resolveSamplingParams, } from "../../models/modelRegistry.js";
 import { sanitizeAnthropicMessagesForTrace } from "../../utils/anthropicTraceSanitizer.js";
 import { extractToolFailureText } from "../../utils/mcpErrorText.js";
 // Import proper types for multimodal message handling
@@ -707,6 +707,20 @@ async function collectVertexStreamChunks(stream, channel, hooks = {}) {
         ...(stepReasoningTokens ? { reasoningTokens: stepReasoningTokens } : {}),
     };
 }
+/**
+ * The answer text of an unforced finalization reply. Text that leads into a
+ * further tool call is preamble, not an answer, so a reply still asking for a
+ * tool yields none.
+ */
+function finalizationAnswerText(content) {
+    if (content.some((block) => block.type === "tool_use")) {
+        return "";
+    }
+    return content
+        .filter((block) => block.type === "text")
+        .map((b) => b.text)
+        .join("");
+}
 export class GoogleVertexProvider extends BaseProvider {
     projectId;
     location;
@@ -2949,9 +2963,9 @@ export class GoogleVertexProvider extends BaseProvider {
      * clamped below the ceiling rather than passed through — an over-large
      * budget is a 400 from the API.
      *
-     * `useFinalResultTool` (schema / structured-output mode) always pairs with
-     * a forced `tool_choice:{type:"any"}` in the request built right after this
-     * call — Anthropic hard-rejects `thinking` combined with a `tool_choice`
+     * `forcesToolChoice` (schema mode on a model that accepts a forced choice)
+     * pairs with a forced `tool_choice:{type:"any"}` in the request built right
+     * after this call — Anthropic hard-rejects `thinking` combined with a `tool_choice`
      * that forces tool use: a live 400, "Thinking may not be enabled when
      * tool_choice forces tool use." So `thinking` is omitted entirely in that
      * mode, preserving the prior (pre-thinking-fix) behaviour of silently
@@ -2968,8 +2982,8 @@ export class GoogleVertexProvider extends BaseProvider {
     buildClaudeThinkingParam(
     // Structural, not TextGenerationOptions: the streaming caller passes
     // StreamOptions, and only these two fields are read.
-    options, maxTokens, useFinalResultTool) {
-        if (useFinalResultTool) {
+    options, maxTokens, forcesToolChoice) {
+        if (forcesToolChoice) {
             if (options.thinkingConfig?.enabled) {
                 logger.debug("[GoogleVertex] Omitting thinking: schema mode forces tool_choice:any, which Anthropic rejects alongside thinking");
             }
@@ -3215,7 +3229,10 @@ export class GoogleVertexProvider extends BaseProvider {
             ...(options.topP !== undefined && { topP: options.topP }),
         }, "vertex.anthropic.stream");
         const streamMaxTokens = resolveClaudeMaxTokens(modelName, options.maxTokens);
-        const streamThinking = this.buildClaudeThinkingParam(options, streamMaxTokens, useFinalResultTool);
+        // Claude 5.5 / 5.1 400 on a forced tool_choice; schema mode leaves them on
+        // auto, steered by the final_result instruction already in the prompt.
+        const forceFinalResult = useFinalResultTool && modelSupportsForcedToolChoice(modelName);
+        const streamThinking = this.buildClaudeThinkingParam(options, streamMaxTokens, forceFinalResult);
         const requestParams = {
             model: modelName,
             // Default to the model's real output ceiling (e.g. 64K for Sonnet 4.x)
@@ -3226,7 +3243,7 @@ export class GoogleVertexProvider extends BaseProvider {
             ...(streamThinking && { thinking: streamThinking }),
             messages: messages,
             ...(tools && tools.length > 0 && { tools }),
-            ...(useFinalResultTool && { tool_choice: { type: "any" } }),
+            ...(forceFinalResult && { tool_choice: { type: "any" } }),
             ...(systemPromptWithSchema && { system: systemPromptWithSchema }),
             ...(streamSampling.temperature !== undefined && {
                 temperature: streamSampling.temperature,
@@ -3858,10 +3875,15 @@ export class GoogleVertexProvider extends BaseProvider {
                             const finalizationStream = await client.messages.stream({
                                 ...requestParams,
                                 max_tokens: terminalMaxTokens,
-                                tool_choice: {
-                                    type: "tool",
-                                    name: "final_result",
-                                },
+                                // Resized, not inherited: terminalMaxTokens can sit below the
+                                // budget requestParams' thinking was sized for.
+                                thinking: this.buildClaudeThinkingParam(options, terminalMaxTokens, forceFinalResult),
+                                ...(forceFinalResult && {
+                                    tool_choice: {
+                                        type: "tool",
+                                        name: "final_result",
+                                    },
+                                }),
                                 ...(cachedFinal.system !== undefined && {
                                     system: cachedFinal.system,
                                 }),
@@ -3905,11 +3927,23 @@ export class GoogleVertexProvider extends BaseProvider {
                                 logger.debug("[GoogleVertex] Forced finalization returned structured output (stream)", { keys: Object.keys(forcedFinalResult.input) });
                             }
                             else {
-                                const capMessage = hitContextLimit
-                                    ? buildContextCapMessage(externalToolCallCount)
-                                    : buildToolLoopCapMessage(maxSteps, externalToolCallCount);
-                                channel.push({ content: capMessage });
-                                aggregatedTurnText += capMessage;
+                                // Unforced (the model refuses a forced choice), the call may
+                                // answer in text instead; keep that answer over a cap notice.
+                                const finalizationText = forceFinalResult
+                                    ? ""
+                                    : finalizationAnswerText(response.content);
+                                if (finalizationText) {
+                                    synthesizedFinalAnswer = true;
+                                    channel.push({ content: finalizationText });
+                                    aggregatedTurnText += finalizationText;
+                                }
+                                else {
+                                    const capMessage = hitContextLimit
+                                        ? buildContextCapMessage(externalToolCallCount)
+                                        : buildToolLoopCapMessage(maxSteps, externalToolCallCount);
+                                    channel.push({ content: capMessage });
+                                    aggregatedTurnText += capMessage;
+                                }
                             }
                         }
                         catch (error) {
@@ -4484,7 +4518,10 @@ export class GoogleVertexProvider extends BaseProvider {
             ...(options.topP !== undefined && { topP: options.topP }),
         }, "vertex.anthropic.generate");
         const generateMaxTokens = resolveClaudeMaxTokens(modelName, options.maxTokens);
-        const generateThinking = this.buildClaudeThinkingParam(options, generateMaxTokens, useFinalResultTool);
+        // Claude 5.5 / 5.1 400 on a forced tool_choice; schema mode leaves them on
+        // auto, steered by the final_result instruction already in the prompt.
+        const forceFinalResult = useFinalResultTool && modelSupportsForcedToolChoice(modelName);
+        const generateThinking = this.buildClaudeThinkingParam(options, generateMaxTokens, forceFinalResult);
         const requestParams = {
             model: modelName,
             // Default to the model's real output ceiling (see stream path note).
@@ -4492,7 +4529,7 @@ export class GoogleVertexProvider extends BaseProvider {
             ...(generateThinking && { thinking: generateThinking }),
             messages,
             ...(tools && tools.length > 0 && { tools }),
-            ...(useFinalResultTool && { tool_choice: { type: "any" } }),
+            ...(forceFinalResult && { tool_choice: { type: "any" } }),
             ...(systemPromptWithSchema && { system: systemPromptWithSchema }),
             ...(generateSampling.temperature !== undefined && {
                 temperature: generateSampling.temperature,
@@ -4901,10 +4938,15 @@ export class GoogleVertexProvider extends BaseProvider {
                     const response = await withTimeout(client.messages.create({
                         ...requestParams,
                         max_tokens: terminalMaxTokens,
-                        tool_choice: {
-                            type: "tool",
-                            name: "final_result",
-                        },
+                        // Resized, not inherited: terminalMaxTokens can sit below the
+                        // budget requestParams' thinking was sized for.
+                        thinking: this.buildClaudeThinkingParam(options, terminalMaxTokens, forceFinalResult),
+                        ...(forceFinalResult && {
+                            tool_choice: {
+                                type: "tool",
+                                name: "final_result",
+                            },
+                        }),
                         ...(cachedFinal.system !== undefined && {
                             system: cachedFinal.system,
                         }),
@@ -4928,9 +4970,20 @@ export class GoogleVertexProvider extends BaseProvider {
                         logger.debug("[GoogleVertex] Forced finalization returned structured output (generate)", { keys: Object.keys(structuredOutput) });
                     }
                     else {
-                        finalText = hitContextLimit
-                            ? buildContextCapMessage(externalToolCallCount)
-                            : buildToolLoopCapMessage(maxSteps, externalToolCallCount);
+                        // Unforced (the model refuses a forced choice), the call may
+                        // answer in text instead; keep that answer over a cap notice.
+                        const finalizationText = forceFinalResult
+                            ? ""
+                            : finalizationAnswerText(response.content);
+                        if (finalizationText) {
+                            finalText = finalizationText;
+                            synthesizedFinalAnswer = true;
+                        }
+                        else {
+                            finalText = hitContextLimit
+                                ? buildContextCapMessage(externalToolCallCount)
+                                : buildToolLoopCapMessage(maxSteps, externalToolCallCount);
+                        }
                     }
                 }
                 catch (error) {

package/dist/providers/openaiChatCompletionsBase.js

@@ -873,7 +873,7 @@ export class OpenAIChatCompletionsProvider extends BaseProvider {
             options.disableInternalFallback === true;
         // The native loop bypasses BaseProvider.executeGeneration, so the turn
         // budget has to be composed here or it stops existing for this provider.
-        return this.runGenerateWithModelFallback(() => this.withTurnTimeout({ ...options, tools: mergedTools }, this.getDescriptorGenerateMs(), (timedOptions) => this.executeNativeGenerate(timedOptions)), callerOwnsFallback);
+        return this.runGenerateWithModelFallback(() => this.withTurnTimeout({ ...options, tools: mergedTools }, this.getDescriptorGenerateMs(), (timedOptions) => this.executeNativeGenerate(timedOptions)), callerOwnsFallback, options);
     }
     async executeNativeGenerate(options) {
         const startTime = Date.now();

package/dist/proxy/vertexAnthropicFallback.d.ts

@@ -22,18 +22,7 @@ import type { VertexAccessTokenProvider, UsageContext, VertexPassthroughTerminal
  * `effort` key, never the sibling settings beside it.
  */
 export declare function mapVertexOutputConfig(value: unknown): Record<string, unknown> | undefined;
-/**
- * Strip what Vertex rejects and pin the API version it requires.
- *
- * Prompt caching constrains every rewrite here. Anthropic caches only up to an
- * explicit `cache_control` marker, at most four per request, over a prefix
- * rendered `tools → system → messages`; anything removed or inserted before a
- * marker invalidates it and everything after. So: never drop a marker, never
- * reorder `system`, and keep each rewrite deterministic so consecutive turns
- * share a prefix. Vertex holds its own cache, apart from the first-party one,
- * so nothing here can disturb first-party hits.
- */
-export declare function buildVertexAnthropicPayload(body: Readonly<Record<string, unknown>>): Record<string, unknown>;
+export declare function buildVertexAnthropicPayload(body: Readonly<Record<string, unknown>>, targetModel?: string): Record<string, unknown>;
 /**
  * Publisher endpoint for a Claude model on Vertex.
  *

package/dist/proxy/vertexAnthropicFallback.js

@@ -13,6 +13,7 @@
  * here because nothing reshapes them.
  */
 import { logger } from "../utils/logger.js";
+import { claudeDisabledThinkingReplacement, modelSupportsForcedToolChoice, } from "../models/modelRegistry.js";
 import { isTransientNetworkError } from "./proxyFetch.js";
 /** Vertex pins the Anthropic API version in the body, not a header. */
 const VERTEX_ANTHROPIC_VERSION = "vertex-2023-10-16";
@@ -334,7 +335,44 @@ function stripBillingBlock(system) {
  * share a prefix. Vertex holds its own cache, apart from the first-party one,
  * so nothing here can disturb first-party hits.
  */
-export function buildVertexAnthropicPayload(body) {
+/**
+ * The client addressed its own model; the fallback target may be a Claude
+ * 5.5 / 5.1 model, which answers a forced `tool_choice` and
+ * `thinking: {type: "disabled"}` with a 400. Reshape both into what the target
+ * accepts rather than fail the turn the fallback exists to rescue.
+ */
+function fitRequestToTarget(payload, targetModel) {
+    const choice = payload.tool_choice;
+    if (record(choice) &&
+        (choice.type === "any" || choice.type === "tool") &&
+        !modelSupportsForcedToolChoice(targetModel)) {
+        payload.tool_choice = {
+            type: "auto",
+            ...(choice.disable_parallel_tool_use !== undefined
+                ? { disable_parallel_tool_use: choice.disable_parallel_tool_use }
+                : {}),
+        };
+        logger.warn(`[vertex-anthropic] ${targetModel} rejects tool_choice "${choice.type}"; sending "auto" instead`);
+    }
+    const thinking = payload.thinking;
+    if (record(thinking) && thinking.type === "disabled") {
+        const outputConfig = payload.output_config;
+        const effort = record(outputConfig) && typeof outputConfig.effort === "string"
+            ? outputConfig.effort
+            : undefined;
+        const replacement = claudeDisabledThinkingReplacement(targetModel, effort);
+        if (replacement === "between_tools") {
+            payload.thinking = { type: "between_tools" };
+        }
+        else if (replacement === "omit") {
+            delete payload.thinking;
+        }
+        if (replacement !== "keep") {
+            logger.debug(`[vertex-anthropic] ${targetModel} rejects thinking "disabled"; ${replacement === "omit" ? "omitting thinking" : "sending between_tools"}`);
+        }
+    }
+}
+export function buildVertexAnthropicPayload(body, targetModel) {
     const dropped = new Set(UNSUPPORTED_FIELDS);
     const payload = Object.fromEntries(Object.entries(body).filter(([key]) => !dropped.has(key)));
     const outputConfig = resolveOutputConfig(payload.output_config, payload.messages);
@@ -359,6 +397,9 @@ export function buildVertexAnthropicPayload(body) {
             payload.system = system;
         }
     }
+    if (targetModel !== undefined) {
+        fitRequestToTarget(payload, targetModel);
+    }
     return { ...payload, anthropic_version: VERTEX_ANTHROPIC_VERSION };
 }
 /**
@@ -500,7 +541,7 @@ export async function dispatchVertexAnthropicPassthrough(request) {
             "content-type": "application/json",
             accept: stream ? "text/event-stream" : "application/json",
         },
-        body: JSON.stringify(buildVertexAnthropicPayload(request.body)),
+        body: JSON.stringify(buildVertexAnthropicPayload(request.body, request.model)),
         ...(request.signal ? { signal: request.signal } : {}),
     });
 }

package/dist/types/model.d.ts

@@ -111,6 +111,12 @@ export type DynamicModelConfig = z.infer<typeof ModelConfigSchema>;
  * Dynamic model registry type
  */
 export type ModelRegistry = z.infer<typeof ModelRegistrySchema>;
+/**
+ * What a request should carry in place of `thinking: {type: "disabled"}` for a
+ * Claude model: the original (`keep`), `between_tools`, or no `thinking` field
+ * at all (`omit`, i.e. adaptive).
+ */
+export type ClaudeDisabledThinkingReplacement = "keep" | "between_tools" | "omit";
 /**
  * Model capabilities interface
  */

package/docs-site/static/search-index.json

@@ -4912,11 +4912,11 @@
 {"objectID":"8bee50a94bc91cf5273efb43aa2f13a39be6cd72e048c55da55bd80bc74ce8a0","title":"Getting Help","url":"/docs/getting-started/installation#getting-help","content":"Check our Troubleshooting Guide\nReview FAQ\nSearch GitHub Issues\nCreate new issue with:\nNode.js version (node --version)\nOperating system\nError message\nSteps to reproduce","hierarchy":{"lvl0":"Getting Started","lvl1":"Installation","lvl2":"Getting Help","lvl3":""}},
 {"objectID":"80210a84a233c58e9a12aa96cedd225ad03c3bfe5344b78032d691be93ae3ba0","title":"Verification Checklist","url":"/docs/getting-started/installation#verification-checklist","content":"[ ] Node.js 18+ installed\n[ ] NeuroLink package installed or accessible via npx\n[ ] API keys configured in .env file\n[ ] neurolink status shows working providers\n[ ] Basic generation command works\n[ ] TypeScript support (if needed)\n[ ] Framework integration (if applicable)","hierarchy":{"lvl0":"Getting Started","lvl1":"Installation","lvl2":"Verification Checklist","lvl3":""}},
 {"objectID":"44c035a6ed0dc3b4a04ad68e17bc22de77840cb664eaee4e84f04bb8bd70caaf","title":"Next Steps","url":"/docs/getting-started/installation#next-steps","content":"Quick Start - Test your installation\nProvider Setup - Configure AI providers\nCLI Commands - Learn available commands\nExamples - See implementation patterns","hierarchy":{"lvl0":"Getting Started","lvl1":"Installation","lvl2":"Next Steps","lvl3":""}},
-{"objectID":"c44f69a5d19212c85a451486bef65999f3ef505311f283fa4a129d90603820ac","title":"⚙️ Provider Configuration Guide","url":"/docs/getting-started/provider-setup","content":"⚙️ Provider Configuration Guide\n\nNeuroLink supports multiple AI providers with flexible authentication methods. This guide covers complete setup for all supported providers.\n\nSupported Providers\n\nThis guide walks through full environment-variable setup for the providers below; the complete roster — including the newer catalog providers and the embedding/media/decision-only providers — is indexed with setup guides at Provider Guides.\n\nProviders configured in this guide\nOpenAI - GPT-4o, GPT-4o-mini, GPT-4-turbo\nAmazon Bedrock - Claude 3.7 Sonnet, Claude 3.5 Sonnet, Claude 3 Haiku\nAmazon SageMaker - Custom models deployed on SageMaker endpoints\nGoogle Vertex AI - Gemini 3 Flash/Pro (preview), Gemini 2.5 Flash, Claude 4.0 Sonnet\nGoogle AI Studio - Gemini 1.5 Pro, Gemini 2.0 Flash, Gemini 1.5 Flash\nAnthropic - Claude 4.5 Opus/Sonnet/Haiku, Claude 4.0 Opus/Sonnet, Claude 3.7 Sonnet\nAzure OpenAI - GPT-4, GPT-3.5-Turbo\nLiteLLM - 100+ models across a broad range of providers via proxy server\nHugging Face - open models served by the unified router (Llama 3.x, Qwen 2.5, DeepSeek, Mistral)\nOllama - Local AI models including Llama 2, Code Llama, Mistral, Vicuna\nOpenRouter - 300+ models from every major lab via one aggregator endpoint\nMistral AI - Mistral Tiny, Small, Medium, and Large models\nDeepSeek - deepseek-chat (V3) and deepseek-reasoner (R1)\nNVIDIA NIM - Llama 3.3 70B and 400+ catalog models via NVIDIA hosted or self-hosted NIM\nLM Studio - Any model loaded in LM Studio desktop app (local, no API key required)\nllama.cpp - Any GGUF model served by llama-server (local, no API key required)\n\nOther providers (setup guides in the Provider Guides index)\n\nOnboarded via the zero-quirk OpenAI-wire-compatible catalog (Tier 2) — each has its own setup guide under providers/:\nGroq - LPU-accelerated inference; default openai/gpt-oss-120b\nCerebras - Wafer-scale inference; default gpt-oss-120b\nSambaNova - default Meta-Llama-3.3-70B-Instruct\nTogether AI - default meta-llama/Llama-3.3-70B-Instruct-Turbo\nFireworks AI - default accounts/fireworks/models/kimi-k2p6\nPerplexity - search-augmented models; default sonar\nCloudflare Workers AI - edge inference\nxAI - Grok models; default grok-4.6\nBaseten - default zai-org/GLM-5.3-Flash (BASETEN_API_KEY)\nGMI Cloud - default MiniMaxAI/MiniMax-M3 (GMICLOUD_API_KEY)\nInception Labs - diffusion LLMs; default mercury-2 (INCEPTION_LABS_API_KEY)\nio.net Intelligence - decentralized GPU inference; default meta-llama/Llama-3.3-70B-Instruct (IO_INTELLIGENCE_API_KEY)\nMancer - default deepseek-v4-flash (MANCER_API_KEY); no tool calling\nUpstage - Solar models; default solar-pro4 (UPSTAGE_API_KEY)\nAPI Route - OpenAI-compatible passthrough; default claude-sonnet-4-6 (API_ROUTE_API_KEY)\n\nEmbedding, media-generation, and decision-only providers — not part of generate()/stream() provider selection in the same way, but each has a setup guide:\nCohere - chat + embed-english-v3.0 embeddings + reranking\nVoyage AI - embedding-only; default voyage-3.5\nJina AI - embeddings + reranking; default jina-embeddings-v3\nReplicate, Stability AI, Ideogram, Recraft - direct image generation\nTypeSafe Jev - decision-only; serves decide(), not generate()/stream(). Set TYPESAFE_API_KEY (or AI_GATEWAY_API_KEY for the gateway transport)\nLaya - decision-only, open-weights; serves decide() on a Laya server or LiteLLM proxy route you configure. Set LAYA_API_KEY + LAYA_BASE_URL; used when TypeSafe isn't configured\n\nVoice providers (TTS/STT/Realtime) are configured further down in this guide — see OpenAI TTS onward.\n\n💰 Model Availability & Cost Considerations\n\nImportant Notes:\nModel Availability: Specific models may not be available in all regions or require special access\nCost Variations: Pricing differs significantly between providers and models (e.g., Claude 3.5 Sonnet vs GPT-4o)\nRate Limits: Each provider has different rate limits and quota restrictions\nLocal vs Cloud: Ollama (local) has no per-request cost but requires hardware resources\nEnterprise Tiers: AWS Bedrock, Google Vertex AI, and Azure typically offer enterprise pricing\n\nBest Practices:\nUse new NeuroLink() with automatic provider selection for cost-optimized routing\nMonitor usage through built-in analytics to track costs\nConsider local models (Ollama) for development and testing\nCheck provider documentation for current pricing and availability\n\n🏢 Enterprise Proxy Support\n\nProviders support corporate proxy environments automatically. Simply set environment variables:\n\nNo code changes required - NeuroLink automatically detects and uses proxy settings.\n\nFor detailed proxy setup → See Enterprise & Proxy Setup Guide\n\nOpenAI Configuration {#openai}\n\nBasic Setup\n\nOptional Configuration\n\nSupported Models\ngpt-4o (default) - Latest multimodal model\ngpt-4o-mini - Cost-effective variant\ngpt-4-turbo - High-performance model\n\nUsage Example\n\nTimeout Configuration\nDefault Timeout: 30 seconds\nSupported Formats: Milliseconds (30000), human-readable ('30s', '1m', '5m')\nEnvironment Variable: OPE","hierarchy":{"lvl0":"Getting Started","lvl1":"⚙️ Provider Configuration Guide","lvl2":"","lvl3":""}},
+{"objectID":"c44f69a5d19212c85a451486bef65999f3ef505311f283fa4a129d90603820ac","title":"⚙️ Provider Configuration Guide","url":"/docs/getting-started/provider-setup","content":"⚙️ Provider Configuration Guide\n\nNeuroLink supports multiple AI providers with flexible authentication methods. This guide covers complete setup for all supported providers.\n\nSupported Providers\n\nThis guide walks through full environment-variable setup for the providers below; the complete roster — including the newer catalog providers and the embedding/media/decision-only providers — is indexed with setup guides at Provider Guides.\n\nProviders configured in this guide\nOpenAI - GPT-4o, GPT-4o-mini, GPT-4-turbo\nAmazon Bedrock - Claude 3.7 Sonnet, Claude 3.5 Sonnet, Claude 3 Haiku\nAmazon SageMaker - Custom models deployed on SageMaker endpoints\nGoogle Vertex AI - Gemini 3 Flash/Pro (preview), Gemini 2.5 Flash, Claude 4.0 Sonnet\nGoogle AI Studio - Gemini 1.5 Pro, Gemini 2.0 Flash, Gemini 1.5 Flash\nAnthropic - Claude 4.5 Opus/Sonnet/Haiku, Claude 4.0 Opus/Sonnet, Claude 3.7 Sonnet\nAzure OpenAI - GPT-4, GPT-3.5-Turbo\nLiteLLM - 100+ models across a broad range of providers via proxy server\nHugging Face - open models served by the unified router (Llama 3.x, Qwen 2.5, DeepSeek, Mistral)\nOllama - Local AI models including Llama 2, Code Llama, Mistral, Vicuna\nOpenRouter - 300+ models from every major lab via one aggregator endpoint\nMistral AI - Mistral Tiny, Small, Medium, and Large models\nDeepSeek - deepseek-chat (V3) and deepseek-reasoner (R1)\nNVIDIA NIM - Llama 3.3 70B and 400+ catalog models via NVIDIA hosted or self-hosted NIM\nLM Studio - Any model loaded in LM Studio desktop app (local, no API key required)\nllama.cpp - Any GGUF model served by llama-server (local, no API key required)\n\nOther providers (setup guides in the Provider Guides index)\n\nOnboarded via the zero-quirk OpenAI-wire-compatible catalog (Tier 2) — each has its own setup guide under providers/:\nGroq - LPU-accelerated inference; default openai/gpt-oss-120b\nCerebras - Wafer-scale inference; default gpt-oss-120b\nSambaNova - default Meta-Llama-3.3-70B-Instruct\nTogether AI - default meta-llama/Llama-3.3-70B-Instruct-Turbo\nFireworks AI - default accounts/fireworks/models/kimi-k3\nPerplexity - search-augmented models; default sonar\nCloudflare Workers AI - edge inference\nxAI - Grok models; default grok-4.6\nBaseten - default zai-org/GLM-5.3-Flash (BASETEN_API_KEY)\nGMI Cloud - default MiniMaxAI/MiniMax-M3 (GMICLOUD_API_KEY)\nInception Labs - diffusion LLMs; default mercury-2 (INCEPTION_LABS_API_KEY)\nio.net Intelligence - decentralized GPU inference; default meta-llama/Llama-3.3-70B-Instruct (IO_INTELLIGENCE_API_KEY)\nMancer - default deepseek-v4-flash (MANCER_API_KEY); no tool calling\nUpstage - Solar models; default solar-pro4 (UPSTAGE_API_KEY)\nAPI Route - OpenAI-compatible passthrough; default claude-sonnet-4-6 (API_ROUTE_API_KEY)\n\nEmbedding, media-generation, and decision-only providers — not part of generate()/stream() provider selection in the same way, but each has a setup guide:\nCohere - chat + embed-english-v3.0 embeddings + reranking\nVoyage AI - embedding-only; default voyage-3.5\nJina AI - embeddings + reranking; default jina-embeddings-v3\nReplicate, Stability AI, Ideogram, Recraft - direct image generation\nTypeSafe Jev - decision-only; serves decide(), not generate()/stream(). Set TYPESAFE_API_KEY (or AI_GATEWAY_API_KEY for the gateway transport)\nLaya - decision-only, open-weights; serves decide() on a Laya server or LiteLLM proxy route you configure. Set LAYA_API_KEY + LAYA_BASE_URL; used when TypeSafe isn't configured\n\nVoice providers (TTS/STT/Realtime) are configured further down in this guide — see OpenAI TTS onward.\n\n💰 Model Availability & Cost Considerations\n\nImportant Notes:\nModel Availability: Specific models may not be available in all regions or require special access\nCost Variations: Pricing differs significantly between providers and models (e.g., Claude 3.5 Sonnet vs GPT-4o)\nRate Limits: Each provider has different rate limits and quota restrictions\nLocal vs Cloud: Ollama (local) has no per-request cost but requires hardware resources\nEnterprise Tiers: AWS Bedrock, Google Vertex AI, and Azure typically offer enterprise pricing\n\nBest Practices:\nUse new NeuroLink() with automatic provider selection for cost-optimized routing\nMonitor usage through built-in analytics to track costs\nConsider local models (Ollama) for development and testing\nCheck provider documentation for current pricing and availability\n\n🏢 Enterprise Proxy Support\n\nProviders support corporate proxy environments automatically. Simply set environment variables:\n\nNo code changes required - NeuroLink automatically detects and uses proxy settings.\n\nFor detailed proxy setup → See Enterprise & Proxy Setup Guide\n\nOpenAI Configuration {#openai}\n\nBasic Setup\n\nOptional Configuration\n\nSupported Models\ngpt-4o (default) - Latest multimodal model\ngpt-4o-mini - Cost-effective variant\ngpt-4-turbo - High-performance model\n\nUsage Example\n\nTimeout Configuration\nDefault Timeout: 30 seconds\nSupported Formats: Milliseconds (30000), human-readable ('30s', '1m', '5m')\nEnvironment Variable: OPENA","hierarchy":{"lvl0":"Getting Started","lvl1":"⚙️ Provider Configuration Guide","lvl2":"","lvl3":""}},
 {"objectID":"44479af76ca558a6630aafa39578fb6543bd892844c3a6c5948ffd58a2d73287","title":"⚙️ Provider Configuration Guide","url":"/docs/getting-started/provider-setup#-provider-configuration-guide","content":"NeuroLink supports multiple AI providers with flexible authentication methods. This guide covers complete setup for all supported providers.","hierarchy":{"lvl0":"Getting Started","lvl1":"⚙️ Provider Configuration Guide","lvl2":"⚙️ Provider Configuration Guide","lvl3":""}},
 {"objectID":"ed4c54afa059a89c0cb4a7815f361a50933fe695ec62b3df5a0bd4ad2e25e431","title":"Supported Providers","url":"/docs/getting-started/provider-setup#supported-providers","content":"This guide walks through full environment-variable setup for the providers below; the complete roster — including the newer catalog providers and the embedding/media/decision-only providers — is indexed with setup guides at Provider Guides.","hierarchy":{"lvl0":"Getting Started","lvl1":"⚙️ Provider Configuration Guide","lvl2":"Supported Providers","lvl3":""}},
 {"objectID":"c0abb48e819713cb16c04d745137321d348118c823351fcf31ab014735dd036e","title":"Providers configured in this guide","url":"/docs/getting-started/provider-setup#providers-configured-in-this-guide","content":"OpenAI - GPT-4o, GPT-4o-mini, GPT-4-turbo\nAmazon Bedrock - Claude 3.7 Sonnet, Claude 3.5 Sonnet, Claude 3 Haiku\nAmazon SageMaker - Custom models deployed on SageMaker endpoints\nGoogle Vertex AI - Gemini 3 Flash/Pro (preview), Gemini 2.5 Flash, Claude 4.0 Sonnet\nGoogle AI Studio - Gemini 1.5 Pro, Gemini 2.0 Flash, Gemini 1.5 Flash\nAnthropic - Claude 4.5 Opus/Sonnet/Haiku, Claude 4.0 Opus/Sonnet, Claude 3.7 Sonnet\nAzure OpenAI - GPT-4, GPT-3.5-Turbo\nLiteLLM - 100+ models across a broad range of providers via proxy server\nHugging Face - open models served by the unified router (Llama 3.x, Qwen 2.5, DeepSeek, Mistral)\nOllama - Local AI models including Llama 2, Code Llama, Mistral, Vicuna\nOpenRouter - 300+ models from every major lab via one aggregator endpoint\nMistral AI - Mistral Tiny, Small, Medium, and Large models\nDeepSeek - deepseek-chat (V3) and deepseek-reasoner (R1)\nNVIDIA NIM - Llama 3.3 70B and 400+ catalog models via NVIDIA hosted or self-hosted NIM\nLM Studio - Any model loaded in LM Studio desktop app (local, no API key required)\nllama.cpp - Any GGUF model served by llama-server (local, no API key required)","hierarchy":{"lvl0":"Getting Started","lvl1":"⚙️ Provider Configuration Guide","lvl2":"Providers configured in this guide","lvl3":""}},
-{"objectID":"cc96a04c9f262c3c1f6f8b8e7c82407cc63406705250afd22947a3567e151721","title":"Other providers (setup guides in the Provider Guides index)","url":"/docs/getting-started/provider-setup#other-providers-setup-guides-in-the-provider-guides-index","content":"Onboarded via the zero-quirk OpenAI-wire-compatible catalog (Tier 2) — each has its own setup guide under providers/:\nGroq - LPU-accelerated inference; default openai/gpt-oss-120b\nCerebras - Wafer-scale inference; default gpt-oss-120b\nSambaNova - default Meta-Llama-3.3-70B-Instruct\nTogether AI - default meta-llama/Llama-3.3-70B-Instruct-Turbo\nFireworks AI - default accounts/fireworks/models/kimi-k2p6\nPerplexity - search-augmented models; default sonar\nCloudflare Workers AI - edge inference\nxAI - Grok models; default grok-4.6\nBaseten - default zai-org/GLM-5.3-Flash (BASETEN_API_KEY)\nGMI Cloud - default MiniMaxAI/MiniMax-M3 (GMICLOUD_API_KEY)\nInception Labs - diffusion LLMs; default mercury-2 (INCEPTION_LABS_API_KEY)\nio.net Intelligence - decentralized GPU inference; default meta-llama/Llama-3.3-70B-Instruct (IO_INTELLIGENCE_API_KEY)\nMancer - default deepseek-v4-flash (MANCER_API_KEY); no tool calling\nUpstage - Solar models; default solar-pro4 (UPSTAGE_API_KEY)\nAPI Route - OpenAI-compatible passthrough; default claude-sonnet-4-6 (API_ROUTE_API_KEY)\n\nEmbedding, media-generation, and decision-only providers — not part of generate()/stream() provider selection in the same way, but each has a setup guide:\nCohere - chat + embed-english-v3.0 embeddings + reranking\nVoyage AI - embedding-only; default voyage-3.5\nJina AI - embeddings + reranking; default jina-embeddings-v3\nReplicate, Stability AI, Ideogram, Recraft - direct image generation\nTypeSafe Jev - decision-only; serves decide(), not generate()/stream(). Set TYPESAFE_API_KEY (or AI_GATEWAY_API_KEY for the gateway transport)\nLaya - decision-only, open-weights; serves decide() on a Laya server or LiteLLM proxy route you configure. Set LAYA_API_KEY + LAYA_BASE_URL; used when TypeSafe isn't configured\n\nVoice providers (TTS/STT/Realtime) are configured further down in this guide — see OpenAI TTS onward.","hierarchy":{"lvl0":"Getting Started","lvl1":"⚙️ Provider Configuration Guide","lvl2":"Other providers (setup guides in the Provider Guides index)","lvl3":""}},
+{"objectID":"cc96a04c9f262c3c1f6f8b8e7c82407cc63406705250afd22947a3567e151721","title":"Other providers (setup guides in the Provider Guides index)","url":"/docs/getting-started/provider-setup#other-providers-setup-guides-in-the-provider-guides-index","content":"Onboarded via the zero-quirk OpenAI-wire-compatible catalog (Tier 2) — each has its own setup guide under providers/:\nGroq - LPU-accelerated inference; default openai/gpt-oss-120b\nCerebras - Wafer-scale inference; default gpt-oss-120b\nSambaNova - default Meta-Llama-3.3-70B-Instruct\nTogether AI - default meta-llama/Llama-3.3-70B-Instruct-Turbo\nFireworks AI - default accounts/fireworks/models/kimi-k3\nPerplexity - search-augmented models; default sonar\nCloudflare Workers AI - edge inference\nxAI - Grok models; default grok-4.6\nBaseten - default zai-org/GLM-5.3-Flash (BASETEN_API_KEY)\nGMI Cloud - default MiniMaxAI/MiniMax-M3 (GMICLOUD_API_KEY)\nInception Labs - diffusion LLMs; default mercury-2 (INCEPTION_LABS_API_KEY)\nio.net Intelligence - decentralized GPU inference; default meta-llama/Llama-3.3-70B-Instruct (IO_INTELLIGENCE_API_KEY)\nMancer - default deepseek-v4-flash (MANCER_API_KEY); no tool calling\nUpstage - Solar models; default solar-pro4 (UPSTAGE_API_KEY)\nAPI Route - OpenAI-compatible passthrough; default claude-sonnet-4-6 (API_ROUTE_API_KEY)\n\nEmbedding, media-generation, and decision-only providers — not part of generate()/stream() provider selection in the same way, but each has a setup guide:\nCohere - chat + embed-english-v3.0 embeddings + reranking\nVoyage AI - embedding-only; default voyage-3.5\nJina AI - embeddings + reranking; default jina-embeddings-v3\nReplicate, Stability AI, Ideogram, Recraft - direct image generation\nTypeSafe Jev - decision-only; serves decide(), not generate()/stream(). Set TYPESAFE_API_KEY (or AI_GATEWAY_API_KEY for the gateway transport)\nLaya - decision-only, open-weights; serves decide() on a Laya server or LiteLLM proxy route you configure. Set LAYA_API_KEY + LAYA_BASE_URL; used when TypeSafe isn't configured\n\nVoice providers (TTS/STT/Realtime) are configured further down in this guide — see OpenAI TTS onward.","hierarchy":{"lvl0":"Getting Started","lvl1":"⚙️ Provider Configuration Guide","lvl2":"Other providers (setup guides in the Provider Guides index)","lvl3":""}},
 {"objectID":"d17be3311722218280d0e76731e7344c620c18f5073e07abbc826f3922db976a","title":"💰 Model Availability & Cost Considerations","url":"/docs/getting-started/provider-setup#-model-availability-cost-considerations","content":"Important Notes:\nModel Availability: Specific models may not be available in all regions or require special access\nCost Variations: Pricing differs significantly between providers and models (e.g., Claude 3.5 Sonnet vs GPT-4o)\nRate Limits: Each provider has different rate limits and quota restrictions\nLocal vs Cloud: Ollama (local) has no per-request cost but requires hardware resources\nEnterprise Tiers: AWS Bedrock, Google Vertex AI, and Azure typically offer enterprise pricing\n\nBest Practices:\nUse new NeuroLink() with automatic provider selection for cost-optimized routing\nMonitor usage through built-in analytics to track costs\nConsider local models (Ollama) for development and testing\nCheck provider documentation for current pricing and availability","hierarchy":{"lvl0":"Getting Started","lvl1":"⚙️ Provider Configuration Guide","lvl2":"💰 Model Availability & Cost Considerations","lvl3":""}},
 {"objectID":"3a1bd0ccb708d37a59e2db3650f689f77fba69e91ec88142c7c9b85f1c18057d","title":"🏢 Enterprise Proxy Support","url":"/docs/getting-started/provider-setup#-enterprise-proxy-support","content":"Providers support corporate proxy environments automatically. Simply set environment variables:\n\nNo code changes required - NeuroLink automatically detects and uses proxy settings.\n\nFor detailed proxy setup → See Enterprise & Proxy Setup Guide","hierarchy":{"lvl0":"Getting Started","lvl1":"⚙️ Provider Configuration Guide","lvl2":"🏢 Enterprise Proxy Support","lvl3":""}},
 {"objectID":"1b0159447e4aee3ffd31efe28600cf755e4cc49d50f354e1a59d9574199213d2","title":"Supported Models","url":"/docs/getting-started/provider-setup#supported-models","content":"gpt-4o (default) - Latest multimodal model\ngpt-4o-mini - Cost-effective variant\ngpt-4-turbo - High-performance model","hierarchy":{"lvl0":"Getting Started","lvl1":"⚙️ Provider Configuration Guide","lvl2":"Supported Models","lvl3":""}},
@@ -5410,29 +5410,29 @@
 {"objectID":"5303398825a285a4052490bdc1ec93aad23b25a4130aca8f58bd5bb231ea52d2","title":"PCM16 output is unplayable in audio players","url":"/docs/getting-started/providers/cartesia#pcm16-output-is-unplayable-in-audio-players","content":"pcm16 is RAW samples at 24 kHz, not a WAV file — players need a\nheader. Either write a 44-byte WAV header yourself before the PCM data,\nor switch to format: \"wav\" which produces a complete RIFF/WAV file\nalready.","hierarchy":{"lvl0":"Getting Started","lvl1":"Cartesia TTS Provider Guide","lvl2":"PCM16 output is unplayable in audio players","lvl3":""}},
 {"objectID":"b2967379807a28639cf50c9c68894b76779dba68fe6f74d6121a76ea0cdf94d3","title":"Streaming use cases","url":"/docs/getting-started/providers/cartesia#streaming-use-cases","content":"This handler is synchronous — it waits for the full audio response. For\nsub-100 ms first-byte latency in voice-agent flows, use CartesiaStream\nin src/lib/adapters/tts/cartesiaHandler.ts directly (it's wired into\nNeuroLink's voice server). The synchronous handler is the right choice\nfor batch generation, file output, and any flow where you process the\nwhole audio buffer at once.","hierarchy":{"lvl0":"Getting Started","lvl1":"Cartesia TTS Provider Guide","lvl2":"Streaming use cases","lvl3":""}},
 {"objectID":"dbb872f4bc4eb26c06d8a4ddc07f67efe59e2ea62bb9c5eda1d4df1df6b9654d","title":"See Also","url":"/docs/getting-started/providers/cartesia#see-also","content":"TTS Feature Guide — overall TTS architecture and supported providers\nFish Audio TTS — sibling low-cost TTS handler\nElevenLabs TTS — sibling TTS with the largest voice library\nAdding a TTS provider — internal reference for the integration pattern\n\nNeed Help? Open a GitHub Discussion or issue.","hierarchy":{"lvl0":"Getting Started","lvl1":"Cartesia TTS Provider Guide","lvl2":"See Also","lvl3":""}},
-{"objectID":"7f5abb3425169d7f2e1c11b1fbb0b6b42e3b5f13f6b5bca11f8c71d79aec7304","title":"Cerebras Provider Guide","url":"/docs/getting-started/providers/cerebras","content":"Cerebras Provider Guide\n\nThe fastest hosted generation available (~3000 tokens/s on GPT-OSS\n120B) via Cerebras' Wafer-Scale Engine — best for throughput-hungry\nworkloads\n\nOverview\n\nCerebras serves open-weight models on its Wafer-Scale Engine (WSE), a\nsingle wafer-sized chip whose on-die memory bandwidth yields generation\nspeeds an order of magnitude above GPU clouds. NeuroLink wraps\napi.cerebras.ai/v1 (OpenAI-compatible, zero-quirk Tier 2 catalog\nentry) so the standard generate / stream contract applies.\n\nThe roster below was verified against a live authenticated /v1/models\non 2026-08-27 — Cerebras retires models aggressively, and previously\ndocumented llama/qwen ids now return 404:\ngpt-oss-120b (default) — OpenAI's open-weight 120B reasoning model, ~3000 tok/s\ngemma-4-31b — Google Gemma 4 31B, ~1850 tok/s\n\nKey Facts\nProtocol: OpenAI-compatible (/v1/chat/completions)\nDefault base URL: https://api.cerebras.ai/v1\nDefault model: gpt-oss-120b\nContext window: 65K tokens on the free tier, 131K on paid tiers (both\n  models). NeuroLink budgets context against the 65K free-tier floor — the\n  account tier isn't knowable from the key, and compacting early on a paid\n  tier is safe while overrunning a 65K window is not.\nMax output: 32K free / 40K paid\nVision: No (text-only roster)\nStreaming: Supported\nTool calling: Supported (native)\nStructured output: Supported — but not combined with tools in one\n  request: the API rejects tools + response_format together with\n  400 wrong_api_format (\"tools\" is incompatible with \"response_format\").\n  NeuroLink handles this the same way as Groq: with tools active the\n  schema is enforced post-hoc on the final text instead of on the wire.\nReasoning trace: gpt-oss-120b emits reasoning deltas before\n  content — see Troubleshooting for the maxTokens implication.\nBilling: no keyless free tier. Even the one-time $5 promotional\n  credit requires saving a payment method (\"you won't be charged now\").\n  Pay-as-you-go starts at $10.\nPricing (per million tokens, checked 2026-08-27): gpt-oss-120b\n  $0.35 in / $0.75 out; gemma-4-31b $0.99 in / $1.49 out.\n\nQuick Start\nGet an API Key\n\nSign up at https://cloud.cerebras.ai (Google\nOAuth works), claim the $5 free credit under Billing → Credits (a\npayment card must be saved — no charge is made), and create an API key\n(prefix csk-).\nConfigure Environment\nGenerate Your First Response\n\nSDK Usage\n\nBasic Generation\n\nStreaming\n\nTool Calling\n\nStructured Output\n\nCombining schema with active tools works, but the schema is enforced\npost-hoc rather than on the wire (see Key Facts) — expect\nstructuredData to be best-effort in that combination, exactly as with\nGroq.\n\nPer-Call Credentials\n\nCLI Usage\n\nProvider Aliases\n\n| Alias      | Example               |\n| ---------- | --------------------- |\n| cerebras | --provider cerebras |\n\nConfiguration Reference\n\n| Environment Variable | Required | Default                      | Description      |\n| -------------------- | -------- | ---------------------------- | ---------------- |\n| CEREBRAS_API_KEY   | Yes      | —                            | Cerebras API key |\n| CEREBRAS_MODEL     | No       | gpt-oss-120b               | Default model    |\n| CEREBRAS_BASE_URL  | No       | https://api.cerebras.ai/v1 | Base URL         |\n\nFeature Support Matrix\n\n| Feature                   | gpt-oss-120b | gemma-4-31b |\n| ------------------------- | ------------ | ----------- |\n| Text generation           | Yes          | Yes         |\n| Streaming                 | Yes          | Yes         |\n| Tool calling              | Yes          | Yes         |\n| Structured output         | Yes          | Yes         |\n| Structured output + tools | Post-hoc     | Post-hoc    |\n| Vision                    | No           | No          |\n| Embeddings                | No           | No          |\n| Context window            | 65K/131K     | 65K/131K    |\n\nTroubleshooting\n\n\"Invalid Cerebras API key\"\n\nGet / rotate at https://cloud.cerebras.ai.\nA bad key returns 401 with \"code\": \"wrong_api_key\", which NeuroLink\nmaps to this message.\n\n402 payment_required on every call\n\nThe account has no balance. Cerebras has no keyless free tier: open\nBilling → Credits → ADD CREDITS in the console, choose \"Start with\nlimited free credits\", and save a payment card — the $5 promo credit\nactivates with no charge. Skipping the claim step during onboarding\n(\"SKIP TO CONSOLE\") leaves the balance at $0.00.\n\nEmpty content with small maxTokens on gpt-oss-120b\n\ngpt-oss-120b is a reasoning model: it spends its first tokens on a\nreasoning channel before emitting content. With a tight budget\n(e.g. maxTokens: 50) the entire budget goes to reasoning,\nfinish_reason is length, and content is empty. Give reasoning\nprompts a few hundred tokens of headroom.\n\n404 \"model not found\" for llama/qwen models\n\nThose models are retired. The live roster is gpt-oss-120b and\ngemma-4-31b only — verify with an authenticated\nGET https://api.cerebras.ai/v1/models.\n\nSee Also\nGroq Provider — sibling speed-focu","hierarchy":{"lvl0":"Getting Started","lvl1":"Cerebras Provider Guide","lvl2":"","lvl3":""}},
+{"objectID":"7f5abb3425169d7f2e1c11b1fbb0b6b42e3b5f13f6b5bca11f8c71d79aec7304","title":"Cerebras Provider Guide","url":"/docs/getting-started/providers/cerebras","content":"Cerebras Provider Guide\n\nThe fastest hosted generation available (~3000 tokens/s on GPT-OSS\n120B) via Cerebras' Wafer-Scale Engine — best for throughput-hungry\nworkloads\n\nOverview\n\nCerebras serves open-weight models on its Wafer-Scale Engine (WSE), a\nsingle wafer-sized chip whose on-die memory bandwidth yields generation\nspeeds an order of magnitude above GPU clouds. NeuroLink wraps\napi.cerebras.ai/v1 (OpenAI-compatible, zero-quirk Tier 2 catalog\nentry) so the standard generate / stream contract applies.\n\nThe roster below was verified against a live authenticated /v1/models\non 2026-09-28 — Cerebras retires models aggressively: gemma-4-31b left\nthe roster in September 2026, and earlier llama/qwen ids return 404:\ngpt-oss-120b (default) — OpenAI's open-weight 120B reasoning model, ~3000 tok/s\n\nThe roster also lists qwen-3.8-27b, which the catalog does not carry yet:\nno chat call has verified it.\n\nKey Facts\nProtocol: OpenAI-compatible (/v1/chat/completions)\nDefault base URL: https://api.cerebras.ai/v1\nDefault model: gpt-oss-120b\nContext window: 65K tokens on the free tier, 131K on paid tiers. NeuroLink budgets context against the 65K free-tier floor — the\n  account tier isn't knowable from the key, and compacting early on a paid\n  tier is safe while overrunning a 65K window is not.\nMax output: 32K free / 40K paid\nVision: No — gemma-4-31b, the only vision-capable model, is retired\nStreaming: Supported\nTool calling: Supported (native)\nStructured output: Supported — but not combined with tools in one\n  request: the API rejects tools + response_format together with\n  400 wrong_api_format (\"tools\" is incompatible with \"response_format\").\n  NeuroLink handles this the same way as Groq: with tools active the\n  schema is enforced post-hoc on the final text instead of on the wire.\nReasoning trace: gpt-oss-120b emits reasoning deltas before\n  content — see Troubleshooting for the maxTokens implication.\nBilling: no keyless free tier. Even the one-time $5 promotional\n  credit requires saving a payment method (\"you won't be charged now\").\n  Pay-as-you-go starts at $10.\nPricing (per million tokens, checked 2026-08-27): gpt-oss-120b\n  $0.35 in / $0.75 out.\n\nQuick Start\nGet an API Key\n\nSign up at https://cloud.cerebras.ai (Google\nOAuth works), claim the $5 free credit under Billing → Credits (a\npayment card must be saved — no charge is made), and create an API key\n(prefix csk-).\nConfigure Environment\nGenerate Your First Response\n\nSDK Usage\n\nBasic Generation\n\nStreaming\n\nTool Calling\n\nStructured Output\n\nCombining schema with active tools works, but the schema is enforced\npost-hoc rather than on the wire (see Key Facts) — expect\nstructuredData to be best-effort in that combination, exactly as with\nGroq.\n\nPer-Call Credentials\n\nCLI Usage\n\nProvider Aliases\n\n| Alias      | Example               |\n| ---------- | --------------------- |\n| cerebras | --provider cerebras |\n\nConfiguration Reference\n\n| Environment Variable | Required | Default                      | Description      |\n| -------------------- | -------- | ---------------------------- | ---------------- |\n| CEREBRAS_API_KEY   | Yes      | —                            | Cerebras API key |\n| CEREBRAS_MODEL     | No       | gpt-oss-120b               | Default model    |\n| CEREBRAS_BASE_URL  | No       | https://api.cerebras.ai/v1 | Base URL         |\n\nFeature Support Matrix\n\n| Feature                   | gpt-oss-120b |\n| ------------------------- | ------------ |\n| Text generation           | Yes          |\n| Streaming                 | Yes          |\n| Tool calling              | Yes          |\n| Structured output         | Yes          |\n| Structured output + tools | Post-hoc     |\n| Vision                    | No           |\n| Embeddings                | No           |\n| Context window            | 65K/131K     |\n\nTroubleshooting\n\n\"Invalid Cerebras API key\"\n\nGet / rotate at https://cloud.cerebras.ai.\nA bad key returns 401 with \"code\": \"wrong_api_key\", which NeuroLink\nmaps to this message.\n\n402 payment_required on every call\n\nThe account has no balance. Cerebras has no keyless free tier: open\nBilling → Credits → ADD CREDITS in the console, choose \"Start with\nlimited free credits\", and save a payment card — the $5 promo credit\nactivates with no charge. Skipping the claim step during onboarding\n(\"SKIP TO CONSOLE\") leaves the balance at $0.00.\n\nEmpty content with small maxTokens on gpt-oss-120b\n\ngpt-oss-120b is a reasoning model: it spends its first tokens on a\nreasoning channel before emitting content. With a tight budget\n(e.g. maxTokens: 50) the entire budget goes to reasoning,\nfinish_reason is length, and content is empty. Give reasoning\nprompts a few hundred tokens of headroom.\n\n404 \"model not found\" for llama/qwen models\n\nThose models are retired, and so is gemma-4-31b. The catalog carries\ngpt-oss-120b only — verify the live roster with an authenticated\nGET https://api.cerebras.ai/v1/models.\n\nSee Also\nGroq Provider — sibling speed-focused OpenAI-compat provider\nxAI Grok Prov","hierarchy":{"lvl0":"Getting Started","lvl1":"Cerebras Provider Guide","lvl2":"","lvl3":""}},
 {"objectID":"2b42e090bd80e32e95e89006b45fed37fa20315824ee536721743206419731f1","title":"Cerebras Provider Guide","url":"/docs/getting-started/providers/cerebras#cerebras-provider-guide","content":"The fastest hosted generation available (~3000 tokens/s on GPT-OSS\n120B) via Cerebras' Wafer-Scale Engine — best for throughput-hungry\nworkloads","hierarchy":{"lvl0":"Getting Started","lvl1":"Cerebras Provider Guide","lvl2":"Cerebras Provider Guide","lvl3":""}},
-{"objectID":"856c92d5719d8c67da883b4fab1071e2385d3f7116f9e9f12d010871dff7509f","title":"Overview","url":"/docs/getting-started/providers/cerebras#overview","content":"Cerebras serves open-weight models on its Wafer-Scale Engine (WSE), a\nsingle wafer-sized chip whose on-die memory bandwidth yields generation\nspeeds an order of magnitude above GPU clouds. NeuroLink wraps\napi.cerebras.ai/v1 (OpenAI-compatible, zero-quirk Tier 2 catalog\nentry) so the standard generate / stream contract applies.\n\nThe roster below was verified against a live authenticated /v1/models\non 2026-08-27 — Cerebras retires models aggressively, and previously\ndocumented llama/qwen ids now return 404:\ngpt-oss-120b (default) — OpenAI's open-weight 120B reasoning model, ~3000 tok/s\ngemma-4-31b — Google Gemma 4 31B, ~1850 tok/s","hierarchy":{"lvl0":"Getting Started","lvl1":"Cerebras Provider Guide","lvl2":"Overview","lvl3":""}},
-{"objectID":"26ab9baccdd8cb8f22ca7cea1d6e854040bed3093d871530515de9b3f990f737","title":"Key Facts","url":"/docs/getting-started/providers/cerebras#key-facts","content":"Protocol: OpenAI-compatible (/v1/chat/completions)\nDefault base URL: https://api.cerebras.ai/v1\nDefault model: gpt-oss-120b\nContext window: 65K tokens on the free tier, 131K on paid tiers (both\n  models). NeuroLink budgets context against the 65K free-tier floor — the\n  account tier isn't knowable from the key, and compacting early on a paid\n  tier is safe while overrunning a 65K window is not.\nMax output: 32K free / 40K paid\nVision: No (text-only roster)\nStreaming: Supported\nTool calling: Supported (native)\nStructured output: Supported — but not combined with tools in one\n  request: the API rejects tools + response_format together with\n  400 wrong_api_format (\"tools\" is incompatible with \"response_format\").\n  NeuroLink handles this the same way as Groq: with tools active the\n  schema is enforced post-hoc on the final text instead of on the wire.\nReasoning trace: gpt-oss-120b emits reasoning deltas before\n  content — see Troubleshooting for the maxTokens implication.\nBilling: no keyless free tier. Even the one-time $5 promotional\n  credit requires saving a payment method (\"you won't be charged now\").\n  Pay-as-you-go starts at $10.\nPricing (per million tokens, checked 2026-08-27): gpt-oss-120b\n  $0.35 in / $0.75 out; gemma-4-31b $0.99 in / $1.49 out.","hierarchy":{"lvl0":"Getting Started","lvl1":"Cerebras Provider Guide","lvl2":"Key Facts","lvl3":""}},
+{"objectID":"856c92d5719d8c67da883b4fab1071e2385d3f7116f9e9f12d010871dff7509f","title":"Overview","url":"/docs/getting-started/providers/cerebras#overview","content":"Cerebras serves open-weight models on its Wafer-Scale Engine (WSE), a\nsingle wafer-sized chip whose on-die memory bandwidth yields generation\nspeeds an order of magnitude above GPU clouds. NeuroLink wraps\napi.cerebras.ai/v1 (OpenAI-compatible, zero-quirk Tier 2 catalog\nentry) so the standard generate / stream contract applies.\n\nThe roster below was verified against a live authenticated /v1/models\non 2026-09-28 — Cerebras retires models aggressively: gemma-4-31b left\nthe roster in September 2026, and earlier llama/qwen ids return 404:\ngpt-oss-120b (default) — OpenAI's open-weight 120B reasoning model, ~3000 tok/s\n\nThe roster also lists qwen-3.8-27b, which the catalog does not carry yet:\nno chat call has verified it.","hierarchy":{"lvl0":"Getting Started","lvl1":"Cerebras Provider Guide","lvl2":"Overview","lvl3":""}},
+{"objectID":"26ab9baccdd8cb8f22ca7cea1d6e854040bed3093d871530515de9b3f990f737","title":"Key Facts","url":"/docs/getting-started/providers/cerebras#key-facts","content":"Protocol: OpenAI-compatible (/v1/chat/completions)\nDefault base URL: https://api.cerebras.ai/v1\nDefault model: gpt-oss-120b\nContext window: 65K tokens on the free tier, 131K on paid tiers. NeuroLink budgets context against the 65K free-tier floor — the\n  account tier isn't knowable from the key, and compacting early on a paid\n  tier is safe while overrunning a 65K window is not.\nMax output: 32K free / 40K paid\nVision: No — gemma-4-31b, the only vision-capable model, is retired\nStreaming: Supported\nTool calling: Supported (native)\nStructured output: Supported — but not combined with tools in one\n  request: the API rejects tools + response_format together with\n  400 wrong_api_format (\"tools\" is incompatible with \"response_format\").\n  NeuroLink handles this the same way as Groq: with tools active the\n  schema is enforced post-hoc on the final text instead of on the wire.\nReasoning trace: gpt-oss-120b emits reasoning deltas before\n  content — see Troubleshooting for the maxTokens implication.\nBilling: no keyless free tier. Even the one-time $5 promotional\n  credit requires saving a payment method (\"you won't be charged now\").\n  Pay-as-you-go starts at $10.\nPricing (per million tokens, checked 2026-08-27): gpt-oss-120b\n  $0.35 in / $0.75 out.","hierarchy":{"lvl0":"Getting Started","lvl1":"Cerebras Provider Guide","lvl2":"Key Facts","lvl3":""}},
 {"objectID":"c3c043ac1f776cffba1044b19f416aafce29755534349bb92136960de36a692b","title":"1. Get an API Key","url":"/docs/getting-started/providers/cerebras#1-get-an-api-key","content":"Sign up at https://cloud.cerebras.ai (Google\nOAuth works), claim the $5 free credit under Billing → Credits (a\npayment card must be saved — no charge is made), and create an API key\n(prefix csk-).","hierarchy":{"lvl0":"Getting Started","lvl1":"Cerebras Provider Guide","lvl2":"1. Get an API Key","lvl3":""}},
 {"objectID":"9e3b6877b6959bc93d1110ec37c7f1ce4af33285ee2a82761d36763d85be92e2","title":"2. Configure Environment","url":"/docs/getting-started/providers/cerebras#2-configure-environment","content":"`bash","hierarchy":{"lvl0":"Getting Started","lvl1":"Cerebras Provider Guide","lvl2":"2. Configure Environment","lvl3":""}},
 {"objectID":"e3829cccd09bb0837aa182c1797d9b0ff9f73005068adc983f16f050b8d21599","title":"Required","url":"/docs/getting-started/providers/cerebras#required","content":"CEREBRASAPIKEY=csk-...","hierarchy":{"lvl0":"Getting Started","lvl1":"Cerebras Provider Guide","lvl2":"Required","lvl3":""}},
-{"objectID":"b1eea51082498c799ccf79c0e90f0879a6170984675a89934be3a4670db89de0","title":"Optional: override the default model (default: gpt-oss-120b)","url":"/docs/getting-started/providers/cerebras#optional-override-the-default-model-default-gpt-oss-120b","content":"CEREBRAS_MODEL=gemma-4-31b","hierarchy":{"lvl0":"Getting Started","lvl1":"Cerebras Provider Guide","lvl2":"Optional: override the default model (default: gpt-oss-120b)","lvl3":""}},
+{"objectID":"b1eea51082498c799ccf79c0e90f0879a6170984675a89934be3a4670db89de0","title":"Optional: override the default model (default: gpt-oss-120b)","url":"/docs/getting-started/providers/cerebras#optional-override-the-default-model-default-gpt-oss-120b","content":"CEREBRAS_MODEL=gpt-oss-120b","hierarchy":{"lvl0":"Getting Started","lvl1":"Cerebras Provider Guide","lvl2":"Optional: override the default model (default: gpt-oss-120b)","lvl3":""}},
 {"objectID":"962285bdf8273490f1457378d234a1ac149267b97d4525c2f24b1b4da267fe1f","title":"CEREBRAS_BASE_URL=https://api.cerebras.ai/v1","url":"/docs/getting-started/providers/cerebras#cerebras_base_urlhttpsapicerebrasaiv1","content":"`","hierarchy":{"lvl0":"Getting Started","lvl1":"Cerebras Provider Guide","lvl2":"CEREBRAS_BASE_URL=https://api.cerebras.ai/v1","lvl3":""}},
 {"objectID":"dc0b39d9332b8719ec6f97b08fa67dd583fb91ea99f0690eea37525ba773c7ae","title":"Structured Output","url":"/docs/getting-started/providers/cerebras#structured-output","content":"Combining schema with active tools works, but the schema is enforced\npost-hoc rather than on the wire (see Key Facts) — expect\nstructuredData to be best-effort in that combination, exactly as with\nGroq.","hierarchy":{"lvl0":"Getting Started","lvl1":"Cerebras Provider Guide","lvl2":"Structured Output","lvl3":""}},
 {"objectID":"456b4dcb39fa485bca2687655be21a417c78bc6361c0d40f4c9c241ea439bcfb","title":"CLI Usage","url":"/docs/getting-started/providers/cerebras#cli-usage","content":"`bash","hierarchy":{"lvl0":"Getting Started","lvl1":"Cerebras Provider Guide","lvl2":"CLI Usage","lvl3":""}},
 {"objectID":"4643c07beb3b8210ea91cc08e566025480892c779bef7b2c796b9c8ebaff6ce1","title":"Default model (gpt-oss-120b)","url":"/docs/getting-started/providers/cerebras#default-model-gpt-oss-120b","content":"pnpm run cli generate \"Quick question\" --provider cerebras","hierarchy":{"lvl0":"Getting Started","lvl1":"Cerebras Provider Guide","lvl2":"Default model (gpt-oss-120b)","lvl3":""}},
-{"objectID":"e0c763d4b5bc1fd75056c4d34a718ac6ad2e70a476fa624d205158fa731db80e","title":"Explicit model","url":"/docs/getting-started/providers/cerebras#explicit-model","content":"pnpm run cli generate \"Hi\" --provider cerebras --model gemma-4-31b","hierarchy":{"lvl0":"Getting Started","lvl1":"Cerebras Provider Guide","lvl2":"Explicit model","lvl3":""}},
+{"objectID":"e0c763d4b5bc1fd75056c4d34a718ac6ad2e70a476fa624d205158fa731db80e","title":"Explicit model","url":"/docs/getting-started/providers/cerebras#explicit-model","content":"pnpm run cli generate \"Hi\" --provider cerebras --model gpt-oss-120b","hierarchy":{"lvl0":"Getting Started","lvl1":"Cerebras Provider Guide","lvl2":"Explicit model","lvl3":""}},
 {"objectID":"a1cc50f0d339695a00d519964c59b8be591a987db884bbe5be1e9176df71b1cb","title":"Streaming","url":"/docs/getting-started/providers/cerebras#streaming-1","content":"pnpm run cli stream \"Count to ten\" --provider cerebras","hierarchy":{"lvl0":"Getting Started","lvl1":"Cerebras Provider Guide","lvl2":"Streaming","lvl3":""}},
 {"objectID":"f92965506a689f101d827e46fd2c597bc08e2e4e4795897527ea24eae93b1599","title":"Loop / chat","url":"/docs/getting-started/providers/cerebras#loop-chat","content":"pnpm run cli loop --provider cerebras\n`","hierarchy":{"lvl0":"Getting Started","lvl1":"Cerebras Provider Guide","lvl2":"Loop / chat","lvl3":""}},
 {"objectID":"00c70f016282b6122ce31ad75b96f97d6ceac48d4df583fd6f5e0e5d92ac54db","title":"Provider Aliases","url":"/docs/getting-started/providers/cerebras#provider-aliases","content":"| Alias      | Example               |\n| ---------- | --------------------- |\n| cerebras | --provider cerebras |","hierarchy":{"lvl0":"Getting Started","lvl1":"Cerebras Provider Guide","lvl2":"Provider Aliases","lvl3":""}},
 {"objectID":"6f804eccfe08ce82b598089930b46f12be01d31332a34b8a0fdc82bf0f492fa1","title":"Configuration Reference","url":"/docs/getting-started/providers/cerebras#configuration-reference","content":"| Environment Variable | Required | Default                      | Description      |\n| -------------------- | -------- | ---------------------------- | ---------------- |\n| CEREBRAS_API_KEY   | Yes      | —                            | Cerebras API key |\n| CEREBRAS_MODEL     | No       | gpt-oss-120b               | Default model    |\n| CEREBRAS_BASE_URL  | No       | https://api.cerebras.ai/v1 | Base URL         |","hierarchy":{"lvl0":"Getting Started","lvl1":"Cerebras Provider Guide","lvl2":"Configuration Reference","lvl3":""}},
-{"objectID":"4f11d403d24ed52edbb5f65bb14374f400a4c4f93c5cfc77031253d7f07afb70","title":"Feature Support Matrix","url":"/docs/getting-started/providers/cerebras#feature-support-matrix","content":"| Feature                   | gpt-oss-120b | gemma-4-31b |\n| ------------------------- | ------------ | ----------- |\n| Text generation           | Yes          | Yes         |\n| Streaming                 | Yes          | Yes         |\n| Tool calling              | Yes          | Yes         |\n| Structured output         | Yes          | Yes         |\n| Structured output + tools | Post-hoc     | Post-hoc    |\n| Vision                    | No           | No          |\n| Embeddings                | No           | No          |\n| Context window            | 65K/131K     | 65K/131K    |","hierarchy":{"lvl0":"Getting Started","lvl1":"Cerebras Provider Guide","lvl2":"Feature Support Matrix","lvl3":""}},
+{"objectID":"4f11d403d24ed52edbb5f65bb14374f400a4c4f93c5cfc77031253d7f07afb70","title":"Feature Support Matrix","url":"/docs/getting-started/providers/cerebras#feature-support-matrix","content":"| Feature                   | gpt-oss-120b |\n| ------------------------- | ------------ |\n| Text generation           | Yes          |\n| Streaming                 | Yes          |\n| Tool calling              | Yes          |\n| Structured output         | Yes          |\n| Structured output + tools | Post-hoc     |\n| Vision                    | No           |\n| Embeddings                | No           |\n| Context window            | 65K/131K     |","hierarchy":{"lvl0":"Getting Started","lvl1":"Cerebras Provider Guide","lvl2":"Feature Support Matrix","lvl3":""}},
 {"objectID":"44d1fb37e97ca28d25351c5c9b256f6290a6893cadc0a4be56dff1a10438120a","title":"\"Invalid Cerebras API key\"","url":"/docs/getting-started/providers/cerebras#invalid-cerebras-api-key","content":"`bash","hierarchy":{"lvl0":"Getting Started","lvl1":"Cerebras Provider Guide","lvl2":"\"Invalid Cerebras API key\"","lvl3":""}},
 {"objectID":"1dd703d4cc118d7afbab83843af03af9886728f3bab92272cace22e9463fa0e7","title":"and shell transcripts retain echoed values):","url":"/docs/getting-started/providers/cerebras#and-shell-transcripts-retain-echoed-values","content":"test -n \"$CEREBRASAPIKEY\" && echo \"CEREBRASAPIKEY is set\" || echo \"CEREBRASAPIKEY is missing\"\n\n\n\nGet / rotate at [https://cloud.cerebras.ai](https://cloud.cerebras.ai).\nA bad key returns 401 with \"code\": \"wrongapikey\"`, which NeuroLink\nmaps to this message.","hierarchy":{"lvl0":"Getting Started","lvl1":"Cerebras Provider Guide","lvl2":"and shell transcripts retain echoed values):","lvl3":""}},
 {"objectID":"507c596f6b7d8b9e2bd492f28a01def0e63693105d3057dda54079bc94e63478","title":"402 payment_required on every call","url":"/docs/getting-started/providers/cerebras#402-payment_required-on-every-call","content":"The account has no balance. Cerebras has no keyless free tier: open\nBilling → Credits → ADD CREDITS in the console, choose \"Start with\nlimited free credits\", and save a payment card — the $5 promo credit\nactivates with no charge. Skipping the claim step during onboarding\n(\"SKIP TO CONSOLE\") leaves the balance at $0.00.","hierarchy":{"lvl0":"Getting Started","lvl1":"Cerebras Provider Guide","lvl2":"402 payment_required on every call","lvl3":""}},
 {"objectID":"87ba20ffd62f6d99291ed1b32232cafab1ea70cfc060f5a59ea5e374b16de169","title":"Empty content with small maxTokens on gpt-oss-120b","url":"/docs/getting-started/providers/cerebras#empty-content-with-small-maxtokens-on-gpt-oss-120b","content":"gpt-oss-120b is a reasoning model: it spends its first tokens on a\nreasoning channel before emitting content. With a tight budget\n(e.g. maxTokens: 50) the entire budget goes to reasoning,\nfinish_reason is length, and content is empty. Give reasoning\nprompts a few hundred tokens of headroom.","hierarchy":{"lvl0":"Getting Started","lvl1":"Cerebras Provider Guide","lvl2":"Empty content with small maxTokens on gpt-oss-120b","lvl3":""}},
-{"objectID":"12792b087dafedbd6d724cb4cfd2f5365fcea8da18d2d14493ff688b79efda80","title":"404 \"model not found\" for llama/qwen models","url":"/docs/getting-started/providers/cerebras#404-model-not-found-for-llamaqwen-models","content":"Those models are retired. The live roster is gpt-oss-120b and\ngemma-4-31b only — verify with an authenticated\nGET https://api.cerebras.ai/v1/models.","hierarchy":{"lvl0":"Getting Started","lvl1":"Cerebras Provider Guide","lvl2":"404 \"model not found\" for llama/qwen models","lvl3":""}},
+{"objectID":"12792b087dafedbd6d724cb4cfd2f5365fcea8da18d2d14493ff688b79efda80","title":"404 \"model not found\" for llama/qwen models","url":"/docs/getting-started/providers/cerebras#404-model-not-found-for-llamaqwen-models","content":"Those models are retired, and so is gemma-4-31b. The catalog carries\ngpt-oss-120b only — verify the live roster with an authenticated\nGET https://api.cerebras.ai/v1/models.","hierarchy":{"lvl0":"Getting Started","lvl1":"Cerebras Provider Guide","lvl2":"404 \"model not found\" for llama/qwen models","lvl3":""}},
 {"objectID":"c122483695ccba53489f6d1403f7b78fa2f9d48c9a35220e08425516b5521183","title":"See Also","url":"/docs/getting-started/providers/cerebras#see-also","content":"Groq Provider — sibling speed-focused OpenAI-compat provider\nxAI Grok Provider — sibling OpenAI-compat with Grok 3\nTier 2 catalog entry guide — how this provider is wired internally\n\nNeed Help? Open a GitHub Discussion or issue.","hierarchy":{"lvl0":"Getting Started","lvl1":"Cerebras Provider Guide","lvl2":"See Also","lvl3":""}},
 {"objectID":"3803b4ecde578f946b8a4fe5139e3ee640d53281541c50578e8a5d47847d5157","title":"Cloudflare Workers AI Provider Guide","url":"/docs/getting-started/providers/cloudflare","content":"Cloudflare Workers AI Provider Guide\n\nOpen-model inference at the edge via Cloudflare Workers AI\n\nOverview\n\nCloudflare Workers AI\nserves Meta Llama, Mistral, and other open models from Cloudflare's\nglobal GPU cluster. NeuroLink talks to the OpenAI-compatible endpoint.\n\nKey Facts\nProtocol: OpenAI-compatible (/v1/chat/completions)\nDefault base URL: https://api.cloudflare.com/client/v4/accounts/{accountId}/ai/v1\nDefault model: @cf/meta/llama-3.3-70b-instruct-fp8-fast\nStreaming: Yes\nTool calling: Limited (model-dependent)\n\nQuick Start\nGet Credentials\n\nYou need both:\nA Cloudflare Account ID (Cloudflare dashboard → right sidebar)\nA Workers AI API token with the Workers AI Read & Write\n  permission (Profile → API Tokens → Create Token)\nConfigure\nGenerate\n\nSupported Models (sample)\n\n| Model ID                                   | Notes          |\n| ------------------------------------------ | -------------- |\n| @cf/meta/llama-3.3-70b-instruct-fp8-fast | Default        |\n| @cf/meta/llama-3.1-70b-instruct          | Llama 3.1 70B  |\n| @cf/meta/llama-3.1-8b-instruct           | Fast tier      |\n| @cf/meta/llama-3.2-11b-vision-instruct   | Vision-capable |\n\nBrowse: https://developers.cloudflare.com/workers-ai/models\n\nCLI Usage\n\nProvider Aliases\n\n| Alias        | Example                 |\n| ------------ | ----------------------- |\n| cloudflare | --provider cloudflare |\n| cf         | --provider cf         |\n\nConfiguration Reference\n\n| Environment Variable    | Required | Default                                    |\n| ----------------------- | -------- | ------------------------------------------ |\n| CLOUDFLARE_ACCOUNT_ID | Yes      | —                                          |\n| CLOUDFLARE_API_KEY    | Yes      | —                                          |\n| CLOUDFLARE_MODEL      | No       | @cf/meta/llama-3.3-70b-instruct-fp8-fast |\n\nSee Also\nTogether AI Provider\nFireworks Provider","hierarchy":{"lvl0":"Getting Started","lvl1":"Cloudflare Workers AI Provider Guide","lvl2":"","lvl3":""}},
 {"objectID":"aafa1a6f2adf2bacc5661cf9ccb309d1e32e300645f037c35a98217b31eb15df","title":"Cloudflare Workers AI Provider Guide","url":"/docs/getting-started/providers/cloudflare#cloudflare-workers-ai-provider-guide","content":"Open-model inference at the edge via Cloudflare Workers AI","hierarchy":{"lvl0":"Getting Started","lvl1":"Cloudflare Workers AI Provider Guide","lvl2":"Cloudflare Workers AI Provider Guide","lvl3":""}},
@@ -5566,14 +5566,14 @@
 {"objectID":"293d0cf78c8b91321aaea4539752c75c5d23b0f630e75d8c039fa5b10759fbd8","title":"Voice not found","url":"/docs/getting-started/providers/elevenlabs#voice-not-found","content":"You passed a voice ID that does not exist in your account. List available voices to confirm:","hierarchy":{"lvl0":"Getting Started","lvl1":"ElevenLabs Provider Guide","lvl2":"Voice not found","lvl3":""}},
 {"objectID":"a8f667c71e278a2fbdf507c9d16d18418a74fc97ae593129deaa675058c728f5","title":"\"Failed to get voices\"","url":"/docs/getting-started/providers/elevenlabs#failed-to-get-voices","content":"Voice discovery failed (network error or invalid key). The 5-minute cache shields against transient failures, but a hard failure at startup will propagate. Ensure ELEVENLABS_API_KEY is valid and the ElevenLabs API is reachable.","hierarchy":{"lvl0":"Getting Started","lvl1":"ElevenLabs Provider Guide","lvl2":"\"Failed to get voices\"","lvl3":""}},
 {"objectID":"58ee78d9a6be3099cc23a438c6255e483cabb54fdd59e63c6d9de2a3e10068ad","title":"See Also","url":"/docs/getting-started/providers/elevenlabs#see-also","content":"TTS Integration Guide — complete multi-provider TTS reference\nOpenAI TTS Provider Guide — alternative TTS provider\nAudio Input (STT) — speech-to-text counterpart\nVoice Agent Guide — building full voice assistants\n\nNeed Help? Join the GitHub Discussions or open an issue.","hierarchy":{"lvl0":"Getting Started","lvl1":"ElevenLabs Provider Guide","lvl2":"See Also","lvl3":""}},
-{"objectID":"b1184b197b42e32c5be5fb34fb171453c9691187c6fd632ea6ee2ffc096329ad","title":"Fireworks AI Provider Guide","url":"/docs/getting-started/providers/fireworks","content":"Fireworks AI Provider Guide\n\nOpen-model inference tuned for low-latency production workloads\n\nOverview\n\nFireworks AI hosts Llama, DeepSeek, Mixtral,\nQwen, and other open models with aggressive throughput optimizations.\nNeuroLink talks to the OpenAI-compatible endpoint at api.fireworks.ai.\n\nKey Facts\nProtocol: OpenAI-compatible (/inference/v1/chat/completions)\nDefault base URL: https://api.fireworks.ai/inference/v1\nDefault model: accounts/fireworks/models/llama-v3p3-70b-instruct\nStreaming: Yes\nTool calling: Yes (model-dependent)\n\nQuick Start\nGet an API Key\n\nhttps://fireworks.ai/account/api-keys\nConfigure Environment\nGenerate\n\nSupported Models (sample)\n\n| Model ID                                             | Notes     |\n| ---------------------------------------------------- | --------- |\n| accounts/fireworks/models/llama-v3p3-70b-instruct  | Default   |\n| accounts/fireworks/models/llama-v3p1-405b-instruct | Flagship  |\n| accounts/fireworks/models/deepseek-r1              | Reasoning |\n| accounts/fireworks/models/mixtral-8x22b-instruct   | MoE       |\n\nBrowse: https://fireworks.ai/models\n\nCLI Usage\n\nProvider Aliases\n\n| Alias       | Example                |\n| ----------- | ---------------------- |\n| fireworks | --provider fireworks |\n\nConfiguration Reference\n\n| Environment Variable | Required | Default                                             |\n| -------------------- | -------- | --------------------------------------------------- |\n| FIREWORKS_API_KEY  | Yes      | —                                                   |\n| FIREWORKS_MODEL    | No       | accounts/fireworks/models/llama-v3p3-70b-instruct |\n| FIREWORKS_BASE_URL | No       | https://api.fireworks.ai/inference/v1             |\n\nTroubleshooting\nModel not found, inaccessible, and/or not deployed — your account\n  has not deployed the requested model. Check\n  https://fireworks.ai/models and either\n  deploy it or pick a serverless one.\n\nSee Also\nTogether AI Provider\nGroq Provider","hierarchy":{"lvl0":"Getting Started","lvl1":"Fireworks AI Provider Guide","lvl2":"","lvl3":""}},
+{"objectID":"b1184b197b42e32c5be5fb34fb171453c9691187c6fd632ea6ee2ffc096329ad","title":"Fireworks AI Provider Guide","url":"/docs/getting-started/providers/fireworks","content":"Fireworks AI Provider Guide\n\nOpen-model inference tuned for low-latency production workloads\n\nOverview\n\nFireworks AI hosts Kimi, GPT-OSS, Qwen, GLM and\nother open models with aggressive throughput optimizations.\nNeuroLink talks to the OpenAI-compatible endpoint at api.fireworks.ai.\n\nKey Facts\nProtocol: OpenAI-compatible (/inference/v1/chat/completions)\nDefault base URL: https://api.fireworks.ai/inference/v1\nDefault model: accounts/fireworks/models/kimi-k3 (vision-capable)\nStreaming: Yes\nTool calling: Yes (model-dependent)\n\nQuick Start\nGet an API Key\n\nhttps://fireworks.ai/account/api-keys\nConfigure Environment\nGenerate\n\nSupported Models (sample)\n\n| Model ID                                 | Vision | Notes                               |\n| ---------------------------------------- | ------ | ----------------------------------- |\n| accounts/fireworks/models/kimi-k3      | Yes    | Default — newest Moonshot flagship  |\n| accounts/fireworks/models/gpt-oss-120b | No     | Text fallback (fallbackModelName) |\n| accounts/fireworks/models/qwen3p8-max  | Yes    | Qwen flagship                       |\n| accounts/fireworks/models/glm-5p3      | No     | Rejects image inputs                |\n\nFireworks lists models on /models that are not deployed for serverless\nuse, so the catalog only keeps ids that answered a real chat call.\nkimi-k2p6, the default until September 2026, now returns 404\nnot deployed and is retired.\n\nBrowse: https://fireworks.ai/models\n\nCLI Usage\n\nProvider Aliases\n\n| Alias       | Example                |\n| ----------- | ---------------------- |\n| fireworks | --provider fireworks |\n\nConfiguration Reference\n\n| Environment Variable | Required | Default                                 |\n| -------------------- | -------- | --------------------------------------- |\n| FIREWORKS_API_KEY  | Yes      | —                                       |\n| FIREWORKS_MODEL    | No       | accounts/fireworks/models/kimi-k3     |\n| FIREWORKS_BASE_URL | No       | https://api.fireworks.ai/inference/v1 |\n\nTroubleshooting\nModel not found, inaccessible, and/or not deployed — your account\n  has not deployed the requested model. Check\n  https://fireworks.ai/models and either\n  deploy it or pick a serverless one.\n\nSee Also\nTogether AI Provider\nGroq Provider","hierarchy":{"lvl0":"Getting Started","lvl1":"Fireworks AI Provider Guide","lvl2":"","lvl3":""}},
 {"objectID":"05cd5f1dffdb316d6e5f1b3ff86da591b78de22e32dc78ccf67aa1f40d59597d","title":"Fireworks AI Provider Guide","url":"/docs/getting-started/providers/fireworks#fireworks-ai-provider-guide","content":"Open-model inference tuned for low-latency production workloads","hierarchy":{"lvl0":"Getting Started","lvl1":"Fireworks AI Provider Guide","lvl2":"Fireworks AI Provider Guide","lvl3":""}},
-{"objectID":"ce4faa67b07a31fda18f8df2e44a84161502930a7c7bda3806406447212d3b32","title":"Overview","url":"/docs/getting-started/providers/fireworks#overview","content":"Fireworks AI hosts Llama, DeepSeek, Mixtral,\nQwen, and other open models with aggressive throughput optimizations.\nNeuroLink talks to the OpenAI-compatible endpoint at api.fireworks.ai.","hierarchy":{"lvl0":"Getting Started","lvl1":"Fireworks AI Provider Guide","lvl2":"Overview","lvl3":""}},
-{"objectID":"cf82705a9b6b783a7d82e376fcee6d19120c08d1bbdf1df8b01a319dda22d70f","title":"Key Facts","url":"/docs/getting-started/providers/fireworks#key-facts","content":"Protocol: OpenAI-compatible (/inference/v1/chat/completions)\nDefault base URL: https://api.fireworks.ai/inference/v1\nDefault model: accounts/fireworks/models/llama-v3p3-70b-instruct\nStreaming: Yes\nTool calling: Yes (model-dependent)","hierarchy":{"lvl0":"Getting Started","lvl1":"Fireworks AI Provider Guide","lvl2":"Key Facts","lvl3":""}},
+{"objectID":"ce4faa67b07a31fda18f8df2e44a84161502930a7c7bda3806406447212d3b32","title":"Overview","url":"/docs/getting-started/providers/fireworks#overview","content":"Fireworks AI hosts Kimi, GPT-OSS, Qwen, GLM and\nother open models with aggressive throughput optimizations.\nNeuroLink talks to the OpenAI-compatible endpoint at api.fireworks.ai.","hierarchy":{"lvl0":"Getting Started","lvl1":"Fireworks AI Provider Guide","lvl2":"Overview","lvl3":""}},
+{"objectID":"cf82705a9b6b783a7d82e376fcee6d19120c08d1bbdf1df8b01a319dda22d70f","title":"Key Facts","url":"/docs/getting-started/providers/fireworks#key-facts","content":"Protocol: OpenAI-compatible (/inference/v1/chat/completions)\nDefault base URL: https://api.fireworks.ai/inference/v1\nDefault model: accounts/fireworks/models/kimi-k3 (vision-capable)\nStreaming: Yes\nTool calling: Yes (model-dependent)","hierarchy":{"lvl0":"Getting Started","lvl1":"Fireworks AI Provider Guide","lvl2":"Key Facts","lvl3":""}},
 {"objectID":"2553a96780b52ca185305c8520070d1ffd546668722c2fa9dfb470e2883fa9ef","title":"1. Get an API Key","url":"/docs/getting-started/providers/fireworks#1-get-an-api-key","content":"https://fireworks.ai/account/api-keys","hierarchy":{"lvl0":"Getting Started","lvl1":"Fireworks AI Provider Guide","lvl2":"1. Get an API Key","lvl3":""}},
-{"objectID":"f08aab0c7818717d789d878d66a349766820749c3296c011c8c3f35782e63a12","title":"Supported Models (sample)","url":"/docs/getting-started/providers/fireworks#supported-models-sample","content":"| Model ID                                             | Notes     |\n| ---------------------------------------------------- | --------- |\n| accounts/fireworks/models/llama-v3p3-70b-instruct  | Default   |\n| accounts/fireworks/models/llama-v3p1-405b-instruct | Flagship  |\n| accounts/fireworks/models/deepseek-r1              | Reasoning |\n| accounts/fireworks/models/mixtral-8x22b-instruct   | MoE       |\n\nBrowse: https://fireworks.ai/models","hierarchy":{"lvl0":"Getting Started","lvl1":"Fireworks AI Provider Guide","lvl2":"Supported Models (sample)","lvl3":""}},
+{"objectID":"f08aab0c7818717d789d878d66a349766820749c3296c011c8c3f35782e63a12","title":"Supported Models (sample)","url":"/docs/getting-started/providers/fireworks#supported-models-sample","content":"| Model ID                                 | Vision | Notes                               |\n| ---------------------------------------- | ------ | ----------------------------------- |\n| accounts/fireworks/models/kimi-k3      | Yes    | Default — newest Moonshot flagship  |\n| accounts/fireworks/models/gpt-oss-120b | No     | Text fallback (fallbackModelName) |\n| accounts/fireworks/models/qwen3p8-max  | Yes    | Qwen flagship                       |\n| accounts/fireworks/models/glm-5p3      | No     | Rejects image inputs                |\n\nFireworks lists models on /models that are not deployed for serverless\nuse, so the catalog only keeps ids that answered a real chat call.\nkimi-k2p6, the default until September 2026, now returns 404\nnot deployed and is retired.\n\nBrowse: https://fireworks.ai/models","hierarchy":{"lvl0":"Getting Started","lvl1":"Fireworks AI Provider Guide","lvl2":"Supported Models (sample)","lvl3":""}},
 {"objectID":"1c6ba5220686d63b86ed6da5aeaff8ad54a0e33503a1f3dfd9bafd095e446665","title":"Provider Aliases","url":"/docs/getting-started/providers/fireworks#provider-aliases","content":"| Alias       | Example                |\n| ----------- | ---------------------- |\n| fireworks | --provider fireworks |","hierarchy":{"lvl0":"Getting Started","lvl1":"Fireworks AI Provider Guide","lvl2":"Provider Aliases","lvl3":""}},
-{"objectID":"0fd84fcdee093aae5dd076045f0363115b84752fb19939ed867be53ec42e7c0e","title":"Configuration Reference","url":"/docs/getting-started/providers/fireworks#configuration-reference","content":"| Environment Variable | Required | Default                                             |\n| -------------------- | -------- | --------------------------------------------------- |\n| FIREWORKS_API_KEY  | Yes      | —                                                   |\n| FIREWORKS_MODEL    | No       | accounts/fireworks/models/llama-v3p3-70b-instruct |\n| FIREWORKS_BASE_URL | No       | https://api.fireworks.ai/inference/v1             |","hierarchy":{"lvl0":"Getting Started","lvl1":"Fireworks AI Provider Guide","lvl2":"Configuration Reference","lvl3":""}},
+{"objectID":"0fd84fcdee093aae5dd076045f0363115b84752fb19939ed867be53ec42e7c0e","title":"Configuration Reference","url":"/docs/getting-started/providers/fireworks#configuration-reference","content":"| Environment Variable | Required | Default                                 |\n| -------------------- | -------- | --------------------------------------- |\n| FIREWORKS_API_KEY  | Yes      | —                                       |\n| FIREWORKS_MODEL    | No       | accounts/fireworks/models/kimi-k3     |\n| FIREWORKS_BASE_URL | No       | https://api.fireworks.ai/inference/v1 |","hierarchy":{"lvl0":"Getting Started","lvl1":"Fireworks AI Provider Guide","lvl2":"Configuration Reference","lvl3":""}},
 {"objectID":"1641ff26216c6b6cb208d2dd83700286afa7680efcbb7f24cc5d63382b705f6c","title":"Troubleshooting","url":"/docs/getting-started/providers/fireworks#troubleshooting","content":"Model not found, inaccessible, and/or not deployed — your account\n  has not deployed the requested model. Check\n  https://fireworks.ai/models and either\n  deploy it or pick a serverless one.","hierarchy":{"lvl0":"Getting Started","lvl1":"Fireworks AI Provider Guide","lvl2":"Troubleshooting","lvl3":""}},
 {"objectID":"016bd37da784e68632e7632baf2ff92d35b9746cf85268f4e9f1007576898945","title":"See Also","url":"/docs/getting-started/providers/fireworks#see-also","content":"Together AI Provider\nGroq Provider","hierarchy":{"lvl0":"Getting Started","lvl1":"Fireworks AI Provider Guide","lvl2":"See Also","lvl3":""}},
 {"objectID":"158e1aff9458883a351d80f993d03d24e7fe73c454666523ed2366580ccb5b30","title":"Fish Audio TTS Provider Guide","url":"/docs/getting-started/providers/fish-audio","content":"Fish Audio TTS Provider Guide\n\nLow-cost text-to-speech — S2 Pro voice cloning, multilingual, ~80%\ncheaper than ElevenLabs\n\nOverview\n\nFish Audio is a low-cost TTS provider focused on voice cloning. NeuroLink\nwraps it as a TTSHandler so it slots into the same\ngenerate({ tts: { provider: \"fish-audio\" } }) flow as OpenAI / ElevenLabs / Azure / Google AI TTS.\nLatest model: s1 (default) — best quality\nspeech-1.6, speech-1.5 — older / cheaper models\nVoice cloning: 15s of reference audio → custom voice id\nLanguages: 14 (English, Mandarin, Cantonese, Japanese, Korean,\n  French, German, Spanish, Italian, Portuguese, Russian, Arabic, Hindi,\n  Indonesian)\n\nKey Facts\nProtocol: Native REST API (POST /v1/tts)\nDefault base URL: https://api.fish.audio\nDefault model: s1\nDefault voice (reference_id): fb6c0e1ea91e427fb9a93b9bbf0a1e4d (Generic Female / English)\nMax text length: 5000 characters\nOutput formats: mp3 (default), wav, pcm16 (raw 16-bit PCM @ 44.1 kHz)\nStreaming: Not implemented in this handler (synchronous synthesis only)\n\nQuick Start\nGet an API Key\n\nSign up at https://fish.audio/ and create an API\nkey from the dashboard.\nConfigure Environment\nSynthesize Your First Audio\n\nSDK Usage\n\nBasic Synthesis (Default Voice)\n\nCustom Voice (Voice Cloning)\n\nGet a reference_id from your Fish Audio dashboard after uploading 15s\nof reference audio:\n\nTTS-Augmented LLM Response\n\nWhen useAiResponse: true, NeuroLink first calls the LLM, then\nsynthesizes the LLM output through Fish Audio:\n\nWAV / PCM16 Output\n\nPer-Call Credentials\n\nCLI Usage\n\nConfiguration Reference\n\n| Environment Variable  | Required | Default                            | Description                |\n| --------------------- | -------- | ---------------------------------- | -------------------------- |\n| FISH_AUDIO_API_KEY  | Yes      | —                                  | Fish Audio API key         |\n| FISH_AUDIO_VOICE_ID | No       | fb6c0e1ea91e427fb9a93b9bbf0a1e4d | Default reference_id voice |\n| FISH_AUDIO_BASE_URL | No       | https://api.fish.audio           | Base URL                   |\n\nVoice Models\n\n| Model        | Notes                          |\n| ------------ | ------------------------------ |\n| s1         | Latest, best quality (default) |\n| speech-1.6 | Previous flagship              |\n| speech-1.5 | Older / cheaper                |\n\nVoices are identified by reference_id strings from the Fish library.\nBrowse and clone voices in your Fish Audio dashboard.\n\nFeature Support Matrix\n\n| Feature        | Fish Audio            |\n| -------------- | --------------------- |\n| Text-to-speech | Yes                   |\n| Voice cloning  | Yes (15s reference)   |\n| Multilingual   | Yes (14 languages)    |\n| MP3 output     | Yes                   |\n| WAV output     | Yes (44.1 kHz)        |\n| PCM16 output   | Yes (raw, no RIFF)    |\n| OPUS output    | Falls back to MP3     |\n| Streaming      | No (synchronous only) |\n| getVoices()  | Not implemented       |\n\nTroubleshooting\n\n\"Invalid Fish Audio API key\"\n\nGet / rotate at https://fish.audio/.\n\n\"Fish Audio rate limit exceeded\"\n\nFree tier has hourly limits. Upgrade your plan or implement exponential\nbackoff. The handler maps 408 / 429 / 5xx to retriable errors.\n\n\"Fish Audio synthesis failed: 422\"\n\nUsually means the reference_id is invalid or the text is too long\n(>5000 chars). Truncate the text or check the voice id in your dashboard.\n\nAudio sounds robotic / low quality\n\nTry a higher-quality model (model: \"s1\" if you're on speech-1.5) or\nclone your own reference voice from a 15s clean audio sample. Default\nvoices are generic — voice-cloned reference_ids almost always sound\nbetter.\n\n\"PCM16 output is unplayable in audio players\"\n\npcm16 is RAW samples, not WAV — players need a header. To play, write\na WAV header yourself (44 bytes) before the PCM data, or use the wav\nformat which produces a complete RIFF/WAV file.\n\nSee Also\nTTS Feature Guide — overall TTS architecture and supported providers\nElevenLabs TTS — sibling TTS provider with the largest voice library\nOpenAI TTS — sibling TTS provider with tts-1 / tts-1-hd\nAdding a TTS provider — internal reference for the integration pattern\n\nNeed Help? Open a GitHub Discussion or issue.","hierarchy":{"lvl0":"Getting Started","lvl1":"Fish Audio TTS Provider Guide","lvl2":"","lvl3":""}},

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@juspay/neurolink",
-  "version": "12.37.4",
+  "version": "12.37.5",
   "packageManager": "pnpm@10.15.1",
   "description": "The pipe layer of an AI nervous system: one interface connecting provider neurons to your application, across three inference types — generate, stream and decide. `decide` returns typed, calibrated judgements from a non-generative model (~400ms, ~$0.00002/call) for routing, tool selection and context budgeting. MCP-native (4 transports), voice TTS/STT/realtime, RAG, agents, memory, compaction, 9 observability exporters. OpenAI · Anthropic · Gemini · Bedrock · Azure · Ollama · TypeSafe Jev and more.",
   "author": {