[ { "id": "grok-4.6", "displayName": "Grok 4.6", "family": "grok-4.6", "contextTokens": 500000, "maxOutputTokens": 128000, "capabilities": { "text": true, "vision": true, "audioInput": false, "audioOutput": false, "imageGeneration": false, "video": false, "reasoning": true, "tools": true, "structuredOutput": true, "streaming": true, "files": true, "webSearch": true }, "parameters": { "temperature": true, "topP": true, "topK": "accepted-on-chat-completions-undocumented", "maxTokens": true, "reasoningEffort": ["low", "medium", "high", "xhigh"], "thinkingBudget": false, "stop": false, "seed": true, "frequencyPenalty": false, "presencePenalty": false }, "pricing": { "inputPerMillion": 2.0, "cachedInputPerMillion": 0.5, "outputPerMillion": 6.0, "longContextThresholdTokens": 200000, "longContextInputPerMillion": 4.0, "longContextCachedInputPerMillion": 1.0, "longContextOutputPerMillion": 12.0, "imageInputPerMillionTokens": 2.0 }, "status": "active", "aliases": [], "notes": "Flagship (Aug 2026). Always-reasoning; reasoning_effort default high, 'none' rejected ('This model does not support `reasoning_effort` value `none`'). reasoning_content returned in chat completions (plain text, also streamed as delta.reasoning_content). Knowledge cutoff 2026-02-01. Docs: 'no text output limit'; API default cap max_completion_tokens=128000. Large hidden system prompt (~640 prompt tokens on an empty request). Supports web_search/x_search/code_interpreter/mcp/file tools on /v1/responses. Rate-limit headers observed: 7200 req / 50M tokens per window." }, { "id": "grok-4.5", "displayName": "Grok 4.5", "family": "grok-4.5", "contextTokens": 500000, "maxOutputTokens": 128000, "capabilities": { "text": true, "vision": true, "audioInput": false, "audioOutput": false, "imageGeneration": false, "video": false, "reasoning": true, "tools": true, "structuredOutput": true, "streaming": true, "files": true, "webSearch": true }, "parameters": { "temperature": true, "topP": true, "topK": "accepted-on-chat-completions-undocumented", "maxTokens": true, "reasoningEffort": ["low", "medium", "high"], "thinkingBudget": false, "stop": false, "seed": true, "frequencyPenalty": false, "presencePenalty": false }, "pricing": { "inputPerMillion": 2.0, "cachedInputPerMillion": 0.3, "outputPerMillion": 6.0, "longContextThresholdTokens": 200000, "longContextInputPerMillion": 4.0, "longContextCachedInputPerMillion": 0.6, "longContextOutputPerMillion": 12.0, "imageInputPerMillionTokens": 2.0 }, "status": "active", "aliases": ["grok-4.5-latest", "grok-build-latest"], "notes": "Coding/agentic model (Jul 2026). Always-reasoning; 'none' rejected; 'xhigh' accepted by the API but docs say it is treated as 'high' on models that do not support it. Very few reasoning tokens on trivial prompts (~13-50). reasoning_content returned. Note the alias 'grok-build-latest' points here, not to grok-build-0.1." }, { "id": "grok-4.3", "displayName": "Grok 4.3", "family": "grok-4.3", "contextTokens": 1000000, "maxOutputTokens": 128000, "capabilities": { "text": true, "vision": true, "audioInput": false, "audioOutput": false, "imageGeneration": false, "video": false, "reasoning": true, "tools": true, "structuredOutput": true, "streaming": true, "files": true, "webSearch": true }, "parameters": { "temperature": true, "topP": true, "topK": "accepted-on-chat-completions-undocumented", "maxTokens": true, "reasoningEffort": ["none", "low", "medium", "high"], "thinkingBudget": false, "stop": false, "seed": true, "frequencyPenalty": false, "presencePenalty": false }, "pricing": { "inputPerMillion": 1.25, "cachedInputPerMillion": 0.2, "outputPerMillion": 2.5, "longContextThresholdTokens": 200000, "longContextInputPerMillion": 2.5, "longContextCachedInputPerMillion": 0.4, "longContextOutputPerMillion": 5.0, "imageInputPerMillionTokens": 1.25 }, "status": "active", "aliases": ["grok-4.3-latest"], "notes": "Best value general model; 1M context. The ONLY probed model that accepts reasoning_effort 'none' (reasoning_tokens=0 -> effectively a non-reasoning mode). 'xhigh' accepted (docs/AI SDK say not supported -> treated as high). Retired May-15-2026 slugs (grok-3, grok-4-0709, grok-4-fast-*, grok-4-1-fast-*) are transparently served by grok-4.3 (response.model = 'grok-4.3'). Retired non-reasoning slugs map to effort 'none', reasoning slugs to 'low'. reasoning_content returned. Batch API 20% discount." }, { "id": "grok-4.20-0309-reasoning", "displayName": "Grok 4.20 Reasoning (0309)", "family": "grok-4.20", "contextTokens": 1000000, "maxOutputTokens": 128000, "capabilities": { "text": true, "vision": true, "audioInput": false, "audioOutput": false, "imageGeneration": false, "video": false, "reasoning": true, "tools": true, "structuredOutput": true, "streaming": true, "files": true, "webSearch": true }, "parameters": { "temperature": true, "topP": true, "topK": "accepted-on-chat-completions-undocumented", "maxTokens": true, "reasoningEffort": false, "thinkingBudget": false, "stop": false, "seed": true, "frequencyPenalty": false, "presencePenalty": false }, "pricing": { "inputPerMillion": 1.25, "cachedInputPerMillion": 0.2, "outputPerMillion": 2.5, "longContextThresholdTokens": 200000, "longContextInputPerMillion": 2.5, "longContextCachedInputPerMillion": 0.4, "longContextOutputPerMillion": 5.0, "imageInputPerMillionTokens": 1.25 }, "status": "active", "aliases": [ "grok-4.20-reasoning-latest", "grok-4.20", "grok-4.20-reasoning", "grok-4.20-0309", "grok-4.20-beta-0309-reasoning", "grok-4.20-beta", "grok-4.20-beta-0309", "grok-4.20-beta-latest", "grok-4.20-beta-latest-reasoning", "grok-4.20-beta-reasoning", "grok-4.20-experimental-beta-0304-reasoning", "grok-4.20-experimental-beta-0304", "grok-4.20-experimental-beta-reasoning-latest", "grok-4.20-experimental-beta-latest", "grok-4.20-reasoning-gv2" ], "notes": "Always-reasoning, fixed depth: ANY reasoning_effort value (incl. 'none') is rejected with 400 'Model grok-4.20-0309-reasoning does not support parameter reasoningEffort.' (both chat completions and /v1/responses reasoning.effort). reasoning_content returned. Occasionally emits stray '\\\\confidence{NN}' tokens after the answer on trivial prompts (observed with top_k/logprobs). Batch API 20% discount." }, { "id": "grok-4.20-0309-non-reasoning", "displayName": "Grok 4.20 Non-Reasoning (0309)", "family": "grok-4.20", "contextTokens": 1000000, "maxOutputTokens": 128000, "capabilities": { "text": true, "vision": true, "audioInput": false, "audioOutput": false, "imageGeneration": false, "video": false, "reasoning": false, "tools": true, "structuredOutput": true, "streaming": true, "files": true, "webSearch": true }, "parameters": { "temperature": true, "topP": true, "topK": "accepted-on-chat-completions-undocumented", "maxTokens": true, "reasoningEffort": false, "thinkingBudget": false, "stop": true, "seed": true, "frequencyPenalty": false, "presencePenalty": false }, "pricing": { "inputPerMillion": 1.25, "cachedInputPerMillion": 0.2, "outputPerMillion": 2.5, "longContextThresholdTokens": 200000, "longContextInputPerMillion": 2.5, "longContextCachedInputPerMillion": 0.4, "longContextOutputPerMillion": 5.0, "imageInputPerMillionTokens": 1.25 }, "status": "active", "aliases": [ "grok-4.20-non-reasoning", "grok-4.20-non-reasoning-latest", "grok-4.20-beta-non-reasoning", "grok-4.20-beta-latest-non-reasoning", "grok-4.20-experimental-beta-0304-non-reasoning", "grok-4.20-experimental-beta-non-reasoning-latest", "grok-4.20-beta-0309-non-reasoning", "grok-4.20-non-reasoning-gv2" ], "notes": "The only true non-reasoning model in the lineup (fastest TTFT, reasoning_tokens always 0, no reasoning_content). The ONLY model that accepts `stop`. reasoning_effort rejected. frequency/presence_penalty still rejected (400). Good default for cheap/fast chat. Batch API 20% discount." }, { "id": "grok-4.20-multi-agent-0309", "displayName": "Grok 4.20 Multi-Agent (0309, beta)", "family": "grok-4.20", "contextTokens": 1000000, "maxOutputTokens": null, "capabilities": { "text": true, "vision": true, "audioInput": false, "audioOutput": false, "imageGeneration": false, "video": false, "reasoning": true, "tools": "server-side-only", "structuredOutput": null, "streaming": true, "files": true, "webSearch": true }, "parameters": { "temperature": null, "topP": null, "topK": null, "maxTokens": false, "reasoningEffort": ["low", "medium", "high", "xhigh"], "thinkingBudget": false, "stop": false, "seed": null, "frequencyPenalty": false, "presencePenalty": false }, "pricing": { "inputPerMillion": 1.25, "cachedInputPerMillion": 0.2, "outputPerMillion": 2.5, "longContextThresholdTokens": 200000, "longContextInputPerMillion": 2.5, "longContextCachedInputPerMillion": 0.4, "longContextOutputPerMillion": 5.0, "imageInputPerMillionTokens": 1.25 }, "status": "beta", "aliases": [ "grok-4.20-multi-agent", "grok-4.20-multi-agent-latest", "grok-4.20-multi-agent-beta-latest", "grok-4.20-multi-agent-experimental-beta-0304", "grok-4.20-multi-agent-experimental-beta-latest", "grok-4.20-multi-agent-beta-0309" ], "notes": "/v1/responses ONLY: chat completions returns 400 'Multi Agent requests are not allowed on chat completions' (probed). reasoning.effort selects agent count (low/medium = 4 agents, high/xhigh = 16), not depth. No client-side function tools, no max_tokens. All leader + sub-agent tokens billed -> expensive; lower rate limits (T0 9 RPS / 2.5M TPM). Not probed for generation (cost). Deliberately NOT recommended as a default chat model in PolyLLM." }, { "id": "grok-build-0.1", "displayName": "Grok Build 0.1", "family": "grok-build", "contextTokens": 256000, "maxOutputTokens": 128000, "capabilities": { "text": true, "vision": true, "audioInput": false, "audioOutput": false, "imageGeneration": false, "video": false, "reasoning": true, "tools": true, "structuredOutput": true, "streaming": true, "files": null, "webSearch": null }, "parameters": { "temperature": true, "topP": true, "topK": "accepted-on-chat-completions-undocumented", "maxTokens": true, "reasoningEffort": false, "thinkingBudget": false, "stop": false, "seed": true, "frequencyPenalty": false, "presencePenalty": false }, "pricing": { "inputPerMillion": 1.0, "cachedInputPerMillion": 0.2, "outputPerMillion": 2.0, "longContextThresholdTokens": 200000, "longContextInputPerMillion": 2.0, "longContextCachedInputPerMillion": 0.4, "longContextOutputPerMillion": 4.0, "imageInputPerMillionTokens": 1.0 }, "status": "active", "aliases": ["grok-code-fast-1", "grok-code-fast", "grok-code-fast-1-0825"], "notes": "Cheapest text model; successor of grok-code-fast-1 (those slugs alias here). Always-reasoning with fixed depth: every reasoning_effort value rejected (400 'does not support parameter reasoningEffort'). Tends to spend many reasoning tokens even on trivial prompts (300-650). reasoning_content returned. Coding-oriented; image input accepted (image_tokens billed)." } ]