{"generatedAt":"2026-08-14","schemaVersion":1,"source":"https://allaiask.com/llm-providers","license":"https://allaiask.com/terms","providers":[{"slug":"openai","name":"OpenAI","legalName":"OpenAI OpCo, LLC","aka":[],"kind":"lab","hq":"San Francisco, USA","foundedYear":2015,"currentModelCount":3,"legacyModelCount":12,"priceRangePerM":[2.25,8],"maxContext":1000000,"medianTokensPerSecond":78,"openAiCompatible":true,"apiBaseUrl":"https://api.openai.com/v1","authModel":"Bearer API key","promptCaching":true,"batchDiscountPct":50,"freeTier":null,"hasFreeTier":false,"freeTierUrl":"https://platform.openai.com/docs/guides/rate-limits","freeTierLimits":"No free API tier published; API usage is billed under the account's usage tier.","freeTierExpiry":null,"rateLimitModel":"Usage tiers 1-5, auto-promoted by cumulative spend and account age","dataResidency":"US by default; EU data residency available on enterprise agreements","trainsOnApiData":false,"slaPublished":true,"docsUrl":"https://platform.openai.com/docs","pricingUrl":"https://openai.com/api/pricing/","statusUrl":"https://status.openai.com","sourceUrl":"https://platform.openai.com/docs/models","verifiedAt":"2026-08-14","rateLimits":{"providerKey":"OpenAI","published":true,"scheme":"usage-tier","tiers":[{"tierName":"Free","qualification":"No payment method on file","sourceUrl":"https://platform.openai.com/docs/guides/rate-limits","limits":[{"modelClass":"documented default/model family","rpm":3,"tpm":40000,"rpd":200,"concurrentRequests":null}]},{"tierName":"Tier 1","qualification":"$5 cumulative spend and account-age requirement","sourceUrl":"https://platform.openai.com/docs/guides/rate-limits","limits":[{"modelClass":"documented default/model family","rpm":500,"tpm":200000,"rpd":10000,"concurrentRequests":null}]},{"tierName":"Tier 3","qualification":"$100 cumulative spend and account-age requirement","sourceUrl":"https://platform.openai.com/docs/guides/rate-limits","limits":[{"modelClass":"documented default/model family","rpm":5000,"tpm":2000000,"rpd":null,"concurrentRequests":null}]}],"headers":[{"name":"retry-after","meaning":"Seconds to wait before retrying, when supplied with a 429"},{"name":"rate-limit response headers","meaning":"Provider-specific remaining and reset counters when documented"}],"exceeded":{"statusCode":429,"retryAfterHeader":"retry-after","guidance":"Use jittered exponential backoff and inspect the rate-limit headers."},"increaseUrl":"https://platform.openai.com/settings/organization/limits","sourceUrl":"https://platform.openai.com/docs/guides/rate-limits","verifiedAt":"2026-08-14","workload":{"profileSlug":"classification-at-volume","callsPerMinute":116,"tokensPerMinute":60320,"summary":"At the production volume in classification-at-volume (116 calls/min; 60,320 tokens/min), the documented cap is sufficient for RPM 500 and TPM 200,000."}},"apiKey":{"providerKey":"OpenAI","steps":[{"instruction":"Open the OpenAI API keys console and select the project that should own the credential.","verifiedAt":"2026-08-14"},{"instruction":"Choose Create new secret key, name it, and select the least-privilege project permissions available for the workload.","verifiedAt":"2026-08-14"},{"instruction":"Copy the key immediately; OpenAI shows the full secret value only at creation.","verifiedAt":"2026-08-14"},{"instruction":"Add a payment method under Billing before making paid API calls; API usage is billed to the owning organization and project.","verifiedAt":"2026-08-14"},{"instruction":"Store the value as OPENAI_API_KEY in a server-side environment or secret manager, never in source control or browser code.","verifiedAt":"2026-08-14"}],"consoleUrl":"https://platform.openai.com/api-keys","keyPrefixFormat":"Project keys begin with sk-proj-; legacy user keys use sk-. Treat both as secrets.","scopeModel":"Project-scoped keys can be restricted by permission; organization and project roles determine who can create, manage, or use them.","rotationSteps":["Create a replacement key in the same project.","Deploy the replacement through the server-side secret manager.","Verify a real request, then revoke the old key."],"revocationSteps":["Open the project API keys page.","Find the key by name or last-used metadata.","Revoke/delete it and remove the old secret from deployments."],"billingModel":"Usage is metered against the owning OpenAI organization/project and charged through the organization billing settings; the key itself is not a separate purchase.","firstCallExampleId":"openai/python/chat","envVar":"OPENAI_API_KEY","paymentRequiredUpfront":false,"scopedToProjectOrOrg":true,"keyShownOnce":true,"revocationUrl":"https://platform.openai.com/settings/organization/api-keys","sourceUrl":"https://platform.openai.com/docs/api-reference/authentication","verifiedAt":"2026-08-14"}},{"slug":"anthropic","name":"Anthropic","legalName":"Anthropic, PBC","aka":[],"kind":"lab","hq":"San Francisco, USA","foundedYear":2021,"currentModelCount":6,"legacyModelCount":7,"priceRangePerM":[2,30],"maxContext":1000000,"medianTokensPerSecond":67,"openAiCompatible":"partial","apiBaseUrl":"https://api.anthropic.com/v1","authModel":"x-api-key header","promptCaching":true,"batchDiscountPct":50,"freeTier":null,"hasFreeTier":false,"freeTierUrl":"https://docs.anthropic.com/en/docs/about-claude/pricing","freeTierLimits":"No free API tier published; API usage requires an enabled billing account.","freeTierExpiry":null,"rateLimitModel":"Usage tiers 1-4, auto-promoted by spend","dataResidency":null,"trainsOnApiData":false,"slaPublished":true,"docsUrl":"https://docs.anthropic.com","pricingUrl":"https://www.anthropic.com/pricing","statusUrl":"https://status.anthropic.com","sourceUrl":"https://docs.anthropic.com/en/docs/about-claude/models","verifiedAt":"2026-08-14","rateLimits":{"providerKey":"Anthropic","published":true,"scheme":"usage-tier","tiers":[{"tierName":"Tier 1","qualification":"$5 cumulative spend","sourceUrl":"https://docs.anthropic.com/en/api/rate-limits","limits":[{"modelClass":"documented default/model family","rpm":50,"tpm":50000,"rpd":null,"concurrentRequests":null}]},{"tierName":"Tier 2","qualification":"$40 cumulative spend and 7 days since payment","sourceUrl":"https://docs.anthropic.com/en/api/rate-limits","limits":[{"modelClass":"documented default/model family","rpm":1000,"tpm":100000,"rpd":null,"concurrentRequests":null}]},{"tierName":"Tier 4","qualification":"$5,000 cumulative spend and 30 days since payment","sourceUrl":"https://docs.anthropic.com/en/api/rate-limits","limits":[{"modelClass":"documented default/model family","rpm":4000,"tpm":400000,"rpd":null,"concurrentRequests":null}]}],"headers":[{"name":"retry-after","meaning":"Seconds to wait before retrying, when supplied with a 429"},{"name":"rate-limit response headers","meaning":"Provider-specific remaining and reset counters when documented"}],"exceeded":{"statusCode":429,"retryAfterHeader":"retry-after","guidance":"Requests and tokens are enforced independently; reduce batch size as well as request frequency."},"increaseUrl":"https://console.anthropic.com/settings/limits","sourceUrl":"https://docs.anthropic.com/en/api/rate-limits","verifiedAt":"2026-08-14","workload":{"profileSlug":"classification-at-volume","callsPerMinute":116,"tokensPerMinute":60320,"summary":"At the production volume in classification-at-volume (116 calls/min; 60,320 tokens/min), the documented cap is not sufficient for RPM 50 and TPM 50,000."}},"apiKey":{"providerKey":"Anthropic","steps":[{"instruction":"Open the Anthropic Console API keys page and select the workspace that should own the credential.","verifiedAt":"2026-08-14"},{"instruction":"Choose Create Key, give it a descriptive name, and keep workspace membership and permissions limited to the required team.","verifiedAt":"2026-08-14"},{"instruction":"Copy the key immediately; Anthropic shows the full secret value only at creation.","verifiedAt":"2026-08-14"},{"instruction":"Add or confirm billing for the workspace before production use; usage is attributed to that workspace and organization.","verifiedAt":"2026-08-14"},{"instruction":"Store the value as ANTHROPIC_API_KEY in a server-side environment or secret manager, never in source control or browser code.","verifiedAt":"2026-08-14"}],"consoleUrl":"https://console.anthropic.com/settings/keys","keyPrefixFormat":"Anthropic API keys use the sk-ant- prefix followed by provider-issued secret characters.","scopeModel":"Keys belong to an Anthropic workspace; workspace membership and organization roles control access rather than a public per-request scope list.","rotationSteps":["Create a new key in the same workspace.","Deploy it and verify a request.","Revoke the previous key after the cutover."],"revocationSteps":["Open Workspace Settings → API Keys.","Select the key to retire.","Revoke it and remove the old value from all deployments."],"billingModel":"Usage is billed to the Anthropic workspace and its organization billing account; generating a key does not itself create a charge.","firstCallExampleId":"anthropic/javascript/chat","envVar":"ANTHROPIC_API_KEY","paymentRequiredUpfront":false,"scopedToProjectOrOrg":true,"keyShownOnce":true,"revocationUrl":"https://console.anthropic.com/settings/keys","sourceUrl":"https://docs.anthropic.com/en/api/getting-started","verifiedAt":"2026-08-14"}},{"slug":"google","name":"Google","legalName":"Google LLC","aka":["Gemini","Google AI Studio","Vertex AI"],"kind":"lab","hq":"Mountain View, USA","foundedYear":1998,"currentModelCount":4,"legacyModelCount":5,"priceRangePerM":[0.85,4.5],"maxContext":2000000,"medianTokensPerSecond":114,"openAiCompatible":"partial","apiBaseUrl":"https://generativelanguage.googleapis.com/v1beta","authModel":"API key (header or query param); OAuth/service-account on Vertex AI","promptCaching":true,"batchDiscountPct":50,"freeTier":"Free tier with daily request cap on Google AI Studio","hasFreeTier":true,"freeTierUrl":"https://ai.google.dev/gemini-api/docs/rate-limits","freeTierLimits":"Free-tier requests and tokens vary by model and project; Google publishes the current quota table.","freeTierExpiry":null,"rateLimitModel":"Free, then Tier 1-3, promoted by billing status","dataResidency":"Global by default; Vertex AI offers selectable regional endpoints","trainsOnApiData":false,"slaPublished":true,"docsUrl":"https://ai.google.dev/gemini-api/docs","pricingUrl":"https://ai.google.dev/gemini-api/docs/pricing","statusUrl":"https://status.cloud.google.com","sourceUrl":"https://ai.google.dev/gemini-api/docs/models","verifiedAt":"2026-08-14","rateLimits":{"providerKey":"Google","published":true,"scheme":"per-project","tiers":[{"tierName":"Free","qualification":"Active project or free trial","sourceUrl":"https://ai.google.dev/gemini-api/docs/rate-limits","limits":[{"modelClass":"documented default/model family","rpm":null,"tpm":null,"rpd":null,"concurrentRequests":null}]},{"tierName":"Tier 1","qualification":"Linked billing account","sourceUrl":"https://ai.google.dev/gemini-api/docs/rate-limits","limits":[{"modelClass":"documented default/model family","rpm":null,"tpm":null,"rpd":null,"concurrentRequests":null}]},{"tierName":"Tier 2","qualification":"$100 paid and 3 days since first payment","sourceUrl":"https://ai.google.dev/gemini-api/docs/rate-limits","limits":[{"modelClass":"documented default/model family","rpm":null,"tpm":null,"rpd":null,"concurrentRequests":null}]}],"headers":[{"name":"retry-after","meaning":"Seconds to wait before retrying, when supplied with a 429"},{"name":"rate-limit response headers","meaning":"Provider-specific remaining and reset counters when documented"}],"exceeded":{"statusCode":429,"retryAfterHeader":null,"guidance":"Check the project quota in AI Studio; limits vary by model and project."},"increaseUrl":"https://aistudio.google.com/rate-limit","sourceUrl":"https://ai.google.dev/gemini-api/docs/rate-limits","verifiedAt":"2026-08-14","workload":{"profileSlug":"classification-at-volume","callsPerMinute":116,"tokensPerMinute":60320,"summary":"This provider publishes no numeric cap for this workload; check the account console before launch."}},"apiKey":null},{"slug":"xai","name":"xAI","legalName":"X.AI Corp.","aka":["Grok"],"kind":"lab","hq":"San Francisco, USA","foundedYear":2023,"currentModelCount":5,"legacyModelCount":2,"priceRangePerM":[1.5625,3],"maxContext":1000000,"medianTokensPerSecond":98,"openAiCompatible":true,"apiBaseUrl":"https://api.x.ai/v1","authModel":"Bearer API key","promptCaching":null,"batchDiscountPct":null,"freeTier":"Free starting credits for new accounts","hasFreeTier":true,"freeTierUrl":"https://docs.x.ai/docs/models","freeTierLimits":"Promotional credits are limited to eligible new accounts; amount and expiry vary by account.","freeTierExpiry":null,"rateLimitModel":"Per-model rate limits scaled by account tier","dataResidency":null,"trainsOnApiData":null,"slaPublished":false,"docsUrl":"https://docs.x.ai","pricingUrl":"https://docs.x.ai/docs/models","statusUrl":"https://status.x.ai","sourceUrl":"https://docs.x.ai/docs/models","verifiedAt":"2026-08-14","rateLimits":{"providerKey":"xAI","published":true,"scheme":"per-project","tiers":[{"tierName":"Default","qualification":"Account/project limit shown in the xAI console","sourceUrl":"https://docs.x.ai/docs/key-information/rate-limits","limits":[{"modelClass":"documented default/model family","rpm":null,"tpm":null,"rpd":null,"concurrentRequests":null}]}],"headers":[{"name":"retry-after","meaning":"Seconds to wait before retrying, when supplied with a 429"},{"name":"rate-limit response headers","meaning":"Provider-specific remaining and reset counters when documented"}],"exceeded":{"statusCode":429,"retryAfterHeader":null,"guidance":"Use the limit shown for the selected model and project, then back off."},"increaseUrl":"https://console.x.ai","sourceUrl":"https://docs.x.ai/docs/key-information/rate-limits","verifiedAt":"2026-08-14","workload":{"profileSlug":"classification-at-volume","callsPerMinute":116,"tokensPerMinute":60320,"summary":"This provider publishes no numeric cap for this workload; check the account console before launch."}},"apiKey":null},{"slug":"deepseek","name":"DeepSeek","legalName":"Hangzhou DeepSeek AI Co., Ltd.","aka":[],"kind":"lab","hq":"Hangzhou, China","foundedYear":2023,"currentModelCount":2,"legacyModelCount":0,"priceRangePerM":[0.66,1.98],"maxContext":1000000,"medianTokensPerSecond":100,"openAiCompatible":true,"apiBaseUrl":"https://api.deepseek.com/v1","authModel":"Bearer API key","promptCaching":null,"batchDiscountPct":null,"freeTier":null,"hasFreeTier":false,"freeTierUrl":"https://api-docs.deepseek.com/quick_start/pricing","freeTierLimits":"No free API tier published; API usage is billed at the listed token rates.","freeTierExpiry":null,"rateLimitModel":"No published hard request caps; dynamic throttling under heavy load","dataResidency":null,"trainsOnApiData":null,"slaPublished":false,"docsUrl":"https://api-docs.deepseek.com","pricingUrl":"https://api-docs.deepseek.com/quick_start/pricing","statusUrl":"https://status.deepseek.com","sourceUrl":"https://api-docs.deepseek.com/quick_start/pricing","verifiedAt":"2026-08-14","rateLimits":null,"apiKey":{"providerKey":"DeepSeek","steps":[{"instruction":"Open DeepSeek Platform API Keys and choose Create API key.","verifiedAt":"2026-08-14"},{"instruction":"Name the key for one environment or service, then confirm creation.","verifiedAt":"2026-08-14"},{"instruction":"Copy the key immediately and store it securely; DeepSeek does not make a lost secret safe to recover.","verifiedAt":"2026-08-14"},{"instruction":"Add account balance under Billing before making paid calls; DeepSeek does not provide an ongoing free tier in this guide.","verifiedAt":"2026-08-14"},{"instruction":"Store the value as DEEPSEEK_API_KEY in a server-side environment or secret manager, never in source control or browser code.","verifiedAt":"2026-08-14"}],"consoleUrl":"https://platform.deepseek.com/api_keys","keyPrefixFormat":"DeepSeek API keys use the sk- prefix followed by provider-issued secret characters; never publish a sample value.","scopeModel":"The key is account-level in the documented console; use separate keys per service/environment because no granular permission matrix is published here.","rotationSteps":["Create a replacement key.","Deploy it and verify a request.","Revoke the previous key and remove it from deployments."],"revocationSteps":["Open Platform → API Keys.","Select the compromised or retired key.","Revoke/delete it, then rotate any affected secrets."],"billingModel":"API usage draws down the DeepSeek account balance; billing belongs to the account, not to a separate key-level wallet.","firstCallExampleId":"deepseek/curl/chat","envVar":"DEEPSEEK_API_KEY","paymentRequiredUpfront":true,"scopedToProjectOrOrg":false,"keyShownOnce":true,"revocationUrl":"https://platform.deepseek.com/api_keys","sourceUrl":"https://api-docs.deepseek.com/","verifiedAt":"2026-08-14"}},{"slug":"mistral","name":"Mistral","legalName":"Mistral AI","aka":[],"kind":"lab","hq":"Paris, France","foundedYear":2023,"currentModelCount":5,"legacyModelCount":0,"priceRangePerM":[0.15,3],"maxContext":256000,"medianTokensPerSecond":118,"openAiCompatible":true,"apiBaseUrl":"https://api.mistral.ai/v1","authModel":"Bearer API key","promptCaching":null,"batchDiscountPct":50,"freeTier":"Free tier with rate-limited experimentation","hasFreeTier":true,"freeTierUrl":"https://docs.mistral.ai/getting-started/quickstart/","freeTierLimits":"Experiment access is rate-limited; current limits depend on account and model.","freeTierExpiry":null,"rateLimitModel":"Tier-based, promoted by spend","dataResidency":"EU-hosted by default","trainsOnApiData":false,"slaPublished":true,"docsUrl":"https://docs.mistral.ai","pricingUrl":"https://mistral.ai/pricing","statusUrl":"https://status.mistral.ai","sourceUrl":"https://docs.mistral.ai/getting-started/models/","verifiedAt":"2026-08-14","rateLimits":{"providerKey":"Mistral","published":true,"scheme":"usage-tier","tiers":[{"tierName":"Experiment","qualification":"Free experimentation account","sourceUrl":"https://docs.mistral.ai/deployment/lap/rate-limits/","limits":[{"modelClass":"documented default/model family","rpm":null,"tpm":null,"rpd":null,"concurrentRequests":null}]},{"tierName":"Production","qualification":"Paid account; model/account limits apply","sourceUrl":"https://docs.mistral.ai/deployment/lap/rate-limits/","limits":[{"modelClass":"documented default/model family","rpm":null,"tpm":null,"rpd":null,"concurrentRequests":null}]}],"headers":[{"name":"retry-after","meaning":"Seconds to wait before retrying, when supplied with a 429"},{"name":"rate-limit response headers","meaning":"Provider-specific remaining and reset counters when documented"}],"exceeded":{"statusCode":429,"retryAfterHeader":"retry-after","guidance":"Reduce concurrency and retry with backoff."},"increaseUrl":"https://console.mistral.ai","sourceUrl":"https://docs.mistral.ai/deployment/lap/rate-limits/","verifiedAt":"2026-08-14","workload":{"profileSlug":"classification-at-volume","callsPerMinute":116,"tokensPerMinute":60320,"summary":"This provider publishes no numeric cap for this workload; check the account console before launch."}},"apiKey":null},{"slug":"groq","name":"Groq","legalName":"Groq, Inc.","aka":[],"kind":"host","hq":"Mountain View, USA","foundedYear":2016,"currentModelCount":3,"legacyModelCount":2,"priceRangePerM":[0.13124999999999998,1.2],"maxContext":131072,"medianTokensPerSecond":780,"openAiCompatible":true,"apiBaseUrl":"https://api.groq.com/openai/v1","authModel":"Bearer API key","promptCaching":null,"batchDiscountPct":50,"freeTier":"Free tier with per-minute and per-day token caps","hasFreeTier":true,"freeTierUrl":"https://console.groq.com/docs/rate-limits","freeTierLimits":"Per-minute and per-day request/token caps vary by model and account tier.","freeTierExpiry":null,"rateLimitModel":"Per-model requests/minute and tokens/minute caps by tier","dataResidency":"US","trainsOnApiData":null,"slaPublished":false,"docsUrl":"https://console.groq.com/docs","pricingUrl":"https://groq.com/pricing","statusUrl":"https://groqstatus.com","sourceUrl":"https://console.groq.com/docs/models","verifiedAt":"2026-08-14","rateLimits":{"providerKey":"Groq","published":true,"scheme":"per-project","tiers":[{"tierName":"Free","qualification":"Free plan","sourceUrl":"https://console.groq.com/docs/rate-limits","limits":[{"modelClass":"documented default/model family","rpm":30,"tpm":6000,"rpd":14400,"concurrentRequests":null}]},{"tierName":"Developer","qualification":"Developer plan","sourceUrl":"https://console.groq.com/docs/rate-limits","limits":[{"modelClass":"documented default/model family","rpm":1000,"tpm":250000,"rpd":null,"concurrentRequests":null}]}],"headers":[{"name":"retry-after","meaning":"Seconds to wait before retrying, when supplied with a 429"},{"name":"rate-limit response headers","meaning":"Provider-specific remaining and reset counters when documented"}],"exceeded":{"statusCode":429,"retryAfterHeader":"retry-after","guidance":"Respect the model and project limits; cached tokens do not count toward limits."},"increaseUrl":"https://console.groq.com/settings/limits","sourceUrl":"https://console.groq.com/docs/rate-limits","verifiedAt":"2026-08-14","workload":{"profileSlug":"classification-at-volume","callsPerMinute":116,"tokensPerMinute":60320,"summary":"At the production volume in classification-at-volume (116 calls/min; 60,320 tokens/min), the documented cap is not sufficient for RPM 30 and TPM 6,000."}},"apiKey":{"providerKey":"Groq","steps":[{"instruction":"Open Groq Console API Keys and select the project that should own the credential.","verifiedAt":"2026-08-14"},{"instruction":"Choose Create API Key, name it for one environment or service, and confirm.","verifiedAt":"2026-08-14"},{"instruction":"Copy the key immediately and store it securely; Groq treats the complete value as a secret.","verifiedAt":"2026-08-14"},{"instruction":"Use the free tier for initial testing or add a payment method to move to paid usage; charges and limits are managed at organization/project level.","verifiedAt":"2026-08-14"},{"instruction":"Store the value as GROQ_API_KEY in a server-side environment or secret manager, never in source control or browser code.","verifiedAt":"2026-08-14"}],"consoleUrl":"https://console.groq.com/keys","keyPrefixFormat":"Groq API keys use the gsk_ prefix followed by provider-issued secret characters.","scopeModel":"Keys are project-specific; organization roles determine who may create or manage them, while project permissions and model policies constrain use.","rotationSteps":["Create a new key in the selected project.","Deploy it and verify a request.","Revoke the old key after the cutover."],"revocationSteps":["Open the project API Keys page.","Select the key to retire or the key exposed in an incident.","Revoke it and replace the secret in every deployment."],"billingModel":"Free-tier requests have the account limits shown by Groq; paid usage is metered and billed to the organization/project, not purchased per key.","firstCallExampleId":"groq/javascript/openai-sdk","envVar":"GROQ_API_KEY","paymentRequiredUpfront":false,"scopedToProjectOrOrg":false,"keyShownOnce":true,"revocationUrl":"https://console.groq.com/keys","sourceUrl":"https://console.groq.com/docs/quickstart","verifiedAt":"2026-08-14"}},{"slug":"cerebras","name":"Cerebras","legalName":"Cerebras Systems Inc.","aka":[],"kind":"host","hq":"Sunnyvale, USA","foundedYear":2015,"currentModelCount":2,"legacyModelCount":0,"priceRangePerM":[0.44999999999999996,2.375],"maxContext":200000,"medianTokensPerSecond":2215,"openAiCompatible":true,"apiBaseUrl":"https://api.cerebras.ai/v1","authModel":"Bearer API key","promptCaching":null,"batchDiscountPct":null,"freeTier":"Free tier with a daily token cap","hasFreeTier":true,"freeTierUrl":"https://inference-docs.cerebras.ai/support/rate-limits","freeTierLimits":"Free access is subject to a daily token cap and account quota.","freeTierExpiry":null,"rateLimitModel":"Per-model requests/minute and tokens/minute caps by tier","dataResidency":"US","trainsOnApiData":null,"slaPublished":false,"docsUrl":"https://inference-docs.cerebras.ai","pricingUrl":"https://www.cerebras.ai/inference","statusUrl":"https://status.cerebras.ai","sourceUrl":"https://www.cerebras.ai/inference","verifiedAt":"2026-08-14","rateLimits":{"providerKey":"Cerebras","published":true,"scheme":"per-project","tiers":[{"tierName":"Free","qualification":"Free account quota","sourceUrl":"https://inference-docs.cerebras.ai/introduction/rate-limits","limits":[{"modelClass":"documented default/model family","rpm":null,"tpm":null,"rpd":null,"concurrentRequests":null}]},{"tierName":"Production","qualification":"Account quota shown in console","sourceUrl":"https://inference-docs.cerebras.ai/introduction/rate-limits","limits":[{"modelClass":"documented default/model family","rpm":null,"tpm":null,"rpd":null,"concurrentRequests":null}]}],"headers":[{"name":"retry-after","meaning":"Seconds to wait before retrying, when supplied with a 429"},{"name":"rate-limit response headers","meaning":"Provider-specific remaining and reset counters when documented"}],"exceeded":{"statusCode":429,"retryAfterHeader":null,"guidance":"Reduce concurrency and consult the account quota."},"increaseUrl":"https://cloud.cerebras.ai","sourceUrl":"https://inference-docs.cerebras.ai/introduction/rate-limits","verifiedAt":"2026-08-14","workload":{"profileSlug":"classification-at-volume","callsPerMinute":116,"tokensPerMinute":60320,"summary":"This provider publishes no numeric cap for this workload; check the account console before launch."}},"apiKey":null},{"slug":"qwen","name":"Qwen","legalName":"Alibaba Cloud Computing Ltd.","aka":["Alibaba Cloud","Model Studio","DashScope"],"kind":"lab","hq":"Hangzhou, China","foundedYear":null,"currentModelCount":3,"legacyModelCount":0,"priceRangePerM":[1.1,2.8000000000000003],"maxContext":256000,"medianTokensPerSecond":49,"openAiCompatible":"partial","apiBaseUrl":"https://dashscope-intl.aliyuncs.com/compatible-mode/v1","authModel":"Bearer API key","promptCaching":null,"batchDiscountPct":null,"freeTier":"Free quota for new Alibaba Cloud accounts","hasFreeTier":true,"freeTierUrl":"https://www.alibabacloud.com/help/en/model-studio/getting-started/free-quota","freeTierLimits":"Quota is limited to eligible new accounts and varies by model, region, and account.","freeTierExpiry":null,"rateLimitModel":"Per-model QPS/QPM caps by account tier","dataResidency":"Singapore/international region via DashScope Intl; mainland China served from a separate region","trainsOnApiData":null,"slaPublished":false,"docsUrl":"https://www.alibabacloud.com/help/en/model-studio/models","pricingUrl":"https://www.alibabacloud.com/help/en/model-studio/models","statusUrl":null,"sourceUrl":"https://www.alibabacloud.com/help/en/model-studio/models","verifiedAt":"2026-08-14","rateLimits":{"providerKey":"Qwen","published":true,"scheme":"account-plan","tiers":[{"tierName":"Free quota","qualification":"New account quota","sourceUrl":"https://www.alibabacloud.com/help/en/model-studio/rate-limit","limits":[{"modelClass":"documented default/model family","rpm":null,"tpm":null,"rpd":null,"concurrentRequests":null}]},{"tierName":"Paid","qualification":"Model Studio account quota","sourceUrl":"https://www.alibabacloud.com/help/en/model-studio/rate-limit","limits":[{"modelClass":"documented default/model family","rpm":null,"tpm":null,"rpd":null,"concurrentRequests":null}]}],"headers":[{"name":"retry-after","meaning":"Seconds to wait before retrying, when supplied with a 429"},{"name":"rate-limit response headers","meaning":"Provider-specific remaining and reset counters when documented"}],"exceeded":{"statusCode":429,"retryAfterHeader":null,"guidance":"Check the region, model, and account quota in Model Studio."},"increaseUrl":"https://bailian.console.aliyun.com","sourceUrl":"https://www.alibabacloud.com/help/en/model-studio/rate-limit","verifiedAt":"2026-08-14","workload":{"profileSlug":"classification-at-volume","callsPerMinute":116,"tokensPerMinute":60320,"summary":"This provider publishes no numeric cap for this workload; check the account console before launch."}},"apiKey":null},{"slug":"amazon","name":"Amazon","legalName":"Amazon Web Services, Inc.","aka":["AWS Bedrock","Nova"],"kind":"lab","hq":"Seattle, USA","foundedYear":2006,"currentModelCount":3,"legacyModelCount":0,"priceRangePerM":[0.06124999999999999,1.4000000000000001],"maxContext":300000,"medianTokensPerSecond":108,"openAiCompatible":false,"apiBaseUrl":"bedrock-runtime.{region}.amazonaws.com (Converse API)","authModel":"AWS SigV4 (IAM credentials)","promptCaching":null,"batchDiscountPct":50,"freeTier":null,"hasFreeTier":false,"freeTierUrl":"https://aws.amazon.com/free/ai/","freeTierLimits":"No provider-wide Nova API free tier is published; AWS account promotions, if any, are separate.","freeTierExpiry":null,"rateLimitModel":"Per-account, per-region AWS service quotas","dataResidency":"Selectable AWS region","trainsOnApiData":false,"slaPublished":true,"docsUrl":"https://docs.aws.amazon.com/nova/latest/userguide/what-is-nova.html","pricingUrl":"https://aws.amazon.com/bedrock/pricing/","statusUrl":"https://health.aws.amazon.com/health/status","sourceUrl":"https://docs.aws.amazon.com/nova/latest/userguide/what-is-nova.html","verifiedAt":"2026-08-14","rateLimits":{"providerKey":"Amazon","published":true,"scheme":"account-plan","tiers":[{"tierName":"AWS default quota","qualification":"AWS account and region","sourceUrl":"https://docs.aws.amazon.com/bedrock/latest/userguide/quotas.html","limits":[{"modelClass":"documented default/model family","rpm":null,"tpm":null,"rpd":null,"concurrentRequests":null}]},{"tierName":"Requested quota","qualification":"Approved Service Quotas increase","sourceUrl":"https://docs.aws.amazon.com/bedrock/latest/userguide/quotas.html","limits":[{"modelClass":"documented default/model family","rpm":null,"tpm":null,"rpd":null,"concurrentRequests":null}]}],"headers":[{"name":"retry-after","meaning":"Seconds to wait before retrying, when supplied with a 429"},{"name":"rate-limit response headers","meaning":"Provider-specific remaining and reset counters when documented"}],"exceeded":{"statusCode":429,"retryAfterHeader":null,"guidance":"Use Service Quotas for the selected Bedrock model and region."},"increaseUrl":"https://console.aws.amazon.com/servicequotas","sourceUrl":"https://docs.aws.amazon.com/bedrock/latest/userguide/quotas.html","verifiedAt":"2026-08-14","workload":{"profileSlug":"classification-at-volume","callsPerMinute":116,"tokensPerMinute":60320,"summary":"This provider publishes no numeric cap for this workload; check the account console before launch."}},"apiKey":null},{"slug":"zai","name":"Z.ai","legalName":"Zhipu AI (Z.ai)","aka":["Zhipu AI","GLM"],"kind":"lab","hq":"Beijing, China","foundedYear":2019,"currentModelCount":1,"legacyModelCount":1,"priceRangePerM":[2.15,2.15],"maxContext":1000000,"medianTokensPerSecond":null,"openAiCompatible":true,"apiBaseUrl":"https://api.z.ai/api/paas/v4","authModel":"Bearer API key","promptCaching":null,"batchDiscountPct":null,"freeTier":"Free trial credits for new accounts","hasFreeTier":true,"freeTierUrl":"https://docs.z.ai/guides/overview/billing","freeTierLimits":"Trial credits are limited to eligible new accounts; amount and expiry vary by account.","freeTierExpiry":null,"rateLimitModel":"Per-model concurrency caps by account tier","dataResidency":null,"trainsOnApiData":null,"slaPublished":false,"docsUrl":"https://docs.z.ai","pricingUrl":"https://docs.z.ai","statusUrl":null,"sourceUrl":"https://docs.z.ai","verifiedAt":"2026-08-14","rateLimits":{"providerKey":"Z.ai","published":true,"scheme":"per-key","tiers":[{"tierName":"Default","qualification":"Account quota shown in the Z.ai console","sourceUrl":"https://docs.z.ai/api-reference/limits","limits":[{"modelClass":"documented default/model family","rpm":null,"tpm":null,"rpd":null,"concurrentRequests":null}]}],"headers":[{"name":"retry-after","meaning":"Seconds to wait before retrying, when supplied with a 429"},{"name":"rate-limit response headers","meaning":"Provider-specific remaining and reset counters when documented"}],"exceeded":{"statusCode":429,"retryAfterHeader":null,"guidance":"Back off and check the model-specific account quota."},"increaseUrl":"https://bigmodel.cn/console","sourceUrl":"https://docs.z.ai/api-reference/limits","verifiedAt":"2026-08-14","workload":{"profileSlug":"classification-at-volume","callsPerMinute":116,"tokensPerMinute":60320,"summary":"This provider publishes no numeric cap for this workload; check the account console before launch."}},"apiKey":null},{"slug":"meta","name":"Meta","legalName":"Meta Platforms, Inc.","aka":["Muse","Meta AI"],"kind":"lab","hq":"Menlo Park, USA","foundedYear":2004,"currentModelCount":2,"legacyModelCount":0,"priceRangePerM":[0.125,2],"maxContext":1048576,"medianTokensPerSecond":null,"openAiCompatible":true,"apiBaseUrl":"https://api.meta.ai/v1","authModel":"Bearer API key","promptCaching":null,"batchDiscountPct":null,"freeTier":null,"hasFreeTier":false,"freeTierUrl":"https://ai.meta.com/pricing","freeTierLimits":"No published free tier for the Model API; the Contributor tier is a steep discount, not a free tier.","freeTierExpiry":null,"rateLimitModel":"Per-account token-based rate limits; the Contributor tier is additionally rate-limited by tokens","dataResidency":null,"trainsOnApiData":null,"slaPublished":false,"docsUrl":"https://ai.meta.com/pricing","pricingUrl":"https://ai.meta.com/pricing","statusUrl":null,"sourceUrl":"https://ai.meta.com/pricing","verifiedAt":"2026-08-14","rateLimits":null,"apiKey":null}]}