Free High-volume cheap LLM inference for AI agents

Run it free (6)

• Groq Free Plan chat models · free_inference · free

  Organization-level Free Plan rate limits for the chat and classifier model ids in the page payload key freeRows. Not the Developer plan table.

  Limits: scope: organization · models: [object Object]

  Source · asOf 2026-10-24 · Rate-limits page fetched twice 2026-10-24 about 10 s apart (identical HTML; the page shows no last-updated date). Parsed from the HTML payload key freeRows (the 'Free Plan Limits' tab), which is separate from devRows (Developer plan, not stored). K suffixes expanded (1K=1000, 2K=2000, 14.4K=14400). The page says: 'The following is a high level summary and there may be exceptions to these limits.' and 'You can view the current, exact rate limits for your organization on the limits page in your account settings.' 'Rate limits apply at the organization level, not individual users.' 'Cached tokens do not count towards your rate limits.' The page also says 'some organizations are also subject to separate per-minute limits on input tokens (ITPM) and output tokens (OTPM)'; no ITPM/OTPM values are published, so none are stored. Change on 2026-10-24: freeRows now reads 'openai/gpt-oss-safeguard-20b 3 1K 2K 200K' (RPM 3, TPM 2K); before 0.12.98 this row stored RPM 30 and TPM 8000 for it. The other five model ids and their values are unchanged. No Llama chat model is in freeRows.

• Cloudflare Workers AI daily neurons · free_inference · free

  10,000 Neurons per day at no charge on Workers Free and Workers Paid. Workers Free cannot buy more. The pool is shared across models.

  Limits: neuronsPerDay: 10000 · resets: 00:00 UTC · sharedAcrossModels: true

  Source · asOf 2026-10-25 · Fetched twice 2026-10-25 about 10 s apart without logging in (HTTP 200, no redirect, identical HTML; the page shows 'Last updated Oct 20, 2026'). 'Our free allocation allows anyone to use a total of 10,000 Neurons per day at no charge.' 'To use more than 10,000 Neurons per day, you need to sign up for the Workers Paid plan.' Free allocation table: 'Workers Free 10,000 Neurons per day N/A - Upgrade to Workers Paid' and 'Workers Paid 10,000 Neurons per day $0.011 / 1,000 Neurons'. 'All limits reset daily at 00:00 UTC.' Paid usage above the allocation is a price row, not a free cap. 'Some models require a paid billing method.' The page lists @cf/moonshotai/kimi-k2.6, @cf/moonshotai/kimi-k2.7-code, @cf/zai-org/glm-5.2, @cf/zai-org/glm-5.3, @cf/zai-org/glm-5.3-flash, @cf/deepseek-ai/deepseek-v4-flash-0731, @cf/deepseek-ai/deepseek-v4.1-flash-1017 and @cf/deepseek-ai/deepseek-v4-pro-0813 ('You can access these models with either the Workers Paid plan or prepaid AI Gateway credits'); these are not free. Per-model token prices are not a $0 SKU.

• Gemini API free tier, standard token price · free_inference · free_tier_unspecified

  Standard input and output marked Free of charge for models whose free-tier cell says that. Includes gemini-3.8-flash, gemini-3.6-flash, gemini-3.5-flash-lite, gemini-3.1-flash-lite, gemini-3-flash-preview, gemini-2.5-pro, gemini-2.5-flash, and gemini-2.5-flash-lite.

  Limits: none stored.

  Source · asOf 2026-10-26 · Pricing page fetched twice 2026-10-24 (identical text; page footer 'Last updated 2026-10-22 UTC'): the Free tier card lists 'Limited access to certain models' and 'Free input & output tokens'; each listed model's Standard Free Tier input and output cells read 'Free of charge'. gemini-3.7-flash and gemini-3.5-flash, listed in this row before 0.12.96, no longer appear on the page, so they were removed rather than kept unsourced. 'Gemini 4 Argon is not available on the Free tier.' and gemini-3.1-pro-preview standard free-tier cells read 'Not available'. Batch free-tier cells read 'Not available' for several of these models (gemini-3.8-flash, gemini-3-flash-preview, gemini-2.5-pro, gemini-2.5-flash). Image-generation free-tier cells fetched were Not available. The Free tier card says 'Content used to improve our products'. https://ai.google.dev/gemini-api/docs/rate-limits (fetched twice 2026-10-24, identical text, 'Last updated 2026-10-15 UTC') publishes no free-tier RPM, TPM or RPD and says 'View your active rate limits in AI Studio', so limits stay null. Not a $0 price-sort row. The page describes gemini-3.8-flash as 'engineered for long-horizon software engineering' and gemini-2.5-pro as 'A Pro model which excels at coding and complex reasoning tasks.' Re-checked 2026-10-26 (v0.12.131): stored quotes still match. https://ai.google.dev/gemini-api/docs/pricing and https://ai.google.dev/gemini-api/docs/rate-limits were each fetched twice (~10 s apart, plain curl, no login, following redirects): HTTP 200, no redirect, HTML differs only inside inline scripts, tag-stripped text identical; both footers now read 'Last updated 2026-10-26 UTC'. Every quote above string-matched the whitespace-normalized text except the older footer stamps, which are fetch-date stamps, not row values; the eight listed models' Standard free-tier input cells still read 'Free of charge', and gemini-3.7-flash and gemini-3.5-flash are still absent; values unchanged (Depot data decision to re-date only, approvalRef 'Ethan delegation 2026-10-21 19:41 ET t55u', decidedBy Agent Depo).

• OpenRouter :free variants and openrouter/free · free_inference · free

  Model ids ending in :free, and the openrouter/free router, are priced at zero on OpenRouter. Which models have a free entry changes.

  Limits: appliesTo: model variants with an ID ending in :free · requestsPerMinute: 20 · requestsPerDayCreditsPurchasedLessThan10: 50 · requestsPerDayCreditsPurchasedAtLeast10: 1000 · dailyWindow: UTC day

  Source · asOf 2026-10-25 · Fetched twice 2026-10-25 about 10 s apart without logging in: https://openrouter.ai/docs/api/reference/limits answers HTTP 308 to https://openrouter.ai/docs/api_reference/limits (HTTP 200; same tag-stripped text both times; no last-modified header; page metadata dateModified 2026-10-10T16:11:54Z). The HTML table cells are empty until scripts run (the page defines the values as constants), so the numbers are taken from the page's markdown view https://openrouter.ai/docs/api_reference/limits.md (HTTP 200, fetched twice, identical): 'Free usage limits: If you're using a free model variant (with an ID ending in `:free`), the following limits apply:' table 'Credits purchased (all time) | Requests per minute | Requests per day', 'Less than 10 | 20 | 50', 'At least 10 | 20 | 1000'. 'Free-model requests allowed per UTC day (see the free usage limits below)'. 'On free variants, purchase at least 10 credits to raise your daily limit, or switch to the paid variant of the model, which has no platform-level request cap.' 'If your account has a negative credit balance, you may see errors, including for free models.' (the HTML renders the status code as a component: 402 Payment Required). The one-credit-below-threshold grace is shown only as the unrendered placeholder '{FREE_MODEL_CREDITS_THRESHOLD - 1}', so it is not stored. The page does not say whether openrouter/free draws on the same caps. Third-party tables were not copied. Do not copy OpenRouter prices or limits onto other Depot providers.

• Mistral Studio free mode · free_inference · free_tier_unspecified

  Free mode lets you create API keys and use included monthly usage within the limits shown on the Limits page (Admin Panel > API > Limits). The docs publish no numeric free allowance; Pay-as-you-go extends usage beyond the included monthly usage from prepaid credits.

  Limits: none stored.

  Source · asOf 2026-10-24 · The old sourceUrl https://docs.mistral.ai/admin/user-management-finops/tier now returns HTTP 308 to https://docs.mistral.ai/admin/billing-usage/usage-limits (page title 'Usage and limits'), which carries the same Free mode statement; sourceUrl updated to the final URL. Page fetched twice 2026-10-24 about 10 s apart (HTTP 200, identical HTML; the page shows no last-updated date); its markdown view (usage-limits.md) was also fetched twice (identical). Quotes below match the HTML text (link markup removed). 'Your Mistral plan defines the included monthly usage and limits available to your Organization.' 'Free mode lets you create API keys and use included monthly usage within the limits shown on the Limits page.' 'Pay-as-you-go lets you extend usage beyond included monthly usage, and this extra usage draws from your prepaid credits. It isn't a separate plan for the API.' 'API rate limits define how much traffic your Organization can send.' 'If the Organization reaches its monthly spending limit, API access can be suspended until the next month begins or an admin increases the limit.' limits stays null: the page publishes no numeric free cap, rate limit or included-usage amount (it only says completion limits are listed per model as tokens per minute and requests per second on the account Limits page). The Ambassador credits and 'free for a limited amount of time' wording noted on 2026-10-03 no longer appears on this page.

• Cerebras free trial credits · free_inference · credits_not_free_forever

  $5 in free credits after adding a verified payment method; they expire 30 days after they're granted and can be used across all public models (Shared Inference). When they run out or expire, API and Playground access stop until you purchase credits.

  Limits: creditsUsd: 5 · expiresDaysAfterGrant: 30 · requiresVerifiedPaymentMethod: true · models: [object Object]

  Source · asOf 2026-10-24 · Rate-limits page fetched twice 2026-10-24 about 10 s apart (identical HTML; the page shows no last-updated date); the page's markdown view (rate-limits.md) was also fetched twice (identical) and its Free Trial table has the same values. Quotes below match the HTML text (curly apostrophes shown straight). Free Trial table (HTML text): 'gpt-oss-120b 5 30K 90K 1M 1M' and 'qwen-3.8-27b 1 5 30K 90K 1M 1M' (the second '1' is the image-limit footnote marker; columns RPM, Uncached TPM, Total TPM, TPH, TPD); K/M suffixes expanded (30K=30000, 90K=90000, 1M=1000000). The table lists exactly these two models. qwen-3.8-27b footnote: 'Image limits: 2 per request, 10 MiB total request payload'. The page says: 'New accounts receive $5 in free credits after adding a verified payment method. These credits expire 30 days after they're granted and can be used across all public models.' 'If you skip adding a payment method at sign-up, Playground and API access remain inactive until you do.' 'Is there a permanently free tier? No.' 'Cerebras doesn't currently offer a no-cost tier that renews automatically or a per-model always-free allowance.' 'This provides an overview of general limits, though specific cases may vary.' 'Rate limits apply at the organization level, not the user level, and vary based on the model.' Developer (Pay as You Go) values are not stored on this free row (a paid tier); since v0.12.129 they are in the plan-limits table (data/limits.json, cerebras / Developer (Pay as You Go)). All stored values re-confirmed unchanged on 2026-10-24. Not a Depot price-sort input.

Reference (docs, public datasets and benchmarks) (0)

None.