Discover free LLM API models across providers with real speed and latency benchmarks.Free models 2773Providers 157Free offerings 8806
| Model | Providers | Speed | Latency | Tests |
|---|---|---|---|---|
OpenAIFree ToolsFilesVision128KOpenAI GPT-4o is a multimodal flagship model with fast text, vision, and audio understanding, optimized for real-time chat, coding assistants, and production API workloads. | +18 moreShow fewer | N/A | N/A | 0 |
MistralaiFree This is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement [here](https://mistral.ai/news/mistral-large-2407/).... |
LMSpeed tracks 2773 LLM models available for free across 157 API providers. Free tiers vary by provider — some offer limited daily requests, others provide free credits for new users. All speed data is from real API tests.
Find a free model, compare its providers, then open the provider or model detail page before you start testing.
Use search, model-family filters, and capability tags to narrow the directory to the free models you actually want to try.
Check provider count, benchmark volume, throughput, and first-token latency so you are not choosing from price alone.
Review the provider page for availability, health checks, pricing notes, and any free-tier limits before building on it.
Common questions about free model tiers and how to use this directory.
| N/A |
| N/A |
| 0 |
Tools文件Multimodal200KAnthropic Claude 3.5 Haiku offers quick responses and efficient throughput for high-volume chat, routing, and lightweight automation. | 42.11 t/s | 2.46 s | 5 |
Nous Research Hermes 3 is a generalist instruct model fine-tuned on Meta Llama 3.1, with strong reasoning, roleplay, multi-turn chat, tool calling, and structured JSON output. | N/A | N/A | 0 |
Mistral Nemo is a 12B open model co-developed by Mistral AI and NVIDIA, optimized for multilingual chat and function calling. | N/A | N/A | 0 |
ToolsFilesVision128KOpenAI GPT-4o Mini is a compact language model in the GPT-4 series, optimized for low-latency responses and efficient inference. | 129.73 t/s | 1.13 s | 15 |
Mistral's official instruct fine-tuned version of [Mixtral 8x22B](/models/mistralai/mixtral-8x22b). It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size. Its strengths include: - strong math, coding,... | N/A | N/A | 0 |
Microsoft WizardLM-2 8x22B is a 141B-parameter MoE instruct model built on Mixtral 8x22B, tuned for complex chat, multilingual reasoning, and agent-style tasks. | N/A | N/A | 0 |
ToolsFilesVision128KOpenAI GPT-4 Turbo delivers GPT-4-level reasoning with a 128K context window, vision support, and lower latency for production chat, analysis, and agent backends. | N/A | N/A | 0 |
ChatVisionAnthropic Claude 3 Haiku is optimized for speed and scale in customer support, routing, and low-latency chat applications. | N/A | N/A | 0 |
16.4K4.1KChatOpenAI GPT-3.5 Turbo is a cost-efficient chat model for high-volume assistants, summarization, and lightweight coding workflows where GPT-4-class quality is not required. | N/A | N/A | 0 |
4.1KChatOpenAI GPT-3.5 Turbo Instruct is a completion-style model tuned for single-turn instructions, legacy integrations, and text generation tasks that predate chat-completions APIs. | N/A | N/A | 0 |
Tools32.8KFiles8.2KOpenAI GPT-4 is a flagship large language model with strong reasoning, instruction following, and tool use, widely used for complex analysis, coding, and production chat applications. | N/A | N/A | 0 |
A model–provider pair whose current input and output prices are both $0 per token. Some providers offer permanent free tiers, others only give one-time credits to new accounts. We mark an offering as free only while its public pricing is zero, and re-check pricing pages regularly.
Most have rate limits — requests per minute, daily caps, or context-length limits — and many require account signup with a verified phone or payment method. Some are time-limited promotions. Always read the provider's terms and quotas before depending on a free endpoint.
Some entries are community-run relays ("公益站") that bundle paid upstream keys and redistribute access for free at the operator's expense. They often advertise larger quotas and a broader model list than official free tiers, but reliability is much lower: operators can pull the plug or disappear overnight, pricing and quotas can change without notice, and many sites are invite-only — requiring a GitHub invite, a forum referral, or a closed community to register. Some keep signups disabled indefinitely. Treat them as best-effort backup channels; keep anything important on official paid endpoints.
Speed varies by model and provider. Sort the table by Most tested for the most reliable benchmarks, or pick a model family from the chips above to drill in. Each row shows median tokens per second and first-token latency from real API tests.
We send identical prompts to each provider through a five-round stress test, count output tokens with tiktoken, and measure both throughput (tokens per second) and time to first token. Numbers are aggregated as medians to resist outliers and refresh on a regular cadence.
For prototypes, side projects, and low-traffic tools, yes. Production traffic will usually hit a rate limit quickly. Treat the free tier as an evaluation channel: validate the model and provider, then move to a paid endpoint with the same model when you scale.
Either no provider currently offers it for free, the free promotion ended, or it has not been benchmarked yet. Open the model's main page to compare paid options, or let us know about a missing free provider via the feedback link in the footer.
