> ## Documentation Index
> Fetch the complete documentation index at: https://zerogpu-claude-friendly-johnson-fww5io.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.
# Text Generation
> Edge generative models for conversation and reasoning.
Text generation models produce new text from an input prompt. ZeroGPU offers open-weight heavyweights — DeepSeek's deepseek-v4-flash, OpenAI's gpt-oss-120b, Alibaba's qwen3-30b-a3b-fp8, and Z.ai's glm-5.2 — for reasoning and tool use, plus conversational and reasoning models from Liquid AI and Meta's llama-3.1-8b-instruct-fast for high-volume summarization. Each request is shown for both the [Responses API](/api-reference/responses) and the OpenAI-compatible [Chat Completions API](/api-reference/chat-completions) — except `qwen3-30b-a3b-fp8`, `glm-5.2`, and `deepseek-v4-flash`, which are Chat Completions only.
| Model | Input /1M | Output /1M | Cached input /1M | Max tokens |
| ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | --------: | ---------: | ---------------: | ---------: |
| 
gpt-oss-120b | \$0.15 | \$0.60 | — | 131,072 |
| 
qwen3-30b-a3b-fp8 | \$0.05 | \$0.30 | — | 32,768 |
| 
glm-5.2 | \$1.10 | \$3.50 | \$0.40 | 262,144 |
| 
deepseek-v4-flash | \$0.16 | \$0.38 | \$0.006 | 1,048,576 |
| 
LFM2.5-1.2B-Instruct | \$0.02 | \$0.05 | — | 32,768 |
| 
LFM2.5-1.2B-Thinking | \$0.02 | \$0.05 | — | 32,768 |
| 
llama-3.1-8b-instruct-fast | \$0.02 | \$0.05 | — | 131,072 |
## gpt-oss-120b
> OpenAI's gpt-oss-120b is an open-weight Mixture-of-Experts model with 117B total parameters (5.1B active per token), served on ZeroGPU for general text generation. It reasons through a problem before answering and returns that reasoning trace alongside the final answer, and it supports function calling, batch tasks, and a 131,072-token context window. When a task needs frontier-level reasoning or tool use beyond what the smaller edge models cover, this is the model.
**References:** [Model docs](https://huggingface.co/openai/gpt-oss-120b) • [Terms](https://zerogpu.ai/terms) • [Privacy](https://zerogpu.ai/privacy-policy)
```bash Responses API theme={null}
curl https://api.zerogpu.ai/v1/responses \
-H "content-type: application/json" \
-H "x-api-key: YOUR_API_KEY" \
-H "x-project-id: YOUR_PROJECT_ID" \
-d '{
"input": "Name my WiFi network something that will make my neighbors laugh. Give me your top 3 with a one-line reason each.",
"model": "gpt-oss-120b",
"max_tokens": 800,
"instructions": "You are a witty naming consultant. Be brief."
}'
```
```bash Chat Completions theme={null}
curl https://api.zerogpu.ai/v1/chat/completions \
-H "content-type: application/json" \
-H "x-api-key: YOUR_API_KEY" \
-H "x-project-id: YOUR_PROJECT_ID" \
-d '{
"model": "gpt-oss-120b",
"messages": [
{
"role": "system",
"content": "You are a witty naming consultant. Be brief."
},
{
"role": "user",
"content": "Name my WiFi network something that will make my neighbors laugh. Give me your top 3 with a one-line reason each."
}
],
"max_tokens": 800
}'
```
The model reasons before it answers and returns the trace alongside the final text — a `reasoning` output item in Responses, and a `reasoning` field on the message in Chat Completions.
```json Responses API theme={null}
{
"id": "id-1784318124857",
"object": "response",
"created_at": 1784318124,
"model": "gpt-oss-120b",
"status": "completed",
"instructions": "You are a witty naming consultant. Be brief.",
"output": [
{
"id": "rs_8d4dc6f3f33d0d28",
"type": "reasoning",
"content": [
{
"type": "reasoning_text",
"text": "We need to respond with a top 3 WiFi names that will make neighbors laugh, each with a one-line reason. Be witty. Keep brief."
}
]
},
{
"id": "msg_9c3dfbf63445d80a",
"type": "message",
"role": "assistant",
"status": "completed",
"content": [
{
"type": "output_text",
"text": "**1. “FBI Surveillance Van #42”** – Neighbors will double-check the street before they even think about streaming.\n\n**2. “Drop It Like It’s Hotspot”** – A pun that’s so cheesy it’ll have the whole block groaning and giggling.\n\n**3. “Tell My Wi-Fi I Love You”** – Because nothing says “I’m caring” like a reminder that even your router needs affection."
}
]
}
],
"usage": {
"input_tokens": 0,
"output_tokens": 0,
"total_tokens": 0
}
}
```
```json Chat Completions theme={null}
{
"id": "id-1784318142640",
"object": "chat.completion",
"created": 1784318142,
"model": "gpt-oss-120b",
"choices": [
{
"index": 0,
"finish_reason": "stop",
"message": {
"role": "assistant",
"content": "**1. “Drop It Like It’s Hotspot”** – A cheeky nod to the song that’ll make anyone pause and grin while they log in.\n\n**2. “FBI Surveillance Van #42”** – The classic prank that’ll have neighbors double-checking their curtains.\n\n**3. “Tell My Wi-Fi I’m Sorry”** – Because we all know the neighbor who borrows bandwidth—now they’ll feel the love (and the guilt).",
"reasoning": "We need to give top 3 witty WiFi network names that will make neighbors laugh, with one-line reason each. Be brief.",
"tool_calls": []
}
}
],
"usage": {
"prompt_tokens": 107,
"completion_tokens": 160,
"total_tokens": 267
}
}
```
## qwen3-30b-a3b-fp8
This model supports the Chat Completions API only — the Responses endpoint
(`/v1/responses`) is not available for this model.
> Alibaba's Qwen3-30B-A3B is an open-weight Mixture-of-Experts model with 30.5B total parameters (3.3B active per token), served on ZeroGPU as an FP8 build for efficient inference. It thinks through a problem before answering and returns that reasoning alongside the final text, and it supports function calling, streaming, batch tasks, and 100+ languages with a 32,768-token context window. When you want frontier-style reasoning and tool use in a lighter, multilingual package, this is the model.
**References:** [Model docs](https://huggingface.co/Qwen/Qwen3-30B-A3B-FP8) • [Terms](https://zerogpu.ai/terms) • [Privacy](https://zerogpu.ai/privacy-policy)
```bash Chat Completions theme={null}
curl https://api.zerogpu.ai/v1/chat/completions \
-H "content-type: application/json" \
-H "x-api-key: YOUR_API_KEY" \
-d '{
"model": "qwen3-30b-a3b-fp8",
"messages": [
{
"role": "system",
"content": "You are a pragmatic senior engineer. Be brief."
},
{
"role": "user",
"content": "My API is getting rate-limited by a third party. Give me 3 battle-tested strategies to handle it, one line each."
}
],
"max_tokens": 800
}'
```
The model reasons before it answers and returns the trace alongside the final text as a `reasoning` field on the message.
```json Response theme={null}
{
"id": "id-1784324156320",
"object": "chat.completion",
"created": 1784324156,
"model": "qwen3-30b-a3b-fp8",
"choices": [
{
"index": 0,
"finish_reason": "stop",
"message": {
"role": "assistant",
"content": "**1. Exponential backoff with jitter** – Retry on 429s with doubling delays plus randomness so your retries don't stampede in sync.\n\n**2. Client-side token bucket** – Throttle your own outbound rate just below the provider's limit so you never hit the wall in the first place.\n\n**3. Cache and coalesce** – Cache hot responses and merge duplicate in-flight requests so repeat calls never reach the third party at all.",
"reasoning": "The user's API is being rate-limited by a third party and wants 3 battle-tested strategies, one line each. The classic answers: exponential backoff with jitter, client-side throttling below the limit, and caching plus request coalescing. Keep each to one line.",
"tool_calls": []
}
}
],
"usage": {
"prompt_tokens": 52,
"completion_tokens": 143,
"total_tokens": 195
}
}
```
## glm-5.2
This model supports the Chat Completions API only — the Responses endpoint
(`/v1/responses`) is not available for this model.
> Z.ai's GLM-5.2 is an open-weight Mixture-of-Experts flagship built for long-horizon tasks, with 753B total parameters activating 8 of 256 experts per token, served on ZeroGPU for general text generation. It sustains a solid 262,144-token (256K) context, reasons through a problem with flexible thinking effort before answering, and supports function calling and batch tasks. MIT-licensed with no usage restrictions. When the work spans entire repos, day-long agent sessions, or long documents, this is the model.
**References:** [Model docs](https://huggingface.co/zai-org/GLM-5.2) • [Terms](https://zerogpu.ai/terms) • [Privacy](https://zerogpu.ai/privacy-policy)
```bash Chat Completions theme={null}
curl https://api.zerogpu.ai/v1/chat/completions \
-H "content-type: application/json" \
-H "x-api-key: YOUR_API_KEY" \
-d '{
"model": "glm-5.2",
"messages": [
{
"role": "system",
"content": "You are a precise code-review assistant. Be brief."
},
{
"role": "user",
"content": "Review this function name: getUserDataAndSendEmailAndLog(). What does it tell you about the function, and how would you refactor it? 3 bullets max."
}
],
"max_tokens": 800
}'
```
The model reasons before it answers and returns the trace alongside the final text as a `reasoning` field on the message.
```json Response theme={null}
{
"id": "id-1784840133815",
"object": "chat.completion",
"created": 1784840133,
"model": "glm-5.2",
"choices": [
{
"index": 0,
"finish_reason": "stop",
"message": {
"role": "assistant",
"content": "**1. The name confesses the crime** – \"And\" in a function name means it violates single responsibility: fetching, emailing, and logging are three separate concerns.\n\n**2. Split it** – Extract `getUserData()`, `sendEmail()`, and `logActivity()`, each independently testable and reusable.\n\n**3. Orchestrate at the edge** – If the sequence matters, compose them in a thin workflow function named for the *why* (e.g. `onUserSignup()`), not the *how*.",
"reasoning": "The name reveals the function does three unrelated things — fetch data, send email, log — a single-responsibility violation. Recommend splitting into three functions plus a thin orchestrator. Keep to 3 bullets.",
"tool_calls": []
}
}
],
"usage": {
"prompt_tokens": 58,
"completion_tokens": 151,
"total_tokens": 209
}
}
```
## deepseek-v4-flash
This model supports the Chat Completions API only — the Responses endpoint
(`/v1/responses`) is not available for this model.
> DeepSeek's DeepSeek-V4-Flash is an open-weight Mixture-of-Experts model built for efficient reasoning, coding, and agentic workflows, with 284B total parameters activating only 13B per token, served on ZeroGPU for general text generation. It sustains a 1,048,576-token (1M) context well suited for analyzing large codebases, long documents, extensive conversations, and complex research tasks, and supports fast non-thinking responses as well as higher-effort reasoning modes for planning, problem-solving, and multi-step automation. MIT-licensed with no usage restrictions.
**References:** [Model docs](https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash) • [Terms](https://zerogpu.ai/terms) • [Privacy](https://zerogpu.ai/privacy-policy)
```bash Chat Completions theme={null}
curl https://api.zerogpu.ai/v1/chat/completions \
-H "content-type: application/json" \
-H "x-api-key: YOUR_API_KEY" \
-d '{
"model": "deepseek-v4-flash",
"messages": [
{
"role": "system",
"content": "You are a pragmatic staff engineer. Be concise."
},
{
"role": "user",
"content": "Plan the migration of a nightly cron-based ETL job to an event-driven pipeline. 4 steps max."
}
],
"max_tokens": 800
}'
```
The model reasons before it answers and returns the trace alongside the final text as a `reasoning` field on the message.
```json Response theme={null}
{
"id": "id-1785523944762",
"object": "chat.completion",
"created": 1785523944,
"model": "deepseek-v4-flash",
"choices": [
{
"index": 0,
"finish_reason": "stop",
"message": {
"role": "assistant",
"content": "**1. Inventory the job** – Document inputs, outputs, schedule, and every downstream consumer of the cron ETL so nothing breaks silently.\n\n**2. Define the events** – Pick the real trigger (file landing, DB change, message) and publish it to a queue or event bus with a versioned schema.\n\n**3. Run in parallel** – Build the event-driven consumer alongside cron, write to a shadow table, and diff outputs until they match.\n\n**4. Cut over with a rollback path** – Point consumers at the new output, keep cron paused (not deleted) for one cycle, then decommission.",
"reasoning": "Cron ETL to event-driven: inventory the current job first, define the trigger events, run the new pipeline in parallel against a shadow output, then cut over with a rollback path. Four steps, each actionable.",
"tool_calls": []
}
}
],
"usage": {
"prompt_tokens": 52,
"completion_tokens": 158,
"total_tokens": 210
}
}
```
## LFM2.5-1.2B-Instruct
> Liquid AI's LFM2.5-1.2B-Instruct is a hybrid architecture model purpose-built for on-device deployment, trained on 28 trillion tokens with multi-stage reinforcement learning. It delivers best-in-class instruction following and native tool-calling at the 1B scale — something very few models this size can do reliably. Its hybrid design gives it significantly faster inference with lower memory usage compared to transformer-only models of the same size. If you need a conversational model that can actually run on real devices without a GPU, this is it. Supports 8 languages including English, Chinese, Japanese, and Spanish.
**References:** [Model docs](https://docs.liquid.ai/deployment/on-device/android/ai-agent-usage-guide#text-models) • [Terms](https://www.liquid.ai/terms-conditions) • [Privacy](https://www.liquid.ai/lfm-license)
```bash Responses API theme={null}
curl https://api.zerogpu.ai/v1/responses \
-H "content-type: application/json" \
-H "x-api-key: YOUR_API_KEY" \
-H "x-project-id: YOUR_PROJECT_ID" \
-d '{
"input": "I just completed a 5K run in 28 minutes. Give me a short motivational follow-up message.",
"model": "LFM2.5-1.2B-Instruct",
"instructions": "You are a friendly in-app assistant for a fitness app."
}'
```
```bash Chat Completions theme={null}
curl https://api.zerogpu.ai/v1/chat/completions \
-H "content-type: application/json" \
-H "x-api-key: YOUR_API_KEY" \
-H "x-project-id: YOUR_PROJECT_ID" \
-d '{
"model": "LFM2.5-1.2B-Instruct",
"messages": [
{
"role": "system",
"content": "You are a friendly in-app assistant for a fitness app."
},
{
"role": "user",
"content": "I just completed a 5K run in 28 minutes. Give me a short motivational follow-up message."
}
]
}'
```
```text Response theme={null}
That's an amazing accomplishment! Keep up the great work, each step brings you closer to your goals. You're stronger than you think!
Would you like tips to help you keep improving?
```
## LFM2.5-1.2B-Thinking
> Liquid AI's LFM2.5-1.2B-Thinking is a compact reasoning model that works through a problem step by step before it answers. Built by Liquid AI, it generates an explicit chain-of-thought trace so for multi-step math, planning, data extraction, and agentic tool-calling, you get verifiable intermediate reasoning, not just a final guess. At 1.2B parameters it fits under a gigabyte and runs fast on CPU at the edge, rivaling models several times its size on reasoning benchmarks. Reach for a frontier model when the task is knowledge-heavy or code-intensive, and keep this one as the planning brain that decides and orchestrates. When the task needs reasoning, this is the model.
**References:** [Model docs](https://docs.liquid.ai/deployment/on-device/android/ai-agent-usage-guide#text-models) • [Terms](https://www.liquid.ai/terms-conditions) • [Privacy](https://www.liquid.ai/lfm-license)
```bash Responses API theme={null}
curl https://api.zerogpu.ai/v1/responses \
-H "content-type: application/json" \
-H "x-api-key: YOUR_API_KEY" \
-H "x-project-id: YOUR_PROJECT_ID" \
-d '{
"input": "Our whole team got locked out of the dashboard this morning after the payment failed. We have a product demo with a customer in 2 hours and cannot log in. Card on file should be valid.",
"model": "LFM2.5-1.2B-Thinking",
"instructions": "You are a support triage assistant. Read the ticket, briefly reason about the signals, then assign one team (Billing, Technical, Account, General) and one priority (Low, Medium, High). Decide once and commit. End with a single line: TEAM | PRIORITY."
}'
```
```bash Chat Completions theme={null}
curl https://api.zerogpu.ai/v1/chat/completions \
-H "content-type: application/json" \
-H "x-api-key: YOUR_API_KEY" \
-H "x-project-id: YOUR_PROJECT_ID" \
-d '{
"model": "LFM2.5-1.2B-Thinking",
"messages": [
{
"role": "system",
"content": "You are a support triage assistant. Read the ticket, briefly reason about the signals, then assign one team (Billing, Technical, Account, General) and one priority (Low, Medium, High). Decide once and commit. End with a single line: TEAM | PRIORITY."
},
{
"role": "user",
"content": "Our whole team got locked out of the dashboard this morning after the payment failed. We have a product demo with a customer in 2 hours and cannot log in. Card on file should be valid."
}
]
}'
```
The model returns its answer alongside an explicit reasoning trace.
```text Response theme={null}
The capital of Japan is **Tokyo**.
**Reasoning:**
1. Japan's political, cultural, and economic center is located in Tokyo.
2. Historically, Tokyo has served as Japan's...
```
## llama-3.1-8b-instruct-fast
> Meta's Llama 3.1 Instruct, tuned for fast, low-cost summarization at scale on the ZeroGPU edge network. Its 128K-token context window takes in entire documents, long transcripts, and full email or chat threads in a single pass. No chunking, no stitching partial summaries back together. Built for the high-volume summarization that runs around your core product: condensing long reports and transcripts, summarizing email and chat threads, and processing articles in bulk. When context length matters and you're summarizing on every request, this is the model that keeps it fast and affordable.
**References:** [Model docs](https://github.com/meta-llama/llama-models/tree/main/models/llama3_1) • [Terms](https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/LICENSE) • [Privacy](https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/USE_POLICY.md)
```bash Responses API theme={null}
curl https://api.zerogpu.ai/v1/responses \
-H "content-type: application/json" \
-H "x-api-key: YOUR_API_KEY" \
-H "x-project-id: YOUR_PROJECT_ID" \
-d '{
"input": "The global semiconductor industry is undergoing one of its most significant structural shifts in decades, driven by a combination of geopolitical tensions, surging demand from artificial intelligence workloads, and a wave of government-backed industrial policy across the United States, Europe, and Asia. At the center of this transformation is a race to onshore chip manufacturing capacity that had, for thirty years, been quietly concentrated in Taiwan and South Korea. The United States CHIPS and Science Act, signed into law in 2022, allocated over $52 billion in subsidies to incentivize domestic semiconductor fabrication. Since then, companies including TSMC, Intel, Samsung, and Micron have announced or broken ground on new fabs in Arizona, Ohio, Texas, and Idaho. However, construction timelines have slipped, costs have ballooned, and a shortage of skilled workers has prompted some manufacturers to bring in engineers from overseas — a move that has drawn political scrutiny even as it addresses a genuine talent gap. Meanwhile, the explosion of AI model training and inference has fundamentally altered the demand profile for chips. Graphics processing units originally designed for gaming, particularly those made by NVIDIA, have become the primary compute substrate for large language models. NVIDIA's H100 and successor Blackwell-series GPUs now trade at significant premiums on secondary markets, with some hyperscalers reporting lead times of over a year for large cluster orders. This bottleneck has accelerated investment in custom silicon: Google's Tensor Processing Units, Amazon's Trainium and Inferentia chips, and Meta's MTIA accelerators are all attempts to reduce dependence on third-party GPU supply chains. On the geopolitical front, the United States has progressively tightened export controls on advanced chips and chip-making equipment destined for China, with the most recent rules targeting gate-all-around transistor technology and high-bandwidth memory. China, in response, has dramatically increased state investment in its domestic semiconductor ecosystem, with companies like SMIC and Huawei making incremental but closely watched progress at advanced nodes. Analysts remain divided on how quickly China can close the gap, with estimates ranging from five to fifteen years depending on assumptions about technology transfer, equipment access, and the pace of indigenous innovation. The equipment layer — often overlooked in public discourse — may prove to be the most consequential chokepoint. ASML, the Dutch company that holds a near-monopoly on extreme ultraviolet lithography machines, has become a focal point of both trade diplomacy and industrial strategy. Without EUV tools, fabricating chips below 7 nanometers at scale is effectively impossible, giving ASML and its supply chain extraordinary leverage in a world where nations are suddenly treating semiconductor access as a matter of national security.",
"model": "llama-3.1-8b-instruct-fast"
}'
```
```bash Chat Completions theme={null}
curl https://api.zerogpu.ai/v1/chat/completions \
-H "content-type: application/json" \
-H "x-api-key: YOUR_API_KEY" \
-H "x-project-id: YOUR_PROJECT_ID" \
-d '{
"model": "llama-3.1-8b-instruct-fast",
"messages": [
{
"role": "user",
"content": "The global semiconductor industry is undergoing one of its most significant structural shifts in decades, driven by a combination of geopolitical tensions, surging demand from artificial intelligence workloads, and a wave of government-backed industrial policy across the United States, Europe, and Asia. At the center of this transformation is a race to onshore chip manufacturing capacity that had, for thirty years, been quietly concentrated in Taiwan and South Korea. The United States CHIPS and Science Act, signed into law in 2022, allocated over $52 billion in subsidies to incentivize domestic semiconductor fabrication. Since then, companies including TSMC, Intel, Samsung, and Micron have announced or broken ground on new fabs in Arizona, Ohio, Texas, and Idaho. However, construction timelines have slipped, costs have ballooned, and a shortage of skilled workers has prompted some manufacturers to bring in engineers from overseas — a move that has drawn political scrutiny even as it addresses a genuine talent gap. Meanwhile, the explosion of AI model training and inference has fundamentally altered the demand profile for chips. Graphics processing units originally designed for gaming, particularly those made by NVIDIA, have become the primary compute substrate for large language models. NVIDIA's H100 and successor Blackwell-series GPUs now trade at significant premiums on secondary markets, with some hyperscalers reporting lead times of over a year for large cluster orders. This bottleneck has accelerated investment in custom silicon: Google's Tensor Processing Units, Amazon's Trainium and Inferentia chips, and Meta's MTIA accelerators are all attempts to reduce dependence on third-party GPU supply chains. On the geopolitical front, the United States has progressively tightened export controls on advanced chips and chip-making equipment destined for China, with the most recent rules targeting gate-all-around transistor technology and high-bandwidth memory. China, in response, has dramatically increased state investment in its domestic semiconductor ecosystem, with companies like SMIC and Huawei making incremental but closely watched progress at advanced nodes. Analysts remain divided on how quickly China can close the gap, with estimates ranging from five to fifteen years depending on assumptions about technology transfer, equipment access, and the pace of indigenous innovation. The equipment layer — often overlooked in public discourse — may prove to be the most consequential chokepoint. ASML, the Dutch company that holds a near-monopoly on extreme ultraviolet lithography machines, has become a focal point of both trade diplomacy and industrial strategy. Without EUV tools, fabricating chips below 7 nanometers at scale is effectively impossible, giving ASML and its supply chain extraordinary leverage in a world where nations are suddenly treating semiconductor access as a matter of national security."
}
]
}'
```
The summary is returned as `output[].content[].text` (Responses API) or `choices[].message.content` (Chat Completions).
```text Response theme={null}
The global semiconductor industry is undergoing a significant transformation driven by geopolitical tensions, surging demand from artificial intelligence workloads, and government-backed industrial policies. A race to onshore chip manufacturing capacity is underway, with the US, Europe, and Asia investing heavily in domestic fabrication, while companies like TSMC, Intel, and Samsung are building new fabs in the US. However, construction timelines have slipped, costs have increased, and a shortage of skilled workers has prompted some manufacturers to bring in overseas engineers. The demand for chips has also changed, with AI model training and inference driving a shortage of graphics processing units, particularly those made by NVIDIA. In response, companies like Google, Amazon, and Meta are investing in custom silicon to reduce dependence on third-party supply chains. The US has tightened export controls on advanced chips and equipment destined for China, which has responded with increased state investment in its domestic semiconductor ecosystem. The equipment layer, particularly ASML's near-monopoly on extreme ultraviolet lithography machines, may prove to be the most consequential chokepoint in the industry.
```