> For clean Markdown of any page, append `.md` to the page URL. > For a complete documentation index, see https://docs.sarvam.ai/llms.txt. > For full documentation content in one file, see https://docs.sarvam.ai/llms-full.txt. > For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.sarvam.ai/_mcp/server. # Gemma 4 31B > Gemma 4 31B is an open-source instruction-tuned model served on Sarvam infrastructure. 128K context window with image input and tool calling. Gemma 4 31B is an [open-source model](/api/getting-started/models/open-source) served by Sarvam in **beta**, and is **not tuned for Indian languages**. Beta access is granted per API key — [contact us](/api/getting-started/help) to request whitelisting. For Indian language workloads use [Sarvam-105B](/api/getting-started/models/sarvam-105b); for document and image understanding in Indian languages, use [Sarvam Vision](/api/getting-started/models/sarvam-vision). A 31B-parameter instruction-tuned model. Its distinguishing feature on Sarvam is **image input** — it is the only chat model here that accepts images alongside text in the chat completions format. ## At a Glance | | | | ---------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Model ID** | `gemma4` | | **What it does** | Chat LLM with image understanding | | **Languages** | Not tuned for Indian languages by Sarvam | | **APIs** | [Open-Source Models API Reference](/api-reference/open-source/chat-completions) (`POST /v2/chat/completions`, OpenAI-compatible, streaming supported) — also see [using an open-source model](/api/getting-started/models/open-source#using-an-open-source-model) | | **Input limits** | 131,072-token context window; images as base64 data URIs only; 10 MB request cap — [all limits](#limits-and-errors) | | **Benchmarks** | None published by Sarvam | | **Pricing** | ₹36.6 input · ₹13.73 cached input · ₹91.5 output — per 1M tokens ([Pricing](/api/getting-started/pricing)) | | **Best for** | Image captioning, classification, and visual question answering | | **Not for** | Indian language workloads or document OCR — use [Sarvam-105B](/api/getting-started/models/sarvam-105b) or [Sarvam Vision](/api/getting-started/models/sarvam-vision) | ## Why you might use it #### Image understanding Accepts images inline as base64 data URIs in the standard `image_url` content part, so you can caption, classify, or answer questions about images. #### Direct answers Not a reasoning model — it replies without a chain-of-thought pass, so the whole token budget goes to the answer. ## Model Specifications #### Key Considerations Each image is estimated at roughly **1,024 tokens** when Sarvam checks your request against the context window. Budget for this when sending several images with a long prompt. ## Gemma 4 31B vs other options | Feature | Gemma 4 31B | GLM-5.2 | Sarvam-105B | Sarvam Vision | | -------------------------- | ------------------ | ----------------------- | ----------------------------------- | ------------------------- | | **Context window** | 131,072 | 524,288 | 128,000 | — | | **Image input** | ✅ | ❌ | ❌ | ✅ (documents) | | **Tool calling** | ✅ | ✅ | ✅ | — | | **Indian language tuning** | None | None | 23 languages | 23 languages | | **Best for** | Image + text tasks | Very long-context tasks | Indian-language chat & agentic work | Document OCR & extraction | For **document** understanding — scanned forms, invoices, PDFs, especially in Indian languages — use [Sarvam Vision](/api/getting-started/models/sarvam-vision), which is purpose-built for OCR and structured extraction. Use `gemma4` for general images where you want a conversational answer rather than structured document output. ## Key Capabilities #### Basic Chat Completion A text-only single-turn request. Only the `model` field differs from a Sarvam chat completion call. #### Python ```python from sarvamai import SarvamAI client = SarvamAI(api_subscription_key="YOUR_SARVAM_API_KEY") response = client.open_source_models.chat_completions_v2( model="gemma4", messages=[ {"role": "user", "content": "Classify this support ticket as billing, technical, or other: 'My invoice shows twice the usage I expected.'"} ], temperature=0.1, max_tokens=100, ) print(response.choices[0].message.content) ``` #### JavaScript ```javascript import { SarvamAIClient } from "sarvamai"; const client = new SarvamAIClient({ apiSubscriptionKey: "YOUR_SARVAM_API_KEY", }); async function main() { const response = await client.openSourceModels.chatCompletionsV2({ model: "gemma4", messages: [ { role: "user", content: "Classify this support ticket as billing, technical, or other: 'My invoice shows twice the usage I expected.'", }, ], temperature: 0.1, max_tokens: 100, }); console.log(response.choices[0].message.content); } main(); ``` #### cURL ```bash curl -X POST https://api.sarvam.ai/v2/chat/completions \ -H "api-subscription-key: $SARVAM_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "messages": [ {"role": "user", "content": "Classify this support ticket as billing, technical, or other: \"My invoice shows twice the usage I expected.\""} ], "model": "gemma4", "temperature": 0.1, "max_tokens": 100 }' ``` #### Image Input Send an image as a content part alongside your text prompt. The image must be a **base64 data URI** — see the note below. #### Python ```python import base64 from sarvamai import SarvamAI client = SarvamAI(api_subscription_key="YOUR_SARVAM_API_KEY") with open("chart.png", "rb") as f: encoded = base64.b64encode(f.read()).decode("utf-8") response = client.open_source_models.chat_completions_v2( model="gemma4", messages=[ { "role": "user", "content": [ {"type": "text", "text": "What trend does this chart show?"}, { "type": "image_url", "image_url": {"url": f"data:image/png;base64,{encoded}"}, }, ], } ], max_tokens=500, ) print(response.choices[0].message.content) ``` #### JavaScript ```javascript import { readFileSync } from "fs"; import { SarvamAIClient } from "sarvamai"; const client = new SarvamAIClient({ apiSubscriptionKey: "YOUR_SARVAM_API_KEY", }); async function main() { const encoded = readFileSync("chart.png").toString("base64"); const response = await client.openSourceModels.chatCompletionsV2({ model: "gemma4", messages: [ { role: "user", content: [ { type: "text", text: "What trend does this chart show?" }, { type: "image_url", image_url: { url: `data:image/png;base64,${encoded}` }, }, ], }, ], max_tokens: 500, }); console.log(response.choices[0].message.content); } main(); ``` #### cURL ```bash # Build the payload so the base64 image does not hit shell argument limits. python3 - <<'PY' import base64, json encoded = base64.b64encode(open("chart.png", "rb").read()).decode() json.dump({ "model": "gemma4", "messages": [{ "role": "user", "content": [ {"type": "text", "text": "What trend does this chart show?"}, {"type": "image_url", "image_url": {"url": f"data:image/png;base64,{encoded}"}}, ], }], "max_tokens": 500, }, open("payload.json", "w")) PY curl -X POST https://api.sarvam.ai/v2/chat/completions \ -H "api-subscription-key: $SARVAM_API_KEY" \ -H "Content-Type: application/json" \ --data-binary @payload.json ``` **Remote image URLs are rejected.** You must inline the image as a base64 data URI, for example `data:image/png;base64,`. Passing an `http://` or `https://` URL returns a validation error. Because images are inlined, they count against the **10 MB** request cap. Base64 encoding adds roughly 33% overhead, so keep source images under about 7 MB. #### Streaming Set `stream` to `true` to receive tokens as server-sent events. #### Python ```python from sarvamai import SarvamAI client = SarvamAI(api_subscription_key="YOUR_SARVAM_API_KEY") stream = client.open_source_models.chat_completions_v2( model="gemma4", messages=[ {"role": "user", "content": "Summarise what a load balancer does in three sentences."} ], max_tokens=300, stream=True, ) for chunk in stream: delta = chunk.choices[0].delta.content if delta: print(delta, end="", flush=True) ``` #### cURL ```bash curl -N -X POST https://api.sarvam.ai/v2/chat/completions \ -H "api-subscription-key: $SARVAM_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "gemma4", "messages": [ {"role": "user", "content": "Summarise what a load balancer does in three sentences."} ], "max_tokens": 300, "stream": true }' ``` ## Parameters Gemma 4 31B accepts the standard OpenAI-compatible parameter set — `temperature`, `top_p`, `max_tokens`, `stream`, `stop`, `n`, `seed`, `frequency_penalty`, `presence_penalty`, `response_format` (Structured Outputs), `tools`, and `tool_choice`. See the [full parameter table](/api/getting-started/models/open-source#supported-parameters) for types, defaults, and ranges. Model-specific notes: * **Images must be base64 data URIs** — remote `http(s)` URLs are rejected. * **No reasoning** — the model answers directly, never returns `reasoning_content`, and `reasoning_effort` is accepted but has no effect. * **`seed` is reproducible** — identical seed and parameters return identical output in current serving. * **Don't ask for JSON in the prompt when `response_format` is set** — an instruction like "Return JSON" alongside a JSON response format makes the model emit whitespace until it exhausts `max_tokens`, billing the full budget for no usable output. Let `response_format` handle the shape. ## Limits and errors Common errors for every model on `/v2/chat/completions` are documented on the [Open-Source Models overview](/api/getting-started/models/open-source#errors). Gemma-4-specific cases: | Condition | Status | Code | What it means | | ---------------------------------------------------- | ------ | ---------------------------- | ------------------------------------------------------------------------------------------------------- | | API key lacks beta access | `400` | `invalid_request_error` | Request whitelisting — see [Beta APIs](/api-reference/beta-apis). | | Missing or invalid API key | `403` | `invalid_api_key_error` | Check the `api-subscription-key` header. | | No credits remaining | `402` | `insufficient_quota_error` | Top up on the [dashboard](https://dashboard.sarvam.ai). | | Unknown or unavailable model id | `404` | `not_found_error` | Confirm the id with [`GET /v2/models`](/api-reference/open-source/models). | | `image_url` pointing at an `http(s)` URL | `400` | `invalid_request_error` | Inline the image as a base64 data URI instead. | | `max_tokens` above 131,072 | `400` | `invalid_request_error` | `max_tokens` cannot exceed the context window. | | Estimated prompt tokens + `max_tokens` above 131,072 | `422` | `unprocessable_entity_error` | Shorten the prompt, send fewer images, or lower `max_tokens`. | | Request body above the model's size cap | `413` | `invalid_request_error` | Encoded images count toward this cap. | | Invalid tool schema | `400` | `invalid_request_error` | See [Tool schemas](/api/getting-started/models/open-source#tool-schemas). | | Whitespace-only reply with `finish_reason: "length"` | `200` | — | `response_format` was combined with a "return JSON" instruction in the prompt — remove the instruction. | ## Support Sarvam supports the serving layer — auth, billing, rate limits, availability. Sarvam does not tune or evaluate this model, so its output quality, reasoning, and language coverage are properties of the model itself. See [Open-Source Models](/api/getting-started/models/open-source) for the full support boundary, and [Talk to us](/api/getting-started/help) for serving issues.