We use cookies to enhance your experience, provide personalised content, and analyse our traffic; see our Cookie Policy.
deepseek/deepseek-v4.1-flashDeepSeek's Flash model that thinks before it codes
DeepSeek V4.1 Flash is the 17 October 2026 release of DeepSeek's Flash model, the one DeepSeek itself has served since that date. According to DeepSeek, it scores higher on coding benchmarks while giving shorter answers than the previous release.
It thinks before answering, about 600 tokens and 15 seconds on a small coding task in our tests, and reads both text and images in a one-million-token window. Tools and JSON are supported. Built for code, calculations and multi-step problems.
On Tchavi you pay with mobile money, with no international card and no KYC, and one API key covers 80+ models. It is OpenAI-compatible: change the base URL, keep your SDK.
About 600 reasoning tokens on a small coding task
According to DeepSeek, better at code than the previous release
About a million input tokens in a single request
Very long answers in a single pass
Screenshots, diagrams and photos alongside your text
Function calling and structured output
Review this Python function and fix the bug that breaks the delivery-fee calculation.
Write a script that turns a CSV sales export into a monthly report per product.
Explain step by step how to repay a 500,000 CFA franc loan in 12 monthly instalments at 2% a month.
V4.1 Flash is the next generation: it also reads images and, according to DeepSeek, codes better. V4 Flash (model: "deepseek-v4-flash") costs less for high volume.
It reasons before answering. Those thinking tokens are billed as output and show up in usage.completion_tokens_details.reasoning_tokens. For instant answers, pick MiMo-V2.6-Flash.
Yes. It is in the budget group, open from the free plan.
Up to 1,048,576 input tokens, and up to 393,216 tokens per answer.
Point the base URL at Tchavi, use your Tchavi key and set model: "deepseek-v4.1-flash" on /v1/chat/completions. The rest of your code stays the same.
Yes. Top up your Tchavi account with Orange Money, MTN MoMo, M-Pesa or another mobile money operator. No bank card is needed. Credits land as soon as the payment is confirmed and are deducted as you use them.
Yes. Keep your current OpenAI SDK, just change the base URL to Tchavi's (shown in the API tab) and use your Tchavi key. The rest of your code stays the same.
import Tchavi from '@tchavi/sdk';
const client = new Tchavi({ apiKey: 'API_KEY' });
const response = await client.chat.completions.create({
model: 'deepseek-v4.1-flash',
messages: [
{
"role": "user",
"content": "Hello!"
}
],
});
console.log(response.choices[0].message.content);
console.log('Credits used:', response.tchavi.credits_used);Every parameter this model accepts on the API. Check the SDK for full typings.
modelRequiredID of the chat model (e.g. `deepseek-v4.1-flash`).
messagesRequiredConversation messages. Each item has a `role` (system/user/assistant) and a `content` that's either a plain string or an array of content blocks (`text`, `image_url`, `document_url`).
temperature1Sampling temperature between 0 and 2. Higher values = more random.
max_tokensMaximum number of tokens to generate in the response.
max_completion_tokensOpenAI alias for `max_tokens`. Either field works; if both are sent, `max_completion_tokens` wins.
streamfalseIf true, partial message deltas are streamed as Server-Sent Events.
toolsFunction-calling toolbox. Pass an array of `{ type: "function", function: { name, description, parameters } }`. Returned tool calls land in `choices[].message.tool_calls`. Only models with `supportsTools: true` accept this.
tool_choiceHow the model picks among tools: `"auto"` (default), `"none"` to force a plain text reply, or `{ type: "function", function: { name } }` to force a specific tool. Only with `supportsTools: true`.
response_formatConstrain the output. Pass `{ type: "json_object" }` to force valid JSON (the model still needs a JSON instruction in your prompt). Only models with `supportsJsonMode: true` honour this.
top_p1Nucleus sampling: only tokens in the top `top_p` probability mass are considered.
seedInteger seed for deterministic output. The same seed + identical request yields the same completion when supported by the provider. OpenAI honours it; Anthropic ignores.
n1Number of completions to generate in one call. Defaults to 1; each extra completion is billed.
stream_optionsStreaming options, e.g. `{ "include_usage": true }` to receive a final SSE chunk with usage counts. Effective only when `stream: true`.
stopUp to 4 sequences where the API will stop generating further tokens.
frequency_penalty0Between -2.0 and 2.0. Positive values penalize tokens that have appeared frequently.
presence_penalty0Between -2.0 and 2.0. Positive values encourage the model to talk about new topics.
userEnd-user identifier passed to the upstream provider for abuse / moderation tracking. Should be stable per end-user.
logit_biasPer-token logit bias `{ "<tokenId>": <-100..100>, ... }`. OpenAI-specific; Anthropic ignores silently.
messages[].content[].image_urlAttach an image on a user message. Pass a content block `{ "type": "image_url", "image_url": { "url": ... } }`. PNG / JPEG / WebP, up to 4 per request. Only models with `supportsImageInput: true` accept this block (e.g. `gpt-4o`, `claude-opus-4-7`).
Estimated over 30 days, for a typical message: ~500 input + ~150 output tokens, billed to the thousandth of a credit.