> ## Documentation Index
> Fetch the complete documentation index at: https://docs.nano-gpt.com/llms.txt
> Use this file to discover all available pages before exploring further.
# Talk to GPT (Legacy)
> Legacy endpoint for chat interactions with the GPT model
## Overview
The Talk to GPT endpoint is our legacy text generation API that also supports web search capabilities through LinkUp integration.
The legacy endpoint supports the same model suffix parser for web search and provider routing as Chat Completions, but new integrations should use `/api/v1/chat/completions`. See [Model Suffixes](/api-reference/miscellaneous/model-suffixes).
The body `provider` field accepts either the existing provider ID string or a structured routing object with fields such as `order`, `only`, `ignore`, `sort`, `max_price`, `allow_fallbacks`, and `require_parameters`. See [Provider Selection > Provider Routing Object](/api-reference/miscellaneous/provider-selection#provider-routing-object).
## Web Search
Enable web search by appending suffixes to the model name:
* **`:online`** - Standard web search (\$0.006 per request)
* **`:online/linkup-deep`** - Deep web search (\$0.06 per request)
Provider routing suffixes such as `:fast` / `:speed`, `:cheap` / `:price` / `:floor`, `:throughput`, `:latency`, `:tools`, and `:caching` / `:cache` / `:cached` are also accepted for eligible models.
If you need direct control over search query, output mode (`searchResults` / `sourcedAnswer` / `structured`), or date/domain filters, use [Direct Web Search API (`POST /api/web`)](/api-reference/endpoint/web-search).
### Example with Web Search
```python Python theme={null}
import requests
import json
BASE_URL = "https://nano-gpt.com/api"
API_KEY = "YOUR_API_KEY"
headers = {
"x-api-key": API_KEY,
"Content-Type": "application/json"
}
# Standard web search
data = {
"prompt": "What are the latest AI breakthroughs this month?",
"model": "openai/gpt-5.2:online",
"messages": []
}
response = requests.post(
f"{BASE_URL}/talk-to-gpt",
headers=headers,
json=data
)
# Deep web search for comprehensive research
data_deep = {
"prompt": "Provide a detailed analysis of recent quantum computing advances",
"model": "openai/gpt-5.2:online/linkup-deep",
"messages": []
}
response_deep = requests.post(
f"{BASE_URL}/talk-to-gpt",
headers=headers,
json=data_deep
)
# Parse response
if response.status_code == 200:
parts = response.text.split('')
text_response = parts[0].strip()
nano_info = json.loads(parts[1].split('')[0])
print("Response:", text_response)
print("Cost:", nano_info['cost'])
```
```javascript JavaScript theme={null}
const BASE_URL = "https://nano-gpt.com/api";
const API_KEY = "YOUR_API_KEY";
// Standard web search
const response = await fetch(`${BASE_URL}/talk-to-gpt`, {
method: 'POST',
headers: {
'x-api-key': API_KEY,
'Content-Type': 'application/json'
},
body: JSON.stringify({
prompt: 'What are the latest AI breakthroughs this month?',
model: 'openai/gpt-5.2:online',
messages: []
})
});
// Deep web search
const deepResponse = await fetch(`${BASE_URL}/talk-to-gpt`, {
method: 'POST',
headers: {
'x-api-key': API_KEY,
'Content-Type': 'application/json'
},
body: JSON.stringify({
prompt: 'Provide a detailed analysis of recent quantum computing advances',
model: 'openai/gpt-5.2:online/linkup-deep',
messages: []
})
});
```
```bash cURL theme={null}
# Standard web search
curl -X POST https://nano-gpt.com/api/talk-to-gpt \
-H "x-api-key: YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"prompt": "What are the latest AI breakthroughs this month?",
"model": "openai/gpt-5.2:online",
"messages": []
}'
# Deep web search
curl -X POST https://nano-gpt.com/api/talk-to-gpt \
-H "x-api-key: YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"prompt": "Provide a detailed analysis of recent quantum computing advances",
"model": "openai/gpt-5.2:online/linkup-deep",
"messages": []
}'
```
## Important Notes
* Web search works with all models - simply append the suffix
* Increases input token count which affects total cost
* Provides access to real-time information
* For new projects, consider using the OpenAI-compatible `/v1/chat/completions` endpoint instead
## OpenAPI
````yaml POST /talk-to-gpt
openapi: 3.1.0
info:
title: NanoGPT API
description: >-
API documentation for the NanoGPT language, image, video, speech-to-text,
and text-to-speech generation services
license:
name: MIT
version: 1.0.0
servers:
- url: https://nano-gpt.com/api
description: NanoGPT API Server
security: []
paths:
/talk-to-gpt:
post:
description: Legacy endpoint for chat interactions with the GPT model
requestBody:
description: Parameters for talking to GPT
content:
application/json:
schema:
$ref: '#/components/schemas/TalkToGptRequest'
required: true
responses:
'200':
description: Talk to GPT response
content:
text/plain:
schema:
type: string
description: Text response followed by metadata in tags
'400':
description: Unexpected error
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
security:
- apiKeyAuth: []
components:
schemas:
TalkToGptRequest:
type: object
required:
- model
properties:
prompt:
type: string
description: The text prompt to send to GPT (optional)
default: ''
example: Please explain the concept of artificial intelligence.
model:
type: string
description: >-
The model to use for generation. The legacy endpoint supports the
same model suffix parser for web search and provider routing,
including ':caching', ':cache', and ':cached', as Chat Completions.
default: minimax/minimax-m2.7
examples:
- minimax/minimax-m2.7
- zai-org/glm-5:fast
- zai-org/glm-5:cheap
- openai/gpt-5.2:online/exa-instant
provider:
description: >-
Optional provider override or structured provider routing controls
for provider-selection-capable models. A string explicitly selects
one provider. An object can set soft order, hard pins, exclusions,
sort preference, price caps, fallback behavior, and
parameter-capability requirements.
oneOf:
- type: string
description: Provider ID or accepted provider display name/alias.
- $ref: '#/components/schemas/ProviderRoutingObject'
messages:
type: array
description: Array of previous message objects for context (optional)
default:
- role: user
content: Hi, I'm just testing!
items:
type: object
required:
- role
- content
properties:
role:
type: string
description: The role of the message author
enum:
- user
- assistant
content:
type: string
description: The content of the message
Error:
required:
- error
- message
type: object
properties:
error:
type: integer
format: int32
message:
type: string
ProviderRoutingObject:
type: object
description: >-
Structured per-request provider routing controls. Per-request controls
take precedence over saved provider preferences and are not merged with
them.
properties:
order:
type: array
description: >-
Soft provider preference order. NanoGPT tries these providers first
when possible, but this does not hard-pin routing to only these
providers. Unknown providers are ignored.
items:
type: string
only:
type: array
description: >-
Hard provider pin. NanoGPT restricts routing to these providers and
fails instead of silently routing elsewhere. Unknown providers
return a structured 400 error with code provider_unknown_provider.
items:
type: string
ignore:
type: array
description: Providers to exclude from routing. Unknown providers are ignored.
items:
type: string
sort:
type: string
description: >-
Routing preference. speed, throughput, latency, and price actively
request that strategy. auto, none, and default are accepted to
suppress stored/default routing preferences without requesting a
provider sort.
enum:
- speed
- throughput
- latency
- price
- auto
- none
- default
quantizations:
type: array
description: >-
Hard allowlist of model weight quantization levels. Providers
without matching known quantization metadata are excluded unless
unknown is included explicitly.
minItems: 1
items:
type: string
enum:
- int4
- fp4
- fp6
- int8
- fp8
- fp16
- bf16
- fp32
- unknown
min_quantization:
type: string
description: >-
Minimum model weight quantization precision floor. Quantizations are
ordered by bit width; integer and floating-point formats with the
same bit width are treated as equivalent. unknown is not valid
because it cannot be compared to a precision floor.
enum:
- int4
- fp4
- fp6
- int8
- fp8
- fp16
- bf16
- fp32
max_price:
type: object
description: >-
Optional provider price caps in USD per 1 million tokens. Pricing
checks are best-effort when provider pricing is unknown.
properties:
prompt:
type: number
description: Maximum prompt/input price in USD per 1 million tokens.
minimum: 0
completion:
type: number
description: Maximum completion/output price in USD per 1 million tokens.
minimum: 0
allow_fallbacks:
type: boolean
description: When false, disables cross-provider fallback for this request.
require_parameters:
type: boolean
description: >-
When true, requires the selected provider to support the requested
parameters on routes that support parameter-level capability checks.
securitySchemes:
apiKeyAuth:
type: apiKey
in: header
name: x-api-key
````