impulse

Vision Large

API id vision-large
Input / 1M
$7.37
at Vispark
Output / 1M
$22.11
at Vispark
Context window
1M
tokens
Max output
66K
tokens per reply
Hosts
1
1 listings
Released
-
date not published

Pricing

List prices at Vispark, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$7.37$22.11
Cached input
100% off input
$0.00

What it costs a month

At Vispark list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$3,206
  • RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$2,565
  • Coding agent1,000 requests a day, 40K in / 2K out, cached$3,980
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$22,994
Use your own numbers

Where to run it

1 host serve Vision Large. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
VisparkCloud
vision-large
$7.37 / $22.11

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
AudioImagesTextVideoPDFs
Produces
Text
Features
Parallel tool callsPDF input

Cheaper alternatives

Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.

Same model, cheaper host

No host sells it for less than Vispark.

Smaller Independent models

No cheaper Independent model keeps its key capabilities.

Other frontier labs

  • Claude Opus 5.5
    Anthropic · on Anthropic
    $4.00 / $20.00
    Has every key capability
    28% less
  • GPT-5.3 Codex
    OpenAI · on OpenAI
    $1.75 / $14.00
    Has every key capability
    56% less
  • Gemini 4 Carbon
    Google · on Google AI Studio
    $2.00 / $10.00
    Has every key capability
    64% less
  • Grok 4.7
    xAI · on xAI
    $2.00 / $6.00
    Has every key capability
    73% less

Open-weight picks

  • Command A Plus
    Cohere · on AIHubMix
    $2.50 / $10.00
    Has every key capability
    60% less
  • Kimi K3.1 Pro
    Moonshot AI · on Databricks
    $2.00 / $10.00
    Has every key capability
    64% less
  • Qwen4 Max
    Alibaba Qwen · on Alibaba DashScope
    $1.50 / $4.50
    Has every key capability
    80% less
  • Inkling
    Independent · on DeepInfra
    $0.95 / $4.05
    Has every key capability
    84% less

Call it

Using Vispark's API.

Python
from litellm import completion

response = completion(
    model="vispark/vision-large",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Vision Large cost?

On Vispark, Vision Large costs $7.37 per million input tokens and $22.11 per million output tokens.

Which APIs offer Vision Large?

Vision Large runs on 1 API: Vispark.

What is Vision Large's context window?

1M tokens, with up to 66K tokens in one reply.

Is Vision Large being retired?

No retirement date is scheduled for it on any API we track.

What are cheaper alternatives to Vision Large?

Models that cost less and keep most of what it can do: Claude Opus 5.5 on Anthropic (28% less), GPT-5.3 Codex on OpenAI (56% less) and Command A Plus on AIHubMix (60% less). Savings are on a mix of 3 input tokens to 1 output token.

What is Vision Large's API model id?

Use vision-large with Vispark.

Sources

Raw catalog entry for vision-large on Vispark
{
  "cache_read_input_token_cost": 0,
  "input_cost_per_token": 0.00000737,
  "litellm_provider": "vispark",
  "max_input_tokens": 1000000,
  "max_output_tokens": 65536,
  "mode": "chat",
  "output_cost_per_token": 0.00002211,
  "source": "https://api.lab.vispark.in/v1/models",
  "supported_endpoints": [
    "/v1/chat/completions",
    "/v1/completions"
  ],
  "supported_modalities": [
    "text",
    "image",
    "audio",
    "video"
  ],
  "supported_output_modalities": [
    "text"
  ],
  "supports_function_calling": true,
  "supports_native_streaming": true,
  "supports_parallel_function_calling": true,
  "supports_pdf_input": true,
  "supports_reasoning": true,
  "supports_response_schema": true,
  "supports_system_messages": true,
  "supports_tool_choice": true,
  "supports_vision": true
}