impulse

DeepSeek Prover V2 671B

Open weights
API id DeepSeek-Prover-V2-671B
Input / 1M
$0.50
at GMI Cloud
Output / 1M
$2.18
at GMI Cloud
Context window
131K
tokens
Max output
160K
tokens per reply
Hosts
2
2 listings
Released
-
date not published

Pricing

List prices at GMI Cloud, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.50$2.18

What it costs a month

At GMI Cloud list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$314
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$318
  • Coding agent1,000 requests a day, 40K in / 2K out$731
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$1,723
Use your own numbers

Where to run it

2 hosts serve DeepSeek Prover V2 671B. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
GMI CloudInference
DeepSeek-Prover-V2-671B
$0.50 / $2.18
Novita AIInference
deepseek-prover-v2-671b
$0.70 / $2.50
+25% vs headline

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
Text
Produces
Text
Open weights
License: DeepSeek License (MIT code)
Runtimes: SGLang, TGI, vLLM

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 GMI Cloud.

Smaller DeepSeek models

No cheaper DeepSeek model keeps its key capabilities.

Other frontier labs

  • Gemini 3.5 Flash Lite
    Google · on Google AI Studio
    $0.30 / $2.50
    Has every key capability
    8% less
  • GPT-5.4 Nano
    OpenAI · on OpenAI
    $0.20 / $1.25
    Has every key capability
    50% less
  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    78% less
  • GPT-6 Luna
    OpenAI · on OpenAI
    $0.10 / $0.50
    Has every key capability
    78% less

Open-weight picks

  • Motif 3
    Independent · on ai&
    $0.50 / $2.00
    Has every key capability
    5% less
  • GLM 5.3
    Zhipu AI · on CLF AI Gateway
    $0.56 / $1.76
    Has every key capability
    7% less
  • Nemotron 3 Ultra 550B A55B
    NVIDIA · on Perplexity
    $0.25 / $2.50
    Has every key capability
    12% less
  • DeepSeek V4 Pro
    DeepSeek · on CLF AI Gateway
    $0.528 / $1.58
    Has every key capability
    14% less

Call it

Using GMI Cloud's API.

Python
from litellm import completion

response = completion(
    model="gmi/DeepSeek-Prover-V2-671B",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does DeepSeek Prover V2 671B cost?

On GMI Cloud, DeepSeek Prover V2 671B costs $0.50 per million input tokens and $2.18 per million output tokens.

Which APIs offer DeepSeek Prover V2 671B?

DeepSeek Prover V2 671B runs on 2 APIs: GMI Cloud and Novita AI.

What is DeepSeek Prover V2 671B's context window?

131K tokens, with up to 160K tokens in one reply.

Is DeepSeek Prover V2 671B being retired?

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

What are cheaper alternatives to DeepSeek Prover V2 671B?

Models that cost less and keep most of what it can do: Gemini 3.5 Flash Lite on Google AI Studio (8% less), GPT-5.4 Nano on OpenAI (50% less) and Motif 3 on ai& (5% less). Savings are on a mix of 3 input tokens to 1 output token.

What is DeepSeek Prover V2 671B's API model id?

Use DeepSeek-Prover-V2-671B with GMI Cloud. Other hosts use their own ids: deepseek-prover-v2-671b on Novita AI.

Sources

Raw catalog entry for DeepSeek-Prover-V2-671B on GMI Cloud
{
  "input_cost_per_token": 5e-7,
  "litellm_provider": "gmi",
  "max_input_tokens": 131072,
  "mode": "chat",
  "output_cost_per_token": 0.00000218,
  "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts"
}