Baltor Get started

Models

DeepSeek-V4-Flash

By deepseek-ai. 290.9 billion parameters, a context window of 1,048,576 tokens and the licence mit.

Facts

Released
2026-04-22 the day the repository was first published on Hugging Face Hugging Face, read
Licence
mit the licence the model card declares Hugging Face, read
Open weights
Yes the weights are published in this Hugging Face repository Hugging Face, read
Parameters
290.9 billion counted from the safetensors weight files Hugging Face, read
Active parameters
20.4 billion estimate estimated from the expert counts and sizes in the configuration model configuration, read
Knowledge cutoff
Unknown
Context window
  • 1,048,576 tokens the maximum position embeddings in the model configuration model configuration, read
Longest output
Unknown
Tool calling
Unknown
Structured output
Unknown
Reasoning controls
Unknown
Inputs and outputs
text in, text out Hugging Face, read
Good for
No source names a use.

Prices

Each provider's own price in US dollars per million tokens, as an openly licensed source lists it
ProviderInputOutputContextAs ofSource
Deep Infra0.090 USD0.180 USD1,048,576 older than 30 days; check the providermodels.dev, read
Pioneer0.100 USD0.200 USD1,000,000 older than 30 days; check the providermodels.dev, read
GMI Cloud0.112 USD0.224 USD1,048,575 older than 30 days; check the providermodels.dev, read
SiliconFlow0.130 USD0.280 USD1,000,000 older than 30 days; check the providermodels.dev, read
Abacus0.140 USD0.280 USD1,000,000 older than 30 days; check the providermodels.dev, read
CoreWeave0.140 USD0.280 USD1,049,000LiteLLM, read
Hugging Face0.140 USD0.280 USD1,048,576 older than 30 days; check the providermodels.dev, read
Nebius Token Factory0.140 USD0.280 USD1,048,576LiteLLM, read
Nvidia0.140 USD0.280 USD1,048,576 older than 30 days; check the providermodels.dev, read
SiliconFlow (China)0.140 USD0.280 USD1,000,000 older than 30 days; check the providermodels.dev, read
tensormesh0.140 USD0.280 USD32,768LiteLLM, read
ai&0.150 USD0.250 USD1,048,576 older than 30 days; check the providermodels.dev, read
inferenceapis0.190 USD0.380 USD1,048,576LiteLLM, read

Run it on your own hardware

Weights are the sizes of the files a source lists, or an estimate from the parameter count where none does. Memory is an estimate: weights plus KV cache plus 512 MiB and 5 percent of the weights for runtime buffers. Check it against your hardware.

QuantizationWeightsMemory at 8,192 tokensMemory at 32,768 tokens
MXFP4145 GiB154 GiB156 GiB

Start it with a local runtime

  • Ollama
    ollama run hf.co/antirez/deepseek-v4-gguf:MXFP4
  • LM Studio
    lms get antirez/deepseek-v4-gguf
    lms server start
  • llama.cpp server
    llama-server -hf antirez/deepseek-v4-gguf:MXFP4 --jinja
  • vLLM
    vllm serve deepseek-ai/DeepSeek-V4-Flash
  • SGLang
    sglang serve --model-path deepseek-ai/DeepSeek-V4-Flash --port 30000

Use it from your harness

Set up for Abacus with the model deepseek-ai/DeepSeek-V4-Flash. Each endpoint page has the same setup for its own address.

OpenCode

Put this in opencode.json in your project folder:

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "abacus": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Abacus",
      "options": {
        "baseURL": "https://routellm.abacus.ai/v1",
        "apiKey": "{env:ABACUS_API_KEY}"
      },
      "models": {
        "deepseek-ai/DeepSeek-V4-Flash": {
          "name": "DeepSeek-V4-Flash"
        }
      }
    }
  }
}
  • OpenCode reads any OpenAI-compatible address through the @ai-sdk/openai-compatible package, and an address that speaks the Responses API through @ai-sdk/openai.

From OpenCode documentation, read .

Pi

Put this in ~/.pi/agent/models.json:

{
  "providers": {
    "abacus": {
      "baseUrl": "https://routellm.abacus.ai/v1",
      "api": "openai-completions",
      "apiKey": "$ABACUS_API_KEY",
      "models": [
        {
          "id": "deepseek-ai/DeepSeek-V4-Flash"
        }
      ]
    }
  }
}
  • The apiKey field can name an environment variable as $NAME.

From Pi documentation, read .

Codex

Codex speaks only the Responses API, and Abacus documents no Responses address. A gateway that offers one can sit in between.

  • Codex speaks the Responses API only: responses is the one supported wire API of a custom provider. Ollama and LM Studio are built in and start with --oss.

From Codex documentation, read .

Claude Code

Claude Code sends Anthropic Messages requests, and Abacus documents no such address. A gateway that translates to that API can sit in between.

  • Claude Code sends Anthropic Messages requests to ANTHROPIC_BASE_URL. Anthropic says it does not support routing Claude Code to models other than Claude through any gateway, so some features may not work with another model.

From Claude Code documentation, read .

Other ways to reach it

Published results

These are results other people published. Baltor did not run them and does not rank models by them.

Two more publishers are linked, never copied, because their terms do not allow it:

  • Artificial Analysis publishes its own intelligence, speed and price measurements.
  • OpenRouter lists current prices and uptime for each provider it routes to.