DeepSeek Coder V2 Instruct

DeepSeek Coder V2 Instruct is a text model from Fireworks AI with a context window of 66K tokens and max output of 66K tokens. Pricing starts at 1.20 per million input tokens and 1.20 per million output tokens (cheapest at Ollama).

Capabilities

Vision Function Calling Reasoning JSON Schema System Messages Web Search Prompt Caching Audio Input Audio Output

Specifications

Model Keyfireworks_ai/accounts/fireworks/models/deepseek-coder-v2-instruct
ProviderFireworks AI
Provider IDfireworks_ai
ModeText
Canonical Namedeepseek-coder-2
Context Window66K tokens
Max Output66K tokens

Pricing

TypePer 1K TokensPer 1M Tokens
Input Tokens0.00121.20
Output Tokens0.00121.20

Benchmarks

Intelligence Index10.6#179
Time to First Token0.00s#1
MATH-5000.7#83

Price Comparison by Provider

Compare prices for DeepSeek Coder V2 Instruct across different providers. The same model may be available through multiple providers at different price points.

Provider
Model Key
Input Price, $
Output Price, $
Ollamaollama/deepseek-coder-v2-baseN/AN/A
Fireworks AIfireworks_ai/accounts/fireworks/models/deepseek-coder-v2-instruct1.201.20

All Variants

All available versions, regions, and API endpoints for DeepSeek Coder V2 Instruct.

Model Key
Provider
Mode
Input Price, $
Output Price, $
Context
Max Output
Vision
Functions
fireworks_ai/accounts/fireworks/models/deepseek-coder-v2-instructFireworks AIText1.201.2066K66Knono
ollama/deepseek-coder-v2-baseOllamaTextN/AN/A8K8Knoyes
ollama/deepseek-coder-v2-instructOllamaTextN/AN/A33K8Knoyes