Context
66K
Max output
66K
Serving providers
2
Cheapest input
$0.00 /1M
Prices are on-demand list rates. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.

Benchmarks

independent evaluations · source: Artificial Analysis
Headline indices

Pricing by serving provider

standard tier · per 1M tokens · click a provider to expand
Serving providerInput /1MOutput /1MEndpoints
OllamaCheapest$0.00$0.001
ComponentUnitStandardBatchCached
Text input/1M tok$0
Text output/1M tok$0
Fireworks AI$1.20$1.201

Price history

input + output $/1M since we started tracking
Input Output
$0.000$0.500$1.00$1.50Jul 15Aug 7Jun 22$0.000$0.000

Cost calculator

estimate your monthly spend on this model
$0
estimated / month

Model IDs

copy the exact identifier for your platform
ollama/deepseek-coder-v2-instructfireworks_ai/accounts/fireworks/models/deepseek-coder-v2-instruct

Frequently asked questions

DeepSeek Coder V2 Instruct pricing, context and availability

How much does DeepSeek Coder V2 Instruct cost?

DeepSeek Coder V2 Instruct costs $0.00 per 1M input tokens and $0.00 per 1M output tokens at its cheapest provider via Ollama. Across 2 serving providers, input prices range from $0.00 to $1.20 per 1M tokens.

What is the context window of DeepSeek Coder V2 Instruct?

DeepSeek Coder V2 Instruct accepts up to 66K tokens of context and can return up to 66K output tokens.

Which providers serve DeepSeek Coder V2 Instruct?

DeepSeek Coder V2 Instruct is available from 2 serving providers, each with its own pricing and model ID. Ollama is currently the cheapest.

What can DeepSeek Coder V2 Instruct do?

DeepSeek Coder V2 Instruct supports tool use and structured output.

Other DeepSeek models

compare pricing across the DeepSeek lineup

Popular comparisons

head-to-head pages featuring DeepSeek Coder V2 Instruct
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI