impulse

L3.1 70B Euryale V2.2

API id L3.1-70B-Euryale-v2.2
Input / 1M
$0.85
at DeepInfra
Output / 1M
$0.85
at DeepInfra
Context window
131K
tokens
Max output
131K
tokens per reply
Hosts
1
1 listings
Released
-
date not published

Pricing

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

TierInput / 1MOutput / 1M
Standard$0.85$0.85

What it costs a month

At DeepInfra list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$319
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$439
  • Coding agent1,000 requests a day, 40K in / 2K out$1,071
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$2,244
Use your own numbers

Where to run it

1 host serve L3.1 70B Euryale V2.2. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
DeepInfraInference
L3.1-70B-Euryale-v2.2
$0.85 / $0.85

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

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 DeepInfra.

Smaller Independent models

No cheaper Independent model keeps its key capabilities.

Other frontier labs

  • GPT-5.4 Nano
    OpenAI · on OpenAI
    $0.20 / $1.25
    Has every key capability
    46% less
  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    76% less
  • GPT-6 Luna
    OpenAI · on OpenAI
    $0.10 / $0.50
    Has every key capability
    76% less
  • GPT-4o Mini
    OpenAI · on OpenAI
    $0.15 / $0.60
    Has every key capability
    69% less

Open-weight picks

  • Nemotron 3 Ultra 550B A55B
    NVIDIA · on Perplexity
    $0.25 / $2.50
    Has every key capability
    4% less
  • DeepSeek V4 Pro
    DeepSeek · on CLF AI Gateway
    $0.528 / $1.58
    Has every key capability
    7% less
  • Kimi K2.7 Code
    Moonshot AI · on CLF AI Gateway
    $0.38 / $1.60
    Has every key capability
    19% less
  • Inkling Small
    Independent · on DeepInfra
    $0.45 / $1.20
    Has every key capability
    25% less

Model line

Newer and older versions, at each lab's own price.

  1. UndatedL31 70B Euryale V2.2Latest$1.48 / $1.48
  2. UndatedL3.1 70B Euryale V2.2This page$0.85 / $0.85

Call it

Using DeepInfra's API.

Python
from litellm import completion

response = completion(
    model="deepinfra/L3.1-70B-Euryale-v2.2",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does L3.1 70B Euryale V2.2 cost?

On DeepInfra, L3.1 70B Euryale V2.2 costs $0.85 per million input tokens and $0.85 per million output tokens.

Which APIs offer L3.1 70B Euryale V2.2?

L3.1 70B Euryale V2.2 runs on 1 API: DeepInfra.

What is L3.1 70B Euryale V2.2's context window?

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

Is L3.1 70B Euryale V2.2 being retired?

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

Is there a newer version of L3.1 70B Euryale V2.2?

Yes. L31 70B Euryale V2.2 is the newest model in this line.

What are cheaper alternatives to L3.1 70B Euryale V2.2?

Models that cost less and keep most of what it can do: GPT-5.4 Nano on OpenAI (46% less), Claude Haiku 5.5 on Anthropic (76% less) and Nemotron 3 Ultra 550B A55B on Perplexity (4% less). Savings are on a mix of 3 input tokens to 1 output token.

What is L3.1 70B Euryale V2.2's API model id?

Use L3.1-70B-Euryale-v2.2 with DeepInfra.

Sources

Raw catalog entry for L3.1-70B-Euryale-v2.2 on DeepInfra
{
  "max_input_tokens": 131072,
  "max_output_tokens": 131072,
  "input_cost_per_token": 8.5e-7,
  "output_cost_per_token": 8.5e-7,
  "litellm_provider": "deepinfra",
  "mode": "chat",
  "supports_tool_choice": false,
  "source": "https://deepinfra.com/pricing"
}