impulse

Palmyra Vision 7B

API id writer.palmyra-vision-7b
Input / 1M
$0.15
at Amazon Bedrock
Output / 1M
$0.60
at Amazon Bedrock
Context window
4K
tokens
Max output
4K
tokens per reply
Hosts
1
2 listings
Released
-
date not published

Pricing

List prices at Amazon Bedrock, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.15$0.60
Batch
50% off
$0.075$0.30
Flex
50% off
$0.075$0.30
Priority
75% more
$0.263$1.05

What it costs a month

At Amazon Bedrock list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$90.00
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$93.60
  • Coding agent1,000 requests a day, 40K in / 2K out$216
  • Overnight batch20,000 requests a day, 4K in / 0.4K out, batch$252
Use your own numbers

Where to run it

1 host serve Palmyra Vision 7B. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
writer.palmyra-vision-7b
$0.15 / $0.60
Show 1 more listings: regions, snapshots and variants
Amazon Bedrock
Mantle
writer.palmyra-vision-7b
$0.15 / $0.60

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
TextImages
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 Amazon Bedrock.

Smaller Independent models

No cheaper Independent model keeps its key capabilities.

Other frontier labs

  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    24% less
  • GPT-6 Luna
    OpenAI · on OpenAI
    $0.10 / $0.50
    Has every key capability
    24% less

Open-weight picks

  • Qwen3.8 27B
    Alibaba Qwen · on EmpirioLabs AI
    $0.17 / $0.50
    Has every key capability
    4% less
  • Ministral 14B 2512
    Mistral AI · on Mistral AI
    $0.20 / $0.20
    Has every key capability
    24% less
  • Nemotron 3.5 Super VL
    NVIDIA · on Kyma API
    $0.081 / $0.472
    Has every key capability
    32% less
  • Gemma 4 31B IT
    Google · on W&B Inference
    $0.10 / $0.34
    Has every key capability
    39% less

Call it

Using Amazon Bedrock's API.

Python
from litellm import completion

response = completion(
    model="bedrock/writer.palmyra-vision-7b",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Palmyra Vision 7B cost?

On Amazon Bedrock, Palmyra Vision 7B costs $0.15 per million input tokens and $0.60 per million output tokens.

Which APIs offer Palmyra Vision 7B?

Palmyra Vision 7B runs on 1 API: Amazon Bedrock.

What is Palmyra Vision 7B's context window?

4K tokens, with up to 4K tokens in one reply.

Is Palmyra Vision 7B being retired?

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

What are cheaper alternatives to Palmyra Vision 7B?

Models that cost less and keep most of what it can do: Claude Haiku 5.5 on Anthropic (24% less), GPT-6 Luna on OpenAI (24% less) and Qwen3.8 27B on EmpirioLabs AI (4% less). Savings are on a mix of 3 input tokens to 1 output token.

What is Palmyra Vision 7B's API model id?

Use writer.palmyra-vision-7b with Amazon Bedrock.

Sources

Raw catalog entry for writer.palmyra-vision-7b on Amazon Bedrock
{
  "input_cost_per_token": 1.5e-7,
  "input_cost_per_token_batches": 7.5e-8,
  "input_cost_per_token_flex": 7.5e-8,
  "input_cost_per_token_priority": 2.625e-7,
  "litellm_provider": "bedrock_converse",
  "max_input_tokens": 4096,
  "max_output_tokens": 4096,
  "mode": "chat",
  "output_cost_per_token": 6e-7,
  "output_cost_per_token_batches": 3e-7,
  "output_cost_per_token_flex": 3e-7,
  "output_cost_per_token_priority": 0.00000105,
  "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
  "supports_vision": true
}