Muse Spark 1.3 API
- Input
- $1.25per 1M tokens
- Output
- $4.25per 1M tokens
- Cached input
- $0.15per 1M tokens
- Context
- 1.0M
Muse Spark 1.3 for OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses.
Explore Muse Spark 1.3 for OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses through the unified API. Supported interfaces and current availability are shown below.
- OpenAI-style Chat Completions
- Anthropic-style Messages
- OpenAI-style Responses
Model details
- Context window
- 1.0M tokens
- Max output
- 1.0M tokens
- Input
- Text, images
- Output
- Text
- Capabilities
- Reasoning, Vision, Tool calling, Streaming, JSON output
- Interfaces
- OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses
Muse Spark 1.3 API pricing
Per 1M tokens. The Inferray price is what you are charged — no gateway fee is added on top of it.
| Metric | Price |
|---|---|
| Input | $1.25 |
| Cached input | $0.15 |
| Output | $4.25 |
What Muse Spark 1.3 costs for real work
Typical workloads at list price, worked out from the rates above. Nothing is added on top.
| Workload | Tokens | Cost |
|---|---|---|
| 1,000 chat replies | 1,500 tokens in, 400 out, each | $3.58 |
| Summarise a 100-page document | 60K tokens in, 2K out | $0.084 |
| 10M tokens of coding-agent work | 10M tokens: 85% cached input, 12% fresh input, 3% output | $4.05 |
| 1M output tokens | Generated text only | $4.25 |
Muse Spark 1.3 is pay-as-you-go only
Muse Spark 1.3 is not included in Token Plans. Call it from a pay-as-you-go balance at the list price above, with no gateway fee.
Why teams pick it
- Muse Spark 1.3 for OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses.
Call Muse Spark 1.3
Muse Spark 1.3 answers on any of the APIs below — pick the one your code already speaks and just swap in your Inferray key.
curl https://api.inferray.com/v1/chat/completions \
-H "Authorization: Bearer inferray_..." \
-H "Content-Type: application/json" \
-d '{
"model": "muse-spark-1.3",
"messages": [
{
"role": "user",
"content": "Hello"
}
]
}'curl https://api.inferray.com/v1/messages \
-H "Authorization: Bearer inferray_..." \
-H "Content-Type: application/json" \
-d '{
"model": "muse-spark-1.3",
"max_tokens": 1024,
"messages": [
{
"role": "user",
"content": "Hello"
}
]
}'curl https://api.inferray.com/v1/responses \
-H "Authorization: Bearer inferray_..." \
-H "Content-Type: application/json" \
-d '{
"model": "muse-spark-1.3",
"input": "Hello"
}'Conversation compaction is also available at POST /v1/responses/compact.
Use Muse Spark 1.3 in your tools
Every coding agent below has a setup guide. Set the model to muse-spark-1.3.
More from Meta
Alternatives to Muse Spark 1.3
Questions about this model
- How much does the Muse Spark 1.3 API cost?
- Muse Spark 1.3 costs $1.25 per 1M input tokens and $4.25 per 1M output tokens on Inferray, and cached input is $0.15 per 1M. That is the list price, with no gateway fee on top.
- Is there a free tier for Muse Spark 1.3?
- No. You add credit and pay Muse Spark 1.3's list rate for each request — seats, projects, and API keys are free, and pay-as-you-go credit never expires.
- Am I charged for failed requests?
- No. A request that fails without returning a result is not billed. If a response fails part-way, the tokens already processed before the failure are charged.
- Is Muse Spark 1.3 included in Token Plans?
- No. Muse Spark 1.3 is pay-as-you-go only; Token Plans cover the other text models in the catalog.
- Can I use Muse Spark 1.3 in Claude Code?
- Yes. Set ANTHROPIC_BASE_URL to https://api.inferray.com, ANTHROPIC_AUTH_TOKEN to your Inferray key, and ANTHROPIC_MODEL to muse-spark-1.3. The same key works in Codex, opencode, Cline, and other agents.
- Does Muse Spark 1.3 support tool calling and vision?
- Muse Spark 1.3 supports tool calling, image input, reasoning, JSON output and streaming on Inferray.
- Is it the real Muse Spark 1.3?
- Yes. A request for muse-spark-1.3 is answered by Muse Spark 1.3 from Meta, billed at its published list price. Inferray never substitutes a different or smaller model.
Prices from the catalog as of November 12, 2026.