Mistral Tiny
mistral-tinyPricing
List prices at Mistral AI, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.25 | $0.25 | |
| Cached input 90% off input | $0.025 | 90% off input |
What it costs a month
At Mistral AI list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$73.50
- RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$75.00
- Coding agent1,000 requests a day, 40K in / 2K out, cached$126
- Overnight batch20,000 requests a day, 4K in / 0.4K out$660
Where to run it
1 host serve Mistral Tiny. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
Mistral AILab API mistral-tiny | $0.25 / $0.25 | mistral-tiny |
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
- Features
- Assistant prefill
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 Mistral AI.
Smaller Mistral AI models
- 5% less
- 30% less
- 40% less
Other frontier labs
- 20% less
- 20% less
Open-weight picks
- 4% less
- 20% less
- 28% less
- 36% less
Call it
Using Mistral AI's API.
from litellm import completion
response = completion(
model="mistral/mistral-tiny",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Mistral Tiny cost?
On Mistral AI, Mistral Tiny costs $0.25 per million input tokens and $0.25 per million output tokens. Cached input costs $0.025 per million tokens.
Which APIs offer Mistral Tiny?
Mistral Tiny runs on 1 API: Mistral AI.
What is Mistral Tiny's context window?
32K tokens, with up to 8K tokens in one reply.
Is Mistral Tiny being retired?
No retirement date is scheduled for it on any API we track.
What are cheaper alternatives to Mistral Tiny?
Models that cost less and keep most of what it can do: Zai Glm 5.3 Flash on Mistral AI (5% less), Claude Haiku 5.5 on Anthropic (20% less), GPT-6 Luna on OpenAI (20% less) and Qwen3 Coder Next on AIHubMix (4% less). Savings are on a mix of 3 input tokens to 1 output token.
What is Mistral Tiny's API model id?
Use mistral-tiny with Mistral AI.
Sources
Raw catalog entry for mistral-tiny on Mistral AI
{
"cache_read_input_token_cost": 2.5e-8,
"input_cost_per_token": 2.5e-7,
"litellm_provider": "mistral",
"max_input_tokens": 32000,
"max_output_tokens": 8191,
"mode": "chat",
"output_cost_per_token": 2.5e-7,
"supports_assistant_prefill": true,
"supports_response_schema": true,
"supports_tool_choice": true
}