Claude Fable 5$22.000/MClaude Opus 4.8$11.000/MClaude Opus 4.7$11.000/MClaude Opus 4.6$11.000/MClaude Opus 4.5$33.000/MClaude Sonnet 3.7$6.600/MClaude Opus 3$33.000/MClaude 2.1$12.800/MClaude 2$12.800/MGPT-5.5$12.500/MGPT-5.2$5.425/MGPT-5.2-Codex$5.425/MGPT-5$3.875/MGPT-4.5$97.500/MGPT-4 Turbo Preview$16.000/MGPT-4$39.000/MGPT-4-32k$78.000/Mo3$19.000/Mo3-mini$2.090/Mo4-mini$2.090/Mo1$28.500/Mo1-mini$5.700/Mo1-preview$28.500/MGemini 3.5 Pro$5.000/MGemini 3.1 Pro$5.000/MGemini 3 Pro$5.000/MGemini 2.5 Pro$3.875/MGemini 1.5 Pro$2.375/MGemini 1.0 Ultra$12.000/MGemini 1.0 Pro$0.800/MClaude Fable 5$22.000/MClaude Opus 4.8$11.000/MClaude Opus 4.7$11.000/MClaude Opus 4.6$11.000/MClaude Opus 4.5$33.000/MClaude Sonnet 3.7$6.600/MClaude Opus 3$33.000/MClaude 2.1$12.800/MClaude 2$12.800/MGPT-5.5$12.500/MGPT-5.2$5.425/MGPT-5.2-Codex$5.425/MGPT-5$3.875/MGPT-4.5$97.500/MGPT-4 Turbo Preview$16.000/MGPT-4$39.000/MGPT-4-32k$78.000/Mo3$19.000/Mo3-mini$2.090/Mo4-mini$2.090/Mo1$28.500/Mo1-mini$5.700/Mo1-preview$28.500/MGemini 3.5 Pro$5.000/MGemini 3.1 Pro$5.000/MGemini 3 Pro$5.000/MGemini 2.5 Pro$3.875/MGemini 1.5 Pro$2.375/MGemini 1.0 Ultra$12.000/MGemini 1.0 Pro$0.800/M
BETA
Subscribe
← Back to Index·All DeepInfra models
DeepInfra
DeepInfraEfficient

Mistral 7B (DI)

Nano

The 7B Mistral that put open-weights chat models on the map. v0.3 added function calling and an extended vocabulary.

Mistral 7B (DI) is a efficient AI model from DeepInfra. It costs $0.070 per million input tokens and $0.070 per million output tokens (blended $0.070/M), with a 32K-token context window.

Profile inherited from upstream Mistral 7B ↗ — this is a hosted variant of the same open-weights model.

Released May 2024Modalities textOfficial model page ↗Provider pricing ↗API docs ↗Compare with another model →Estimate monthly cost →
INPUT
$0.070/M
per million input tokens
OUTPUT
$0.070/M
per million output tokens
BLENDED 70/30
$0.070/M
default reference rate · how it's calculated →
CONTEXT
32K
32,000 tokens
What it's good at
  • Open weights (Apache 2.0)
  • Single-GPU
  • Function calling
  • Wide ecosystem
Typical use cases
  • Self-hosted small chat
  • Fine-tune base
  • Edge deployments
Benchmarks
vs. best public score
Scores inherited from Mistral 7B — this is a hosted variant of the same open-weights model, so the underlying benchmark scores are identical.
MMLU62%
Multitask academic knowledge across 57 subjects.
HumanEval30%
Python function synthesis from docstrings.
LMArena Elo1072 Elo
Crowd-sourced head-to-head preference Elo rating.
Hand-curated from each provider's published reports and public leaderboards. Methodology varies across sources — treat as directional rather than authoritative.
More from DeepInfra
See all 11 →
Llama 3.3 70B (DI)
Serverless · 128K ctx
in $0.230/Mout $0.400/M
Llama 3.1 405B (DI)
Serverless · 128K ctx
in $0.800/Mout $0.800/M
Llama 3.1 70B (DI)
Balanced · 128K ctx
in $0.350/Mout $0.400/M
Mixtral 8x7B (DI)
MoE · 32K ctx
in $0.240/Mout $0.240/M
DeepSeek-R1 (DI)
Reasoning · 64K ctx
in $0.550/Mout $2.190/M
Qwen2.5-72B (DI)
Balanced · 128K ctx
in $0.350/Mout $0.400/M
Frequently asked questions

How much does Mistral 7B (DI) cost?

Mistral 7B (DI) costs $0.070 per million input tokens and $0.070 per million output tokens, for a blended reference rate of $0.070 per million tokens.

What is Mistral 7B (DI)'s context window?

Mistral 7B (DI) supports up to 32K tokens of context (32,000 tokens).

What is Mistral 7B (DI) best for?

Mistral 7B (DI) is well suited to Open weights (Apache 2.0), Single-GPU and Function calling.

Who makes Mistral 7B (DI)?

Mistral 7B (DI) is developed and served by DeepInfra. It was released in May 2024.